Background: Lung cancer (LC) is a leading cause of cancer-related mortality, and immunotherapy (IO) has shown promise in treating advanced-stage LC. However, identifying patients likely to benefit from IO and monitoring treatment response remains challenging. This study aims to develop a predictive model for progression-free survival (PFS) in LC patients with IO based on clinical features and advanced imaging biomarkers.
Materials and methods: A retrospective analysis was conducted on a cohort of 206 LC patients receiving IO treatment. Pre-treatment computed tomography images were used to extract advanced imaging biomarkers, including intratumoral and peritumoral-vasculature radiomics. Clinical features, including age, gene status, hematology, and staging, were also collected. Key radiomic and clinical features for predicting IO outcomes were identified using a two-step feature selection process, including univariate Cox regression and chi-squared test, followed by sequential forward selection. The DeepSurv model was constructed to predict PFS based on clinical and radiomic features. Model performance was evaluated using the area under the time-dependent receiver operating characteristic curve (AUC) and concordance index (C-index).
Results: Combining radiomics of intratumoral heterogeneity and peritumoral-vasculature with clinical features demonstrated a significant enhancement (p < 0.001) in predicting IO response. The proposed DeepSurv model exhibited a prediction performance with AUCs ranging from 0.76 to 0.80 and a C-index of 0.83. Furthermore, the predicted personalized PFS curves revealed a significant difference (p < 0.05) between patients with favorable and unfavorable prognoses.
Conclusions: Integrating intratumoral and peritumoral-vasculature radiomics with clinical features enabled the development of a predictive model for PFS in LC patients with IO. The proposed model's capability to estimate individualized PFS probability and differentiate the prognosis status held promise to facilitate personalized medicine and improve patient outcomes in LC.
{"title":"Personalized prediction of immunotherapy response in lung cancer patients using advanced radiomics and deep learning.","authors":"Chien-Yi Liao, Yuh-Min Chen, Yu-Te Wu, Heng-Sheng Chao, Hwa-Yen Chiu, Ting-Wei Wang, Jyun-Ru Chen, Tsu-Hui Shiao, Chia-Feng Lu","doi":"10.1186/s40644-024-00779-4","DOIUrl":"10.1186/s40644-024-00779-4","url":null,"abstract":"<p><strong>Background: </strong>Lung cancer (LC) is a leading cause of cancer-related mortality, and immunotherapy (IO) has shown promise in treating advanced-stage LC. However, identifying patients likely to benefit from IO and monitoring treatment response remains challenging. This study aims to develop a predictive model for progression-free survival (PFS) in LC patients with IO based on clinical features and advanced imaging biomarkers.</p><p><strong>Materials and methods: </strong>A retrospective analysis was conducted on a cohort of 206 LC patients receiving IO treatment. Pre-treatment computed tomography images were used to extract advanced imaging biomarkers, including intratumoral and peritumoral-vasculature radiomics. Clinical features, including age, gene status, hematology, and staging, were also collected. Key radiomic and clinical features for predicting IO outcomes were identified using a two-step feature selection process, including univariate Cox regression and chi-squared test, followed by sequential forward selection. The DeepSurv model was constructed to predict PFS based on clinical and radiomic features. Model performance was evaluated using the area under the time-dependent receiver operating characteristic curve (AUC) and concordance index (C-index).</p><p><strong>Results: </strong>Combining radiomics of intratumoral heterogeneity and peritumoral-vasculature with clinical features demonstrated a significant enhancement (p < 0.001) in predicting IO response. The proposed DeepSurv model exhibited a prediction performance with AUCs ranging from 0.76 to 0.80 and a C-index of 0.83. Furthermore, the predicted personalized PFS curves revealed a significant difference (p < 0.05) between patients with favorable and unfavorable prognoses.</p><p><strong>Conclusions: </strong>Integrating intratumoral and peritumoral-vasculature radiomics with clinical features enabled the development of a predictive model for PFS in LC patients with IO. The proposed model's capability to estimate individualized PFS probability and differentiate the prognosis status held promise to facilitate personalized medicine and improve patient outcomes in LC.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11440728/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142342218","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}
Pub Date : 2024-09-26DOI: 10.1186/s40644-024-00777-6
Rui Guo, Wanpu Yan, Fei Wang, Hua Su, Xiangxi Meng, Qing Xie, Wei Zhao, Zhi Yang, Nan Li
{"title":"Correction: The utility of <sup>18</sup>F-FDG PET/CT for predicting the pathological response and prognosis to neoadjuvant immunochemotherapy in resectable non-small-cell lung cancer.","authors":"Rui Guo, Wanpu Yan, Fei Wang, Hua Su, Xiangxi Meng, Qing Xie, Wei Zhao, Zhi Yang, Nan Li","doi":"10.1186/s40644-024-00777-6","DOIUrl":"https://doi.org/10.1186/s40644-024-00777-6","url":null,"abstract":"","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11425872/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142342217","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}
Pub Date : 2024-09-20DOI: 10.1186/s40644-024-00762-z
Atena Najdian, Davood Beiki, Milad Abbasi, Ali Gholamrezanezhad, Hojjat Ahmadzadehfar, Ali Mohammad Amani, Mehdi Shafiee Ardestani, Majid Assadi
Multimodal imaging unfolds as an innovative approach that synergistically employs a spectrum of imaging techniques either simultaneously or sequentially. The integration of computed tomography (CT), magnetic resonance imaging (MRI), single-photon emission computed tomography (SPECT), positron emission tomography (PET), and optical imaging (OI) results in a comprehensive and complementary understanding of complex biological processes. This innovative approach combines the strengths of each method and overcoming their individual limitations. By harmoniously blending data from these modalities, it significantly improves the accuracy of cancer diagnosis and aids in treatment decision-making processes. Nanoparticles possess a high potential for facile functionalization with radioactive isotopes and a wide array of contrast agents. This strategic modification serves to augment signal amplification, significantly enhance image sensitivity, and elevate contrast indices. Such tailored nanoparticles constructs exhibit a promising avenue for advancing imaging modalities in both preclinical and clinical setting. Furthermore, nanoparticles function as a unified nanoplatform for the co-localization of imaging agents and therapeutic payloads, thereby optimizing the efficiency of cancer management strategies. Consequently, radiolabeled nanoparticles exhibit substantial potential in driving forward the realms of multimodal imaging and theranostic applications. This review discusses the potential applications of molecular imaging in cancer diagnosis, the utilization of nanotechnology-based radiolabeled materials in multimodal imaging and theranostic applications, as well as recent advancements in this field. It also highlights challenges including cytotoxicity and regulatory compliance, essential considerations for effective clinical translation of nanoradiopharmaceuticals in multimodal imaging and theranostic applications.
{"title":"Exploring innovative strides in radiolabeled nanoparticle progress for multimodality cancer imaging and theranostic applications.","authors":"Atena Najdian, Davood Beiki, Milad Abbasi, Ali Gholamrezanezhad, Hojjat Ahmadzadehfar, Ali Mohammad Amani, Mehdi Shafiee Ardestani, Majid Assadi","doi":"10.1186/s40644-024-00762-z","DOIUrl":"https://doi.org/10.1186/s40644-024-00762-z","url":null,"abstract":"<p><p>Multimodal imaging unfolds as an innovative approach that synergistically employs a spectrum of imaging techniques either simultaneously or sequentially. The integration of computed tomography (CT), magnetic resonance imaging (MRI), single-photon emission computed tomography (SPECT), positron emission tomography (PET), and optical imaging (OI) results in a comprehensive and complementary understanding of complex biological processes. This innovative approach combines the strengths of each method and overcoming their individual limitations. By harmoniously blending data from these modalities, it significantly improves the accuracy of cancer diagnosis and aids in treatment decision-making processes. Nanoparticles possess a high potential for facile functionalization with radioactive isotopes and a wide array of contrast agents. This strategic modification serves to augment signal amplification, significantly enhance image sensitivity, and elevate contrast indices. Such tailored nanoparticles constructs exhibit a promising avenue for advancing imaging modalities in both preclinical and clinical setting. Furthermore, nanoparticles function as a unified nanoplatform for the co-localization of imaging agents and therapeutic payloads, thereby optimizing the efficiency of cancer management strategies. Consequently, radiolabeled nanoparticles exhibit substantial potential in driving forward the realms of multimodal imaging and theranostic applications. This review discusses the potential applications of molecular imaging in cancer diagnosis, the utilization of nanotechnology-based radiolabeled materials in multimodal imaging and theranostic applications, as well as recent advancements in this field. It also highlights challenges including cytotoxicity and regulatory compliance, essential considerations for effective clinical translation of nanoradiopharmaceuticals in multimodal imaging and theranostic applications.</p>","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":null,"pages":null},"PeriodicalIF":3.5,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11416024/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142280554","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}
Pub Date : 2024-09-19DOI: 10.1186/s40644-024-00773-w
David Ventura, Philipp Rassek, Philipp Schindler, Burak Han Akkurt, Linus Bredensteiner, Martin Bögemann, Katrin Schlack, Robert Seifert, Michael Schäfers, Wolfgang Roll, Kambiz Rahbar
Prostate-specific membrane antigen positron emission tomography (PSMA-PET) is an essential tool for patient selection before radioligand therapy (RLT). Interim-staging with PSMA-PET during RLT allows for therapy monitoring. However, its added value over post-treatment imaging is poorly elucidated. The aim of this study was to compare early treatment response assessed by post-therapeutic whole-body scans (WBS) with interim-staging by PSMA-PET after 2 cycles in order to prognosticate OS. Men with metastasized castration-resistant PC (mCRPC) who had received at least two cycles of RLT, and interim PSMA-PET were evaluated retrospectively. PROMISE V2 framework was used to categorize PSMA expression and assess response to treatment. Response was defined as either disease control rate (DCR) for responders or progression for non-responders. A total of 188 men with mCRPC who underwent RLT between February 2015 and December 2021 were included. The comparison of different imaging modalities revealed a strong and significant correlation with Cramer V test: e.g. response on WBS during second cycle compared to interim PET after two cycles of RLT (cφ = 0.888, P < 0.001, n = 188). The median follow-up time was 14.7 months (range: 3–63 months; 125 deaths occurred). Median overall survival (OS) time was 14.5 months (95% CI: 11.9–15.9). In terms of OS analysis, early progression during therapy revealed a significantly higher likelihood of death: e.g. second cycle WBS (15 vs. 25 months, P < 0.001) with a HR of 2.81 (P < 0.001) or at PET timepoint after 2 cycles of RLT (11 vs. 24 months, P < 0.001) with a HR of 3.5 (P < 0.001). For early biochemical response, a PSA decline of at least 50% after two cycles of RLT indicates a significantly lower likelihood of death (26 vs. 17 months, P < 0.001) with a HR of 0.5 (P < 0.001). Response assessment of RLT by WBS and interim PET after two cycles of RLT have high congruence and can identify patients at risk of poor outcome. This indicates that interim PET might be omitted for response assessment, but future trials corroborating these findings are warranted.
{"title":"Early treatment response assessment with [177Lu]PSMA whole-body-scintigraphy compared to interim PSMA-PET","authors":"David Ventura, Philipp Rassek, Philipp Schindler, Burak Han Akkurt, Linus Bredensteiner, Martin Bögemann, Katrin Schlack, Robert Seifert, Michael Schäfers, Wolfgang Roll, Kambiz Rahbar","doi":"10.1186/s40644-024-00773-w","DOIUrl":"https://doi.org/10.1186/s40644-024-00773-w","url":null,"abstract":"Prostate-specific membrane antigen positron emission tomography (PSMA-PET) is an essential tool for patient selection before radioligand therapy (RLT). Interim-staging with PSMA-PET during RLT allows for therapy monitoring. However, its added value over post-treatment imaging is poorly elucidated. The aim of this study was to compare early treatment response assessed by post-therapeutic whole-body scans (WBS) with interim-staging by PSMA-PET after 2 cycles in order to prognosticate OS. Men with metastasized castration-resistant PC (mCRPC) who had received at least two cycles of RLT, and interim PSMA-PET were evaluated retrospectively. PROMISE V2 framework was used to categorize PSMA expression and assess response to treatment. Response was defined as either disease control rate (DCR) for responders or progression for non-responders. A total of 188 men with mCRPC who underwent RLT between February 2015 and December 2021 were included. The comparison of different imaging modalities revealed a strong and significant correlation with Cramer V test: e.g. response on WBS during second cycle compared to interim PET after two cycles of RLT (cφ = 0.888, P < 0.001, n = 188). The median follow-up time was 14.7 months (range: 3–63 months; 125 deaths occurred). Median overall survival (OS) time was 14.5 months (95% CI: 11.9–15.9). In terms of OS analysis, early progression during therapy revealed a significantly higher likelihood of death: e.g. second cycle WBS (15 vs. 25 months, P < 0.001) with a HR of 2.81 (P < 0.001) or at PET timepoint after 2 cycles of RLT (11 vs. 24 months, P < 0.001) with a HR of 3.5 (P < 0.001). For early biochemical response, a PSA decline of at least 50% after two cycles of RLT indicates a significantly lower likelihood of death (26 vs. 17 months, P < 0.001) with a HR of 0.5 (P < 0.001). Response assessment of RLT by WBS and interim PET after two cycles of RLT have high congruence and can identify patients at risk of poor outcome. This indicates that interim PET might be omitted for response assessment, but future trials corroborating these findings are warranted.","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142261995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-17DOI: 10.1186/s40644-024-00774-9
Giulia Santo, Maria Cucè, Antonino Restuccia, Teresa Del Giudice, Pierfrancesco Tassone, Francesco Cicone, Pierosandro Tagliaferri, Giuseppe Lucio Cascini
Direct comparisons between [18F]FDG PET/CT findings and clinical occurrence of immune-related adverse events (irAEs) based on independent assessments of clinical and imaging features in patients receiving immune checkpoint inhibitors (ICIs) are missing. Our aim was to estimate sites, frequency, and timing of immune-related PET findings during ICIs treatment in patients with melanoma and NSCLC, and to assess their correlation with clinical irAEs. Prognostic implications of immune-related events were also investigated. Fifty-one patients with melanoma (47%) or NSCLC (53%) undergoing multiple PET examinations during anti-PD1/PDL1 treatment were retrospectively included. Clinical irAEs were graded according to CTCAE v.5.0. Abnormal PET findings suggestive of immune activation were described by two readers blinded to the clinical data. Progression-free survival (PFS) and overall survival (OS) were analyzed with the Kaplan-Meier method in patients stratified according to the presence of irAEs, immune-related PET findings or both. Twenty-one patients showed clinical irAEs only (n = 6), immune-related PET findings only (n = 6), or both (n = 9). In patients whose imaging findings corresponded to clinical irAEs (n = 7), a positive correlation between SUVmax and the severity of the clinical event was observed (rs=0.763, p = 0.046). Clinical irAEs occurred more frequently in patients without macroscopic disease than in metastatic patients (55% vs. 23%, p = 0.039). Patients who developed clinical irAEs had a significantly longer PFS than patients who remained clinically asymptomatic, both in the overall cohort (p = 0.011) and in the subgroup of (n = 35) patients with metastatic disease (p = 0.019). The occurrence of immune-related PET findings significantly stratified PFS in the overall cohort (p = 0.040), and slightly missed statistical significance in patients with metastatic disease (p = 0.08). The best stratification of PFS was achieved when all patients who developed immune-related events, either clinically relevant or detected by PET only, were grouped together both in the overall cohort (p = 0.002) and in patients with metastatic disease (p = 0.004). In the whole sample, OS was longer in patients who developed any immune-related events (p = 0.032). Patients with melanoma or NSCLC under ICI treatment can develop clinical irAEs, immune-related PET findings, or both. The occurrence of immune-related events has a prognostic impact. Combining clinical information with PET assessment improved outcome stratification.
在接受免疫检查点抑制剂(ICIs)治疗的患者中,目前还没有基于临床和影像学特征独立评估的[18F]FDG PET/CT检查结果与免疫相关不良事件(irAEs)临床发生率之间的直接比较。我们的目的是估计黑色素瘤和 NSCLC 患者在 ICIs 治疗期间出现免疫相关 PET 发现的部位、频率和时间,并评估它们与临床 irAEs 的相关性。研究还探讨了免疫相关事件的预后影响。回顾性纳入了51名在抗PD1/PDL1治疗期间接受多次PET检查的黑色素瘤(47%)或NSCLC(53%)患者。临床 irAE 根据 CTCAE v.5.0 进行分级。提示免疫激活的 PET 异常发现由两名对临床数据保密的阅读者进行描述。采用卡普兰-梅耶法(Kaplan-Meier method)分析了根据虹膜AEs、免疫相关PET结果或两者的存在对患者进行分层的无进展生存期(PFS)和总生存期(OS)。21例患者仅出现临床虹膜异常(6例)、仅出现免疫相关PET结果(6例)或两者均有(9例)。在成像结果与临床虹膜急性缺失相一致的患者中(n = 7),观察到 SUVmax 与临床事件的严重程度呈正相关(rs=0.763,p = 0.046)。与转移性患者相比,无大体病变的患者发生临床虹膜AE的频率更高(55% vs. 23%,p = 0.039)。无论是在总体队列(p = 0.011)中,还是在转移性疾病患者亚组(n = 35)(p = 0.019)中,出现临床虹膜异常的患者的PFS明显长于临床无症状的患者。免疫相关PET检查结果的出现对总体队列的PFS分层有显著影响(p = 0.040),对转移性疾病患者的分层略微缺乏统计学意义(p = 0.08)。如果将所有发生免疫相关事件(无论是临床相关事件还是仅通过 PET 检测到的事件)的患者归为一组,则可对总体队列(p = 0.002)和转移性疾病患者(p = 0.004)的 PFS 进行最佳分层。在整个样本中,发生任何免疫相关事件的患者的OS更长(p = 0.032)。接受 ICI 治疗的黑色素瘤或 NSCLC 患者可能出现临床免疫相关事件、免疫相关 PET 发现或两者兼而有之。免疫相关事件的发生对预后有影响。将临床信息与 PET 评估相结合可改善预后分层。
{"title":"Immune-related [18F]FDG PET findings in patients undergoing checkpoint inhibitors treatment: correlation with clinical adverse events and prognostic implications","authors":"Giulia Santo, Maria Cucè, Antonino Restuccia, Teresa Del Giudice, Pierfrancesco Tassone, Francesco Cicone, Pierosandro Tagliaferri, Giuseppe Lucio Cascini","doi":"10.1186/s40644-024-00774-9","DOIUrl":"https://doi.org/10.1186/s40644-024-00774-9","url":null,"abstract":"Direct comparisons between [18F]FDG PET/CT findings and clinical occurrence of immune-related adverse events (irAEs) based on independent assessments of clinical and imaging features in patients receiving immune checkpoint inhibitors (ICIs) are missing. Our aim was to estimate sites, frequency, and timing of immune-related PET findings during ICIs treatment in patients with melanoma and NSCLC, and to assess their correlation with clinical irAEs. Prognostic implications of immune-related events were also investigated. Fifty-one patients with melanoma (47%) or NSCLC (53%) undergoing multiple PET examinations during anti-PD1/PDL1 treatment were retrospectively included. Clinical irAEs were graded according to CTCAE v.5.0. Abnormal PET findings suggestive of immune activation were described by two readers blinded to the clinical data. Progression-free survival (PFS) and overall survival (OS) were analyzed with the Kaplan-Meier method in patients stratified according to the presence of irAEs, immune-related PET findings or both. Twenty-one patients showed clinical irAEs only (n = 6), immune-related PET findings only (n = 6), or both (n = 9). In patients whose imaging findings corresponded to clinical irAEs (n = 7), a positive correlation between SUVmax and the severity of the clinical event was observed (rs=0.763, p = 0.046). Clinical irAEs occurred more frequently in patients without macroscopic disease than in metastatic patients (55% vs. 23%, p = 0.039). Patients who developed clinical irAEs had a significantly longer PFS than patients who remained clinically asymptomatic, both in the overall cohort (p = 0.011) and in the subgroup of (n = 35) patients with metastatic disease (p = 0.019). The occurrence of immune-related PET findings significantly stratified PFS in the overall cohort (p = 0.040), and slightly missed statistical significance in patients with metastatic disease (p = 0.08). The best stratification of PFS was achieved when all patients who developed immune-related events, either clinically relevant or detected by PET only, were grouped together both in the overall cohort (p = 0.002) and in patients with metastatic disease (p = 0.004). In the whole sample, OS was longer in patients who developed any immune-related events (p = 0.032). Patients with melanoma or NSCLC under ICI treatment can develop clinical irAEs, immune-related PET findings, or both. The occurrence of immune-related events has a prognostic impact. Combining clinical information with PET assessment improved outcome stratification.","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142261997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-16DOI: 10.1186/s40644-024-00768-7
Ji Wu, Jian Li, Bo Huang, Sunbin Dong, Luyang Wu, Xiping Shen, Zhigang Zheng
We aimed to develop and externally validate a CT-based deep learning radiomics model for predicting overall survival (OS) in clear cell renal cell carcinoma (ccRCC) patients, and investigate the association of radiomics with tumor heterogeneity and microenvironment. The clinicopathological data and contrast-enhanced CT images of 512 ccRCC patients from three institutions were collected. A total of 3566 deep learning radiomics features were extracted from 3D regions of interest. We generated the deep learning radiomics score (DLRS), and validated this score using an external cohort from TCIA. Patients were divided into high and low-score groups by the DLRS. Sequencing data from the corresponding TCGA cohort were used to reveal the differences of tumor heterogeneity and microenvironment between different radiomics score groups. What’s more, univariate and multivariate Cox regression were used to identify independent risk factors of poor OS after operation. A combined model was developed by incorporating the DLRS and clinicopathological features. The SHapley Additive exPlanation method was used for interpretation of predictive results. At multivariate Cox regression analysis, the DLRS was identified as an independent risk factor of poor OS. The genomic landscape of different radiomics score groups was investigated. The heterogeneity of tumor cell and tumor microenvironment significantly varied between both groups. In the test cohort, the combined model had a great predictive performance, with AUCs (95%CI) for 1, 3 and 5-year OS of 0.879(0.868–0.931), 0.854(0.819–0.899) and 0.831(0.813–0.868), respectively. There was a significant difference in survival time between different groups stratified by the combined model. This model showed great discrimination and calibration, outperforming the existing prognostic models (all p values < 0.05). The combined model allowed for the prognostic prediction of ccRCC patients by incorporating the DLRS and significant clinicopathologic features. The radiomics features could reflect the tumor heterogeneity and microenvironment.
{"title":"Radiomics predicts the prognosis of patients with clear cell renal cell carcinoma by reflecting the tumor heterogeneity and microenvironment","authors":"Ji Wu, Jian Li, Bo Huang, Sunbin Dong, Luyang Wu, Xiping Shen, Zhigang Zheng","doi":"10.1186/s40644-024-00768-7","DOIUrl":"https://doi.org/10.1186/s40644-024-00768-7","url":null,"abstract":"We aimed to develop and externally validate a CT-based deep learning radiomics model for predicting overall survival (OS) in clear cell renal cell carcinoma (ccRCC) patients, and investigate the association of radiomics with tumor heterogeneity and microenvironment. The clinicopathological data and contrast-enhanced CT images of 512 ccRCC patients from three institutions were collected. A total of 3566 deep learning radiomics features were extracted from 3D regions of interest. We generated the deep learning radiomics score (DLRS), and validated this score using an external cohort from TCIA. Patients were divided into high and low-score groups by the DLRS. Sequencing data from the corresponding TCGA cohort were used to reveal the differences of tumor heterogeneity and microenvironment between different radiomics score groups. What’s more, univariate and multivariate Cox regression were used to identify independent risk factors of poor OS after operation. A combined model was developed by incorporating the DLRS and clinicopathological features. The SHapley Additive exPlanation method was used for interpretation of predictive results. At multivariate Cox regression analysis, the DLRS was identified as an independent risk factor of poor OS. The genomic landscape of different radiomics score groups was investigated. The heterogeneity of tumor cell and tumor microenvironment significantly varied between both groups. In the test cohort, the combined model had a great predictive performance, with AUCs (95%CI) for 1, 3 and 5-year OS of 0.879(0.868–0.931), 0.854(0.819–0.899) and 0.831(0.813–0.868), respectively. There was a significant difference in survival time between different groups stratified by the combined model. This model showed great discrimination and calibration, outperforming the existing prognostic models (all p values < 0.05). The combined model allowed for the prognostic prediction of ccRCC patients by incorporating the DLRS and significant clinicopathologic features. The radiomics features could reflect the tumor heterogeneity and microenvironment.","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142261998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-15DOI: 10.1186/s40644-024-00770-z
Yue Yao, Xuan Su, Lei Deng, JingBin Zhang, Zengmiao Xu, Jianying Li, Xiaohui Li
To explore the effects of tube voltage, radiation dose and adaptive statistical iterative reconstruction (ASiR-V) strength level on the detection and characterization of pulmonary nodules by an artificial intelligence (AI) software in ultra-low-dose chest CT (ULDCT). An anthropomorphic thorax phantom containing 12 spherical simulated nodules (Diameter: 12 mm, 10 mm, 8 mm, 5 mm; CT value: -800HU, -630HU, 100HU) was scanned with three ULDCT protocols: Dose-1 (70kVp:0.11mSv, 100kVp:0.10mSv), Dose-2 (70kVp:0.34mSv, 100kVp:0.32mSv), Dose-3 (70kVp:0.53mSv, 100kVp:0.51mSv). All scanning protocols were repeated five times. CT images were reconstructed using four different strength levels of ASiR-V (0%=FBP, 30%, 50%, 70%ASiR-V) with a slice thickness of 1.25 mm. The characteristics of the physical nodules were used as reference standards. All images were analyzed using a commercially available AI software to identify nodules for calculating nodule detection rate (DR) and to obtain their long diameter and short diameter, which were used to calculate the deformation coefficient (DC) and size measurement deviation percentage (SP) of nodules. DR, DC and SP of different imaging groups were statistically compared. Image noise decreased with the increase of ASiR-V strength level, and the 70 kV images had lower noise under the same strength level (mean-value 70 kV: 40.14 ± 7.05 (dose 1), 27.55 ± 7.38 (dose 2), 23.88 ± 6.98 (dose 3); 100 kV: 42.36 ± 7.62 (dose 1); 30.78 ± 6.87 (dose 2); 26.49 ± 6.61 (dose 3)). Under the same dose level, there were no differences in DR between 70 kV and 100 kV (dose 1: 58.76% vs. 58.33%; dose 2: 73.33% vs. 70.83%; dose 3: 75.42% vs. 75.42%, all p > 0.05). The DR of GGNs increased significantly at dose 2 and higher (70 kV: 38.12% (dose 1), 60.63% (dose 2), 64.38% (dose 3); 100 kV: 37.50% (dose 1), 59.38% (dose 2), 66.25% (dose 3)). In general, the use of ASiR-V at higher strength levels (> 50%) and 100 kV provided better (lower) DC and SP. Detection rates are similar between 70 kV and 100 kV scans. The 70 kV images have better noise performance under the same ASiR-V level, while images of 100 kV and higher ASiR-V levels are better in preserving the nodule morphology (lower DC and SP); the dose levels above 0.33mSv provide high sensitivity for nodules detection, especially the simulated ground glass nodules.
{"title":"Effects of tube voltage, radiation dose and adaptive statistical iterative reconstruction strength level on the detection and characterization of pulmonary nodules in ultra-low-dose chest CT","authors":"Yue Yao, Xuan Su, Lei Deng, JingBin Zhang, Zengmiao Xu, Jianying Li, Xiaohui Li","doi":"10.1186/s40644-024-00770-z","DOIUrl":"https://doi.org/10.1186/s40644-024-00770-z","url":null,"abstract":"To explore the effects of tube voltage, radiation dose and adaptive statistical iterative reconstruction (ASiR-V) strength level on the detection and characterization of pulmonary nodules by an artificial intelligence (AI) software in ultra-low-dose chest CT (ULDCT). An anthropomorphic thorax phantom containing 12 spherical simulated nodules (Diameter: 12 mm, 10 mm, 8 mm, 5 mm; CT value: -800HU, -630HU, 100HU) was scanned with three ULDCT protocols: Dose-1 (70kVp:0.11mSv, 100kVp:0.10mSv), Dose-2 (70kVp:0.34mSv, 100kVp:0.32mSv), Dose-3 (70kVp:0.53mSv, 100kVp:0.51mSv). All scanning protocols were repeated five times. CT images were reconstructed using four different strength levels of ASiR-V (0%=FBP, 30%, 50%, 70%ASiR-V) with a slice thickness of 1.25 mm. The characteristics of the physical nodules were used as reference standards. All images were analyzed using a commercially available AI software to identify nodules for calculating nodule detection rate (DR) and to obtain their long diameter and short diameter, which were used to calculate the deformation coefficient (DC) and size measurement deviation percentage (SP) of nodules. DR, DC and SP of different imaging groups were statistically compared. Image noise decreased with the increase of ASiR-V strength level, and the 70 kV images had lower noise under the same strength level (mean-value 70 kV: 40.14 ± 7.05 (dose 1), 27.55 ± 7.38 (dose 2), 23.88 ± 6.98 (dose 3); 100 kV: 42.36 ± 7.62 (dose 1); 30.78 ± 6.87 (dose 2); 26.49 ± 6.61 (dose 3)). Under the same dose level, there were no differences in DR between 70 kV and 100 kV (dose 1: 58.76% vs. 58.33%; dose 2: 73.33% vs. 70.83%; dose 3: 75.42% vs. 75.42%, all p > 0.05). The DR of GGNs increased significantly at dose 2 and higher (70 kV: 38.12% (dose 1), 60.63% (dose 2), 64.38% (dose 3); 100 kV: 37.50% (dose 1), 59.38% (dose 2), 66.25% (dose 3)). In general, the use of ASiR-V at higher strength levels (> 50%) and 100 kV provided better (lower) DC and SP. Detection rates are similar between 70 kV and 100 kV scans. The 70 kV images have better noise performance under the same ASiR-V level, while images of 100 kV and higher ASiR-V levels are better in preserving the nodule morphology (lower DC and SP); the dose levels above 0.33mSv provide high sensitivity for nodules detection, especially the simulated ground glass nodules.","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142261999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-13DOI: 10.1186/s40644-024-00771-y
Wei Shi, Yingshi Su, Rui Zhang, Wei Xia, Zhenqiang Lian, Ning Mao, Yanyu Wang, Anqin Zhang, Xin Gao, Yan Zhang
This study investigated the clinical value of breast magnetic resonance imaging (MRI) radiomics for predicting axillary lymph node metastasis (ALNM) and to compare the discriminative abilities of different combinations of MRI sequences. This study included 141 patients diagnosed with invasive breast cancer from two centers (center 1: n = 101, center 2: n = 40). Patients from center 1 were randomly divided into training set and test set 1. Patients from center 2 were assigned to the test set 2. All participants underwent preoperative MRI, and four distinct MRI sequences were obtained. The volume of interest (VOI) of the breast tumor was delineated on the dynamic contrast-enhanced (DCE) postcontrast phase 2 sequence, and the VOIs of other sequences were adjusted when required. Subsequently, radiomics features were extracted from the VOIs using an open-source package. Both single- and multisequence radiomics models were constructed using the logistic regression method in the training set. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and precision of the radiomics model for the test set 1 and test set 2 were calculated. Finally, the diagnostic performance of each model was compared with the diagnostic level of junior and senior radiologists. The single-sequence ALNM classifier derived from DCE postcontrast phase 1 had the best performance for both test set 1 (AUC = 0.891) and test set 2 (AUC = 0.619). The best-performing multisequence ALNM classifiers for both test set 1 (AUC = 0.910) and test set 2 (AUC = 0.717) were generated from DCE postcontrast phase 1, T2-weighted imaging, and diffusion-weighted imaging single-sequence ALNM classifiers. Both had a higher diagnostic level than the junior and senior radiologists. The combination of DCE postcontrast phase 1, T2-weighted imaging, and diffusion-weighted imaging radiomics features had the best performance in predicting ALNM from breast cancer. Our study presents a well-performing and noninvasive tool for ALNM prediction in patients with breast cancer.
{"title":"Prediction of axillary lymph node metastasis using a magnetic resonance imaging radiomics model of invasive breast cancer primary tumor","authors":"Wei Shi, Yingshi Su, Rui Zhang, Wei Xia, Zhenqiang Lian, Ning Mao, Yanyu Wang, Anqin Zhang, Xin Gao, Yan Zhang","doi":"10.1186/s40644-024-00771-y","DOIUrl":"https://doi.org/10.1186/s40644-024-00771-y","url":null,"abstract":"This study investigated the clinical value of breast magnetic resonance imaging (MRI) radiomics for predicting axillary lymph node metastasis (ALNM) and to compare the discriminative abilities of different combinations of MRI sequences. This study included 141 patients diagnosed with invasive breast cancer from two centers (center 1: n = 101, center 2: n = 40). Patients from center 1 were randomly divided into training set and test set 1. Patients from center 2 were assigned to the test set 2. All participants underwent preoperative MRI, and four distinct MRI sequences were obtained. The volume of interest (VOI) of the breast tumor was delineated on the dynamic contrast-enhanced (DCE) postcontrast phase 2 sequence, and the VOIs of other sequences were adjusted when required. Subsequently, radiomics features were extracted from the VOIs using an open-source package. Both single- and multisequence radiomics models were constructed using the logistic regression method in the training set. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and precision of the radiomics model for the test set 1 and test set 2 were calculated. Finally, the diagnostic performance of each model was compared with the diagnostic level of junior and senior radiologists. The single-sequence ALNM classifier derived from DCE postcontrast phase 1 had the best performance for both test set 1 (AUC = 0.891) and test set 2 (AUC = 0.619). The best-performing multisequence ALNM classifiers for both test set 1 (AUC = 0.910) and test set 2 (AUC = 0.717) were generated from DCE postcontrast phase 1, T2-weighted imaging, and diffusion-weighted imaging single-sequence ALNM classifiers. Both had a higher diagnostic level than the junior and senior radiologists. The combination of DCE postcontrast phase 1, T2-weighted imaging, and diffusion-weighted imaging radiomics features had the best performance in predicting ALNM from breast cancer. Our study presents a well-performing and noninvasive tool for ALNM prediction in patients with breast cancer.","PeriodicalId":9548,"journal":{"name":"Cancer Imaging","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142185434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-12DOI: 10.1186/s40644-024-00751-2
<h3>O1 A randomized controlled trial of preoperative prostate artery embolization before transurethral resection of prostate glands larger than 80cc</h3><h4>Zong Yi Chin<sup>1</sup>, Alvin YM Lee<sup>2</sup>, Neo Shu Hui<sup>3</sup>, Ng Tze Kiat<sup>2</sup>, Edwin Jonathan Aslim<sup>2</sup>, Allen SP Sim<sup>4</sup>, Pradesh Kumar<sup>5</sup>, John SP Yuen<sup>2</sup>, Kenneth Chen<sup>2</sup>, Sivanathan Chandramohan<sup>1</sup>