首页 > 最新文献

Cancer Imaging最新文献

英文 中文
Qualitative and quantitative analysis of solid renal tumors by high-frame-rate contrast-enhanced ultrasound. 通过高帧率对比增强超声对实体肾肿瘤进行定性和定量分析。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2024-10-15 DOI: 10.1186/s40644-024-00788-3
Hailan Wu, Jiayu Shi, Long Gao, Jingling Wang, WenXin Yuan, WeiPing Zhang, Zhixing Liu, Yi Mao

Objective: To analyze the characteristics of high-frame-rate contrast-enhanced ultrasound (H-CEUS) in solid renal tumors using qualitative and quantitative methods.

Methods: Seventy-five patients who underwent preoperative conventional ultrasound (US), conventional contrast-enhanced ultrasound (C-CEUS), and H-CEUS examination of renal tumors were retrospectively analyzed, with a total of 89 renal masses. The masses were divided into the benign (30 masses) and malignant groups (59 masses) based on the results of enhanced computer tomography and pathology. The location, diameter, shape, border, calcification, and color doppler blood flow imaging (CDFI) of the lesions were observed by US, and the characteristics of the C-CEUS and H-CEUS images were qualitatively and quantitatively analyzed. The χ² test or Fisher's exact probability method was used to compare the US image characteristics between the benign and malignant groups, and the image characteristics of C-CEUS and H-CEUS between the benign and malignant groups. Moreover, the nonparametric Mann-Whitney test was used to compare the differences in C-CEUS and H-CEUS time-intensity curve (TIC) parameters.

Results: Significant differences in gender, surgical approach, echogenicity, and CDFI were observed between the malignant and benign groups (p = 0.003, < 0.001, < 0.001, = 0003). Qualitative analysis also revealed significant differences in the mode of wash-out and fill-in direction between C-CEUS and H-CEUS in the malignant group (p = 0.041, 0.002). In addition, the homogeneity of enhancement showed significant differences between the two contrast models in the benign group (p = 0.009). Quantitative analysis indicated that the TIC parameters peak intensity (PI), deceleration time (DT) /2, area under the curve (AUC), and mean transition time (MTT) were significantly lower in the H-CEUS model compared to the C-CEUS model in both the benign and malignant groups. (all p < 0.001). In contrast, ascending slope of rise curve (AS) was significantly higher in the H-CEUS model compared to the C-CEUS model in the malignant group (p = 0.048).

Conclusions: In renal tumors, H-CEUS shows clearer internal enhancement of the mass and the changes in the wash-out period. The quantitative TIC parameters PI, DT/2, AUC, and MTT were lower in H-CEUS compared to C-CEUS. Both the quantitative and qualitative analyses indicated that H-CEUS better displays the characteristics of solid renal masses compared with C-CEUS.

目的采用定性和定量方法分析肾实体瘤高帧率对比增强超声检查(H-CEUS)的特点:回顾性分析了75例术前接受常规超声(US)、常规对比增强超声(C-CEUS)和H-CEUS检查的肾脏肿瘤患者,共计89个肾脏肿块。根据增强计算机断层扫描和病理结果,将肿块分为良性组(30 个)和恶性组(59 个)。通过 US 观察病变的位置、直径、形状、边界、钙化和彩色多普勒血流成像(CDFI),并对 C-CEUS 和 H-CEUS 图像的特征进行定性和定量分析。采用χ²检验或费雪精确概率法比较良性组和恶性组之间的US图像特征,以及良性组和恶性组之间的C-CEUS和H-CEUS图像特征。此外,还采用非参数 Mann-Whitney 检验比较了 C-CEUS 和 H-CEUS 时间强度曲线(TIC)参数的差异:结果:恶性组和良性组在性别、手术方式、回声强度和 CDFI 方面存在显著差异(P = 0.003,结论:在肾肿瘤中,H-CEUS 时间强度曲线(TIC)参数与 C-CEUS 时间强度曲线(TIC)参数存在显著差异(P = 0.003):在肾脏肿瘤中,H-CEUS 能更清晰地显示肿块内部强化和冲洗期的变化。与 C-CEUS 相比,H-CEUS 的 TIC 定量参数 PI、DT/2、AUC 和 MTT 均较低。定量和定性分析均表明,与 C-CEUS 相比,H-CEUS 能更好地显示实性肾肿块的特征。
{"title":"Qualitative and quantitative analysis of solid renal tumors by high-frame-rate contrast-enhanced ultrasound.","authors":"Hailan Wu, Jiayu Shi, Long Gao, Jingling Wang, WenXin Yuan, WeiPing Zhang, Zhixing Liu, Yi Mao","doi":"10.1186/s40644-024-00788-3","DOIUrl":"https://doi.org/10.1186/s40644-024-00788-3","url":null,"abstract":"<p><strong>Objective: </strong>To analyze the characteristics of high-frame-rate contrast-enhanced ultrasound (H-CEUS) in solid renal tumors using qualitative and quantitative methods.</p><p><strong>Methods: </strong>Seventy-five patients who underwent preoperative conventional ultrasound (US), conventional contrast-enhanced ultrasound (C-CEUS), and H-CEUS examination of renal tumors were retrospectively analyzed, with a total of 89 renal masses. The masses were divided into the benign (30 masses) and malignant groups (59 masses) based on the results of enhanced computer tomography and pathology. The location, diameter, shape, border, calcification, and color doppler blood flow imaging (CDFI) of the lesions were observed by US, and the characteristics of the C-CEUS and H-CEUS images were qualitatively and quantitatively analyzed. The χ² test or Fisher's exact probability method was used to compare the US image characteristics between the benign and malignant groups, and the image characteristics of C-CEUS and H-CEUS between the benign and malignant groups. Moreover, the nonparametric Mann-Whitney test was used to compare the differences in C-CEUS and H-CEUS time-intensity curve (TIC) parameters.</p><p><strong>Results: </strong>Significant differences in gender, surgical approach, echogenicity, and CDFI were observed between the malignant and benign groups (p = 0.003, < 0.001, < 0.001, = 0003). Qualitative analysis also revealed significant differences in the mode of wash-out and fill-in direction between C-CEUS and H-CEUS in the malignant group (p = 0.041, 0.002). In addition, the homogeneity of enhancement showed significant differences between the two contrast models in the benign group (p = 0.009). Quantitative analysis indicated that the TIC parameters peak intensity (PI), deceleration time (DT) /2, area under the curve (AUC), and mean transition time (MTT) were significantly lower in the H-CEUS model compared to the C-CEUS model in both the benign and malignant groups. (all p < 0.001). In contrast, ascending slope of rise curve (AS) was significantly higher in the H-CEUS model compared to the C-CEUS model in the malignant group (p = 0.048).</p><p><strong>Conclusions: </strong>In renal tumors, H-CEUS shows clearer internal enhancement of the mass and the changes in the wash-out period. The quantitative TIC parameters PI, DT/2, AUC, and MTT were lower in H-CEUS compared to C-CEUS. Both the quantitative and qualitative analyses indicated that H-CEUS better displays the characteristics of solid renal masses compared with C-CEUS.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"24 1","pages":"139"},"PeriodicalIF":3.5,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11481758/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142458639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Correction: Contrast enhanced ultrasound of liver lesions in patients treated for childhood malignancies. 更正:儿童恶性肿瘤患者肝脏病变的对比增强超声检查。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2024-10-14 DOI: 10.1186/s40644-024-00785-6
Ayatullah G Mostafa, Zachary Abramson, Mina Ghbrial, Som Biswas, Sherwin Chan, Himani Darji, Jessica Gartrell, Seth E Karol, Yimei Li, Daniel A Mulrooney, Tushar Patni, Tarek M Zaghloul, M Beth McCarville
{"title":"Correction: Contrast enhanced ultrasound of liver lesions in patients treated for childhood malignancies.","authors":"Ayatullah G Mostafa, Zachary Abramson, Mina Ghbrial, Som Biswas, Sherwin Chan, Himani Darji, Jessica Gartrell, Seth E Karol, Yimei Li, Daniel A Mulrooney, Tushar Patni, Tarek M Zaghloul, M Beth McCarville","doi":"10.1186/s40644-024-00785-6","DOIUrl":"https://doi.org/10.1186/s40644-024-00785-6","url":null,"abstract":"","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"24 1","pages":"138"},"PeriodicalIF":3.5,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11472479/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142458637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Clinical value of SUVpeak-to-tumor centroid distance on FDG PET/CT for predicting neoadjuvant chemotherapy response in patients with breast cancer. FDG PET/CT 上 SUVpeak 与肿瘤中心点距离对预测乳腺癌患者新辅助化疗反应的临床价值。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2024-10-11 DOI: 10.1186/s40644-024-00787-4
Sun-Pyo Hong, Sang Mi Lee, Ik Dong Yoo, Jong Eun Lee, Sun Wook Han, Sung Yong Kim, Jeong Won Lee

Background: Since it has been found that the maximum metabolic activity of a cancer lesion shifts toward the lesion edge during cancer progression, normalized distances from the hot spot of radiotracer uptake to tumor centroid (NHOC) and tumor perimeter (NHOP) have been suggested as novel F-18 fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) parameters that can reflect cancer aggressiveness. This study aimed to investigate whether NHOC and NHOP parameters could predict pathological response to neoadjuvant chemotherapy (NAC) and progression-free survival (PFS) in breast cancer patients.

Methods: This study retrospectively enrolled 135 female patients with breast cancer who underwent pretreatment FDG PET/CT and received NAC and subsequent surgical resection. From PET/CT images, normalized distances of maximum SUV and peak SUV-to-tumor centroid (NHOCmax and NHOCpeak) and -to-tumor perimeter (NHOPmax and NHOPpeak) were measured, in addition to conventional PET/CT parameters.

Results: Of 135 patients, 32 (23.7%) achieved pathological complete response (pCR), and 34 (25.2%) had events during follow-up. In the receiver operating characteristic (ROC) curve analysis, NHOCmax showed the highest area under the ROC curve value (0.710) for predicting pCR, followed by NHOCpeak (0.694). In the multivariate logistic regression analysis, NHOCmax, NHOCpeak, and NHOPmax were independent predictors for pCR (p < 0.05). In the multivariate survival analysis, NHOCpeak (p = 0.026) was an independent predictor for PFS along with metabolic tumor volume, with patients having higher NHOCpeak showing worse PFS.

Conclusion: NHOCpeak on pretreatment FDG PET/CT could be a potential imaging parameter for predicting NAC response and survival in patients with breast cancer.

背景:研究发现,在癌症进展过程中,癌症病灶的最大代谢活性会向病灶边缘移动,因此有人提出,从放射性示踪剂摄取热点到肿瘤中心点(NHOC)和肿瘤周长(NHOP)的归一化距离是可以反映癌症侵袭性的新的F-18氟脱氧葡萄糖(FDG)正电子发射断层扫描/计算机断层扫描(PET/CT)参数。本研究旨在探讨NHOC和NHOP参数能否预测乳腺癌患者对新辅助化疗(NAC)的病理反应和无进展生存期(PFS):该研究回顾性地纳入了135名接受FDG PET/CT治疗的女性乳腺癌患者,这些患者接受了新辅助化疗和随后的手术切除。除常规 PET/CT 参数外,还测量了 PET/CT 图像中最大 SUV 和峰值 SUV 到肿瘤中心点(NHOCmax 和 NHOCpeak)和肿瘤周长(NHOPmax 和 NHOPpeak)的归一化距离:在135名患者中,32人(23.7%)获得了病理完全反应(pCR),34人(25.2%)在随访期间发生了病变。在接收者操作特征(ROC)曲线分析中,NHOCmax预测pCR的ROC曲线下面积值最高(0.710),其次是NHOCpeak(0.694)。在多变量逻辑回归分析中,NHOCmax、NHOCpeak 和 NHOPmax 都是 pCR 的独立预测因子(p 结论:NHOCmax、NHOCpeak 和 NHOPmax 都是 pCR 的独立预测因子:治疗前 FDG PET/CT 的 NHOCpeak 可能是预测乳腺癌患者 NAC 反应和生存期的潜在影像学参数。
{"title":"Clinical value of SUVpeak-to-tumor centroid distance on FDG PET/CT for predicting neoadjuvant chemotherapy response in patients with breast cancer.","authors":"Sun-Pyo Hong, Sang Mi Lee, Ik Dong Yoo, Jong Eun Lee, Sun Wook Han, Sung Yong Kim, Jeong Won Lee","doi":"10.1186/s40644-024-00787-4","DOIUrl":"10.1186/s40644-024-00787-4","url":null,"abstract":"<p><strong>Background: </strong>Since it has been found that the maximum metabolic activity of a cancer lesion shifts toward the lesion edge during cancer progression, normalized distances from the hot spot of radiotracer uptake to tumor centroid (NHOC) and tumor perimeter (NHOP) have been suggested as novel F-18 fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) parameters that can reflect cancer aggressiveness. This study aimed to investigate whether NHOC and NHOP parameters could predict pathological response to neoadjuvant chemotherapy (NAC) and progression-free survival (PFS) in breast cancer patients.</p><p><strong>Methods: </strong>This study retrospectively enrolled 135 female patients with breast cancer who underwent pretreatment FDG PET/CT and received NAC and subsequent surgical resection. From PET/CT images, normalized distances of maximum SUV and peak SUV-to-tumor centroid (NHOCmax and NHOCpeak) and -to-tumor perimeter (NHOPmax and NHOPpeak) were measured, in addition to conventional PET/CT parameters.</p><p><strong>Results: </strong>Of 135 patients, 32 (23.7%) achieved pathological complete response (pCR), and 34 (25.2%) had events during follow-up. In the receiver operating characteristic (ROC) curve analysis, NHOCmax showed the highest area under the ROC curve value (0.710) for predicting pCR, followed by NHOCpeak (0.694). In the multivariate logistic regression analysis, NHOCmax, NHOCpeak, and NHOPmax were independent predictors for pCR (p < 0.05). In the multivariate survival analysis, NHOCpeak (p = 0.026) was an independent predictor for PFS along with metabolic tumor volume, with patients having higher NHOCpeak showing worse PFS.</p><p><strong>Conclusion: </strong>NHOCpeak on pretreatment FDG PET/CT could be a potential imaging parameter for predicting NAC response and survival in patients with breast cancer.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"24 1","pages":"136"},"PeriodicalIF":3.5,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11468257/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142406159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multimodal apparent diffusion MRI model in noninvasive evaluation of breast cancer and Ki-67 expression. 无创评估乳腺癌和 Ki-67 表达的多模态表观弥散 MRI 模型
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2024-10-11 DOI: 10.1186/s40644-024-00780-x
Huan Chang, Jinming Chen, Dawei Wang, Hongxia Li, Lei Ming, Yuting Li, Dan Yu, Yu Xin Yang, Peng Kong, Wenjing Jia, Qingqing Yan, Xinhui Liu, Qingshi Zeng

Background: To assess the capability of multimodal apparent diffusion (MAD) weighted magnetic resonance imaging (MRI) to distinguish between malignant and benign breast lesions, and to predict Ki-67 expression level in breast cancer.

Methods: This retrospective study was conducted with 93 patients who had postoperative pathology-confirmed breast cancer or benign breast lesions. MAD images were acquired using a 3.0 T MRI scanner with 16 b values. The MAD parameters, as flow (fF, DF), unimpeded (fluid) (fUI), hindered (fH, DH, and αH), and restricted (fR, DR), were calculated. The differences of the parameters were compared by Mann-Whitney U test between the benign/malignant lesions and high/low Ki-67 expression level. The diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC).

Results: The fR in the malignant lesions was significantly higher than in the benign lesions (P = 0.001), whereas the fUI and DH were found to be significantly lower (P = 0.007 and P < 0.001, respectively). Compared with individual parameter in differentiating malignant from benign breast lesions, the combination parameters of MAD (fR, DH, and fUI) provided the highest AUC (0.851). Of the 73 malignant lesions, 42 (57.5%) were assessed as Ki-67 low expression and 31 (42.5%) were Ki-67 high expression. The Ki-67 high status showed lower DH, higher DF and higher αH (P < 0.05). The combination parameters of DH, DF, and αH provided the highest AUC (0.691) for evaluating Ki-67 expression level.

Conclusions: MAD weighted MRI is a useful method for the breast lesions diagnostics and the preoperative prediction of Ki-67 expression level.

研究背景目的:评估多模态表观弥散(MAD)加权磁共振成像(MRI)区分乳腺恶性和良性病变以及预测乳腺癌Ki-67表达水平的能力:这项回顾性研究的对象是93名术后病理证实为乳腺癌或良性乳腺病变的患者。使用 3.0 T MRI 扫描仪采集了 16 个 b 值的 MAD 图像。计算了 MAD 参数,包括流动(fF、DF)、无阻(流体)(fUI)、受阻(fH、DH 和 αH)和受限(fR、DR)。通过 Mann-Whitney U 检验比较良性/恶性病变和高/低 Ki-67 表达水平之间的参数差异。诊断性能通过接收者操作特征曲线下面积(AUC)进行评估:恶性病变的 fR 明显高于良性病变(P = 0.001),而 fUI 和 DH 则明显低于良性病变(P = 0.007,P R、DH 和 fUI 的 AUC 最高(0.851)。在 73 个恶性病灶中,42 个(57.5%)被评估为 Ki-67 低表达,31 个(42.5%)为 Ki-67 高表达。Ki-67高表达状态显示较低的DH、较高的DF和较高的αH(P H、DF和αH为评估Ki-67表达水平提供了最高的AUC(0.691)):结论:MAD 加权磁共振成像是诊断乳腺病变和术前预测 Ki-67 表达水平的有效方法。
{"title":"Multimodal apparent diffusion MRI model in noninvasive evaluation of breast cancer and Ki-67 expression.","authors":"Huan Chang, Jinming Chen, Dawei Wang, Hongxia Li, Lei Ming, Yuting Li, Dan Yu, Yu Xin Yang, Peng Kong, Wenjing Jia, Qingqing Yan, Xinhui Liu, Qingshi Zeng","doi":"10.1186/s40644-024-00780-x","DOIUrl":"10.1186/s40644-024-00780-x","url":null,"abstract":"<p><strong>Background: </strong>To assess the capability of multimodal apparent diffusion (MAD) weighted magnetic resonance imaging (MRI) to distinguish between malignant and benign breast lesions, and to predict Ki-67 expression level in breast cancer.</p><p><strong>Methods: </strong>This retrospective study was conducted with 93 patients who had postoperative pathology-confirmed breast cancer or benign breast lesions. MAD images were acquired using a 3.0 T MRI scanner with 16 b values. The MAD parameters, as flow (f<sub>F</sub>, D<sub>F</sub>), unimpeded (fluid) (f<sub>UI</sub>), hindered (f<sub>H</sub>, D<sub>H</sub>, and α<sub>H</sub>), and restricted (f<sub>R</sub>, D<sub>R</sub>), were calculated. The differences of the parameters were compared by Mann-Whitney U test between the benign/malignant lesions and high/low Ki-67 expression level. The diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC).</p><p><strong>Results: </strong>The f<sub>R</sub> in the malignant lesions was significantly higher than in the benign lesions (P = 0.001), whereas the f<sub>UI</sub> and D<sub>H</sub> were found to be significantly lower (P = 0.007 and P < 0.001, respectively). Compared with individual parameter in differentiating malignant from benign breast lesions, the combination parameters of MAD (f<sub>R</sub>, D<sub>H</sub>, and f<sub>UI</sub>) provided the highest AUC (0.851). Of the 73 malignant lesions, 42 (57.5%) were assessed as Ki-67 low expression and 31 (42.5%) were Ki-67 high expression. The Ki-67 high status showed lower D<sub>H</sub>, higher D<sub>F</sub> and higher α<sub>H</sub> (P < 0.05). The combination parameters of D<sub>H</sub>, D<sub>F</sub>, and α<sub>H</sub> provided the highest AUC (0.691) for evaluating Ki-67 expression level.</p><p><strong>Conclusions: </strong>MAD weighted MRI is a useful method for the breast lesions diagnostics and the preoperative prediction of Ki-67 expression level.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"24 1","pages":"137"},"PeriodicalIF":3.5,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11470582/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142406160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A deep learning model to enhance the classification of primary bone tumors based on incomplete multimodal images in X-ray, CT, and MRI. 基于 X 光、CT 和 MRI 的不完整多模态图像的深度学习模型,用于增强原发性骨肿瘤的分类。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2024-10-10 DOI: 10.1186/s40644-024-00784-7
Liwen Song, Chuanpu Li, Lilian Tan, Menghong Wang, Xiaqing Chen, Qiang Ye, Shisi Li, Rui Zhang, Qinghai Zeng, Zhuoyao Xie, Wei Yang, Yinghua Zhao

Background: Accurately classifying primary bone tumors is crucial for guiding therapeutic decisions. The National Comprehensive Cancer Network guidelines recommend multimodal images to provide different perspectives for the comprehensive evaluation of primary bone tumors. However, in clinical practice, most patients' medical multimodal images are often incomplete. This study aimed to build a deep learning model using patients' incomplete multimodal images from X-ray, CT, and MRI alongside clinical characteristics to classify primary bone tumors as benign, intermediate, or malignant.

Methods: In this retrospective study, a total of 1305 patients with histopathologically confirmed primary bone tumors (internal dataset, n = 1043; external dataset, n = 262) were included from two centers between January 2010 and December 2022. We proposed a Primary Bone Tumor Classification Transformer Network (PBTC-TransNet) fusion model to classify primary bone tumors. Areas under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate the model's classification performance.

Results: The PBTC-TransNet fusion model achieved satisfactory micro-average AUCs of 0.847 (95% CI: 0.832, 0.862) and 0.782 (95% CI: 0.749, 0.817) on the internal and external test sets. For the classification of benign, intermediate, and malignant primary bone tumors, the model respectively achieved AUCs of 0.827/0.727, 0.740/0.662, and 0.815/0.745 on the internal/external test sets. Furthermore, across all patient subgroups stratified by the distribution of imaging modalities, the PBTC-TransNet fusion model gained micro-average AUCs ranging from 0.700 to 0.909 and 0.640 to 0.847 on the internal and external test sets, respectively. The model showed the highest micro-average AUC of 0.909, accuracy of 84.3%, micro-average sensitivity of 84.3%, and micro-average specificity of 92.1% in those with only X-rays on the internal test set. On the external test set, the PBTC-TransNet fusion model gained the highest micro-average AUC of 0.847 for patients with X-ray + CT.

Conclusions: We successfully developed and externally validated the transformer-based PBTC-Transnet fusion model for the effective classification of primary bone tumors. This model, rooted in incomplete multimodal images and clinical characteristics, effectively mirrors real-life clinical scenarios, thus enhancing its strong clinical practicability.

背景:原发性骨肿瘤的准确分类对于指导治疗决策至关重要。美国国家综合癌症网络指南建议采用多模态图像,从不同角度对原发性骨肿瘤进行综合评估。然而,在临床实践中,大多数患者的医学多模态图像往往是不完整的。本研究旨在利用患者不完整的X光、CT和MRI多模态图像,结合临床特征建立一个深度学习模型,将原发性骨肿瘤分为良性、中度和恶性:在这项回顾性研究中,共纳入了两个中心在 2010 年 1 月至 2022 年 12 月间收治的 1305 例经组织病理学确诊的原发性骨肿瘤患者(内部数据集,n = 1043;外部数据集,n = 262)。我们提出了一种原发性骨肿瘤分类变换网络(PBTC-TransNet)融合模型来对原发性骨肿瘤进行分类。我们计算了接收者操作特征曲线下面积(AUC)、准确率、灵敏度和特异性,以评估该模型的分类性能:结果:PBTC-TransNet 融合模型在内部和外部测试集中取得了令人满意的微平均 AUC 值,分别为 0.847(95% CI:0.832, 0.862)和 0.782(95% CI:0.749, 0.817)。对于良性、中度和恶性原发性骨肿瘤的分类,该模型在内部/外部测试集上的AUC分别为0.827/0.727、0.740/0.662和0.815/0.745。此外,在按成像模式分布分层的所有患者亚组中,PBTC-TransNet 融合模型在内部和外部测试集上获得的微平均 AUC 分别为 0.700 至 0.909 和 0.640 至 0.847。在内部测试集上,该模型的微观平均 AUC 最高,为 0.909,准确率为 84.3%,微观平均灵敏度为 84.3%,在仅有 X 光片的情况下,微观平均特异性为 92.1%。在外部测试集上,PBTC-TransNet 融合模型对 X 光+CT 患者的微观平均 AUC 最高,为 0.847:我们成功开发了基于变压器的 PBTC-Transnet 融合模型,并对其进行了外部验证,从而有效地对原发性骨肿瘤进行分类。该模型植根于不完整的多模态图像和临床特征,有效反映了真实的临床场景,从而增强了其强大的临床实用性。
{"title":"A deep learning model to enhance the classification of primary bone tumors based on incomplete multimodal images in X-ray, CT, and MRI.","authors":"Liwen Song, Chuanpu Li, Lilian Tan, Menghong Wang, Xiaqing Chen, Qiang Ye, Shisi Li, Rui Zhang, Qinghai Zeng, Zhuoyao Xie, Wei Yang, Yinghua Zhao","doi":"10.1186/s40644-024-00784-7","DOIUrl":"10.1186/s40644-024-00784-7","url":null,"abstract":"<p><strong>Background: </strong>Accurately classifying primary bone tumors is crucial for guiding therapeutic decisions. The National Comprehensive Cancer Network guidelines recommend multimodal images to provide different perspectives for the comprehensive evaluation of primary bone tumors. However, in clinical practice, most patients' medical multimodal images are often incomplete. This study aimed to build a deep learning model using patients' incomplete multimodal images from X-ray, CT, and MRI alongside clinical characteristics to classify primary bone tumors as benign, intermediate, or malignant.</p><p><strong>Methods: </strong>In this retrospective study, a total of 1305 patients with histopathologically confirmed primary bone tumors (internal dataset, n = 1043; external dataset, n = 262) were included from two centers between January 2010 and December 2022. We proposed a Primary Bone Tumor Classification Transformer Network (PBTC-TransNet) fusion model to classify primary bone tumors. Areas under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate the model's classification performance.</p><p><strong>Results: </strong>The PBTC-TransNet fusion model achieved satisfactory micro-average AUCs of 0.847 (95% CI: 0.832, 0.862) and 0.782 (95% CI: 0.749, 0.817) on the internal and external test sets. For the classification of benign, intermediate, and malignant primary bone tumors, the model respectively achieved AUCs of 0.827/0.727, 0.740/0.662, and 0.815/0.745 on the internal/external test sets. Furthermore, across all patient subgroups stratified by the distribution of imaging modalities, the PBTC-TransNet fusion model gained micro-average AUCs ranging from 0.700 to 0.909 and 0.640 to 0.847 on the internal and external test sets, respectively. The model showed the highest micro-average AUC of 0.909, accuracy of 84.3%, micro-average sensitivity of 84.3%, and micro-average specificity of 92.1% in those with only X-rays on the internal test set. On the external test set, the PBTC-TransNet fusion model gained the highest micro-average AUC of 0.847 for patients with X-ray + CT.</p><p><strong>Conclusions: </strong>We successfully developed and externally validated the transformer-based PBTC-Transnet fusion model for the effective classification of primary bone tumors. This model, rooted in incomplete multimodal images and clinical characteristics, effectively mirrors real-life clinical scenarios, thus enhancing its strong clinical practicability.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"24 1","pages":"135"},"PeriodicalIF":3.5,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11468403/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142399497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Application of preoperative advanced diffusion magnetic resonance imaging in evaluating the postoperative recurrence of lower grade gliomas. 术前高级弥散磁共振成像在评估低级别胶质瘤术后复发中的应用。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2024-10-09 DOI: 10.1186/s40644-024-00782-9
Luyue Gao, Yuanhao Li, Hongquan Zhu, Yufei Liu, Shihui Li, Li Li, Jiaxuan Zhang, Nanxi Shen, Wenzhen Zhu

Background: Recurrence of lower grade glioma (LrGG) appeared to be unavoidable despite considerable research performed in last decades. Thus, we evaluated the postoperative recurrence within two years after the surgery in patients with LrGG by preoperative advanced diffusion magnetic resonance imaging (dMRI).

Materials and methods: 48 patients with lower-grade gliomas (23 recurrence, 25 nonrecurrence) were recruited into this study. Different models of dMRI were reconstructed, including apparent fiber density (AFD), white matter tract integrity (WMTI), diffusion tensor imaging (DTI), diffusion kurtosis imaging (DKI), neurite orientation dispersion and density imaging (NODDI), Bingham NODDI and standard model imaging (SMI). Orthogonal Partial Least Squares-Discriminant Analysis (OPLS-DA) was used to construct a multiparametric prediction model for the diagnosis of postoperative recurrence.

Results: The parameters derived from each dMRI model, including AFD, axon water fraction (AWF), mean diffusivity (MD), mean kurtosis (MK), fractional anisotropy (FA), intracellular volume fraction (ICVF), extra-axonal perpendicular diffusivity (De), extra-axonal parallel diffusivity (De) and free water fraction (fw), showed significant differences between nonrecurrence group and recurrence group. The extra-axonal perpendicular diffusivity (De) had the highest area under curve (AUC = 0.885), which was significantly higher than others. The variable importance for the projection (VIP) value of De was also the highest. The AUC value of the multiparametric prediction model merging AFD, WMTI, DTI, DKI, NODDI, Bingham NODDI and SMI was up to 0.96.

Conclusion: Preoperative advanced dMRI showed great efficacy in evaluating postoperative recurrence of LrGG and De of SMI might be a valuable marker.

背景:尽管在过去几十年中进行了大量研究,但低级别胶质瘤(LrGG)的复发似乎是不可避免的。因此,我们通过术前高级弥散磁共振成像(dMRI)评估了低级别胶质瘤患者术后两年内的复发情况。材料与方法:本研究共招募了 48 例低级别胶质瘤患者(23 例复发,25 例未复发)。重建了不同的 dMRI 模型,包括表观纤维密度(AFD)、白质束完整性(WMTI)、弥散张量成像(DTI)、弥散峰度成像(DKI)、神经元定向弥散和密度成像(NODDI)、宾汉姆 NODDI 和标准模型成像(SMI)。利用正交偏最小二乘判别分析(OPLS-DA)构建了用于诊断术后复发的多参数预测模型:各dMRI模型得出的参数,包括AFD、轴突水分数(AWF)、平均扩散率(MD)、平均峰度(MK)、各向异性分数(FA)、细胞内体积分数(ICVF)、轴外垂直扩散率(De⊥)、轴外平行扩散率(De∥)和游离水分数(fw),在未复发组和复发组之间存在显著差异。轴外垂直扩散率(De⊥)的曲线下面积(AUC = 0.885)最高,明显高于其他变量。De⊥ 对投影的变量重要性(VIP)值也是最高的。合并 AFD、WMTI、DTI、DKI、NODDI、Bingham NODDI 和 SMI 的多参数预测模型的 AUC 值高达 0.96:术前晚期 dMRI 在评估 LrGG 术后复发方面显示出很高的疗效,而 SMI 的 De⊥ 可能是一个有价值的标记。
{"title":"Application of preoperative advanced diffusion magnetic resonance imaging in evaluating the postoperative recurrence of lower grade gliomas.","authors":"Luyue Gao, Yuanhao Li, Hongquan Zhu, Yufei Liu, Shihui Li, Li Li, Jiaxuan Zhang, Nanxi Shen, Wenzhen Zhu","doi":"10.1186/s40644-024-00782-9","DOIUrl":"10.1186/s40644-024-00782-9","url":null,"abstract":"<p><strong>Background: </strong>Recurrence of lower grade glioma (LrGG) appeared to be unavoidable despite considerable research performed in last decades. Thus, we evaluated the postoperative recurrence within two years after the surgery in patients with LrGG by preoperative advanced diffusion magnetic resonance imaging (dMRI).</p><p><strong>Materials and methods: </strong>48 patients with lower-grade gliomas (23 recurrence, 25 nonrecurrence) were recruited into this study. Different models of dMRI were reconstructed, including apparent fiber density (AFD), white matter tract integrity (WMTI), diffusion tensor imaging (DTI), diffusion kurtosis imaging (DKI), neurite orientation dispersion and density imaging (NODDI), Bingham NODDI and standard model imaging (SMI). Orthogonal Partial Least Squares-Discriminant Analysis (OPLS-DA) was used to construct a multiparametric prediction model for the diagnosis of postoperative recurrence.</p><p><strong>Results: </strong>The parameters derived from each dMRI model, including AFD, axon water fraction (AWF), mean diffusivity (MD), mean kurtosis (MK), fractional anisotropy (FA), intracellular volume fraction (ICVF), extra-axonal perpendicular diffusivity (De<sup>⊥</sup>), extra-axonal parallel diffusivity (De<sup>∥</sup>) and free water fraction (fw), showed significant differences between nonrecurrence group and recurrence group. The extra-axonal perpendicular diffusivity (De<sup>⊥</sup>) had the highest area under curve (AUC = 0.885), which was significantly higher than others. The variable importance for the projection (VIP) value of De<sup>⊥</sup> was also the highest. The AUC value of the multiparametric prediction model merging AFD, WMTI, DTI, DKI, NODDI, Bingham NODDI and SMI was up to 0.96.</p><p><strong>Conclusion: </strong>Preoperative advanced dMRI showed great efficacy in evaluating postoperative recurrence of LrGG and De<sup>⊥</sup> of SMI might be a valuable marker.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"24 1","pages":"134"},"PeriodicalIF":3.5,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11462830/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142388243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Outstanding increase in tumor-to-background ratio over time allows tumor localization by [89Zr]Zr-PSMA-617 PET/CT in early biochemical recurrence of prostate cancer. 在前列腺癌早期生化复发中,肿瘤与背景的比值随着时间的推移显著增加,这使得[89Zr]Zr-PSMA-617 PET/CT 能够对肿瘤进行定位。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2024-10-07 DOI: 10.1186/s40644-024-00778-5
Caroline Burgard, Florian Rosar, Elena Larsen, Fadi Khreish, Johannes Linxweiler, Robert J Marlowe, Andrea Schaefer-Schuler, Stephan Maus, Sven Petto, Mark Bartholomä, Samer Ezziddin

Background: Positron emission tomography/computed tomography (PET/CT) using prostate-specific membrane antigen (PSMA)-targeted radiotracers labeled with zirconium-89 (89Zr; half-life ~ 78.41 h) showed promise in localizing biochemical recurrence of prostate cancer (BCR) in pilot studies.

Methods: Retrospective analysis of 38 consecutive men with BCR (median [minimum-maximum] prostate-specific antigen 0.52 (0.12-2.50 ng/mL) undergoing [89Zr]Zr-PSMA-617 PET/CT post-negative [68Ga]Ga-PSMA-11 PET/CT. PET/CT acquisition 1-h, 24-h, and 48-h post-injection of a median (minimum-maximum) [89Zr]Zr-PSMA-617 tracer activity of 123 (84-166) MBq.

Results: [89Zr]Zr-PSMA-617 PET/CT detected altogether 57 lesions: 18 local recurrences, 33 lymph node metastases, 6 bone metastases in 30/38 men with BCR (78%) and prior negative conventional PSMA PET/CT. Lesion uptake significantly increased from 1-h to 24-h and, in a majority of cases, from 24-h to 48-h. Tumor-to-background ratios significantly increased over time, with absolute increases of 100 or more. No side effects were noted. After [89Zr]Zr-PSMA-617 PET/CT-based treatment, prostate-specific antigen concentration decreased in all patients, becoming undetectable in a third of patients.

Limitations: retrospective, single center design; infrequent histopathological and imaging verification.

Conclusion: This large series provides further evidence that [89Zr]Zr-PSMA-617 PET/CT is a beneficial imaging modality to localize early BCR. A remarkable increase in tumor-to-background ratio over time allows localization of tumor unidentified on conventional PSMA PET/CT.

背景:使用锆-89(89Zr;半衰期~78.41 h)标记的前列腺特异性膜抗原(PSMA)靶向放射性核素的正电子发射断层扫描/计算机断层扫描(PET/CT)在试点研究中显示有望定位前列腺癌(BCR)的生化复发:回顾性分析38名连续BCR男性患者(前列腺特异性抗原中位数[最小值-最大值]为0.52(0.12-2.50纳克/毫升),在[68Ga]Ga-PSMA-11 PET/CT阴性后接受[89Zr]Zr-PSMA-617 PET/CT检查。PET/CT 采集注射后 1 小时、24 小时和 48 小时的中位(最小-最大)[89Zr]Zr-PSMA-617 示踪剂活性为 123 (84-166) MBq:结果:[89Zr]Zr-PSMA-617 PET/CT 共检测到 57 个病灶:在 30/38 名患有 BCR(78%)且之前常规 PSMA PET/CT 阴性的男性患者中,共发现了 18 个局部复发病灶、33 个淋巴结转移灶和 6 个骨转移灶。病灶摄取量从 1 小时到 24 小时明显增加,大多数病例的摄取量从 24 小时到 48 小时也明显增加。随着时间的推移,肿瘤与背景的比率明显增加,绝对值增加了100或更多。没有发现任何副作用。所有患者接受[89Zr]Zr-PSMA-617 PET/CT治疗后,前列腺特异性抗原浓度均有所下降,三分之一的患者检测不到前列腺特异性抗原:这一大型系列研究进一步证明,[89Zr]Zr-PSMA-617 PET/CT 是一种对早期 BCR 定位有益的成像模式。随着时间的推移,肿瘤与背景的比值会明显增加,因此可以对传统 PSMA PET/CT 无法识别的肿瘤进行定位。
{"title":"Outstanding increase in tumor-to-background ratio over time allows tumor localization by [<sup>89</sup>Zr]Zr-PSMA-617 PET/CT in early biochemical recurrence of prostate cancer.","authors":"Caroline Burgard, Florian Rosar, Elena Larsen, Fadi Khreish, Johannes Linxweiler, Robert J Marlowe, Andrea Schaefer-Schuler, Stephan Maus, Sven Petto, Mark Bartholomä, Samer Ezziddin","doi":"10.1186/s40644-024-00778-5","DOIUrl":"https://doi.org/10.1186/s40644-024-00778-5","url":null,"abstract":"<p><strong>Background: </strong>Positron emission tomography/computed tomography (PET/CT) using prostate-specific membrane antigen (PSMA)-targeted radiotracers labeled with zirconium-89 (<sup>89</sup>Zr; half-life ~ 78.41 h) showed promise in localizing biochemical recurrence of prostate cancer (BCR) in pilot studies.</p><p><strong>Methods: </strong>Retrospective analysis of 38 consecutive men with BCR (median [minimum-maximum] prostate-specific antigen 0.52 (0.12-2.50 ng/mL) undergoing [<sup>89</sup>Zr]Zr-PSMA-617 PET/CT post-negative [<sup>68</sup>Ga]Ga-PSMA-11 PET/CT. PET/CT acquisition 1-h, 24-h, and 48-h post-injection of a median (minimum-maximum) [<sup>89</sup>Zr]Zr-PSMA-617 tracer activity of 123 (84-166) MBq.</p><p><strong>Results: </strong>[<sup>89</sup>Zr]Zr-PSMA-617 PET/CT detected altogether 57 lesions: 18 local recurrences, 33 lymph node metastases, 6 bone metastases in 30/38 men with BCR (78%) and prior negative conventional PSMA PET/CT. Lesion uptake significantly increased from 1-h to 24-h and, in a majority of cases, from 24-h to 48-h. Tumor-to-background ratios significantly increased over time, with absolute increases of 100 or more. No side effects were noted. After [<sup>89</sup>Zr]Zr-PSMA-617 PET/CT-based treatment, prostate-specific antigen concentration decreased in all patients, becoming undetectable in a third of patients.</p><p><strong>Limitations: </strong>retrospective, single center design; infrequent histopathological and imaging verification.</p><p><strong>Conclusion: </strong>This large series provides further evidence that [<sup>89</sup>Zr]Zr-PSMA-617 PET/CT is a beneficial imaging modality to localize early BCR. A remarkable increase in tumor-to-background ratio over time allows localization of tumor unidentified on conventional PSMA PET/CT.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"24 1","pages":"132"},"PeriodicalIF":3.5,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11457487/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142388245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
-New frontiers in domain-inspired radiomics and radiogenomics: increasing role of molecular diagnostics in CNS tumor classification and grading following WHO CNS-5 updates. -领域启发放射组学和放射基因组学的新前沿:继世界卫生组织 CNS-5 更新之后,分子诊断在中枢神经系统肿瘤分类和分级中的作用日益增强。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2024-10-07 DOI: 10.1186/s40644-024-00769-6
Gagandeep Singh, Annie Singh, Joseph Bae, Sunil Manjila, Vadim Spektor, Prateek Prasanna, Angela Lignelli

Gliomas and Glioblastomas represent a significant portion of central nervous system (CNS) tumors associated with high mortality rates and variable prognosis. In 2021, the World Health Organization (WHO) updated its Glioma classification criteria, most notably incorporating molecular markers including CDKN2A/B homozygous deletion, TERT promoter mutation, EGFR amplification, + 7/-10 chromosome copy number changes, and others into the grading and classification of adult and pediatric Gliomas. The inclusion of these markers and the corresponding introduction of new Glioma subtypes has allowed for more specific tailoring of clinical interventions and has inspired a new wave of Radiogenomic studies seeking to leverage medical imaging information to explore the diagnostic and prognostic implications of these new biomarkers. Radiomics, deep learning, and combined approaches have enabled the development of powerful computational tools for MRI analysis correlating imaging characteristics with various molecular biomarkers integrated into the updated WHO CNS-5 guidelines. Recent studies have leveraged these methods to accurately classify Gliomas in accordance with these updated molecular-based criteria based solely on non-invasive MRI, demonstrating the great promise of Radiogenomic tools. In this review, we explore the relative benefits and drawbacks of these computational frameworks and highlight the technical and clinical innovations presented by recent studies in the landscape of fast evolving molecular-based Glioma subtyping. Furthermore, the potential benefits and challenges of incorporating these tools into routine radiological workflows, aiming to enhance patient care and optimize clinical outcomes in the evolving field of CNS tumor management, have been highlighted.

胶质瘤和胶质母细胞瘤在中枢神经系统(CNS)肿瘤中占很大比例,死亡率高且预后不一。2021 年,世界卫生组织(WHO)更新了胶质瘤分类标准,其中最引人注目的是将 CDKN2A/B 基因同源缺失、TERT 启动子突变、表皮生长因子受体扩增、+7/-10 染色体拷贝数变化等分子标记纳入成人和儿童胶质瘤的分级和分类。这些标记物的纳入以及相应的新胶质瘤亚型的引入,使得临床干预措施更具针对性,并激发了新一轮放射基因组学研究的热潮,这些研究试图利用医学影像信息来探索这些新生物标记物的诊断和预后意义。放射组学、深度学习和综合方法使人们能够开发出强大的核磁共振成像分析计算工具,将成像特征与各种分子生物标记物相关联,并将其纳入最新的世界卫生组织 CNS-5 指南。最近的研究利用这些方法,仅凭无创磁共振成像就能根据这些最新的基于分子的标准对胶质瘤进行准确分类,展示了放射基因组学工具的巨大前景。在这篇综述中,我们探讨了这些计算框架的相对优势和缺点,并重点介绍了在基于分子的胶质瘤亚型快速发展的背景下,近期研究带来的技术和临床创新。此外,我们还强调了将这些工具纳入常规放射学工作流程的潜在好处和挑战,目的是在不断发展的中枢神经系统肿瘤管理领域加强患者护理和优化临床结果。
{"title":"-New frontiers in domain-inspired radiomics and radiogenomics: increasing role of molecular diagnostics in CNS tumor classification and grading following WHO CNS-5 updates.","authors":"Gagandeep Singh, Annie Singh, Joseph Bae, Sunil Manjila, Vadim Spektor, Prateek Prasanna, Angela Lignelli","doi":"10.1186/s40644-024-00769-6","DOIUrl":"10.1186/s40644-024-00769-6","url":null,"abstract":"<p><p>Gliomas and Glioblastomas represent a significant portion of central nervous system (CNS) tumors associated with high mortality rates and variable prognosis. In 2021, the World Health Organization (WHO) updated its Glioma classification criteria, most notably incorporating molecular markers including CDKN2A/B homozygous deletion, TERT promoter mutation, EGFR amplification, + 7/-10 chromosome copy number changes, and others into the grading and classification of adult and pediatric Gliomas. The inclusion of these markers and the corresponding introduction of new Glioma subtypes has allowed for more specific tailoring of clinical interventions and has inspired a new wave of Radiogenomic studies seeking to leverage medical imaging information to explore the diagnostic and prognostic implications of these new biomarkers. Radiomics, deep learning, and combined approaches have enabled the development of powerful computational tools for MRI analysis correlating imaging characteristics with various molecular biomarkers integrated into the updated WHO CNS-5 guidelines. Recent studies have leveraged these methods to accurately classify Gliomas in accordance with these updated molecular-based criteria based solely on non-invasive MRI, demonstrating the great promise of Radiogenomic tools. In this review, we explore the relative benefits and drawbacks of these computational frameworks and highlight the technical and clinical innovations presented by recent studies in the landscape of fast evolving molecular-based Glioma subtyping. Furthermore, the potential benefits and challenges of incorporating these tools into routine radiological workflows, aiming to enhance patient care and optimize clinical outcomes in the evolving field of CNS tumor management, have been highlighted.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"24 1","pages":"133"},"PeriodicalIF":3.5,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11460168/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142388244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Computed tomography-based radiomics nomogram for prediction of lympho-vascular and perineural invasion in esophageal squamous cell cancer patients: a retrospective cohort study. 基于计算机断层扫描的放射组学提名图用于预测食管鳞状细胞癌患者的淋巴管和神经周围侵犯:一项回顾性队列研究。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2024-10-04 DOI: 10.1186/s40644-024-00781-w
Bin Tang, Fan Wu, Lin Peng, Xuefeng Leng, Yongtao Han, Qifeng Wang, Junxiang Wu, Lucia Clara Orlandini

Purpose: Lympho-vascular invasion (LVI) and perineural invasion (PNI) have been established as prognostic factors in various types of cancers. The preoperative prediction of LVI and PNI has the potential to guide personalized medicine strategies for patients with esophageal squamous cell cancer (ESCC). This study investigates whether radiomics features derived from preoperative contrast-enhanced CT could predict LVI and PNI in ESCC patients.

Methods and materials: A retrospective cohort of 544 ESCC patients who underwent esophagectomy were included in this study. Preoperative contrast-enhanced CT images, pathological results of PNI and LVI, and clinical characteristics were collected. For each patient, the gross tumor volume (GTV-T) and lymph nodes volume (GTV-N) were delineated and four categories of radiomics features (first-order, shape, textural and wavelet) were extracted from GTV-T and GTV-N. The Mann-Whitney U test was used to select significant features associated with LVI and PNI in turn. Subsequently, radiomics signatures for LVI and PNI were constructed using LASSO regression with ten-fold cross-validation. Significant clinical characteristics were combined with radiomics signature to develop two nomogram models for predicting LVI and PNI, respectively. The area under the curve (AUC) and calibration curve were used to evaluate the predictive performance of the models.

Results: The radiomics signature for LVI prediction consisted of 28 features, while the PNI radiomics signature comprised 14 features. The AUCs of the LVI radiomics signature were 0.77 and 0.74 in the training and validation groups, respectively, while the AUCs of the PNI radiomics signature were 0.69 and 0.68 in the training and validation groups. The nomograms incorporating radiomics signatures and significant clinical characteristics such as age, gender, thrombin time and D-Dimer showed improved predictive performance for both LVI (AUC: 0.82 and 0.80 in the training and validation group) and PNI (AUC: 0.75 and 0.72 in the training and validation groups) compared to the radiomics signature alone.

Conclusion: The radiomics features extracted from preoperative contrast-enhanced CT of gross tumor and lymph nodes have demonstrated their potential in predicting LVI and PNI in ESCC patients. Furthermore, the incorporation of clinical characteristics has shown additional value, resulting in improved predictive performance.

目的:淋巴管侵犯(LVI)和神经周围侵犯(PNI)已被确定为各类癌症的预后因素。术前预测 LVI 和 PNI 有可能为食管鳞状细胞癌(ESCC)患者的个性化医疗策略提供指导。本研究探讨了从术前对比增强 CT 中得出的放射组学特征是否能预测 ESCC 患者的 LVI 和 PNI:本研究纳入了 544 名接受食管切除术的 ESCC 患者的回顾性队列。研究收集了术前对比增强 CT 图像、PNI 和 LVI 的病理结果以及临床特征。为每位患者划定肿瘤总体积(GTV-T)和淋巴结体积(GTV-N),并从 GTV-T 和 GTV-N 中提取四类放射组学特征(一阶、形状、纹理和小波)。采用 Mann-Whitney U 检验依次筛选出与 LVI 和 PNI 相关的重要特征。随后,利用 LASSO 回归和十倍交叉验证构建了 LVI 和 PNI 的放射组学特征。将重要的临床特征与放射组学特征相结合,建立了两个提名图模型,分别用于预测 LVI 和 PNI。曲线下面积(AUC)和校准曲线用于评估模型的预测性能:预测 LVI 的放射组学特征包括 28 个特征,而预测 PNI 的放射组学特征包括 14 个特征。在训练组和验证组中,LVI放射组学特征的AUC分别为0.77和0.74,而在训练组和验证组中,PNI放射组学特征的AUC分别为0.69和0.68。与单独的放射组学特征相比,包含放射组学特征和重要临床特征(如年龄、性别、凝血酶时间和D-二聚体)的提名图对LVI(训练组和验证组的AUC分别为0.82和0.80)和PNI(训练组和验证组的AUC分别为0.75和0.72)的预测性能都有所提高:结论:从术前造影剂增强 CT 的肿瘤和淋巴结提取的放射组学特征证明了它们在预测 ESCC 患者 LVI 和 PNI 方面的潜力。此外,结合临床特征也显示出了额外的价值,从而提高了预测性能。
{"title":"Computed tomography-based radiomics nomogram for prediction of lympho-vascular and perineural invasion in esophageal squamous cell cancer patients: a retrospective cohort study.","authors":"Bin Tang, Fan Wu, Lin Peng, Xuefeng Leng, Yongtao Han, Qifeng Wang, Junxiang Wu, Lucia Clara Orlandini","doi":"10.1186/s40644-024-00781-w","DOIUrl":"10.1186/s40644-024-00781-w","url":null,"abstract":"<p><strong>Purpose: </strong>Lympho-vascular invasion (LVI) and perineural invasion (PNI) have been established as prognostic factors in various types of cancers. The preoperative prediction of LVI and PNI has the potential to guide personalized medicine strategies for patients with esophageal squamous cell cancer (ESCC). This study investigates whether radiomics features derived from preoperative contrast-enhanced CT could predict LVI and PNI in ESCC patients.</p><p><strong>Methods and materials: </strong>A retrospective cohort of 544 ESCC patients who underwent esophagectomy were included in this study. Preoperative contrast-enhanced CT images, pathological results of PNI and LVI, and clinical characteristics were collected. For each patient, the gross tumor volume (GTV-T) and lymph nodes volume (GTV-N) were delineated and four categories of radiomics features (first-order, shape, textural and wavelet) were extracted from GTV-T and GTV-N. The Mann-Whitney U test was used to select significant features associated with LVI and PNI in turn. Subsequently, radiomics signatures for LVI and PNI were constructed using LASSO regression with ten-fold cross-validation. Significant clinical characteristics were combined with radiomics signature to develop two nomogram models for predicting LVI and PNI, respectively. The area under the curve (AUC) and calibration curve were used to evaluate the predictive performance of the models.</p><p><strong>Results: </strong>The radiomics signature for LVI prediction consisted of 28 features, while the PNI radiomics signature comprised 14 features. The AUCs of the LVI radiomics signature were 0.77 and 0.74 in the training and validation groups, respectively, while the AUCs of the PNI radiomics signature were 0.69 and 0.68 in the training and validation groups. The nomograms incorporating radiomics signatures and significant clinical characteristics such as age, gender, thrombin time and D-Dimer showed improved predictive performance for both LVI (AUC: 0.82 and 0.80 in the training and validation group) and PNI (AUC: 0.75 and 0.72 in the training and validation groups) compared to the radiomics signature alone.</p><p><strong>Conclusion: </strong>The radiomics features extracted from preoperative contrast-enhanced CT of gross tumor and lymph nodes have demonstrated their potential in predicting LVI and PNI in ESCC patients. Furthermore, the incorporation of clinical characteristics has shown additional value, resulting in improved predictive performance.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"24 1","pages":"131"},"PeriodicalIF":3.5,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11451056/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142375132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
CT-based conventional radiomics and quantification of intratumoral heterogeneity for predicting benign and malignant renal lesions. 基于 CT 的常规放射组学和瘤内异质性量化,用于预测良性和恶性肾脏病变。
IF 3.5 2区 医学 Q2 ONCOLOGY Pub Date : 2024-10-02 DOI: 10.1186/s40644-024-00775-8
Shuanbao Yu, Yang Yang, Zeyuan Wang, Haoke Zheng, Jinshan Cui, Yonghao Zhan, Junxiao Liu, Peng Li, Yafeng Fan, Wendong Jia, Meng Wang, Bo Chen, Jin Tao, Yuhong Li, Xuepei Zhang

Background: With the increasing incidence of renal lesions, pretreatment differentiation between benign and malignant lesions is crucial for optimized management. This study aimed to develop a machine learning model utilizing radiomic features extracted from various regions of interest (ROIs), intratumoral ecological diversity features, and clinical factors to classify renal lesions.

Methods: CT images (arterial phase) of 1,795 renal lesions with confirmed pathology from three hospital sites were split into development (1184, 66%) and test (611, 34%) cohorts by surgery date. Conventional radiomic features were extracted from eight ROIs of arterial phase images. Intratumoral ecological diversity features were derived from intratumoral subregions. The combined model incorporating these features with clinical factors was developed, and its performance was compared with radiologists' interpretation.

Results: Combining intratumoral and peritumoral radiomic features, along with ecological diversity features yielded the highest AUC of 0.929 among all combinations of features extracted from CT scans. After incorporating clinical factors into the features extracted from CT images, our combined model outperformed the interpretation of radiologists in the whole (AUC = 0.946 vs 0.823, P < 0.001) and small renal lesion (AUC = 0.935 vs 0.745, P < 0.001) test cohorts. Furthermore, the combined model exhibited favorable concordance and provided the highest net benefit across threshold probabilities exceeding 60%. In the whole and small renal lesion test cohorts, the AUCs for subgroups with predicted risk below or above 95% sensitivity and specificity cutoffs were 0.974 and 0.978, respectively.

Conclusions: The combined model, incorporating intratumoral and peritumoral radiomic features, ecological diversity features, and clinical factors showed good performance for distinguishing benign from malignant renal lesions, surpassing radiologists' diagnoses in both whole and small renal lesions. It has the potential to save patients from unnecessary invasive biopsies/surgeries and to enhance clinical decision-making.

背景:随着肾脏病变发病率的增加,良性和恶性病变的预处理区分对于优化治疗至关重要。本研究旨在开发一种机器学习模型,利用从不同感兴趣区(ROI)提取的放射学特征、瘤内生态多样性特征和临床因素对肾脏病变进行分类:按手术日期将三家医院 1795 例确诊病变的肾脏 CT 图像(动脉期)分为开发组(1184 例,66%)和测试组(611 例,34%)。从动脉相位图像的八个 ROI 提取常规放射学特征。瘤内生态多样性特征来自瘤内子区域。将这些特征与临床因素结合在一起的综合模型得以开发,并将其性能与放射科医生的解释进行了比较:结果:在所有从 CT 扫描中提取的特征组合中,结合瘤内和瘤周放射学特征以及生态多样性特征得出的 AUC 最高,为 0.929。在将临床因素纳入从 CT 图像中提取的特征后,我们的组合模型在整体上优于放射科医生的判读(AUC = 0.946 vs 0.823,P 结论:将瘤内和瘤周放射学特征与生态多样性特征相结合的组合模型,在所有从 CT 扫描中提取的特征组合中,AUC 最高,为 0.929:结合瘤内和瘤周放射学特征、生态多样性特征和临床因素的组合模型在区分肾脏良恶性病变方面表现良好,在肾脏整体病变和小病变方面均优于放射科医生的诊断。它有望使患者免于不必要的侵入性活检/手术,并提高临床决策水平。
{"title":"CT-based conventional radiomics and quantification of intratumoral heterogeneity for predicting benign and malignant renal lesions.","authors":"Shuanbao Yu, Yang Yang, Zeyuan Wang, Haoke Zheng, Jinshan Cui, Yonghao Zhan, Junxiao Liu, Peng Li, Yafeng Fan, Wendong Jia, Meng Wang, Bo Chen, Jin Tao, Yuhong Li, Xuepei Zhang","doi":"10.1186/s40644-024-00775-8","DOIUrl":"10.1186/s40644-024-00775-8","url":null,"abstract":"<p><strong>Background: </strong>With the increasing incidence of renal lesions, pretreatment differentiation between benign and malignant lesions is crucial for optimized management. This study aimed to develop a machine learning model utilizing radiomic features extracted from various regions of interest (ROIs), intratumoral ecological diversity features, and clinical factors to classify renal lesions.</p><p><strong>Methods: </strong>CT images (arterial phase) of 1,795 renal lesions with confirmed pathology from three hospital sites were split into development (1184, 66%) and test (611, 34%) cohorts by surgery date. Conventional radiomic features were extracted from eight ROIs of arterial phase images. Intratumoral ecological diversity features were derived from intratumoral subregions. The combined model incorporating these features with clinical factors was developed, and its performance was compared with radiologists' interpretation.</p><p><strong>Results: </strong>Combining intratumoral and peritumoral radiomic features, along with ecological diversity features yielded the highest AUC of 0.929 among all combinations of features extracted from CT scans. After incorporating clinical factors into the features extracted from CT images, our combined model outperformed the interpretation of radiologists in the whole (AUC = 0.946 vs 0.823, P < 0.001) and small renal lesion (AUC = 0.935 vs 0.745, P < 0.001) test cohorts. Furthermore, the combined model exhibited favorable concordance and provided the highest net benefit across threshold probabilities exceeding 60%. In the whole and small renal lesion test cohorts, the AUCs for subgroups with predicted risk below or above 95% sensitivity and specificity cutoffs were 0.974 and 0.978, respectively.</p><p><strong>Conclusions: </strong>The combined model, incorporating intratumoral and peritumoral radiomic features, ecological diversity features, and clinical factors showed good performance for distinguishing benign from malignant renal lesions, surpassing radiologists' diagnoses in both whole and small renal lesions. It has the potential to save patients from unnecessary invasive biopsies/surgeries and to enhance clinical decision-making.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":"24 1","pages":"130"},"PeriodicalIF":3.5,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11446113/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142364517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Cancer Imaging
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1