首页 > 最新文献

BMC Medical Imaging最新文献

英文 中文
The application value of support vector machine model based on multimodal MRI in predicting IDH-1mutation and Ki-67 expression in glioma 基于多模态磁共振成像的支持向量机模型在预测胶质瘤中 IDH-1 突变和 Ki-67 表达中的应用价值
IF 2.7 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-16 DOI: 10.1186/s12880-024-01414-1
He-Xin Liang, Zong-Ying Wang, Yao Li, An-Ning Ren, Zhi-Feng Chen, Xi-Zhen Wang, Xi-Ming Wang, Zhen-Guo Yuan
To investigate the application value of support vector machine (SVM) model based on diffusion-weighted imaging (DWI), dynamic contrast-enhanced (DCE) and amide proton transfer- weighted (APTW) imaging in predicting isocitrate dehydrogenase 1(IDH-1) mutation and Ki-67 expression in glioma. The DWI, DCE and APTW images of 309 patients with glioma confirmed by pathology were retrospectively analyzed and divided into the IDH-1 group (IDH-1(+) group and IDH-1(-) group) and Ki-67 group (low expression group (Ki-67 ≤ 10%) and high expression group (Ki-67 > 10%)). All cases were divided into the training set, and validation set according to the ratio of 7:3. The training set was used to select features and establish machine learning models. The SVM model was established with the data after feature selection. Four single sequence models and one combined model were established in IDH-1 group and Ki-67 group. The receiver operator characteristic (ROC) curve was used to evaluate the diagnostic performance of the model. Validation set data was used for further validation. Both in the IDH-1 group and Ki-67 group, the combined model had better predictive efficiency than single sequence model, although the single sequence model had a better predictive efficiency. In the Ki-67 group, the combined model was built from six selected radiomics features, and the AUC were 0.965 and 0.931 in the training and validation sets, respectively. In the IDH-1 group, the combined model was built from four selected radiomics features, and the AUC were 0.997 and 0.967 in the training and validation sets, respectively. The radiomics model established by DWI, DCE and APTW images could be used to detect IDH-1 mutation and Ki-67 expression in glioma patients before surgery. The prediction performance of the radiomics model based on the combination sequence was better than that of the single sequence model.
研究基于扩散加权成像(DWI)、动态对比增强成像(DCE)和酰胺质子转移加权成像(APTW)的支持向量机(SVM)模型在预测胶质瘤中异柠檬酸脱氢酶1(IDH-1)突变和Ki-67表达方面的应用价值。回顾性分析了309例经病理证实的胶质瘤患者的DWI、DCE和APTW图像,并将其分为IDH-1组(IDH-1(+)组和IDH-1(-)组)和Ki-67组(低表达组(Ki-67≤10%)和高表达组(Ki-67>10%))。所有病例按照 7:3 的比例分为训练集和验证集。训练集用于选择特征和建立机器学习模型。通过特征选择后的数据建立 SVM 模型。在 IDH-1 组和 Ki-67 组中建立了四个单一序列模型和一个组合模型。接收器操作者特征曲线(ROC)用于评估模型的诊断性能。验证集数据用于进一步验证。在 IDH-1 组和 Ki-67 组中,联合模型的预测效率均优于单一序列模型,但单一序列模型的预测效率更高。在 Ki-67 组中,组合模型是由六个选定的放射组学特征建立的,在训练集和验证集中的 AUC 分别为 0.965 和 0.931。在 IDH-1 组中,综合模型由四个选定的放射组学特征建立,训练集和验证集的 AUC 分别为 0.997 和 0.967。通过DWI、DCE和APTW图像建立的放射组学模型可用于胶质瘤患者术前IDH-1突变和Ki-67表达的检测。基于组合序列的放射组学模型的预测性能优于单一序列模型。
{"title":"The application value of support vector machine model based on multimodal MRI in predicting IDH-1mutation and Ki-67 expression in glioma","authors":"He-Xin Liang, Zong-Ying Wang, Yao Li, An-Ning Ren, Zhi-Feng Chen, Xi-Zhen Wang, Xi-Ming Wang, Zhen-Guo Yuan","doi":"10.1186/s12880-024-01414-1","DOIUrl":"https://doi.org/10.1186/s12880-024-01414-1","url":null,"abstract":"To investigate the application value of support vector machine (SVM) model based on diffusion-weighted imaging (DWI), dynamic contrast-enhanced (DCE) and amide proton transfer- weighted (APTW) imaging in predicting isocitrate dehydrogenase 1(IDH-1) mutation and Ki-67 expression in glioma. The DWI, DCE and APTW images of 309 patients with glioma confirmed by pathology were retrospectively analyzed and divided into the IDH-1 group (IDH-1(+) group and IDH-1(-) group) and Ki-67 group (low expression group (Ki-67 ≤ 10%) and high expression group (Ki-67 > 10%)). All cases were divided into the training set, and validation set according to the ratio of 7:3. The training set was used to select features and establish machine learning models. The SVM model was established with the data after feature selection. Four single sequence models and one combined model were established in IDH-1 group and Ki-67 group. The receiver operator characteristic (ROC) curve was used to evaluate the diagnostic performance of the model. Validation set data was used for further validation. Both in the IDH-1 group and Ki-67 group, the combined model had better predictive efficiency than single sequence model, although the single sequence model had a better predictive efficiency. In the Ki-67 group, the combined model was built from six selected radiomics features, and the AUC were 0.965 and 0.931 in the training and validation sets, respectively. In the IDH-1 group, the combined model was built from four selected radiomics features, and the AUC were 0.997 and 0.967 in the training and validation sets, respectively. The radiomics model established by DWI, DCE and APTW images could be used to detect IDH-1 mutation and Ki-67 expression in glioma patients before surgery. The prediction performance of the radiomics model based on the combination sequence was better than that of the single sequence model.","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"28 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Accuracy of deep learning in the differential diagnosis of coronary artery stenosis: a systematic review and meta-analysis 深度学习在冠状动脉狭窄鉴别诊断中的准确性:系统回顾和荟萃分析
IF 2.7 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-16 DOI: 10.1186/s12880-024-01403-4
Li Tu, Ying Deng, Yun Chen, Yi Luo
In recent years, as deep learning has received widespread attention in the field of heart disease, some studies have explored the potential of deep learning based on coronary angiography (CAG) or coronary CT angiography (CCTA) images in detecting the extent of coronary artery stenosis. However, there is still a lack of a systematic understanding of its diagnostic accuracy, impeding the advancement of intelligent diagnosis of coronary artery stenosis. Therefore, we conducted this study to review the accuracy of image-based deep learning in detecting coronary artery stenosis. We retrieved PubMed, Cochrane, Embase, and Web of Science until April 11, 2023. The risk of bias in the included studies was appraised using the QUADAS-2 tool. We extracted the accuracy of deep learning in the test set and performed subgroup analyses by binary and multiclass classification scenarios. We performed a subgroup analysis based on different degrees of stenosis and applied a double arcsine transformation to process the data. The analysis was done by using R. Our systematic review finally included 18 studies, involving 3568 patients and 13,362 images. In the included studies, deep learning models were constructed based on CAG and CCTA. In binary classification tasks, the accuracy for detecting > 25%, > 50% and > 70% degrees of stenosis at the vessel level were 0.81 (95% CI: 0.71–0.85), 0.73 (95% CI: 0.58–0.88) and 0.61 (95% CI: 0.56–0.65), respectively. In multiclass classification tasks, the accuracy for detecting 0–25%, 25–50%, 50–70%, and 70–100% degrees of stenosis at the vessel level were 0.78 (95% CI: 0.73–0.84), 0.86 (95% CI: 0.78–0.93), 0.83 (95% CI: 0.70–0.97), and 0.70 (95% CI: 0.42–0.98), respectively. Our study shows that deep learning models based on CAG and CCTA appear to be relatively accurate in diagnosing different degrees of coronary artery stenosis. However, for various degrees of stenosis, their accuracy still needs to be further improved.
近年来,随着深度学习在心脏病领域受到广泛关注,一些研究探索了基于冠状动脉造影(CAG)或冠状动脉CT造影(CCTA)图像的深度学习在检测冠状动脉狭窄程度方面的潜力。然而,目前仍缺乏对其诊断准确性的系统了解,阻碍了冠状动脉狭窄智能诊断的发展。因此,我们开展了这项研究,以回顾基于图像的深度学习在检测冠状动脉狭窄方面的准确性。我们检索了截至 2023 年 4 月 11 日的 PubMed、Cochrane、Embase 和 Web of Science。我们使用 QUADAS-2 工具评估了纳入研究的偏倚风险。我们提取了深度学习在测试集中的准确性,并按二元分类和多类分类情况进行了分组分析。我们根据不同的狭窄程度进行了亚组分析,并应用双弧线变换来处理数据。我们的系统综述最终纳入了 18 项研究,涉及 3568 名患者和 13362 张图像。在纳入的研究中,我们基于 CAG 和 CCTA 构建了深度学习模型。在二元分类任务中,检测血管狭窄程度大于 25%、大于 50%、大于 70% 的准确率分别为 0.81(95% CI:0.71-0.85)、0.73(95% CI:0.58-0.88)和 0.61(95% CI:0.56-0.65)。在多类分类任务中,检测血管水平 0-25%、25-50%、50-70% 和 70-100% 狭窄度的准确率分别为 0.78(95% CI:0.73-0.84)、0.86(95% CI:0.78-0.93)、0.83(95% CI:0.70-0.97)和 0.70(95% CI:0.42-0.98)。我们的研究表明,基于 CAG 和 CCTA 的深度学习模型在诊断不同程度的冠状动脉狭窄方面似乎相对准确。然而,对于不同程度的狭窄,其准确性仍有待进一步提高。
{"title":"Accuracy of deep learning in the differential diagnosis of coronary artery stenosis: a systematic review and meta-analysis","authors":"Li Tu, Ying Deng, Yun Chen, Yi Luo","doi":"10.1186/s12880-024-01403-4","DOIUrl":"https://doi.org/10.1186/s12880-024-01403-4","url":null,"abstract":"In recent years, as deep learning has received widespread attention in the field of heart disease, some studies have explored the potential of deep learning based on coronary angiography (CAG) or coronary CT angiography (CCTA) images in detecting the extent of coronary artery stenosis. However, there is still a lack of a systematic understanding of its diagnostic accuracy, impeding the advancement of intelligent diagnosis of coronary artery stenosis. Therefore, we conducted this study to review the accuracy of image-based deep learning in detecting coronary artery stenosis. We retrieved PubMed, Cochrane, Embase, and Web of Science until April 11, 2023. The risk of bias in the included studies was appraised using the QUADAS-2 tool. We extracted the accuracy of deep learning in the test set and performed subgroup analyses by binary and multiclass classification scenarios. We performed a subgroup analysis based on different degrees of stenosis and applied a double arcsine transformation to process the data. The analysis was done by using R. Our systematic review finally included 18 studies, involving 3568 patients and 13,362 images. In the included studies, deep learning models were constructed based on CAG and CCTA. In binary classification tasks, the accuracy for detecting > 25%, > 50% and > 70% degrees of stenosis at the vessel level were 0.81 (95% CI: 0.71–0.85), 0.73 (95% CI: 0.58–0.88) and 0.61 (95% CI: 0.56–0.65), respectively. In multiclass classification tasks, the accuracy for detecting 0–25%, 25–50%, 50–70%, and 70–100% degrees of stenosis at the vessel level were 0.78 (95% CI: 0.73–0.84), 0.86 (95% CI: 0.78–0.93), 0.83 (95% CI: 0.70–0.97), and 0.70 (95% CI: 0.42–0.98), respectively. Our study shows that deep learning models based on CAG and CCTA appear to be relatively accurate in diagnosing different degrees of coronary artery stenosis. However, for various degrees of stenosis, their accuracy still needs to be further improved.","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"16 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Integration of texture analysis based on DCE-MRI Ktrans map and metabolomics of early bone marrow microvascular changes in alloxan-induced diabetic rabbits 基于 DCE-MRI Ktrans 图谱的纹理分析与代谢组学对阿脲诱导糖尿病兔骨髓微血管早期变化的整合研究
IF 2.7 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-16 DOI: 10.1186/s12880-024-01416-z
Yan Wang, Liang Li, Yuchen Yan, Tian Zhang, Lei Hu, Jun Chen, Yunfei Zha
To evaluate early bone marrow microvascular changes in alloxan-induced diabetic rabbits using IDEAL-IQ fat quantification, texture analysis based on DCE-MRI Ktrans map, and metabolomics. 24 male Japanese rabbits were randomly divided into diabetic (n = 12) and control (n = 12) groups. All rabbits underwent sagittal MRI of the lumbar vertebrae at the 0th,4th, 8th, 12th, and 16th week, respectively. The fat fraction (FF) ratio and quantitative permeability of the lumbar bone marrow was measured. Texture parameters were extracted from DCE-MRI Ktrans map. At 16th week, lumbar vertebrae 5 and 6 were used for histological analysis. Lumbar vertebra 7 was crushed to obtain bone marrow for metabolomics research. The FF ratio and Ktrans of the lumbar bone marrow in diabetic group were increased significantly at 16th week (t = 2.226, P = 0.02; Z = -2.721, P < 0.01). Nine texture feature parameters based on DCE-MRI Ktrans map were significantly different between the groups at the 16th week (all P < 0.05). Pathway analysis showed that diabetic bone marrow microvascular changes were mainly related to linoleic acid metabolism. Differential metabolites were correlated with the number of adipocytes, FF ratio, and permeability parameters. The integration of metabolomics with texture analysis based on DCE-MRI Ktrans map may be used to evaluate diabetic bone marrow microvascular changes at an early stage. It remains to be validated in clinical studies whether the integration of metabolomics with texture analysis based on the DCE-MRI Ktrans map can effectively evaluate diabetic bone marrow.
利用 IDEAL-IQ 脂肪定量、基于 DCE-MRI Ktrans 图的纹理分析和代谢组学评估阿脲诱导的糖尿病兔的早期骨髓微血管变化。24 只雄性日本兔被随机分为糖尿病组(12 只)和对照组(12 只)。所有兔子分别在第 0 周、第 4 周、第 8 周、第 12 周和第 16 周接受腰椎矢状面核磁共振成像检查。测量了腰椎骨髓的脂肪率(FF)和定量渗透性。纹理参数是从 DCE-MRI Ktrans 图中提取的。第16周时,对腰椎5和6进行组织学分析。腰椎7被粉碎以获取骨髓用于代谢组学研究。第16周时,糖尿病组腰椎骨髓的FF比值和Ktrans显著增加(t = 2.226,P = 0.02;Z = -2.721,P < 0.01)。第16周时,基于DCE-MRI Ktrans图的9个纹理特征参数在组间存在明显差异(P均<0.05)。通路分析表明,糖尿病骨髓微血管变化主要与亚油酸代谢有关。差异代谢物与脂肪细胞数量、FF比率和通透性参数相关。代谢组学与基于DCE-MRI Ktrans图的纹理分析相结合,可用于早期评估糖尿病骨髓微血管的变化。基于DCE-MRI Ktrans图的代谢组学与纹理分析的整合能否有效评估糖尿病骨髓,还有待临床研究验证。
{"title":"Integration of texture analysis based on DCE-MRI Ktrans map and metabolomics of early bone marrow microvascular changes in alloxan-induced diabetic rabbits","authors":"Yan Wang, Liang Li, Yuchen Yan, Tian Zhang, Lei Hu, Jun Chen, Yunfei Zha","doi":"10.1186/s12880-024-01416-z","DOIUrl":"https://doi.org/10.1186/s12880-024-01416-z","url":null,"abstract":"To evaluate early bone marrow microvascular changes in alloxan-induced diabetic rabbits using IDEAL-IQ fat quantification, texture analysis based on DCE-MRI Ktrans map, and metabolomics. 24 male Japanese rabbits were randomly divided into diabetic (n = 12) and control (n = 12) groups. All rabbits underwent sagittal MRI of the lumbar vertebrae at the 0th,4th, 8th, 12th, and 16th week, respectively. The fat fraction (FF) ratio and quantitative permeability of the lumbar bone marrow was measured. Texture parameters were extracted from DCE-MRI Ktrans map. At 16th week, lumbar vertebrae 5 and 6 were used for histological analysis. Lumbar vertebra 7 was crushed to obtain bone marrow for metabolomics research. The FF ratio and Ktrans of the lumbar bone marrow in diabetic group were increased significantly at 16th week (t = 2.226, P = 0.02; Z = -2.721, P < 0.01). Nine texture feature parameters based on DCE-MRI Ktrans map were significantly different between the groups at the 16th week (all P < 0.05). Pathway analysis showed that diabetic bone marrow microvascular changes were mainly related to linoleic acid metabolism. Differential metabolites were correlated with the number of adipocytes, FF ratio, and permeability parameters. The integration of metabolomics with texture analysis based on DCE-MRI Ktrans map may be used to evaluate diabetic bone marrow microvascular changes at an early stage. It remains to be validated in clinical studies whether the integration of metabolomics with texture analysis based on the DCE-MRI Ktrans map can effectively evaluate diabetic bone marrow.","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"4 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Ultrasomics differentiation of malignant and benign focal liver lesions based on contrast-enhanced ultrasound 基于对比增强超声的肝脏恶性和良性病灶的超声组学鉴别
IF 2.7 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-16 DOI: 10.1186/s12880-024-01426-x
Hang-Tong Hu, Ming-De Li, Jian-Chao Zhang, Si-Min Ruan, Shan-Shan Wu, Xin-Xin Lin, Hai-Yu Kang, Xiao-Yan Xie, Ming-De Lu, Ming Kuang, Er-Jiao Xu, Wei Wang
To establish a nomogram for differentiating malignant and benign focal liver lesions (FLLs) using ultrasomics features derived from contrast-enhanced ultrasound (CEUS). 527 patients were retrospectively enrolled. On the training cohort, ultrasomics features were extracted from CEUS and b-mode ultrasound (BUS). Automatic feature selection and model development were performed using the Ultrasomics-Platform software, outputting the corresponding ultrasomics scores. A nomogram based on the ultrasomics scores from artery phase (AP), portal venous phase (PVP) and delayed phase (DP) of CEUS, and clinical factors were established. On the validation cohort, the diagnostic performance of the nomogram was assessed and compared with seniorexpert and resident radiologists. In the training cohort, the AP, PVP and DP scores exhibited better differential performance than BUS score, with area under the curve (AUC) of 84.1-85.1% compared with the BUS (74.6%, P < 0.05). In the validation cohort, the AUC of combined nomogram and expert was significantly higher than that of the resident (91.4% vs. 89.5% vs. 79.3%, P < 0.05). The combined nomogram had a comparable sensitivity with the expert and resident (95.2% vs. 98.4% vs. 97.6%), while the expert had a higher specificity than the nomogram and the resident (80.6% vs. 72.2% vs. 61.1%, P = 0.205). A CEUS ultrasomics based nomogram had an expert level performance in FLL characterization.
利用对比增强超声(CEUS)得出的超声组学特征,建立区分肝脏恶性和良性病灶(FLLs)的提名图。研究人员回顾性招募了 527 名患者。在训练队列中,从CEUS和双模式超声(BUS)中提取了超声组学特征。使用超声组学平台软件进行自动特征选择和模型开发,并输出相应的超声组学评分。根据CEUS动脉期(AP)、门静脉期(PVP)和延迟期(DP)的超声组学评分和临床因素建立了提名图。在验证队列中,评估了提名图的诊断性能,并与老年专家和常驻放射科医生进行了比较。在训练队列中,AP、PVP 和 DP 评分的差异化表现优于 BUS 评分,曲线下面积(AUC)为 84.1-85.1%,而 BUS 为 74.6%,P < 0.05。在验证队列中,联合提名图和专家的 AUC 明显高于住院医师(91.4% vs. 89.5% vs. 79.3%,P < 0.05)。联合提名图的灵敏度与专家和住院医师相当(95.2% vs. 98.4% vs. 97.6%),而专家的特异性高于提名图和住院医师(80.6% vs. 72.2% vs. 61.1%,P = 0.205)。基于CEUS超声组学的提名图在FLL定性方面的表现达到了专家水平。
{"title":"Ultrasomics differentiation of malignant and benign focal liver lesions based on contrast-enhanced ultrasound","authors":"Hang-Tong Hu, Ming-De Li, Jian-Chao Zhang, Si-Min Ruan, Shan-Shan Wu, Xin-Xin Lin, Hai-Yu Kang, Xiao-Yan Xie, Ming-De Lu, Ming Kuang, Er-Jiao Xu, Wei Wang","doi":"10.1186/s12880-024-01426-x","DOIUrl":"https://doi.org/10.1186/s12880-024-01426-x","url":null,"abstract":"To establish a nomogram for differentiating malignant and benign focal liver lesions (FLLs) using ultrasomics features derived from contrast-enhanced ultrasound (CEUS). 527 patients were retrospectively enrolled. On the training cohort, ultrasomics features were extracted from CEUS and b-mode ultrasound (BUS). Automatic feature selection and model development were performed using the Ultrasomics-Platform software, outputting the corresponding ultrasomics scores. A nomogram based on the ultrasomics scores from artery phase (AP), portal venous phase (PVP) and delayed phase (DP) of CEUS, and clinical factors were established. On the validation cohort, the diagnostic performance of the nomogram was assessed and compared with seniorexpert and resident radiologists. In the training cohort, the AP, PVP and DP scores exhibited better differential performance than BUS score, with area under the curve (AUC) of 84.1-85.1% compared with the BUS (74.6%, P < 0.05). In the validation cohort, the AUC of combined nomogram and expert was significantly higher than that of the resident (91.4% vs. 89.5% vs. 79.3%, P < 0.05). The combined nomogram had a comparable sensitivity with the expert and resident (95.2% vs. 98.4% vs. 97.6%), while the expert had a higher specificity than the nomogram and the resident (80.6% vs. 72.2% vs. 61.1%, P = 0.205). A CEUS ultrasomics based nomogram had an expert level performance in FLL characterization.","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"19 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Medical image analysis using improved SAM-Med2D: segmentation and classification perspectives 使用改进型 SAM-Med2D 进行医学图像分析:分割和分类视角
IF 2.7 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-16 DOI: 10.1186/s12880-024-01401-6
Jiakang Sun, Ke Chen, Zhiyi He, Siyuan Ren, Xinyang He, Xu Liu, Cheng Peng
Recently emerged SAM-Med2D represents a state-of-the-art advancement in medical image segmentation. Through fine-tuning the Large Visual Model, Segment Anything Model (SAM), on extensive medical datasets, it has achieved impressive results in cross-modal medical image segmentation. However, its reliance on interactive prompts may restrict its applicability under specific conditions. To address this limitation, we introduce SAM-AutoMed, which achieves automatic segmentation of medical images by replacing the original prompt encoder with an improved MobileNet v3 backbone. The performance on multiple datasets surpasses both SAM and SAM-Med2D. Current enhancements on the Large Visual Model SAM lack applications in the field of medical image classification. Therefore, we introduce SAM-MedCls, which combines the encoder of SAM-Med2D with our designed attention modules to construct an end-to-end medical image classification model. It performs well on datasets of various modalities, even achieving state-of-the-art results, indicating its potential to become a universal model for medical image classification.
最近出现的 SAM-Med2D 代表了医学图像分割领域的最新进展。通过在大量医疗数据集上对大型视觉模型--任意分割模型(SAM)进行微调,它在跨模态医疗图像分割方面取得了令人瞩目的成果。然而,它对交互式提示的依赖可能会限制其在特定条件下的适用性。为了解决这一局限性,我们引入了 SAM-AutoMed,它通过用改进的 MobileNet v3 骨干网取代原有的提示编码器来实现医学图像的自动分割。它在多个数据集上的性能超过了 SAM 和 SAM-Med2D。目前对大型视觉模型 SAM 的改进缺乏在医学图像分类领域的应用。因此,我们推出了 SAM-MedCls,它将 SAM-Med2D 的编码器与我们设计的注意力模块相结合,构建了端到端的医学图像分类模型。它在各种模式的数据集上表现良好,甚至达到了最先进的结果,这表明它有潜力成为医学图像分类的通用模型。
{"title":"Medical image analysis using improved SAM-Med2D: segmentation and classification perspectives","authors":"Jiakang Sun, Ke Chen, Zhiyi He, Siyuan Ren, Xinyang He, Xu Liu, Cheng Peng","doi":"10.1186/s12880-024-01401-6","DOIUrl":"https://doi.org/10.1186/s12880-024-01401-6","url":null,"abstract":"Recently emerged SAM-Med2D represents a state-of-the-art advancement in medical image segmentation. Through fine-tuning the Large Visual Model, Segment Anything Model (SAM), on extensive medical datasets, it has achieved impressive results in cross-modal medical image segmentation. However, its reliance on interactive prompts may restrict its applicability under specific conditions. To address this limitation, we introduce SAM-AutoMed, which achieves automatic segmentation of medical images by replacing the original prompt encoder with an improved MobileNet v3 backbone. The performance on multiple datasets surpasses both SAM and SAM-Med2D. Current enhancements on the Large Visual Model SAM lack applications in the field of medical image classification. Therefore, we introduce SAM-MedCls, which combines the encoder of SAM-Med2D with our designed attention modules to construct an end-to-end medical image classification model. It performs well on datasets of various modalities, even achieving state-of-the-art results, indicating its potential to become a universal model for medical image classification.","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"3 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Assessing muscle invasion in bladder cancer via virtual biopsy: a study on quantitative parameters and classical radiomics features from dual-energy CT imaging 通过虚拟活检评估膀胱癌的肌肉侵犯:双能 CT 成像定量参数和经典放射组学特征研究
IF 2.7 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-16 DOI: 10.1186/s12880-024-01427-w
Mengting Hu, Wei Wei, Jingyi Zhang, Shigeng Wang, Xiaoyu Tong, Yong Fan, Qiye Cheng, Yijun Liu, Jianying Li, Lei Liu
To evaluate the prediction value of Dual-energy CT (DECT)-based quantitative parameters and radiomics model in preoperatively predicting muscle invasion in bladder cancer (BCa). A retrospective study was performed on 126 patients with BCa who underwent DECT urography (DECTU) in our hospital. Patients were randomly divided into training and test cohorts with a ratio of 7:3. Quantitative parameters derived from DECTU were identified through univariate and multivariate logistic regression analysis to construct a DECT model. Radiomics features were extracted from the 40, 70, 100 keV and iodine-based material-decomposition (IMD) images in the venous phase to construct radiomics models from individual and combined images using a support vector machine classifier, and the optimal performing model was chosen as the final radiomics model. Subsequently, a fusion model combining the DECT parameters and the radiomics model was established. The diagnostic performances of all three models were evaluated through receiver operating characteristic (ROC) curves and the clinical usefulness was estimated using decision curve analysis (DCA). The normalized iodine concentration (NIC) in DECT was an independent factor in diagnosing muscle invasion of BCa. The optimal multi-image radiomics model had predictive performance with an area-under-the-curve (AUC) of 0.867 in the test cohort, better than the AUC = 0.704 with NIC. The fusion model showed an increased level of performance, although the difference in AUC (0.893) was not statistically significant. Additionally, it demonstrated superior performance in DCA. For lesions smaller than 3 cm, the fusion model showed a high predictive capability, achieving an AUC value of 0.911. There was a slight improvement in model performance, although the difference was not statistically significant. This improvement was observed when comparing the AUC values of the DECT and radiomics models, which were 0.726 and 0.884, respectively. The proposed fusion model combing NIC and the optimal multi-image radiomics model in DECT showed good diagnostic capability in predicting muscle invasiveness of BCa.
评估基于双能 CT(DECT)的定量参数和放射组学模型在术前预测膀胱癌(BCa)肌肉侵犯方面的预测价值。本院对126名接受DECT尿路造影术(DECTU)的膀胱癌患者进行了回顾性研究。患者以 7:3 的比例随机分为训练组和测试组。通过单变量和多变量逻辑回归分析确定了 DECTU 的定量参数,从而构建了 DECT 模型。从静脉期的 40、70、100 keV 和基于碘的物质分解(IMD)图像中提取放射组学特征,使用支持向量机分类器从单个和组合图像中构建放射组学模型,并选择性能最佳的模型作为最终的放射组学模型。随后,结合 DECT 参数和放射组学模型建立了一个融合模型。通过接收者操作特征曲线(ROC)评估了所有三种模型的诊断性能,并通过决策曲线分析(DCA)估算了临床实用性。DECT 中的归一化碘浓度(NIC)是诊断 BCa 肌肉侵犯的一个独立因素。最佳多图像放射组学模型具有预测性能,在测试队列中的曲线下面积(AUC)为 0.867,优于 NIC 的 AUC = 0.704。尽管 AUC(0.893)的差异在统计学上并不显著,但融合模型的性能水平有所提高。此外,它在 DCA 中也表现出更优越的性能。对于小于 3 厘米的病变,融合模型显示出较高的预测能力,AUC 值达到 0.911。模型的性能略有提高,但差异无统计学意义。在比较 DECT 模型和放射组学模型的 AUC 值(分别为 0.726 和 0.884)时,可以观察到这种改进。在 DECT 中结合 NIC 和最佳多图像放射组学模型的融合模型在预测 BCa 的肌肉侵袭性方面显示出良好的诊断能力。
{"title":"Assessing muscle invasion in bladder cancer via virtual biopsy: a study on quantitative parameters and classical radiomics features from dual-energy CT imaging","authors":"Mengting Hu, Wei Wei, Jingyi Zhang, Shigeng Wang, Xiaoyu Tong, Yong Fan, Qiye Cheng, Yijun Liu, Jianying Li, Lei Liu","doi":"10.1186/s12880-024-01427-w","DOIUrl":"https://doi.org/10.1186/s12880-024-01427-w","url":null,"abstract":"To evaluate the prediction value of Dual-energy CT (DECT)-based quantitative parameters and radiomics model in preoperatively predicting muscle invasion in bladder cancer (BCa). A retrospective study was performed on 126 patients with BCa who underwent DECT urography (DECTU) in our hospital. Patients were randomly divided into training and test cohorts with a ratio of 7:3. Quantitative parameters derived from DECTU were identified through univariate and multivariate logistic regression analysis to construct a DECT model. Radiomics features were extracted from the 40, 70, 100 keV and iodine-based material-decomposition (IMD) images in the venous phase to construct radiomics models from individual and combined images using a support vector machine classifier, and the optimal performing model was chosen as the final radiomics model. Subsequently, a fusion model combining the DECT parameters and the radiomics model was established. The diagnostic performances of all three models were evaluated through receiver operating characteristic (ROC) curves and the clinical usefulness was estimated using decision curve analysis (DCA). The normalized iodine concentration (NIC) in DECT was an independent factor in diagnosing muscle invasion of BCa. The optimal multi-image radiomics model had predictive performance with an area-under-the-curve (AUC) of 0.867 in the test cohort, better than the AUC = 0.704 with NIC. The fusion model showed an increased level of performance, although the difference in AUC (0.893) was not statistically significant. Additionally, it demonstrated superior performance in DCA. For lesions smaller than 3 cm, the fusion model showed a high predictive capability, achieving an AUC value of 0.911. There was a slight improvement in model performance, although the difference was not statistically significant. This improvement was observed when comparing the AUC values of the DECT and radiomics models, which were 0.726 and 0.884, respectively. The proposed fusion model combing NIC and the optimal multi-image radiomics model in DECT showed good diagnostic capability in predicting muscle invasiveness of BCa.","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"16 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Diagnostic value and efficacy evaluation value of transvaginal color doppler ultrasound parameters for uterine scar pregnancy and sub-type after cesarean section 经阴道彩色多普勒超声参数对剖宫产术后子宫瘢痕妊娠及亚型的诊断价值和疗效评估价值
IF 2.7 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-13 DOI: 10.1186/s12880-024-01405-2
Yuting Peng, Jia Liu, Jun Xie, Quanlv Li
We aimed to probe the diagnostic value of transvaginal color Doppler ultrasound (TV-CDU) parameters in cesarean scar pregnancy (CSP) and CSP sub-types, and the relevant factors affecting patients’ surgical effects. Seventy-five CSP patients (all requested termination of pregnancy) were selected as the observation group, and 75 normal pregnant women with a history of cesarean section were selected as the control group. All the study subjects underwent TV-CDU and their cesarean scar muscle (CSM) thickness, minimum sagittal muscle thickness and resistance index (RI) of blood flow in the anterior wall of the lower uterine segment were calculated. The diagnostic value of CSM, minimum sagittal muscle thickness, and RI for CSP and CSP sub-types was analyzed. The patients in the observation group were grouped into the effective group and the ineffective group according to whether the surgical treatment was effective or not, and the independent factors affecting CSP efficacy were analyzed. The observation group had lower CSM, minimum sagittal muscle thickness and RI than the control group. CSM, RI, and minimum sagittal thickness in patients with type II CSP were lower than those in patients with type I, and these indicators in patients with type III were lower than those in patients with type II. The area under the curve (AUC) of CSM, RI and minimum sagittal muscle thickness in combination for CSP diagnosis and the AUC for CSP sub-types were higher than those of each indicator alone. Gestational sac size and CSM were independent factors affecting CSP treatment. Changes in TV-CDU parameters facilitates CSP diagnosis after cesarean section. CSM, minimum sagittal muscle thickness changes, and RI in combination possesses high value for CSP diagnosis and CSP sub-types. Gestational sac size and CSM are independent factors affecting CSP treatment.
我们旨在探究经阴道彩色多普勒超声(TV-CDU)参数在剖宫产瘢痕妊娠(CSP)及CSP亚型中的诊断价值,以及影响患者手术效果的相关因素。选取 75 例 CSP 患者(均要求终止妊娠)作为观察组,75 例有剖宫产史的正常孕妇作为对照组。所有研究对象均接受 TV-CDU,并计算其剖宫产瘢痕肌(CSM)厚度、最小矢状肌厚度和子宫下段前壁血流阻力指数(RI)。分析了CSM、最小矢状肌厚度和RI对CSP和CSP亚型的诊断价值。根据手术治疗是否有效将观察组患者分为有效组和无效组,并分析影响 CSP 疗效的独立因素。观察组的 CSM、最小矢状肌厚度和 RI 均低于对照组。II 型 CSP 患者的 CSM、RI 和最小矢状肌厚度均低于 I 型患者,而 III 型患者的这些指标均低于 II 型患者。CSM、RI和最小矢状肌厚度三项指标联合用于CSP诊断的曲线下面积(AUC)以及用于CSP亚型的AUC均高于单独使用每项指标时的曲线下面积(AUC)。妊娠囊大小和CSM是影响CSP治疗的独立因素。TV-CDU参数的变化有助于剖宫产术后的CSP诊断。CSM、最小矢状肌厚度变化和RI的组合对CSP诊断和CSP亚型具有很高的价值。妊娠囊大小和CSM是影响CSP治疗的独立因素。
{"title":"Diagnostic value and efficacy evaluation value of transvaginal color doppler ultrasound parameters for uterine scar pregnancy and sub-type after cesarean section","authors":"Yuting Peng, Jia Liu, Jun Xie, Quanlv Li","doi":"10.1186/s12880-024-01405-2","DOIUrl":"https://doi.org/10.1186/s12880-024-01405-2","url":null,"abstract":"We aimed to probe the diagnostic value of transvaginal color Doppler ultrasound (TV-CDU) parameters in cesarean scar pregnancy (CSP) and CSP sub-types, and the relevant factors affecting patients’ surgical effects. Seventy-five CSP patients (all requested termination of pregnancy) were selected as the observation group, and 75 normal pregnant women with a history of cesarean section were selected as the control group. All the study subjects underwent TV-CDU and their cesarean scar muscle (CSM) thickness, minimum sagittal muscle thickness and resistance index (RI) of blood flow in the anterior wall of the lower uterine segment were calculated. The diagnostic value of CSM, minimum sagittal muscle thickness, and RI for CSP and CSP sub-types was analyzed. The patients in the observation group were grouped into the effective group and the ineffective group according to whether the surgical treatment was effective or not, and the independent factors affecting CSP efficacy were analyzed. The observation group had lower CSM, minimum sagittal muscle thickness and RI than the control group. CSM, RI, and minimum sagittal thickness in patients with type II CSP were lower than those in patients with type I, and these indicators in patients with type III were lower than those in patients with type II. The area under the curve (AUC) of CSM, RI and minimum sagittal muscle thickness in combination for CSP diagnosis and the AUC for CSP sub-types were higher than those of each indicator alone. Gestational sac size and CSM were independent factors affecting CSP treatment. Changes in TV-CDU parameters facilitates CSP diagnosis after cesarean section. CSM, minimum sagittal muscle thickness changes, and RI in combination possesses high value for CSP diagnosis and CSP sub-types. Gestational sac size and CSM are independent factors affecting CSP treatment.","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"21 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142225611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Predicting invasion in early-stage ground-glass opacity pulmonary adenocarcinoma: a radiomics-based machine learning approach 预测早期磨玻璃不透明肺腺癌的侵袭:基于放射组学的机器学习方法
IF 2.7 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-13 DOI: 10.1186/s12880-024-01421-2
Junjie Bin, Mei Wu, Meiyun Huang, Yuguang Liao, Yuli Yang, Xianqiong Shi, Siqi Tao
To design a pulmonary ground-glass nodules (GGN) classification method based on computed tomography (CT) radiomics and machine learning for prediction of invasion in early-stage ground-glass opacity (GGO) pulmonary adenocarcinoma. This retrospective study included pulmonary GGN patients who were histologically confirmed to have adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma cancer (IAC) from 2020 to 2023. CT images of all patients were automatically segmented and 107 radiomic features were obtained for each patient. Classification models were developed using random forest (RF) and cross-validation, including three one-versus-others models and one three-class model. For each model, features were ranked by normalized Gini importance, and a minimal subset was selected with a cumulative importance exceeding 0.9. These selected features were then used to train the final models. The models’ performance metrics, including area under the curve (AUC), accuracy, sensitivity, and specificity, were computed. AUC and accuracy were compared to determine the final optimal method. The study comprised 193 patients (mean age 54 ± 11 years, 65 men), including 65 AIS, 54 MIA, and 74 IAC, divided into one training cohort (N = 154) and one test cohort (N = 39). The final three-class RF model outperformed three individual one-versus-others models in distinguishing each class from the other two. For the multiclass classification model, the AUC, accuracy, sensitivity, and specificity were 0.87, 0.79, 0.62, and 0.88 for AIS; 0.90, 0.79, 0.54, and 0.89 for MIA; and 0.87, 0.69, 0.73, and 0.67 for IAC, respectively. A radiomics-based multiclass RF model could effectively differentiate three types of pulmonary GGN, which enabled early diagnosis of GGO pulmonary adenocarcinoma.
设计一种基于计算机断层扫描(CT)放射组学和机器学习的肺磨玻璃结节(GGN)分类方法,用于预测早期磨玻璃不透明(GGO)肺腺癌的侵袭情况。这项回顾性研究纳入了2020年至2023年经组织学证实为原位腺癌(AIS)、微侵袭性腺癌(MIA)或侵袭性腺癌(IAC)的肺GGN患者。对所有患者的 CT 图像进行了自动分割,并获得了每位患者的 107 个放射学特征。利用随机森林(RF)和交叉验证建立了分类模型,其中包括三个 "单对单 "模型和一个 "三类 "模型。对于每个模型,根据归一化基尼重要性对特征进行排序,并选择累计重要性超过 0.9 的最小子集。这些选定的特征随后被用于训练最终模型。计算模型的性能指标,包括曲线下面积(AUC)、准确率、灵敏度和特异性。对 AUC 和准确性进行比较,以确定最终的最佳方法。研究对象包括 193 名患者(平均年龄 54 ± 11 岁,65 名男性),其中包括 65 名 AIS 患者、54 名 MIA 患者和 74 名 IAC 患者,分为一个训练队列(N = 154)和一个测试队列(N = 39)。最终的三类 RF 模型在区分每一类和其他两类方面优于三个单独的 "单对单 "模型。就多级分类模型而言,AIS 的 AUC、准确性、灵敏度和特异性分别为 0.87、0.79、0.62 和 0.88;MIA 的 AUC、准确性、灵敏度和特异性分别为 0.90、0.79、0.54 和 0.89;IAC 的 AUC、准确性、灵敏度和特异性分别为 0.87、0.69、0.73 和 0.67。基于放射组学的多分类射频模型可有效区分三种类型的肺GGN,从而实现GGO肺腺癌的早期诊断。
{"title":"Predicting invasion in early-stage ground-glass opacity pulmonary adenocarcinoma: a radiomics-based machine learning approach","authors":"Junjie Bin, Mei Wu, Meiyun Huang, Yuguang Liao, Yuli Yang, Xianqiong Shi, Siqi Tao","doi":"10.1186/s12880-024-01421-2","DOIUrl":"https://doi.org/10.1186/s12880-024-01421-2","url":null,"abstract":"To design a pulmonary ground-glass nodules (GGN) classification method based on computed tomography (CT) radiomics and machine learning for prediction of invasion in early-stage ground-glass opacity (GGO) pulmonary adenocarcinoma. This retrospective study included pulmonary GGN patients who were histologically confirmed to have adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma cancer (IAC) from 2020 to 2023. CT images of all patients were automatically segmented and 107 radiomic features were obtained for each patient. Classification models were developed using random forest (RF) and cross-validation, including three one-versus-others models and one three-class model. For each model, features were ranked by normalized Gini importance, and a minimal subset was selected with a cumulative importance exceeding 0.9. These selected features were then used to train the final models. The models’ performance metrics, including area under the curve (AUC), accuracy, sensitivity, and specificity, were computed. AUC and accuracy were compared to determine the final optimal method. The study comprised 193 patients (mean age 54 ± 11 years, 65 men), including 65 AIS, 54 MIA, and 74 IAC, divided into one training cohort (N = 154) and one test cohort (N = 39). The final three-class RF model outperformed three individual one-versus-others models in distinguishing each class from the other two. For the multiclass classification model, the AUC, accuracy, sensitivity, and specificity were 0.87, 0.79, 0.62, and 0.88 for AIS; 0.90, 0.79, 0.54, and 0.89 for MIA; and 0.87, 0.69, 0.73, and 0.67 for IAC, respectively. A radiomics-based multiclass RF model could effectively differentiate three types of pulmonary GGN, which enabled early diagnosis of GGO pulmonary adenocarcinoma.","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"27 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142227701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep learning-based techniques for estimating high-quality full-dose positron emission tomography images from low-dose scans: a systematic review 从低剂量扫描中估算高质量全剂量正电子发射断层扫描图像的深度学习技术:系统性综述
IF 2.7 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-11 DOI: 10.1186/s12880-024-01417-y
Negisa Seyyedi, Ali Ghafari, Navisa Seyyedi, Peyman Sheikhzadeh
This systematic review aimed to evaluate the potential of deep learning algorithms for converting low-dose Positron Emission Tomography (PET) images to full-dose PET images in different body regions. A total of 55 articles published between 2017 and 2023 by searching PubMed, Web of Science, Scopus and IEEE databases were included in this review, which utilized various deep learning models, such as generative adversarial networks and UNET, to synthesize high-quality PET images. The studies involved different datasets, image preprocessing techniques, input data types, and loss functions. The evaluation of the generated PET images was conducted using both quantitative and qualitative methods, including physician evaluations and various denoising techniques. The findings of this review suggest that deep learning algorithms have promising potential in generating high-quality PET images from low-dose PET images, which can be useful in clinical practice.
本系统综述旨在评估深度学习算法将不同身体区域的低剂量正电子发射断层扫描(PET)图像转换为全剂量 PET 图像的潜力。本综述通过搜索 PubMed、Web of Science、Scopus 和 IEEE 数据库,共收录了 55 篇发表于 2017 年至 2023 年间的文章,这些文章利用生成式对抗网络和 UNET 等各种深度学习模型来合成高质量 PET 图像。这些研究涉及不同的数据集、图像预处理技术、输入数据类型和损失函数。使用定量和定性方法对生成的 PET 图像进行了评估,包括医生评估和各种去噪技术。综述结果表明,深度学习算法在从低剂量正电子发射计算机断层图像生成高质量正电子发射计算机断层图像方面具有广阔的前景,可在临床实践中发挥作用。
{"title":"Deep learning-based techniques for estimating high-quality full-dose positron emission tomography images from low-dose scans: a systematic review","authors":"Negisa Seyyedi, Ali Ghafari, Navisa Seyyedi, Peyman Sheikhzadeh","doi":"10.1186/s12880-024-01417-y","DOIUrl":"https://doi.org/10.1186/s12880-024-01417-y","url":null,"abstract":"This systematic review aimed to evaluate the potential of deep learning algorithms for converting low-dose Positron Emission Tomography (PET) images to full-dose PET images in different body regions. A total of 55 articles published between 2017 and 2023 by searching PubMed, Web of Science, Scopus and IEEE databases were included in this review, which utilized various deep learning models, such as generative adversarial networks and UNET, to synthesize high-quality PET images. The studies involved different datasets, image preprocessing techniques, input data types, and loss functions. The evaluation of the generated PET images was conducted using both quantitative and qualitative methods, including physician evaluations and various denoising techniques. The findings of this review suggest that deep learning algorithms have promising potential in generating high-quality PET images from low-dose PET images, which can be useful in clinical practice.","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"44 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142225598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The reliability of virtual non-contrast reconstructions of photon-counting detector CT scans in assessing abdominal organs 光子计数探测器 CT 扫描的虚拟非对比重建在评估腹部器官方面的可靠性
IF 2.7 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2024-09-09 DOI: 10.1186/s12880-024-01419-w
Ibolyka Dudás, Leona Schultz, Márton Benke, Ákos Szücs, Pál Novák Kaposi, Attila Szijártó, Pál Maurovich-Horvat, Bettina Katalin Budai
Spectral imaging of photon-counting detector CT (PCD-CT) scanners allows for generating virtual non-contrast (VNC) reconstruction. By analyzing 12 abdominal organs, we aimed to test the reliability of VNC reconstructions in preserving HU values compared to real unenhanced CT images. Our study included 34 patients with pancreatic cystic neoplasm (PCN). The VNC reconstructions were generated from unenhanced, arterial, portal, and venous phase PCD-CT scans using the Liver-VNC algorithm. The observed 11 abdominal organs were segmented by the TotalSegmentator algorithm, the PCNs were segmented manually. Average densities were extracted from unenhanced scans (HUunenhanced), postcontrast (HUpostcontrast) scans, and VNC reconstructions (HUVNC). The error was calculated as HUerror=HUVNC–HUunenhanced. Pearson’s or Spearman’s correlation was used to assess the association. Reproducibility was evaluated by intraclass correlation coefficients (ICC). Significant differences between HUunenhanced and HUVNC[unenhanced] were found in vertebrae, paraspinal muscles, liver, and spleen. HUVNC[unenhanced] showed a strong correlation with HUunenhanced in all organs except spleen (r = 0.45) and kidneys (r = 0.78 and 0.73). In all postcontrast phases, the HUVNC had strong correlations with HUunenhanced in all organs except the spleen and kidneys. The HUerror had significant correlations with HUunenhanced in the muscles and vertebrae; and with HUpostcontrast in the spleen, vertebrae, and paraspinal muscles in all postcontrast phases. All organs had at least one postcontrast VNC reconstruction that showed good-to-excellent agreement with HUunenhanced during ICC analysis except the vertebrae (ICC: 0.17), paraspinal muscles (ICC: 0.64–0.79), spleen (ICC: 0.21–0.47), and kidneys (ICC: 0.10–0.31). VNC reconstructions are reliable in at least one postcontrast phase for most organs, but further improvement is needed before VNC can be utilized to examine the spleen, kidneys, and vertebrae.
光子计数探测器 CT(PCD-CT)扫描仪的光谱成像可生成虚拟非对比度(VNC)重建。通过分析 12 个腹部器官,我们旨在测试 VNC 重建与真实未增强 CT 图像相比在保留 HU 值方面的可靠性。我们的研究包括 34 名胰腺囊性肿瘤(PCN)患者。VNC 重建是使用 Liver-VNC 算法从未增强、动脉、门脉和静脉相 PCD-CT 扫描中生成的。观察到的 11 个腹部器官采用 TotalSegmentator 算法进行分割,PCN 则采用人工分割。从未增强扫描(HUunenhanced)、对比后扫描(HUpostcontrast)和 VNC 重建(HUVNC)中提取平均密度。误差计算公式为:HUerror=HUVNC-HUunenhanced。皮尔逊或斯皮尔曼相关性用于评估相关性。再现性通过类内相关系数(ICC)进行评估。在脊椎、脊柱旁肌肉、肝脏和脾脏中,HU 增强与 HUVNC[未增强]之间存在显著差异。除脾脏(r = 0.45)和肾脏(r = 0.78 和 0.73)外,HUVNC[未增强]与 HUunenhanced 在所有器官中都显示出很强的相关性。在所有对比后阶段,除脾脏和肾脏外,所有器官的 HUVNC 与 HUunenhanced 都有很强的相关性。在肌肉和椎骨中,HUerror 与 HUunenhanced 有显著相关性;在所有对比后阶段,脾脏、椎骨和脊柱旁肌肉与 HUpostcontrast 有显著相关性。除脊椎(ICC:0.17)、脊柱旁肌肉(ICC:0.64-0.79)、脾脏(ICC:0.21-0.47)和肾脏(ICC:0.10-0.31)外,在 ICC 分析期间,所有器官都至少有一个对比后 VNC 重构与 HU 增强显示出良好到极佳的一致性。VNC 重建在大多数器官的至少一个对比后阶段是可靠的,但在利用 VNC 检查脾脏、肾脏和脊椎骨之前还需要进一步改进。
{"title":"The reliability of virtual non-contrast reconstructions of photon-counting detector CT scans in assessing abdominal organs","authors":"Ibolyka Dudás, Leona Schultz, Márton Benke, Ákos Szücs, Pál Novák Kaposi, Attila Szijártó, Pál Maurovich-Horvat, Bettina Katalin Budai","doi":"10.1186/s12880-024-01419-w","DOIUrl":"https://doi.org/10.1186/s12880-024-01419-w","url":null,"abstract":"Spectral imaging of photon-counting detector CT (PCD-CT) scanners allows for generating virtual non-contrast (VNC) reconstruction. By analyzing 12 abdominal organs, we aimed to test the reliability of VNC reconstructions in preserving HU values compared to real unenhanced CT images. Our study included 34 patients with pancreatic cystic neoplasm (PCN). The VNC reconstructions were generated from unenhanced, arterial, portal, and venous phase PCD-CT scans using the Liver-VNC algorithm. The observed 11 abdominal organs were segmented by the TotalSegmentator algorithm, the PCNs were segmented manually. Average densities were extracted from unenhanced scans (HUunenhanced), postcontrast (HUpostcontrast) scans, and VNC reconstructions (HUVNC). The error was calculated as HUerror=HUVNC–HUunenhanced. Pearson’s or Spearman’s correlation was used to assess the association. Reproducibility was evaluated by intraclass correlation coefficients (ICC). Significant differences between HUunenhanced and HUVNC[unenhanced] were found in vertebrae, paraspinal muscles, liver, and spleen. HUVNC[unenhanced] showed a strong correlation with HUunenhanced in all organs except spleen (r = 0.45) and kidneys (r = 0.78 and 0.73). In all postcontrast phases, the HUVNC had strong correlations with HUunenhanced in all organs except the spleen and kidneys. The HUerror had significant correlations with HUunenhanced in the muscles and vertebrae; and with HUpostcontrast in the spleen, vertebrae, and paraspinal muscles in all postcontrast phases. All organs had at least one postcontrast VNC reconstruction that showed good-to-excellent agreement with HUunenhanced during ICC analysis except the vertebrae (ICC: 0.17), paraspinal muscles (ICC: 0.64–0.79), spleen (ICC: 0.21–0.47), and kidneys (ICC: 0.10–0.31). VNC reconstructions are reliable in at least one postcontrast phase for most organs, but further improvement is needed before VNC can be utilized to examine the spleen, kidneys, and vertebrae.","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"61 1","pages":""},"PeriodicalIF":2.7,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142225614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
BMC Medical 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