European Journal of Radiology Open最新文献_第6页

Clinical and MRI variables associated with close or positive margins during breast-conserving surgery using MRI projection mapping in breast carcinoma with nonmass enhancement 在非肿块增强的乳腺癌保乳手术中，MRI投影成像与边缘闭合或阳性相关的临床和MRI变量

IF 2.9 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-09-01 DOI: 10.1016/j.ejro.2025.100681

Maki Amano , Jun Ozeki , Yumi Koyama , Xiaoyan Tang , Fumi Nozaki , Mayumi Tani , Yasuo Amano

Purpose

To evaluate the utility of a magnetic resonance imaging (MRI) projection mapping system (PMS) for determining the resection lines during breast-conserving surgery (BCS) in patients with breast cancer presenting with nonmass enhancement (NME) and identify the clinical or MRI variables associated with close or positive margins.

Materials and methods

Forty-one patients with breast cancer exhibiting NME were enrolled. In the operating room, a maximum intensity projection image generated from supine MRI was projected onto the breast using a PMS, which employed a structured light method to measure the surface of the breast. Cancer contours delineated on the MRI-PMS, with an additional safety margin, served as the resection lines for cylindrical BCS. Margins were pathologically categorized as negative (> 2 mm), close (≤ 2 mm), or positive. The association between margin status and clinical or MRI variables was analyzed.

Results

Surgical margins were negative in 24 patients (58.5 %), close in 15 (36.6 %), and positive in 2 (4.9 %). There were significant differences in the maximum diameter of nonmass components (NMCs) shown by pathology, that of NME on MRI, and the discrepancy between the two diameters between patients with negative margin and those with close or positive margin (< 0.05 for all). Receiver operating characteristics revealed that threshold of 40 mm for NMEs provided high specificity of 91.7 %.

Conclusion

The MRI-PMS led to a low rate of positive margins during BCS in patients with breast cancer with NMEs. Large NMCs and NMEs are associated with positive or close margin.

目的评估磁共振成像（MRI）投影成像系统（PMS）在乳腺癌保乳手术（BCS）期间确定非肿块增强（NME）患者切除线的效用，并确定与边缘闭合或阳性相关的临床或MRI变量。材料与方法入选41例表现为NME的乳腺癌患者。在手术室中，使用PMS将仰卧位MRI产生的最大强度投影图像投影到乳房上，PMS采用结构光法测量乳房表面。在MRI-PMS上划定的肿瘤轮廓，具有额外的安全裕度，作为圆柱形BCS的切除线。切缘病理分类为阴性（≤2 mm）、接近（≤2 mm）或阳性。分析了切缘状态与临床或MRI变量之间的关系。结果手术切缘阴性24例（58.5% %），闭合15例（36.6 %），阳性2例（4.9 %）。病理显示的非肿块成分（NMCs）最大直径与MRI显示的NME最大直径、切缘阴性患者与切缘相近或阳性患者的最大直径差异均有统计学意义（均为0.05）。接受者工作特征显示，NMEs的阈值为40 mm，特异性为91.7 %。结论MRI-PMS可导致合并NMEs的乳腺癌患者BCS阳性切缘率低。大型nmc和NMEs与正边际或近边际相关。

{"title":"Clinical and MRI variables associated with close or positive margins during breast-conserving surgery using MRI projection mapping in breast carcinoma with nonmass enhancement","authors":"Maki Amano , Jun Ozeki , Yumi Koyama , Xiaoyan Tang , Fumi Nozaki , Mayumi Tani , Yasuo Amano","doi":"10.1016/j.ejro.2025.100681","DOIUrl":"10.1016/j.ejro.2025.100681","url":null,"abstract":"<div><h3>Purpose</h3><div>To evaluate the utility of a magnetic resonance imaging (MRI) projection mapping system (PMS) for determining the resection lines during breast-conserving surgery (BCS) in patients with breast cancer presenting with nonmass enhancement (NME) and identify the clinical or MRI variables associated with close or positive margins.</div></div><div><h3>Materials and methods</h3><div>Forty-one patients with breast cancer exhibiting NME were enrolled. In the operating room, a maximum intensity projection image generated from supine MRI was projected onto the breast using a PMS, which employed a structured light method to measure the surface of the breast. Cancer contours delineated on the MRI-PMS, with an additional safety margin, served as the resection lines for cylindrical BCS. Margins were pathologically categorized as negative (> 2 mm), close (≤ 2 mm), or positive. The association between margin status and clinical or MRI variables was analyzed.</div></div><div><h3>Results</h3><div>Surgical margins were negative in 24 patients (58.5 %), close in 15 (36.6 %), and positive in 2 (4.9 %). There were significant differences in the maximum diameter of nonmass components (NMCs) shown by pathology, that of NME on MRI, and the discrepancy between the two diameters between patients with negative margin and those with close or positive margin (< 0.05 for all). Receiver operating characteristics revealed that threshold of 40 mm for NMEs provided high specificity of 91.7 %.</div></div><div><h3>Conclusion</h3><div>The MRI-PMS led to a low rate of positive margins during BCS in patients with breast cancer with NMEs. Large NMCs and NMEs are associated with positive or close margin.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100681"},"PeriodicalIF":2.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Performance of an artificial intelligence tool for multi-step acute stroke imaging: A multicenter diagnostic study 多步急性脑卒中成像人工智能工具的性能：一项多中心诊断研究

IF 2.9 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-08-29 DOI: 10.1016/j.ejro.2025.100678

Thibault Agripnidis , Angela Ayobi , Sarah Quenet , Yasmina Chaibi , Christophe Avare , Alexis Jacquier , Nadine Girard , Jean-François Hak , Anthony Reyre , Gilles Brun , Ahmed-Ali El Ahmadi

Objective

Several artificial intelligence (AI) tools have been developed to assist in the stroke imaging workflow, which remains a major disease of the 21st century. This study evaluated the combined performance of an FDA-cleared and CE-marked AI-based device with three modules designed to detect intracerebral hemorrhage (ICH), identify large vessel occlusion (LVO), and calculate Alberta Stroke Program Early CT Scores (ASPECTS).

Materials & methods

Non-contrast CT (NCCT) and/or computed tomography angiography (CTA) for suspicion of stroke acquired at La Timone and Nord University hospitals (Marseille, France) between March 2019 and March 2020 were retrospectively collected. The AI tool, CINA-HEAD (Avicenna.AI), processed the data to flag ICH, LVO, and calculate ASPECTS. The results were compared to ground truth evaluations by four expert neuroradiologists to compute diagnostic performances.

Results

A total of 373 NCCT and 331 CTA from 405 patients (mean age 64.9 ± 18.9 SD, 52.6 % female) were included. The AI tool achieved an accuracy of 94.6 % [95 % CI: 91.8 %-96.7 %] for ICH detection on NCCT and of 86.4 % [95 % CI: 82.2 %-89.9 %] for LVO identification on CTA. The region-based ASPECTS analysis yielded an accuracy of 88.6 % [95 % CI: 87.8 %-89.3 %] and the dichotomized ASPECTS classification (ASPECTS ≥ 6) achieved 80.4 % accuracy.

Conclusion

This study demonstrates the reliable, stepwise performance of an AI-based stroke imaging tool across the diagnostic cascade of ICH and LVO detection and ASPECTS scoring. Such robust multi-stage evaluation supports its potential for streamlining acute stroke triage and decision-making.

目的：脑卒中仍是21世纪的主要疾病，目前已开发了多种人工智能（AI）工具来辅助脑卒中成像工作流程。本研究评估了fda批准和ce标记的人工智能设备的综合性能，该设备具有三个模块，用于检测脑出血（ICH）、识别大血管闭塞（LVO）和计算阿尔伯塔卒中计划早期CT评分（ASPECTS）。材料和方法回顾性收集2019年3月至2020年3月在La Timone和Nord University医院（法国马赛）获得的疑似卒中的非对比CT （NCCT）和/或计算机断层扫描血管造影（CTA）。人工智能工具china - head（阿维森纳）AI)，处理数据标记ICH， LVO，并计算ASPECTS。结果与四位神经放射专家的真实评估进行比较，以计算诊断性能。结果405例患者（平均年龄64.9 ± 18.9 SD，女性52.6% %）共纳入373例NCCT和331例CTA。人工智能工具在NCCT上检测ICH的准确率为94.6 %[95 % CI: 91.8 %-96.7 %]，在CTA上识别LVO的准确率为86.4 %[95 % CI: 82.2 %-89.9 %]。基于区域的ASPECTS分析的准确率为88.6% %[95 % CI: 87.8 %- 89.3% %]，二分类的ASPECTS分类（ASPECTS≥6）的准确率为80.4 %。本研究证明了基于人工智能的脑卒中成像工具在ICH和LVO检测的诊断级联以及ASPECTS评分方面具有可靠的、逐步的性能。这种强大的多阶段评估支持其简化急性卒中分诊和决策的潜力。

{"title":"Performance of an artificial intelligence tool for multi-step acute stroke imaging: A multicenter diagnostic study","authors":"Thibault Agripnidis , Angela Ayobi , Sarah Quenet , Yasmina Chaibi , Christophe Avare , Alexis Jacquier , Nadine Girard , Jean-François Hak , Anthony Reyre , Gilles Brun , Ahmed-Ali El Ahmadi","doi":"10.1016/j.ejro.2025.100678","DOIUrl":"10.1016/j.ejro.2025.100678","url":null,"abstract":"<div><h3>Objective</h3><div>Several artificial intelligence (AI) tools have been developed to assist in the stroke imaging workflow, which remains a major disease of the 21st century. This study evaluated the combined performance of an FDA-cleared and CE-marked AI-based device with three modules designed to detect intracerebral hemorrhage (ICH), identify large vessel occlusion (LVO), and calculate Alberta Stroke Program Early CT Scores (ASPECTS).</div></div><div><h3>Materials & methods</h3><div>Non-contrast CT (NCCT) and/or computed tomography angiography (CTA) for suspicion of stroke acquired at La Timone and Nord University hospitals (Marseille, France) between March 2019 and March 2020 were retrospectively collected. The AI tool, CINA-HEAD (Avicenna.AI), processed the data to flag ICH, LVO, and calculate ASPECTS. The results were compared to ground truth evaluations by four expert neuroradiologists to compute diagnostic performances.</div></div><div><h3>Results</h3><div>A total of 373 NCCT and 331 CTA from 405 patients (mean age 64.9 ± 18.9 SD, 52.6 % female) were included. The AI tool achieved an accuracy of 94.6 % [95 % CI: 91.8 %-96.7 %] for ICH detection on NCCT and of 86.4 % [95 % CI: 82.2 %-89.9 %] for LVO identification on CTA. The region-based ASPECTS analysis yielded an accuracy of 88.6 % [95 % CI: 87.8 %-89.3 %] and the dichotomized ASPECTS classification (ASPECTS ≥ 6) achieved 80.4 % accuracy.</div></div><div><h3>Conclusion</h3><div>This study demonstrates the reliable, stepwise performance of an AI-based stroke imaging tool across the diagnostic cascade of ICH and LVO detection and ASPECTS scoring. Such robust multi-stage evaluation supports its potential for streamlining acute stroke triage and decision-making.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100678"},"PeriodicalIF":2.9,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144917052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CT Radiomics-based machine learning approach for the invasiveness of pulmonary ground-glass nodules prediction 基于CT放射组学的肺磨玻璃结节侵袭性预测的机器学习方法

IF 2.9 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-08-23 DOI: 10.1016/j.ejro.2025.100680

Rui Chen , Hu Zhang , Xingwen Huang , Haitao Han , Jinbo Jian

Objective

To develop and validate a machine learning model based on CT radiomics to improve the ability to differentiate pathological subtypes of pulmonary ground-glass nodules (GGN).

Methods

A retrospective analysis was conducted on clinical data and radiological images from 392 patients with lung adenocarcinoma at Binzhou Medical University Hospital between January 1, 2020 to May 31, 2023. All patients underwent preoperative thin-section chest CT scans and surgical resection. A total of 400 GGNs were included. Regions of interest (ROI) were delineated on the slice showing the largest diameter of the lesions. Based on pathological confirmation, the nodules were divided into two groups: Group 1 (adenocarcinoma in situ, AIS or minimally invasive adenocarcinoma, MIA, 209 nodules) and Group 2 (invasive adenocarcinoma, IAC, 191nodules). The dataset was randomly split into a training set (280 nodules, 70 %) and a validation set (120 nodules, 30 %) at a 7:3 ratio. In the training set, feature dimensionality reduction was performed using minimum redundancy maximum relevance (mRMR) as well as least absolute shrinkage and selection operator (LASSO) to screen out discriminative radiomics features. Then seven machine learning models—logistic regression (LR), support vector machine (SVM), random forest (RF), extra trees, XGBoost, GradientBoosting, and AdaBoost—were constructed. Model performance and prediction efficacy were evaluated based on indicators such as area under the curve (AUC), accuracy, specificity, and sensitivity using receiver operating characteristic (ROC) curves.

Results

Eight radiomics features were ultimately identified. Among the seven models, the GradientBoosting model exhibited the best performance, achieving an AUC of 0.929 (95 % CI: 0.9004–0.9584), accuracy of 0.85, sensitivity of 0.851, and specificity of 0.849 in the training set.

Conclusion

The GradientBoosting model based on CT radiomics features demonstrates superior performance in predicting pathological subtypes of ground glass nodular lung adenocarcinoma, providing a reliable auxiliary tool for clinical diagnosis.

目的建立并验证基于CT放射组学的机器学习模型，以提高肺磨玻璃结节（GGN）病理亚型的鉴别能力。方法回顾性分析滨州医科大学附属医院2020年1月1日至2023年5月31日392例肺腺癌患者的临床资料和影像学资料。所有患者术前均行胸部薄层CT扫描和手术切除。共纳入400个ggn。感兴趣区域（ROI）在显示病变最大直径的切片上勾画。根据病理证实，将结节分为两组：1组（原位腺癌，AIS或微创腺癌，MIA， 209个结节）和2组（侵袭性腺癌，IAC， 191个结节）。数据集以7:3的比例随机分为训练集（280个结节，70 %）和验证集（120个结节，30 %）。在训练集中，使用最小冗余最大相关性（mRMR）以及最小绝对收缩和选择算子（LASSO）进行特征降维，以筛选出判别性放射组学特征。然后构建了逻辑回归（LR）、支持向量机（SVM）、随机森林（RF）、额外树（extra trees）、XGBoost、GradientBoosting和adaboost等7个机器学习模型。采用受试者工作特征（ROC）曲线，根据曲线下面积（AUC）、准确度、特异性和敏感性等指标评价模型的性能和预测效果。结果最终确定了八个放射组学特征。7个模型中，GradientBoosting模型表现最好，AUC为0.929(95 % CI: 0.9004-0.9584)，准确率为0.85，灵敏度为0.851，特异性为0.849。结论基于CT放射组学特征的GradientBoosting模型在预测磨玻璃结节性肺腺癌病理亚型方面具有较好的效果，为临床诊断提供了可靠的辅助工具。

{"title":"CT Radiomics-based machine learning approach for the invasiveness of pulmonary ground-glass nodules prediction","authors":"Rui Chen , Hu Zhang , Xingwen Huang , Haitao Han , Jinbo Jian","doi":"10.1016/j.ejro.2025.100680","DOIUrl":"10.1016/j.ejro.2025.100680","url":null,"abstract":"<div><h3>Objective</h3><div>To develop and validate a machine learning model based on CT radiomics to improve the ability to differentiate pathological subtypes of pulmonary ground-glass nodules (GGN).</div></div><div><h3>Methods</h3><div>A retrospective analysis was conducted on clinical data and radiological images from 392 patients with lung adenocarcinoma at Binzhou Medical University Hospital between January 1, 2020 to May 31, 2023. All patients underwent preoperative thin-section chest CT scans and surgical resection. A total of 400 GGNs were included. Regions of interest (ROI) were delineated on the slice showing the largest diameter of the lesions. Based on pathological confirmation, the nodules were divided into two groups: Group 1 (adenocarcinoma in situ, AIS or minimally invasive adenocarcinoma, MIA, 209 nodules) and Group 2 (invasive adenocarcinoma, IAC, 191nodules). The dataset was randomly split into a training set (280 nodules, 70 %) and a validation set (120 nodules, 30 %) at a 7:3 ratio. In the training set, feature dimensionality reduction was performed using minimum redundancy maximum relevance (mRMR) as well as least absolute shrinkage and selection operator (LASSO) to screen out discriminative radiomics features. Then seven machine learning models—logistic regression (LR), support vector machine (SVM), random forest (RF), extra trees, XGBoost, GradientBoosting, and AdaBoost—were constructed. Model performance and prediction efficacy were evaluated based on indicators such as area under the curve (AUC), accuracy, specificity, and sensitivity using receiver operating characteristic (ROC) curves.</div></div><div><h3>Results</h3><div>Eight radiomics features were ultimately identified. Among the seven models, the GradientBoosting model exhibited the best performance, achieving an AUC of 0.929 (95 % CI: 0.9004–0.9584), accuracy of 0.85, sensitivity of 0.851, and specificity of 0.849 in the training set.</div></div><div><h3>Conclusion</h3><div>The GradientBoosting model based on CT radiomics features demonstrates superior performance in predicting pathological subtypes of ground glass nodular lung adenocarcinoma, providing a reliable auxiliary tool for clinical diagnosis.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100680"},"PeriodicalIF":2.9,"publicationDate":"2025-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Diagnostic performance of dual-layer spectral CT Radiomics and deep learning for differentiating osteoblastic bone metastases from bone islands 双层光谱CT放射组学和深度学习鉴别成骨细胞骨转移和骨岛的诊断价值

IF 2.9 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-08-20 DOI: 10.1016/j.ejro.2025.100679

Yuchao Xiong , Wei Guo , Xuwen Zeng , Fan Xu , Li Wu , Jiahui Ou

Background

This study aimed to compare the diagnostic performance of radiomic features derived from dual-layer spectral detector computed tomography (DLSCT) and a deep learning (DL) model applied to conventional CT images in the differentiation of osteoblastic bone metastases (OBM) from bone islands (BI).

Methods

This retrospective study included patients with osteogenic lesions who underwent DLSCT examinations between March 2023 and September 2023. We extracted first-order radiomic features (e.g., mean, maximum, entropy) from both conventional and spectral images. A previously validated DL model was applied to the conventional CT images. We evaluated diagnostic performance using ROC curve analysis, comparing AUC, sensitivity, and specificity.

Results

The study included 216 lesions from 94 patients (66 ± 12 years; 48 males, 46 females): 125 BI and 91 OBM lesions. Significant differences were observed between OBM and BI groups for the mean, maximum, entropy, and uniformity of first-order radiomic features (all P < 0.05). DLSCT (entropy from VMI40keV) and the DL model had comparable AUCs (0.93 vs. 0.96; P = 0.274). However, DLSCT showed superior sensitivity (92 % vs. 62 %; P = 0.002) but comparable specificity (88 % vs. 96 %; P = 0.07) for diagnosing OBM compared to the DL model.

Conclusion

Radiomic features from DLSCT differentiate between BI and OBM with diagnostic performance comparable to that of a DL model. Furthermore, VMI40keV image-derived entropy demonstrated superior sensitivity in diagnosing OBM compared to the DL model.

本研究旨在比较双层光谱检测器计算机断层扫描（DLSCT）和应用于传统CT图像的深度学习（DL）模型的放射学特征在区分成骨细胞骨转移（OBM）和骨岛（BI）中的诊断性能。方法本回顾性研究纳入了2023年3月至2023年9月期间接受DLSCT检查的成骨病变患者。我们从常规图像和光谱图像中提取一阶放射特征（例如，平均值，最大值，熵）。将先前验证的DL模型应用于常规CT图像。我们使用ROC曲线分析评估诊断效果，比较AUC、敏感性和特异性。结果共纳入94例患者的216个病变（66例 ± ，12岁，男48例，女46例）：BI 125个，OBM 91个。在一阶放射学特征的平均值、最大值、熵和均匀性方面，OBM组和BI组之间存在显著差异（P均为 <； 0.05）。DLSCT（来自VMI40keV的熵）和DL模型具有可比的auc （0.93 vs. 0.96; P = 0.274）。然而，与DL模型相比，DLSCT在诊断OBM方面表现出更高的灵敏度（92 %对62 %；P = 0.002）和相当的特异性（88 %对96 %；P = 0.07）。结论DLSCT的放射学特征可以区分BI和OBM，其诊断性能与DL模型相当。此外，与DL模型相比，VMI40keV图像衍生熵在诊断OBM方面表现出更高的灵敏度。

{"title":"Diagnostic performance of dual-layer spectral CT Radiomics and deep learning for differentiating osteoblastic bone metastases from bone islands","authors":"Yuchao Xiong , Wei Guo , Xuwen Zeng , Fan Xu , Li Wu , Jiahui Ou","doi":"10.1016/j.ejro.2025.100679","DOIUrl":"10.1016/j.ejro.2025.100679","url":null,"abstract":"<div><h3>Background</h3><div>This study aimed to compare the diagnostic performance of radiomic features derived from dual-layer spectral detector computed tomography (DLSCT) and a deep learning (DL) model applied to conventional CT images in the differentiation of osteoblastic bone metastases (OBM) from bone islands (BI).</div></div><div><h3>Methods</h3><div>This retrospective study included patients with osteogenic lesions who underwent DLSCT examinations between March 2023 and September 2023. We extracted first-order radiomic features (e.g., mean, maximum, entropy) from both conventional and spectral images. A previously validated DL model was applied to the conventional CT images. We evaluated diagnostic performance using ROC curve analysis, comparing AUC, sensitivity, and specificity.</div></div><div><h3>Results</h3><div>The study included 216 lesions from 94 patients (66 ± 12 years; 48 males, 46 females): 125 BI and 91 OBM lesions. Significant differences were observed between OBM and BI groups for the mean, maximum, entropy, and uniformity of first-order radiomic features (all P < 0.05). DLSCT (entropy from VMI40keV) and the DL model had comparable AUCs (0.93 vs. 0.96; P = 0.274). However, DLSCT showed superior sensitivity (92 % vs. 62 %; P = 0.002) but comparable specificity (88 % vs. 96 %; P = 0.07) for diagnosing OBM compared to the DL model.</div></div><div><h3>Conclusion</h3><div>Radiomic features from DLSCT differentiate between BI and OBM with diagnostic performance comparable to that of a DL model. Furthermore, VMI40keV image-derived entropy demonstrated superior sensitivity in diagnosing OBM compared to the DL model.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100679"},"PeriodicalIF":2.9,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144879230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Diaphragmatic curvature analysis using dynamic digital radiography 动态数字射线照相法分析横膈膜曲率

IF 2.9 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-08-05 DOI: 10.1016/j.ejro.2025.100676

Takuya Hino , Akinori Tsunomori , Noriaki Wada , Akinori Hata , Taiki Fukuda , Yusei Nakamura , Yoshitake Yamada , Tomoyuki Hida , Mizuki Nishino , Masako Ueyama , Atsuko Kurosaki , Takeshi Kubo , Shoji Kudoh , Kousei Ishigami , Hiroto Hatabu

Purpose

To investigate area under diaphragm (AUD) obtained by dynamic digital radiography (DDR) for the differentiation between normal subjects and chronic obstructive pulmonary disease (COPD) patients.

Methods

This retrospective study included healthy volunteers and COPD patients recruited from 2009 to 2014 at Fukujuji Hospital, who received DDR and pulmonary functional test. AUD was defined as an area under a hemidiaphragm and above the line connecting the ipsilateral costophrenic angle to the top of the hemidiaphragm on DDR image. AUD in full inspiration minus AUD in full expiration (ΔAUD) was also calculated. The diaphragmatic surface was demarcated manually on DDR image to calculate AUD. Three-group comparison of AUD and ΔAUD among normal, mild COPD, and severe COPD subjects was tested with one-way analysis of variance, followed by multiple comparison with Tukey-Kramer method. The diagnostic accuracy of COPD by ΔAUD was assessed using receiver-operating-characteristics (ROC) curve.

Results

Sixty-eight participants (36 men, 29 COPD patients) were enrolled. AUD in full inspiration was larger in healthy volunteers than in COPD patients (right, p < 0.001; left, p = 0.02). ΔAUD were different in the three-group comparison (right, normal, 208.7 ± 184.6 mm², mild COPD, −18.1 ± 117.5 mm², severe COPD −97.5 ± 150.0 mm², p < 0.001; left, normal, 254.9 ± 131.5 mm², mild COPD, −12.5 ± 136.5 mm², severe COPD, −100.7 ± 134.1 mm², p < 0.001). ROC curve showed high diagnostic performance of COPD by unilateral ΔAUD (right, area-under curve 0.942; left, area-under-curve 0.965).

Conclusion

The value of ΔAUD was smaller according to the severity of COPD. ΔAUD can be helpful in distinguishing healthy subjects from COPD patients.

目的探讨动态数字x线摄影（DDR）获得的膈下面积（AUD）在鉴别慢性阻塞性肺疾病（COPD）患者中的价值。方法回顾性研究纳入2009 - 2014年在福大学医院招募的健康志愿者和COPD患者，接受DDR和肺功能检查。AUD定义为DDR图像上半膈下、同侧肋膈角与半膈顶部连线以上的区域。同时计算充分吸气时的澳元减去完全呼气时的澳元（ΔAUD）。在DDR图像上手动标定膈面，计算AUD。三组比较正常、轻度和重度COPD受试者的AUD和ΔAUD，采用单因素方差分析，然后采用Tukey-Kramer法进行多重比较。采用受试者-工作特征（ROC）曲线评价ΔAUD对COPD的诊断准确性。结果共纳入68名参与者（36名男性，29名COPD患者）。健康志愿者完全吸气时的AUD大于COPD患者(右，p <； 0.001；离开时,p = 0.02)。Δ澳大利亚是不同的三组比较(正常, 208.7±184.6  平方毫米,轻微的慢性阻塞性肺病, −18.1±117.5  平方毫米,严重的慢性阻塞性肺病 −97.5±150.0  平方毫米,p & lt; 0.001;离开,正常,254.9 ±131.5  平方毫米,轻微的慢性阻塞性肺病, −12.5±136.5  平方毫米,严重的慢性阻塞性肺病, −100.7±134.1  平方毫米,p & lt; 0.001)。ROC曲线显示单侧ΔAUD对COPD有较高的诊断价值(右，曲线下面积0.942；左侧，曲线下面积0.965)。结论ΔAUD值随COPD的严重程度而变小。ΔAUD可以帮助区分健康受试者和COPD患者。

{"title":"Diaphragmatic curvature analysis using dynamic digital radiography","authors":"Takuya Hino , Akinori Tsunomori , Noriaki Wada , Akinori Hata , Taiki Fukuda , Yusei Nakamura , Yoshitake Yamada , Tomoyuki Hida , Mizuki Nishino , Masako Ueyama , Atsuko Kurosaki , Takeshi Kubo , Shoji Kudoh , Kousei Ishigami , Hiroto Hatabu","doi":"10.1016/j.ejro.2025.100676","DOIUrl":"10.1016/j.ejro.2025.100676","url":null,"abstract":"<div><h3>Purpose</h3><div>To investigate area under diaphragm (AUD) obtained by dynamic digital radiography (DDR) for the differentiation between normal subjects and chronic obstructive pulmonary disease (COPD) patients.</div></div><div><h3>Methods</h3><div>This retrospective study included healthy volunteers and COPD patients recruited from 2009 to 2014 at Fukujuji Hospital, who received DDR and pulmonary functional test. AUD was defined as an area under a hemidiaphragm and above the line connecting the ipsilateral costophrenic angle to the top of the hemidiaphragm on DDR image. AUD in full inspiration minus AUD in full expiration (ΔAUD) was also calculated. The diaphragmatic surface was demarcated manually on DDR image to calculate AUD. Three-group comparison of AUD and ΔAUD among normal, mild COPD, and severe COPD subjects was tested with one-way analysis of variance, followed by multiple comparison with Tukey-Kramer method. The diagnostic accuracy of COPD by ΔAUD was assessed using receiver-operating-characteristics (ROC) curve.</div></div><div><h3>Results</h3><div>Sixty-eight participants (36 men, 29 COPD patients) were enrolled. AUD in full inspiration was larger in healthy volunteers than in COPD patients (right, p < 0.001; left, p = 0.02). ΔAUD were different in the three-group comparison (right, normal, 208.7 ± 184.6 mm<sup>2</sup>, mild COPD, −18.1 ± 117.5 mm<sup>2</sup>, severe COPD −97.5 ± 150.0 mm<sup>2</sup>, p < 0.001; left, normal, 254.9 ± 131.5 mm<sup>2</sup>, mild COPD, −12.5 ± 136.5 mm<sup>2</sup>, severe COPD, −100.7 ± 134.1 mm<sup>2</sup>, p < 0.001). ROC curve showed high diagnostic performance of COPD by unilateral ΔAUD (right, area-under curve 0.942; left, area-under-curve 0.965).</div></div><div><h3>Conclusion</h3><div>The value of ΔAUD was smaller according to the severity of COPD. ΔAUD can be helpful in distinguishing healthy subjects from COPD patients.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100676"},"PeriodicalIF":2.9,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AI-driven assessment of over-scanning in chest CT: A systematic review and meta-analysis 人工智能对胸部CT过度扫描的评估：系统回顾和荟萃分析

IF 2.9 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-07-30 DOI: 10.1016/j.ejro.2025.100674

Mo’men Bani-Ahmad , Andrew England , Laura McLaughlin , Marwan Alshipli , Kholoud Alzyoud , Yasser H. Hadi , Mark McEntee

Introduction

Scan range is crucial for CT acquisitions. However, irrelevant over-scanning in CT is common and contributes to a significant radiation dose. This review explores the role of artificial intelligence (AI) in addressing manual over-scanning in chest CT imaging.

Methods

A systematic search of peer-reviewed publications was conducted between December 2015 and March 2025 in Embase, Scopus, Ovid, EBSCOhost, and PubMed. Two reviewers and an academic lecturer independently reviewed the articles to ensure adherence to inclusion criteria. The quality of the included studies was assessed using CLAIM and QUADAS-2 tools. Summary estimates on over-scanning at the upper and lower boundaries of the scan range in chest CT were derived using meta-analysis.

Results

Five studies employed AI algorithms to assess manual over-scanning in chest CT using either 2D topograms or 3D axial images at low and standard doses. These models accurately determine the extent of over-scanning, demonstrating strong agreement with radiologist evaluations. All included studies revealed significant variation in over-scanning at the superior (13.5 mm) and inferior (30.2 mm) boundaries of the scan range (p < 0.001), with approximately two-thirds of the total over-scanning (43.2 mm) occurring at the inferior level (abdomen).

Conclusions

Integrating AI tools into the over-scanning evaluation process may optimise chest CT imaging protocols and enhance patient safety by reducing over-scanning and radiation dose through real-time monitoring and retrospective analysis.

扫描范围对CT采集至关重要。然而，CT中不相关的过扫描是常见的，并导致显著的辐射剂量。本文综述了人工智能（AI）在解决胸部CT成像中人工过扫中的作用。方法系统检索Embase、Scopus、Ovid、EBSCOhost和PubMed中2015年12月~ 2025年3月的同行评议论文。两名审稿人和一名学术讲师独立审查了这些文章，以确保符合纳入标准。使用CLAIM和QUADAS-2工具评估纳入研究的质量。通过荟萃分析得出胸部CT扫描范围上下边界过扫描的汇总估计。结果5项研究采用人工智能算法评估低剂量和标准剂量下胸部CT人工过扫描，包括2D地形图或3D轴向图像。这些模型准确地确定了过度扫描的程度，与放射科医生的评估非常一致。所有纳入的研究显示，扫描范围的上（13.5 mm）和下（30.2 mm）边界的过度扫描有显著差异（p <； 0.001），大约三分之二的过度扫描（43.2 mm）发生在下水平（腹部）。结论通过实时监测和回顾性分析，将人工智能工具整合到胸部CT过扫描评估过程中，可通过减少过扫描和辐射剂量，优化胸部CT成像方案，提高患者安全性。

{"title":"AI-driven assessment of over-scanning in chest CT: A systematic review and meta-analysis","authors":"Mo’men Bani-Ahmad , Andrew England , Laura McLaughlin , Marwan Alshipli , Kholoud Alzyoud , Yasser H. Hadi , Mark McEntee","doi":"10.1016/j.ejro.2025.100674","DOIUrl":"10.1016/j.ejro.2025.100674","url":null,"abstract":"<div><h3>Introduction</h3><div>Scan range is crucial for CT acquisitions. However, irrelevant over-scanning in CT is common and contributes to a significant radiation dose. This review explores the role of artificial intelligence (AI) in addressing manual over-scanning in chest CT imaging.</div></div><div><h3>Methods</h3><div>A systematic search of peer-reviewed publications was conducted between December 2015 and March 2025 in Embase, Scopus, Ovid, EBSCOhost, and PubMed. Two reviewers and an academic lecturer independently reviewed the articles to ensure adherence to inclusion criteria. The quality of the included studies was assessed using CLAIM and QUADAS-2 tools. Summary estimates on over-scanning at the upper and lower boundaries of the scan range in chest CT were derived using meta-analysis.</div></div><div><h3>Results</h3><div>Five studies employed AI algorithms to assess manual over-scanning in chest CT using either 2D topograms or 3D axial images at low and standard doses. These models accurately determine the extent of over-scanning, demonstrating strong agreement with radiologist evaluations. All included studies revealed significant variation in over-scanning at the superior (13.5 mm) and inferior (30.2 mm) boundaries of the scan range (p < 0.001), with approximately two-thirds of the total over-scanning (43.2 mm) occurring at the inferior level (abdomen).</div></div><div><h3>Conclusions</h3><div>Integrating AI tools into the over-scanning evaluation process may optimise chest CT imaging protocols and enhance patient safety by reducing over-scanning and radiation dose through real-time monitoring and retrospective analysis.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100674"},"PeriodicalIF":2.9,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144724529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of assumed tumour volume in multiple myeloma using dual-energy spectral CT and its correlation between haematological findings 双能谱CT评估多发性骨髓瘤的假定肿瘤体积及其与血液学表现的相关性

IF 2.9 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-07-29 DOI: 10.1016/j.ejro.2025.100675

Tetsuya Kosaka , Chisaki Masuda , Sachiho Tatebe , Risen Hirai , Akira Tanimura

Objectives

To measure the assumed tumour volume in the humerus of patients with multiple myeloma using dual-energy spectral computed tomography (DESCT) and to evaluate the correlation with haematological indicators.

Methods

We retrospectively analysed 82 DESCT examinations of 22 patients diagnosed with multiple myeloma. After extracting the bilateral humeri and removing the bone tissue, we measured the volume of the assumed tumour area using a single threshold based on Hounsfield unit values and double thresholds using material density images. We analysed the correlations between tumour volume and haematological indicators (β2-microglobulin, M-protein, free light chain, albumin, lactate dehydrogenase) and the trends after treatment intervention.

Results

A moderate correlation was identified between the assumed tumour volume in the initial scan and the β2-microglobulin level, with a correlation coefficient of ρ = 0.69 for the volume calculated from a single threshold value of Hounsfield unit and ρ = 0.57 for the volume calculated from a double threshold value of the bone(fat) material density image. No significant correlation was found between the assumed tumour volume and the M-protein or free light chain levels. In patients who underwent three or more follow-up evaluations after the initial examination, there was a similarity in the changes in the assumed tumour volume and β2-microglobulin levels after treatment.

Conclusion

Extracting assumed tumour volume using DESCT has sufficient potential as a biomarker for multiple myeloma.

目的应用双能谱计算机断层扫描（DESCT）测量多发性骨髓瘤患者肱骨推定肿瘤体积，并评价其与血液学指标的相关性。方法回顾性分析22例多发性骨髓瘤患者的82例DESCT检查结果。在提取双侧肱骨并去除骨组织后，我们使用基于Hounsfield单位值的单阈值和使用材料密度图像的双阈值测量假设肿瘤区域的体积。我们分析了肿瘤体积与血液学指标（β2-微球蛋白、m蛋白、游离轻链、白蛋白、乳酸脱氢酶）的相关性以及治疗干预后的趋势。结果初始扫描假定肿瘤体积与β2微球蛋白水平存在中等相关性，单霍斯菲尔德单位阈值计算的体积相关系数为ρ = 0.69，双骨（脂肪）物质密度图像阈值计算的体积相关系数为ρ = 0.57。假设的肿瘤体积与m蛋白或游离轻链水平之间没有明显的相关性。在初始检查后接受三次或三次以上随访评估的患者中，治疗后假定肿瘤体积和β2微球蛋白水平的变化相似。结论利用DESCT提取假定肿瘤体积作为多发性骨髓瘤的生物标志物具有足够的潜力。

{"title":"Evaluation of assumed tumour volume in multiple myeloma using dual-energy spectral CT and its correlation between haematological findings","authors":"Tetsuya Kosaka , Chisaki Masuda , Sachiho Tatebe , Risen Hirai , Akira Tanimura","doi":"10.1016/j.ejro.2025.100675","DOIUrl":"10.1016/j.ejro.2025.100675","url":null,"abstract":"<div><h3>Objectives</h3><div>To measure the assumed tumour volume in the humerus of patients with multiple myeloma using dual-energy spectral computed tomography (DESCT) and to evaluate the correlation with haematological indicators.</div></div><div><h3>Methods</h3><div>We retrospectively analysed 82 DESCT examinations of 22 patients diagnosed with multiple myeloma. After extracting the bilateral humeri and removing the bone tissue, we measured the volume of the assumed tumour area using a single threshold based on Hounsfield unit values and double thresholds using material density images. We analysed the correlations between tumour volume and haematological indicators (β2-microglobulin, M-protein, free light chain, albumin, lactate dehydrogenase) and the trends after treatment intervention.</div></div><div><h3>Results</h3><div>A moderate correlation was identified between the assumed tumour volume in the initial scan and the β2-microglobulin level, with a correlation coefficient of ρ = 0.69 for the volume calculated from a single threshold value of Hounsfield unit and ρ = 0.57 for the volume calculated from a double threshold value of the bone(fat) material density image. No significant correlation was found between the assumed tumour volume and the M-protein or free light chain levels. In patients who underwent three or more follow-up evaluations after the initial examination, there was a similarity in the changes in the assumed tumour volume and β2-microglobulin levels after treatment.</div></div><div><h3>Conclusion</h3><div>Extracting assumed tumour volume using DESCT has sufficient potential as a biomarker for multiple myeloma.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100675"},"PeriodicalIF":2.9,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Diagnostic accuracy of MRI radiomics in predicting lymph node metastasis in prostate cancer: A systematic review MRI放射组学预测前列腺癌淋巴结转移的诊断准确性：系统综述

IF 2.9 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-07-28 DOI: 10.1016/j.ejro.2025.100673

Alireza Teymouri , Mohammad Saeid Khonji , Parisa Alaghi , Sina Azadnajafabad , Ava Teymouri , Sina Delazar

Purpose

Prostate cancer (PCa) is frequently associated with pelvic lymph node metastasis (PLNM), which may be missed by conventional imaging, particularly in micrometastatic disease. MRI-based radiomics offers potential to improve detection. This review evaluates recent advancements and diagnostic accuracy of MRI radiomics for predicting PLNM in PCa patients.

Methods

PubMed, Embase, and Web of Science were systematically searched through January 1, 2025, using terms like “prostate cancer,” “radiomics,” and “pelvic lymph node metastasis.” Eligible studies were assessed using the Radiomics Quality Score (RQS). Study characteristics and performance metrics were narratively synthesized. Pooled area under the receiver operating characteristic curve (AUC) was calculated for PLNM prediction in studies using prostate as regions of interest (ROI), reported with 95 % confidence intervals (CI); p-value < 0.05 was considered significant.

Results

Nine studies (2021–2024) involving 2344 PCa patients were included. Radiomics models using prostate as ROI achieved a pooled AUC of 0.78 (95 %CI: 0.72–0.84) with mild heterogeneity (I² = 19.81 %, p < 0.38). Models with lymph nodes as ROI showed AUCs of 0.93–0.95. Integrating imaging reports and clinical data often improved diagnostic accuracy. Radiomics outperformed clinical nomograms in five studies, although the difference was insignificant in one study (p > 0.05). Median RQS was 16/36; studies lacked prospective design and cost-effectiveness analysis.

Conclusion

MRI radiomics predicts PLNM with moderate accuracy, particularly when using pelvic lymph nodes as ROI. Standardized protocols, feature extraction, and clinical data integration are crucial for consistency. Prospective studies with larger cohorts are needed to validate these findings.

目的前列腺癌（PCa）常与盆腔淋巴结转移（PLNM）相关，这可能被常规影像学所遗漏，特别是在微转移性疾病中。基于核磁共振的放射组学提供了改进检测的潜力。本文综述了MRI放射组学预测PCa患者PLNM的最新进展和诊断准确性。方法使用“前列腺癌”、“放射组学”和“盆腔淋巴结转移”等术语，系统地检索到2025年1月1日的spubmed、Embase和Web of Science。使用放射组学质量评分（RQS）对符合条件的研究进行评估。叙述性地综合了研究特点和绩效指标。在使用前列腺作为感兴趣区域（ROI）的研究中，计算受试者工作特征曲线（AUC）下的汇总面积，以95% %置信区间（CI）进行PLNM预测；p值<； 0.05被认为是显著的。结果纳入9项研究（2021-2024），涉及2344例PCa患者。使用前列腺作为ROI的放射组学模型的合并AUC为0.78(95 %CI: 0.72-0.84)，具有轻度异质性（I²= 19.81 %,p <； 0.38）。以淋巴结为ROI的模型auc为0.93 ~ 0.95。将影像学报告和临床资料相结合通常可以提高诊断的准确性。放射组学在五项研究中优于临床形态图，尽管其中一项研究的差异不显著（p >； 0.05）。中位RQS为16/36；研究缺乏前瞻性设计和成本-效果分析。结论mri放射组学预测PLNM具有中等准确性，特别是当使用盆腔淋巴结作为ROI时。标准化的协议、特征提取和临床数据整合对于一致性至关重要。需要更大规模的前瞻性研究来验证这些发现。

{"title":"Diagnostic accuracy of MRI radiomics in predicting lymph node metastasis in prostate cancer: A systematic review","authors":"Alireza Teymouri , Mohammad Saeid Khonji , Parisa Alaghi , Sina Azadnajafabad , Ava Teymouri , Sina Delazar","doi":"10.1016/j.ejro.2025.100673","DOIUrl":"10.1016/j.ejro.2025.100673","url":null,"abstract":"<div><h3>Purpose</h3><div>Prostate cancer (PCa) is frequently associated with pelvic lymph node metastasis (PLNM), which may be missed by conventional imaging, particularly in micrometastatic disease. MRI-based radiomics offers potential to improve detection. This review evaluates recent advancements and diagnostic accuracy of MRI radiomics for predicting PLNM in PCa patients.</div></div><div><h3>Methods</h3><div>PubMed, Embase, and Web of Science were systematically searched through January 1, 2025, using terms like “prostate cancer,” “radiomics,” and “pelvic lymph node metastasis.” Eligible studies were assessed using the Radiomics Quality Score (RQS). Study characteristics and performance metrics were narratively synthesized. Pooled area under the receiver operating characteristic curve (AUC) was calculated for PLNM prediction in studies using prostate as regions of interest (ROI), reported with 95 % confidence intervals (CI); p-value < 0.05 was considered significant.</div></div><div><h3>Results</h3><div>Nine studies (2021–2024) involving 2344 PCa patients were included. Radiomics models using prostate as ROI achieved a pooled AUC of 0.78 (95 %CI: 0.72–0.84) with mild heterogeneity (I² = 19.81 %, p < 0.38). Models with lymph nodes as ROI showed AUCs of 0.93–0.95. Integrating imaging reports and clinical data often improved diagnostic accuracy. Radiomics outperformed clinical nomograms in five studies, although the difference was insignificant in one study (p > 0.05). Median RQS was 16/36; studies lacked prospective design and cost-effectiveness analysis.</div></div><div><h3>Conclusion</h3><div>MRI radiomics predicts PLNM with moderate accuracy, particularly when using pelvic lymph nodes as ROI. Standardized protocols, feature extraction, and clinical data integration are crucial for consistency. Prospective studies with larger cohorts are needed to validate these findings.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100673"},"PeriodicalIF":2.9,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Combination of imaging features on pancreatic CT for predicting early recurrence after upfront pancreatoduodenectomy of pancreatic ductal adenocarcinoma 结合胰腺CT影像特征预测胰管腺癌术前胰十二指肠切除术后早期复发

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-07-26 DOI: 10.1016/j.ejro.2025.100672

Shuanglin Zhang , Yi-Xuan Guo , Gui-Xue Dai , Xiumin Qi , Hao Wang , Yongping Zhou , Kai Zhang , Fang-Ming Chen

Purpose

This study aimed to identify preoperative computed tomography (CT) imaging features for predicting early recurrence after upfront pancreatoduodenectomy of pancreatic ductal adenocarcinoma (PDAC), and to assess the diagnostic performance and prognostic relevance of their combination.

Methods

This study retrospectively included PDAC patients who underwent pancreatoduodenectomy and preoperative pancreatic CT between January 2016 and December 2023. Early recurrence is defined based on imaging evidence or pathology within 12 months after surgery. Significant imaging features for early recurrence were identified using univariate and multivariate analyses. Disease-free survival (DFS) and overall survival (OS) were analyzed in relation to these significant imaging features.

Results

A total of 149 patients were evaluated (median age: 67 years; interquartile range: 41–89 years; 82 men), among whom 70 (47.0 %) experienced early recurrence. Rim enhancement, tumor necrosis, peripancreatic tumor infiltration, and suspicious metastatic lymph nodes, were independently associated with early recurrence. When any two or more of these four significant imaging features were combined, the specificity was 86.1 % (68/79) and the sensitivity was 88.6 % (60/70). DFS and OS were significantly worse in PDAC patients with two or more of these features compared to those with none or only one (all log-rank P < 0.001).

Conclusion

A combination of two or more imaging features such as rim enhancement, tumor necrosis, peripancreatic tumor infiltration, and suspicious metastatic lymph nodes, could be used as a prognostic imaging marker for early recurrence, demonstrating effective diagnostic performance and an association with DFS and OS after pancreatoduodenectomy of PDAC.

目的本研究旨在探讨术前CT影像学特征对胰管腺癌（PDAC）早期复发的预测价值，并评估其联合诊断的价值和预后相关性。方法回顾性研究2016年1月至2023年12月期间行胰十二指肠切除术和术前胰腺CT的PDAC患者。早期复发是根据手术后12个月内的影像学证据或病理来定义的。通过单因素和多因素分析确定早期复发的重要影像学特征。分析无病生存期（DFS）和总生存期（OS）与这些重要影像学特征的关系。结果共纳入149例患者(中位年龄：67岁；四分位数范围：41-89岁；男性82例)，其中早期复发70例（47.0 %）。边缘增强、肿瘤坏死、胰腺周围肿瘤浸润和可疑的转移性淋巴结与早期复发独立相关。当这四种重要影像学特征中的任何两种或两种以上合并时，特异性为86.1 %(68/79)，敏感性为88.6% %（60/70）。与没有或只有一种特征的PDAC患者相比，具有上述两种或两种以上特征的PDAC患者的DFS和OS明显更差（所有log-rank P <； 0.001）。结论结合两种或两种以上影像学表现，如边缘增强、肿瘤坏死、胰腺周围肿瘤浸润、可疑转移淋巴结等，可作为PDAC早期复发的预后影像学标志，具有有效的诊断价值，并与PDAC术后DFS和OS相关。

{"title":"Combination of imaging features on pancreatic CT for predicting early recurrence after upfront pancreatoduodenectomy of pancreatic ductal adenocarcinoma","authors":"Shuanglin Zhang , Yi-Xuan Guo , Gui-Xue Dai , Xiumin Qi , Hao Wang , Yongping Zhou , Kai Zhang , Fang-Ming Chen","doi":"10.1016/j.ejro.2025.100672","DOIUrl":"10.1016/j.ejro.2025.100672","url":null,"abstract":"<div><h3>Purpose</h3><div>This study aimed to identify preoperative computed tomography (CT) imaging features for predicting early recurrence after upfront pancreatoduodenectomy of pancreatic ductal adenocarcinoma (PDAC), and to assess the diagnostic performance and prognostic relevance of their combination.</div></div><div><h3>Methods</h3><div>This study retrospectively included PDAC patients who underwent pancreatoduodenectomy and preoperative pancreatic CT between January 2016 and December 2023. Early recurrence is defined based on imaging evidence or pathology within 12 months after surgery. Significant imaging features for early recurrence were identified using univariate and multivariate analyses. Disease-free survival (DFS) and overall survival (OS) were analyzed in relation to these significant imaging features.</div></div><div><h3>Results</h3><div>A total of 149 patients were evaluated (median age: 67 years; interquartile range: 41–89 years; 82 men), among whom 70 (47.0 %) experienced early recurrence. Rim enhancement, tumor necrosis, peripancreatic tumor infiltration, and suspicious metastatic lymph nodes, were independently associated with early recurrence. When any two or more of these four significant imaging features were combined, the specificity was 86.1 % (68/79) and the sensitivity was 88.6 % (60/70). DFS and OS were significantly worse in PDAC patients with two or more of these features compared to those with none or only one (all log-rank <em>P</em> < 0.001).</div></div><div><h3>Conclusion</h3><div>A combination of two or more imaging features such as rim enhancement, tumor necrosis, peripancreatic tumor infiltration, and suspicious metastatic lymph nodes, could be used as a prognostic imaging marker for early recurrence, demonstrating effective diagnostic performance and an association with DFS and OS after pancreatoduodenectomy of PDAC.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100672"},"PeriodicalIF":1.8,"publicationDate":"2025-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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 3D content-based image retrieval system on chest HRCT: Performance assessment for interstitial lung diseases and usual interstitial pneumonia 基于深度学习的胸部HRCT三维内容图像检索系统：对间质性肺疾病和常见性间质性肺炎的性能评价

IF 1.8 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

European Journal of Radiology Open

Pub Date : 2025-07-23 DOI: 10.1016/j.ejro.2025.100670

Akira Oosawa , Atsuko Kurosaki , Atsushi Miyamoto , Shigeo Hanada , Yuichiro Nei , Hiroshi Nakahama , Yui Takahashi , Takahiro Mitsumura , Hisashi Takaya , Tomohisa Baba , Tae Iwasawa , Masatoshi Hori , Shoji Kido , Takashi Ogura , Noriyuki Tomiyama , Kazuma Kishi , Meiyo Tamaoka

Background

Diffuse parenchymal lung diseases have various conditions and CT imaging findings. Differentiating interstitial lung diseases (ILDs) and determining the presence or absence of usual interstitial pneumonia (UIP), can be challenging, even for experienced radiologists. To address this challenge, we developed a 3D-content-based image retrieval system (CBIR) and investigated its clinical usefulness.

Methods

Using deep learning technology, we developed a prototype system that analyzes thin-slice whole lung HRCT images, automatically registers them in a database, and retrieves similar images. To evaluate search performance, we used a database of 2058 cases and assessed image similarity between query and retrieved cases using a 5-point visual score (5: Similar, 4: Somewhat similar, 3: Neither, 2: Somewhat dissimilar, 1: Dissimilar). To assess clinical usefulness, we evaluated the concordance of labels (ILD/non-ILD, with/without UIP) between query and retrieved cases, using a database of 301 cases across 57 diseases.

Results

For search performance, the mean score of visual similarity between 70 queries and their top 5 retrieved cases was 4.37 ± 0.83. For clinical usefulness, label concordance between 25 queries and their top 5 retrieved cases was assessed across 4 labels. For ILD, the mean concordance of labels was 0.94 ± 0.15, while for non-ILD, it was 0.64 ± 0.31. For cases with UIP, the mean concordance of labels was 0.86 ± 0.17, while for cases without UIP, it was 0.83 ± 0.24.

Conclusions

Our CBIR system showed high accuracy for identifying cases with/without UIP, suggesting its potential to support UIP differentiation in clinical practice.

背景弥漫性肺实质疾病有多种症状和CT影像表现。鉴别间质性肺疾病（ild）和确定是否存在通常的间质性肺炎（UIP），可能是具有挑战性的，即使是经验丰富的放射科医生。为了解决这一挑战，我们开发了一个基于3d内容的图像检索系统（CBIR）并研究了其临床用途。方法利用深度学习技术，开发了一个原型系统，对全肺HRCT薄层图像进行分析，自动注册到数据库中，并检索相似图像。为了评估搜索性能，我们使用了一个包含2058个案例的数据库，并使用5分视觉评分来评估查询和检索案例之间的图像相似性（5分相似，4分有点相似，3分都不相似，2分有点不相似，1分不相似）。为了评估临床有用性，我们使用涵盖57种疾病的301例数据库，评估了查询和检索病例之间标签（ILD/非ILD，有/没有UIP）的一致性。结果在搜索性能方面，70个查询与前5个检索案例的视觉相似度平均得分为4.37 ± 0.83。对于临床有用性，在4个标签上评估25个查询和前5个检索病例之间的标签一致性。对于ILD，标签的平均一致性为0.94 ± 0.15，而对于非ILD，其平均一致性为0.64 ± 0.31。对于有UIP的病例，标签的平均一致性为0.86 ± 0.17，而对于没有UIP的病例，标签的平均一致性为0.83 ± 0.24。结论我们的CBIR系统对UIP有较高的识别准确率，可用于临床UIP的鉴别。

{"title":"Deep-learning-based 3D content-based image retrieval system on chest HRCT: Performance assessment for interstitial lung diseases and usual interstitial pneumonia","authors":"Akira Oosawa , Atsuko Kurosaki , Atsushi Miyamoto , Shigeo Hanada , Yuichiro Nei , Hiroshi Nakahama , Yui Takahashi , Takahiro Mitsumura , Hisashi Takaya , Tomohisa Baba , Tae Iwasawa , Masatoshi Hori , Shoji Kido , Takashi Ogura , Noriyuki Tomiyama , Kazuma Kishi , Meiyo Tamaoka","doi":"10.1016/j.ejro.2025.100670","DOIUrl":"10.1016/j.ejro.2025.100670","url":null,"abstract":"<div><h3>Background</h3><div>Diffuse parenchymal lung diseases have various conditions and CT imaging findings. Differentiating interstitial lung diseases (ILDs) and determining the presence or absence of usual interstitial pneumonia (UIP), can be challenging, even for experienced radiologists. To address this challenge, we developed a 3D-content-based image retrieval system (CBIR) and investigated its clinical usefulness.</div></div><div><h3>Methods</h3><div>Using deep learning technology, we developed a prototype system that analyzes thin-slice whole lung HRCT images, automatically registers them in a database, and retrieves similar images. To evaluate search performance, we used a database of 2058 cases and assessed image similarity between query and retrieved cases using a 5-point visual score (5: Similar, 4: Somewhat similar, 3: Neither, 2: Somewhat dissimilar, 1: Dissimilar). To assess clinical usefulness, we evaluated the concordance of labels (ILD/non-ILD, with/without UIP) between query and retrieved cases, using a database of 301 cases across 57 diseases.</div></div><div><h3>Results</h3><div>For search performance, the mean score of visual similarity between 70 queries and their top 5 retrieved cases was 4.37 ± 0.83. For clinical usefulness, label concordance between 25 queries and their top 5 retrieved cases was assessed across 4 labels. For ILD, the mean concordance of labels was 0.94 ± 0.15, while for non-ILD, it was 0.64 ± 0.31. For cases with UIP, the mean concordance of labels was 0.86 ± 0.17, while for cases without UIP, it was 0.83 ± 0.24.</div></div><div><h3>Conclusions</h3><div>Our CBIR system showed high accuracy for identifying cases with/without UIP, suggesting its potential to support UIP differentiation in clinical practice.</div></div>","PeriodicalId":38076,"journal":{"name":"European Journal of Radiology Open","volume":"15 ","pages":"Article 100670"},"PeriodicalIF":1.8,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0