Academic Radiology最新文献

英文中文

Prognostic Value of Pseudotime from Texture Parameters of [18F]fluorodeoxyglucose PET/CT in Resectable Pancreatic Ductal Adenocarcinoma [18F]氟脱氧葡萄糖PET/CT纹理参数伪时间对可切除胰导管腺癌的预后价值。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-01-01 DOI: 10.1016/j.acra.2025.10.016

Wonseok Whi MD, PhD , Seung Hyup Hyun MD, PhD , Hyunjong Lee MD, PhD , Jeong Il Yu MD, PhD , Kwang Hyuck Lee MD, PhD , Jin Seok Heo MD, PhD , Joon Young Choi MD, PhD

Rationale and Objectives

This study evaluates the prognostic value of pseudotime derived from radiomics texture parameters on [¹⁸F]fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) images of resectable pancreatic ductal adenocarcinoma (PDAC) patients.

Materials and Methods

We retrospectively analyzed data from 711 patients who underwent FDG PET/CT before surgery. We extracted 56 radiomics features and calculated the pseudotime, a continuous metric estimating disease progression, using the Phenopath algorithm. Clinicopathologic features and other conventional PET parameters were also obtained. Correlation analyses were performed between the conventional PET parameters and pseudotime, and survival analysis was performed according to the clinicopathologic variables.

Results

Correlation analysis revealed that pseudotime correlates weakly with SUVmax and SUVmean and strongly with the metabolic tumor volume (MTV) and total lesion glycolysis (TLG). A multivariate survival analysis revealed that pseudotime is an independent predictor of disease-free survival (hazard ratio [HR] = 1.67, p < 0.001, c-index = 0.59), showing stronger prognostic performance than MTV (HR = 1.48, p = 0.009, c = 0.57) and TLG (HR = 1.39, p = 0.03, c = 0.56). When pseudotime was combined with TLG for risk stratification, the integrated model demonstrated the strongest prognostic separation among subgroups. Texture parameters related to homogeneity correlated positively with pseudotime, and those representing heterogeneity showed mixed correlations, highlighting the complexity of tumor biology.

Conclusion

Our findings indicate that pseudotime is a meaningful prognostic biomarker in resectable PDAC patients undergoing surgery, with stronger predictive power than established metabolic parameters. Stratification performance improved when it was combined with conventional markers.

基本原理和目的：本研究评估可切除胰导管腺癌（PDAC）患者的放射组学纹理参数所得伪时间的预后价值。材料和方法：我们回顾性分析了711例术前接受FDG PET/CT检查的患者的资料。我们提取了56个放射组学特征，并使用Phenopath算法计算了假时间，这是一种估计疾病进展的连续度量。同时获得临床病理特征及其他常规PET参数。常规PET参数与假时间进行相关性分析，根据临床病理变量进行生存分析。结果：相关分析显示，假时间与SUVmax和SUVmean相关性较弱，与代谢肿瘤体积（MTV）和病变总糖酵解（TLG）相关性较强。多变量生存分析显示，假时间是无病生存的独立预测因子（风险比[HR] = 1.67, p < 0.001, c-index = 0.59），比MTV （HR = 1.48, p = 0.009, c = 0.57）和TLG （HR = 1.39, p = 0.03, c = 0.56）表现出更强的预后效果。当假时间与TLG相结合进行风险分层时，综合模型显示亚组之间的预后分离最强。同质性相关的纹理参数与伪时间呈正相关，异质性相关的纹理参数与伪时间呈混合相关，凸显了肿瘤生物学的复杂性。结论：我们的研究结果表明，假时间是可切除的PDAC患者接受手术的有意义的预后生物标志物，比既定的代谢参数具有更强的预测能力。与常规标记物联合使用可提高分层效果。

{"title":"Prognostic Value of Pseudotime from Texture Parameters of [18F]fluorodeoxyglucose PET/CT in Resectable Pancreatic Ductal Adenocarcinoma","authors":"Wonseok Whi MD, PhD , Seung Hyup Hyun MD, PhD , Hyunjong Lee MD, PhD , Jeong Il Yu MD, PhD , Kwang Hyuck Lee MD, PhD , Jin Seok Heo MD, PhD , Joon Young Choi MD, PhD","doi":"10.1016/j.acra.2025.10.016","DOIUrl":"10.1016/j.acra.2025.10.016","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>This study evaluates the prognostic value of pseudotime derived from radiomics texture parameters on [<sup>18</sup>F]fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) images of resectable pancreatic ductal adenocarcinoma (PDAC) patients.</div></div><div><h3>Materials and Methods</h3><div>We retrospectively analyzed data from 711 patients who underwent FDG PET/CT before surgery. We extracted 56 radiomics features and calculated the pseudotime, a continuous metric estimating disease progression, using the Phenopath algorithm. Clinicopathologic features and other conventional PET parameters were also obtained. Correlation analyses were performed between the conventional PET parameters and pseudotime, and survival analysis was performed according to the clinicopathologic variables.</div></div><div><h3>Results</h3><div>Correlation analysis revealed that pseudotime correlates weakly with SUVmax and SUVmean and strongly with the metabolic tumor volume (MTV) and total lesion glycolysis (TLG). A multivariate survival analysis revealed that pseudotime is an independent predictor of disease-free survival (hazard ratio [HR] = 1.67, p < 0.001, c-index = 0.59), showing stronger prognostic performance than MTV (HR = 1.48, p = 0.009, c = 0.57) and TLG (HR = 1.39, p = 0.03, c = 0.56). When pseudotime was combined with TLG for risk stratification, the integrated model demonstrated the strongest prognostic separation among subgroups. Texture parameters related to homogeneity correlated positively with pseudotime, and those representing heterogeneity showed mixed correlations, highlighting the complexity of tumor biology.</div></div><div><h3>Conclusion</h3><div>Our findings indicate that pseudotime is a meaningful prognostic biomarker in resectable PDAC patients undergoing surgery, with stronger predictive power than established metabolic parameters. Stratification performance improved when it was combined with conventional markers.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"33 1","pages":"Pages 189-200"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145394975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Clinical and Radiologic Contextualization of Automated BAC Quantification: A Commentary 自动BAC定量的临床和放射背景：评论。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-01-01 DOI: 10.1016/j.acra.2025.08.057

Ahmet Gürkan Erdemir MD , Gamze Durhan Assoc. Prof.

引用次数: 0

Dual-Vessel Microcirculation Imaging in Discriminating Non-Hodgkin Lymphoma Subtypes Using Super-Resolution Ultrasound: An Exploring Study 超分辨率超声双血管微循环成像鉴别非霍奇金淋巴瘤亚型的探索性研究。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-01-01 DOI: 10.1016/j.acra.2025.10.015

YiJie Dong MD , Qing Hua MD , ShuJun Xia MD , CongCong Yuan MD , Cheng Li MD , YanYan Song PhD , YuHang Zheng PhD , RuoLin Tao MD , ZhenHua Liu MD , YuLu Zhang MS , FangGang Wu MS , Wei Guo PhD , Yuan Tian MS , JianQiao Zhou MD

Background

Identifying the subtype of intranodal non-Hodgkin lymphoma (NHL) is crucial for clinical management.

Rationale and Objectives

To display dual-vessel systems (microvascular and microlymphatic circulation) of intranodal NHL using super-resolution ultrasound (SRUS), and explore the diagnostic performance of SRUS imaging for predicting B-cell and T-cell subtypes NHL.

Materials and Methods

A total of 49 patients with intranodal NHL underwent dual-vessel system SRUS imaging via intravenous and intra-lymph node routes. Least absolute shrinkage and selection operator (LASSO) regression, fitted the LASSO model and leave-one-out cross-validation (LOOCV) were used for model development and internal validation.

Results

Among the 49 patients, 40 were diagnosed with B-cell NHL and 9 with T-cell NHL. Variables including LDmax, LDLmin, and VCmin were selected and the logistic regression model achieved discrimination of B-cell and T-cell subtype of lymphoma with an AUC of 0.831 (0.594–0.969).

Conclusion

Dual-vessel SRUS imaging can display real time microvascular and microlymphatic circulation of intranodal NHL in physiological status. With quantitative analysis of SRUS offers a potential non-invasive diagnostic alternative in differentiating NHL subtype.

背景：确定结内非霍奇金淋巴瘤（NHL）亚型对临床治疗至关重要。原理和目的：利用超分辨率超声（SRUS）显示结内NHL的双血管系统（微血管和微淋巴循环），并探讨SRUS成像在预测b细胞和t细胞亚型NHL中的诊断性能。材料和方法：共有49例结内NHL患者通过静脉和淋巴结内途径行双血管系统SRUS成像。最小绝对收缩和选择算子（LASSO）回归，拟合LASSO模型和留一交叉验证（LOOCV）用于模型开发和内部验证。结果：49例患者中，40例诊断为b细胞NHL， 9例诊断为t细胞NHL。选取LDmax、LDLmin、VCmin等变量，logistic回归模型实现了b细胞和t细胞亚型淋巴瘤的区分，AUC为0.831（0.594-0.969）。结论：双血管SRUS成像可实时显示结内NHL生理状态下的微血管和微淋巴循环。SRUS的定量分析为区分NHL亚型提供了一种潜在的非侵入性诊断选择。

{"title":"Dual-Vessel Microcirculation Imaging in Discriminating Non-Hodgkin Lymphoma Subtypes Using Super-Resolution Ultrasound: An Exploring Study","authors":"YiJie Dong MD , Qing Hua MD , ShuJun Xia MD , CongCong Yuan MD , Cheng Li MD , YanYan Song PhD , YuHang Zheng PhD , RuoLin Tao MD , ZhenHua Liu MD , YuLu Zhang MS , FangGang Wu MS , Wei Guo PhD , Yuan Tian MS , JianQiao Zhou MD","doi":"10.1016/j.acra.2025.10.015","DOIUrl":"10.1016/j.acra.2025.10.015","url":null,"abstract":"<div><h3>Background</h3><div>Identifying the subtype of intranodal non-Hodgkin lymphoma (NHL) is crucial for clinical management.</div></div><div><h3>Rationale and Objectives</h3><div>To display dual-vessel systems (microvascular and microlymphatic circulation) of intranodal NHL using super-resolution ultrasound (SRUS), and explore the diagnostic performance of SRUS imaging for predicting B-cell and T-cell subtypes NHL.</div></div><div><h3>Materials and Methods</h3><div>A total of 49 patients with intranodal NHL underwent dual-vessel system SRUS imaging via intravenous and intra-lymph node routes. Least absolute shrinkage and selection operator (LASSO) regression, fitted the LASSO model and leave-one-out cross-validation (LOOCV) were used for model development and internal validation.</div></div><div><h3>Results</h3><div>Among the 49 patients, 40 were diagnosed with B-cell NHL and 9 with T-cell NHL. Variables including LDmax, LDLmin, and VCmin were selected and the logistic regression model achieved discrimination of B-cell and T-cell subtype of lymphoma with an AUC of 0.831 (0.594–0.969).</div></div><div><h3>Conclusion</h3><div>Dual-vessel SRUS imaging can display real time microvascular and microlymphatic circulation of intranodal NHL in physiological status. With quantitative analysis of SRUS offers a potential non-invasive diagnostic alternative in differentiating NHL subtype.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"33 1","pages":"Pages 35-46"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145402303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Predictive Model for False-Negative Results in Ultrasound-Guided Percutaneous Transthoracic Needle Lung Biopsy 超声引导下经皮经胸肺穿刺活检假阴性结果的预测模型。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-01-01 DOI: 10.1016/j.acra.2025.10.023

Jiawei Yi , Ke Bi , Mengjun Shen , Kaiwen Wu , Xinyu Zhao , Runhe Xia , Yang Cong , Yi Li , Yin Wang

Objectives

This study aimed to develop a post-procedural predictive model for assessing the risk of false-negative results in ultrasound-guided percutaneous transthoracic needle lung biopsy (US-PTLB).

Material and Methods

Two prospective cohorts were designed for model development and validation. Patients scheduled for US-PTLB underwent B-mode ultrasound (B-US), color Doppler flow imaging (CDFI), ultrasound elastography, and contrast-enhanced ultrasound (CEUS) of the lesions, with the final diagnosis confirmed through comprehensive evaluation. Risk factors associated with false-negative results were identified, and multivariate logistic regression was used to construct the predictive model. The model's performance was further evaluated in an independent cohort to assess its impact on reducing the incidence of false-negative results through targeted interventions.

Results

The US-PTLB false-negative risk prediction model was constructed using data from 129 patients, of whom 35 (29.1%) were ultimately diagnosed with false-negative results. Predictors included age, lesion size, elasticity score, lesion necrosis, and enhancement intensity on CEUS. The model demonstrated excellent discrimination, with an area under the curve of 0.922, sensitivity of 88.6%, and specificity of 90.4%. Internal validation in 70 independently collected patients confirmed robust model performance. Application of the model in 423 patients, coupled with second biopsies for high-risk patients, led to a significant reduction in the incidence of false-negative results.

Conclusion

This predictive model, combining clinical parameters with multimodal ultrasound features, serves as a robust post-procedural tool for objectively assessing false-negative risk in ultrasound-guided percutaneous transthoracic needle lung biopsy. Its clinical application enables early risk stratification, minimizes false-negative rates, and enhances diagnostic precision.

目的：本研究旨在建立一种术后预测模型，用于评估超声引导下经皮经胸穿刺肺活检（US-PTLB）假阴性结果的风险。材料和方法：设计了两个前瞻性队列进行模型开发和验证。行US-PTLB的患者对病变行b超（B-US）、彩色多普勒血流显像（CDFI）、超声弹性成像（ultrasound elastography，超声造影）、超声造影（contrast-enhanced ultrasound， CEUS）检查，综合评价后确定最终诊断。确定与假阴性结果相关的危险因素，并采用多因素logistic回归构建预测模型。在一个独立的队列中进一步评估了该模型的性能，以评估其通过有针对性的干预措施减少假阴性结果发生率的影响。结果：利用129例患者的数据构建US-PTLB假阴性风险预测模型，其中35例（29.1%）最终诊断为假阴性。预测因素包括年龄、病变大小、弹性评分、病变坏死和超声造影增强强度。该模型具有良好的鉴别能力，曲线下面积为0.922，灵敏度为88.6%，特异度为90.4%。在70名独立收集的患者中进行的内部验证证实了模型的稳健性能。在423例患者中应用该模型，再加上对高危患者进行第二次活检，导致假阴性结果的发生率显著降低。结论：该预测模型将临床参数与多模态超声特征相结合，可作为超声引导下经皮经胸肺穿刺活检假阴性风险客观评估的可靠术后工具。它的临床应用使早期风险分层，最大限度地减少假阴性率，提高诊断精度。

{"title":"A Predictive Model for False-Negative Results in Ultrasound-Guided Percutaneous Transthoracic Needle Lung Biopsy","authors":"Jiawei Yi , Ke Bi , Mengjun Shen , Kaiwen Wu , Xinyu Zhao , Runhe Xia , Yang Cong , Yi Li , Yin Wang","doi":"10.1016/j.acra.2025.10.023","DOIUrl":"10.1016/j.acra.2025.10.023","url":null,"abstract":"<div><h3>Objectives</h3><div>This study aimed to develop a post-procedural predictive model for assessing the risk of false-negative results in ultrasound-guided percutaneous transthoracic needle lung biopsy (US-PTLB).</div></div><div><h3>Material and Methods</h3><div>Two prospective cohorts were designed for model development and validation. Patients scheduled for US-PTLB underwent B-mode ultrasound (B-US), color Doppler flow imaging (CDFI), ultrasound elastography, and contrast-enhanced ultrasound (CEUS) of the lesions, with the final diagnosis confirmed through comprehensive evaluation. Risk factors associated with false-negative results were identified, and multivariate logistic regression was used to construct the predictive model. The model's performance was further evaluated in an independent cohort to assess its impact on reducing the incidence of false-negative results through targeted interventions.</div></div><div><h3>Results</h3><div>The US-PTLB false-negative risk prediction model was constructed using data from 129 patients, of whom 35 (29.1%) were ultimately diagnosed with false-negative results. Predictors included age, lesion size, elasticity score, lesion necrosis, and enhancement intensity on CEUS. The model demonstrated excellent discrimination, with an area under the curve of 0.922, sensitivity of 88.6%, and specificity of 90.4%. Internal validation in 70 independently collected patients confirmed robust model performance. Application of the model in 423 patients, coupled with second biopsies for high-risk patients, led to a significant reduction in the incidence of false-negative results.</div></div><div><h3>Conclusion</h3><div>This predictive model, combining clinical parameters with multimodal ultrasound features, serves as a robust post-procedural tool for objectively assessing false-negative risk in ultrasound-guided percutaneous transthoracic needle lung biopsy. Its clinical application enables early risk stratification, minimizes false-negative rates, and enhances diagnostic precision.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"33 1","pages":"Pages 134-146"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145460223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Author Response to “Clinical and Radiologic Contextualization of Automated BAC Quantification: A Commentary ” 作者对“致编辑的信：使用基于unet的深度学习检测心血管疾病来量化乳房x光片中的乳腺动脉钙化”的回复。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-01-01 DOI: 10.1016/j.acra.2025.09.041

Wenbo Li MSc , Qiyu Zhang BSc , Dale J. Black BSc , Huanjun Ding PhD , Carlos Iribarren MD, MPH, PhD , Alireza Shojazadeh MD , Sabee Molloi PhD

引用次数: 0

Predictions of Response in Non-small Cell Lung Cancer Patients Treated with Immune Checkpoint Inhibitors Using Clinical Data, Deep Learning, and Radiomics 使用临床数据、深度学习和放射组学预测免疫检查点抑制剂治疗的非小细胞肺癌患者的反应

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-01-01 DOI: 10.1016/j.acra.2025.09.037

Chunxiao Wang , Yuxin Li , Yang Ji, Kang Yu, Chunhui Qin, Ling Liu, Yunjia Shuai, Jiahui Chen, Ao Li, Tong Zhang

Background

Determining predictive biomarkers for immunotherapy response in non-small cell lung cancer (NSCLC) patients is a complex task.

Objective

This research aimed to develop a multimodal model (CRDL) integrating clinical data, deep learning (DL), and radiomics (Rad) to predict immune responses in NSCLC patients receiving checkpoint blockade therapies. This study also evaluated whether CRDL outperforms unimodal, pre-fusion models (Pre-FMs) and post-fusion models (Post-FMs).

Methods

This is a retrospective study that utilized data from 228 lung cancer patients at the Memorial Sloan Kettering Cancer Center, with varying Programmed Death-Ligand 1(PD-L1) expression levels among the patients. 228 NSCLC patients were randomly divided into two groups in a 7:3 ratio: the training cohort (n = 159) and the validation cohort (n = 69). Image histological features were extracted using the "PyRadiomics" package, and DL features were obtained through the deep convolutional neural network from chest computed tomography images, and clinical data from the patients were also collected. Feature reduction was performed using t-tests and the Least absolute shrinkage and selection operator regression. Unimodal modal and Pre-FMs were constructed using random forests, while the post-fusion model was developed using a support vector machine approach. The performance of the model was measured by the area under the receiver operating characteristic curve (AUC).

Results

512 DL features and 382 Rad features were extracted. The CRDL model demonstrated superior performance with AUC values of 0.884 in the validation dataset and 0.976 in the training dataset, surpassing the best DL model in both unimodal and pre-fusion settings, which had training and validation AUCs of 0.854 and 0.749.

Conclusion

The CRDL model accurately forecasts immunotherapy responses in NSCLC patients, offering one dependable non-invasive test.

背景：确定非小细胞肺癌（NSCLC）患者免疫治疗反应的预测性生物标志物是一项复杂的任务。目的：本研究旨在建立一种整合临床数据、深度学习（DL）和放射组学（Rad）的多模态模型（CRDL），以预测接受检查点阻断治疗的NSCLC患者的免疫反应。本研究还评估了CRDL是否优于单峰模型、融合前模型（Pre-FMs）和融合后模型（Post-FMs）。方法：这是一项回顾性研究，利用了纪念斯隆凯特琳癌症中心228名肺癌患者的数据，这些患者的程序性死亡配体1（PD-L1）表达水平不同。228例NSCLC患者按7:3的比例随机分为两组：训练组（n=159）和验证组（n=69）。使用“PyRadiomics”软件包提取图像组织学特征，通过深度卷积神经网络提取胸部ct图像的DL特征，并收集患者的临床资料。使用t检验和最小绝对收缩和选择算子回归进行特征缩减。采用随机森林方法构建单峰模型和预融合模型，采用支持向量机方法构建融合后模型。该模型的性能通过接收机工作特性曲线下面积（AUC）来衡量。结果：提取DL特征512个，Rad特征382个。CRDL模型在验证集和训练集的AUC值分别为0.884和0.976，优于单峰和预融合设置下的最佳DL模型，前者的训练AUC和验证AUC分别为0.854和0.749。结论：CRDL模型准确预测非小细胞肺癌患者的免疫治疗反应，提供了一种可靠的无创检测方法。

{"title":"Predictions of Response in Non-small Cell Lung Cancer Patients Treated with Immune Checkpoint Inhibitors Using Clinical Data, Deep Learning, and Radiomics","authors":"Chunxiao Wang , Yuxin Li , Yang Ji, Kang Yu, Chunhui Qin, Ling Liu, Yunjia Shuai, Jiahui Chen, Ao Li, Tong Zhang","doi":"10.1016/j.acra.2025.09.037","DOIUrl":"10.1016/j.acra.2025.09.037","url":null,"abstract":"<div><h3>Background</h3><div>Determining predictive biomarkers for immunotherapy response in non-small cell lung cancer (NSCLC) patients is a complex task.</div></div><div><h3>Objective</h3><div>This research aimed to develop a multimodal model (CRDL) integrating clinical data, deep learning (DL), and radiomics (Rad) to predict immune responses in NSCLC patients receiving checkpoint blockade therapies. This study also evaluated whether CRDL outperforms unimodal, pre-fusion models (Pre-FMs) and post-fusion models (Post-FMs).</div></div><div><h3>Methods</h3><div>This is a retrospective study that utilized data from 228 lung cancer patients at the Memorial Sloan Kettering Cancer Center, with varying Programmed Death-Ligand 1(PD-L1) expression levels among the patients. 228 NSCLC patients were randomly divided into two groups in a 7:3 ratio: the training cohort (<em>n  </em>=69). Image histological features were extracted using the \"PyRadiomics\" package, and DL features were obtained through the deep convolutional neural network from chest computed tomography images, and clinical data from the patients were also collected. Feature reduction was performed using t-tests and the Least absolute shrinkage and selection operator regression. Unimodal modal and Pre-FMs were constructed using random forests, while the post-fusion model was developed using a support vector machine approach. The performance of the model was measured by the area under the receiver operating characteristic curve (AUC).</div></div><div><h3>Results</h3><div>512 DL features and 382 Rad features were extracted. The CRDL model demonstrated superior performance with AUC values of 0.884 in the validation dataset and 0.976 in the training dataset, surpassing the best DL model in both unimodal and pre-fusion settings, which had training and validation AUCs of 0.854 and 0.749.</div></div><div><h3>Conclusion</h3><div>The CRDL model accurately forecasts immunotherapy responses in NSCLC patients, offering one dependable non-invasive test.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"33 1","pages":"Pages 236-254"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145294394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Interpretable Radiomics Model Based on Pituitary MRI to Predict Growth Hormone Deficiency in Short-statured Children: A Multicenter Study 基于垂体MRI的可解释放射组学模型预测矮小儿童生长激素缺乏症：一项多中心研究。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-01-01 DOI: 10.1016/j.acra.2025.10.006

Fukun Shi , Xianqing Ren , Qian Xu , Jiameng Si , Yihao Yan , Junjie Shu , Shengli Shi , Ke Jin , Fenfen Li , Jiajia Zhang , Lan Zhang

Rationale and Objectives

To develop and validate an interpretable radiomics model based on pituitary MRI to predict growth hormone deficiency (GHD) in children with short stature.

Methods

This retrospective multicenter study enrolled 202 children (105 GHD, 97 idiopathic short stature [ISS]) as an internal cohort (7:3 ratio for training/testing cohorts) from institution I, and 138 children (61 GHD, 77 ISS) from institution II and institution III as an external validation cohort. Radiomics features were selected by SelectKBest and least absolute shrinkage and selection operator (LASSO), subsequently used to construct six machine learning models. Diagnostic performance of model was evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and calibration curves. The interpretability of the model was assessed using Shapley additive explanations (SHAP).

Results

A total of 17 radiomics features were selected. Among all classifiers, support vector machine (SVM)-based radiomics model exhibited the highest diagnostic performance, with AUCs of 0.877 (95% CI: 0.813, 0.928), 0.878 (95% CI: 0.786, 0.951), and 0.885 (95% CI: 0.833, 0.937) in training, testing, and external validation cohorts, respectively. The SVM-integrated clinical-radiomics model yielded comparable efficacy, with AUCs of 0.874 (95% CI: 0.812, 0.928), 0.878 (95% CI: 0.786, 0.952), and 0.889 (95% CI: 0.830, 0.939) across the same cohorts. Both radiomics-based models significantly outperformed the clinical model (all p<0.001), while no statistically significant difference was observed between the radiomics and clinical-radiomics models (all p>0.05). The SHAP analysis identified three key radiomics features with significant differences between GHD and ISS groups (all p<0.001).

Conclusions

The interpretable radiomics-driven SVM model effectively predicts GH levels, providing a clinically viable, non-invasive alternative to GH stimulation test in children with short stature.

基本原理和目的：开发并验证基于垂体MRI的可解释放射组学模型，以预测矮小儿童的生长激素缺乏症（GHD）。方法：这项回顾性多中心研究纳入了来自第一机构的202名儿童（105名GHD， 97名特发性身材矮小[ISS]）作为内部队列（训练/测试队列的比例为7:3），以及来自第二机构和第三机构的138名儿童（61名GHD， 77名ISS）作为外部验证队列。通过SelectKBest和最小绝对收缩和选择算子（LASSO）选择放射组学特征，随后用于构建六个机器学习模型。通过受试者工作特征曲线下面积（AUC）、灵敏度、特异性和校准曲线评价模型的诊断性能。采用Shapley加性解释（SHAP）评价模型的可解释性。结果：共选取17个放射组学特征。在所有分类器中，基于支持向量机（SVM）的放射组学模型表现出最高的诊断性能，在训练、测试和外部验证队列中的auc分别为0.877 （95% CI: 0.813, 0.928）、0.878 （95% CI: 0.786, 0.951）和0.885 （95% CI: 0.833, 0.937）。支持向量机集成的临床放射组学模型产生了相当的疗效，在相同的队列中，auc分别为0.874 （95% CI: 0.812, 0.928）、0.878 （95% CI: 0.786, 0.952）和0.889 （95% CI: 0.830, 0.939）。两种基于放射组学的模型均显著优于临床模型（均p0.05）。SHAP分析确定了三个关键的放射组学特征，在GHD组和ISS组之间存在显著差异。结论：可解释的放射组学驱动的SVM模型有效地预测生长激素水平，为矮小儿童提供了临床可行的、无创的替代生长激素刺激试验的方法。

{"title":"An Interpretable Radiomics Model Based on Pituitary MRI to Predict Growth Hormone Deficiency in Short-statured Children: A Multicenter Study","authors":"Fukun Shi , Xianqing Ren , Qian Xu , Jiameng Si , Yihao Yan , Junjie Shu , Shengli Shi , Ke Jin , Fenfen Li , Jiajia Zhang , Lan Zhang","doi":"10.1016/j.acra.2025.10.006","DOIUrl":"10.1016/j.acra.2025.10.006","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>To develop and validate an interpretable radiomics model based on pituitary MRI to predict growth hormone deficiency (GHD) in children with short stature.</div></div><div><h3>Methods</h3><div>This retrospective multicenter study enrolled 202 children (105 GHD, 97 idiopathic short stature [ISS]) as an internal cohort (7:3 ratio for training/testing cohorts) from institution I, and 138 children (61 GHD, 77 ISS) from institution II and institution III as an external validation cohort. Radiomics features were selected by SelectKBest and least absolute shrinkage and selection operator (LASSO), subsequently used to construct six machine learning models. Diagnostic performance of model was evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and calibration curves. The interpretability of the model was assessed using Shapley additive explanations (SHAP).</div></div><div><h3>Results</h3><div>A total of 17 radiomics features were selected. Among all classifiers, support vector machine (SVM)-based radiomics model exhibited the highest diagnostic performance, with AUCs of 0.877 (95% <em>CI</em>: 0.813, 0.928), 0.878 (95% <em>CI</em>: 0.786, 0.951), and 0.885 (95% <em>CI</em>: 0.833, 0.937) in training, testing, and external validation cohorts, respectively. The SVM-integrated clinical-radiomics model yielded comparable efficacy, with AUCs of 0.874 (95% <em>CI</em>: 0.812, 0.928), 0.878 (95% <em>CI</em>: 0.786, 0.952), and 0.889 (95% <em>CI</em>: 0.830, 0.939) across the same cohorts. Both radiomics-based models significantly outperformed the clinical model (all <em>p</em><0.001), while no statistically significant difference was observed between the radiomics and clinical-radiomics models (all <em>p</em>>0.05). The SHAP analysis identified three key radiomics features with significant differences between GHD and ISS groups (all <em>p</em><0.001).</div></div><div><h3>Conclusions</h3><div>The interpretable radiomics-driven SVM model effectively predicts GH levels, providing a clinically viable, non-invasive alternative to GH stimulation test in children with short stature.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"33 1","pages":"Pages 168-179"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145395046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Trends in R01 and R01 Equivalent Funding to Radiology 放射学的R01和R01等效资助趋势。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-01-01 DOI: 10.1016/j.acra.2025.09.039

Kelly M. Gillen PhD, MBA , Mert Şişman , Alan Wu , Arindam RoyChoudhury PhD , Ajay Gupta MD, MS

Rationale and Objectives

With a budget of almost $48 billion in 2024, including $37 billion allocated for extramural funding, the National Institutes of Health (NIH) is the major funding source for biomedical research in the United States. Given the multi-faceted impact of NIH funding on academic institutions and their communities, we sought to characterize trends in research project grant funding to departments of radiology.

This study aimed to assess trends in R01 and R01 equivalent award funding to departments of radiology from 2014 to 2024.

Materials and Methods

All funding data were retrieved from NIH RePORTER (Research Portfolio Online Reporting Tools) and limited to R01 and R01 equivalent awards (R01⁺) to all clinical departments (ACDs) from NIH FY 2014 and FY 2024. Awards and funding data included ACDs as categorized by the Blue Ridge Institute for Medical Research. Information on principal investigator (PI) advanced degrees was obtained by web searches and visiting the PI’s faculty page through their respective academic institution.

Results

From 2014 to 2024, there was a 54.3% increase in the number of R01s awarded to radiology as compared to a 31.7% increase in R01s awarded to ACDs. There was a 69.0% increase in the number of R01⁺s awarded to radiology as compared to a 34.4% increase in R01⁺s awarded to ACDs during this same period.

Conclusion

Since FY2014, there has been an increase in funding from the NIH to ACDs and specifically to radiology, but departments of radiology are outpacing ACDs in several key R01 and R01⁺ funding metrics, including greater increases in the number of awards.

基本原理和目标：美国国立卫生研究院（NIH）是美国生物医学研究的主要资金来源，2024年的预算近480亿美元，其中包括370亿美元的校外资金。鉴于NIH资助对学术机构及其社区的多方面影响，我们试图描述放射学部门研究项目资助的趋势。本研究旨在评估2014 - 2024年放射科R01和R01等效奖励资金的趋势。材料和方法：所有资助数据均从NIH RePORTER（研究组合在线报告工具）检索，仅限于NIH 2014财年和2024财年向所有临床部门（ACDs）提供的R01和R01等效奖励（R01+）。奖励和资助数据包括由蓝岭医学研究所分类的acd。有关首席研究员（PI）高级学位的信息可通过网络搜索和访问其各自学术机构的PI教员页面获得。结果：从2014年到2024年，授予放射学的r01数量增加了54.3%，而授予ACDs的r01数量增加了31.7%。在同一期间，放射科获发01+s的人数增加了69.0%，而辅助护理科获发01+s的人数则增加了34.4%。结论：自2014财年以来，NIH对ACDs的资助有所增加，特别是对放射学的资助，但放射学部门在几个关键的R01和R01+资助指标上超过了ACDs，包括奖励数量的更大增长。

{"title":"Trends in R01 and R01 Equivalent Funding to Radiology","authors":"Kelly M. Gillen PhD, MBA , Mert Şişman , Alan Wu , Arindam RoyChoudhury PhD , Ajay Gupta MD, MS","doi":"10.1016/j.acra.2025.09.039","DOIUrl":"10.1016/j.acra.2025.09.039","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>With a budget of almost $48 billion in 2024, including $37 billion allocated for extramural funding, the National Institutes of Health (NIH) is the major funding source for biomedical research in the United States. Given the multi-faceted impact of NIH funding on academic institutions and their communities, we sought to characterize trends in research project grant funding to departments of radiology.</div><div>This study aimed to assess trends in R01 and R01 equivalent award funding to departments of radiology from 2014 to 2024.</div></div><div><h3>Materials and Methods</h3><div>All funding data were retrieved from NIH RePORTER (Research Portfolio Online Reporting Tools) and limited to R01 and R01 equivalent awards (R01<sup>+</sup>) to all clinical departments (ACDs) from NIH FY 2014 and FY 2024. Awards and funding data included ACDs as categorized by the Blue Ridge Institute for Medical Research. Information on principal investigator (PI) advanced degrees was obtained by web searches and visiting the PI’s faculty page through their respective academic institution.</div></div><div><h3>Results</h3><div>From 2014 to 2024, there was a 54.3% increase in the number of R01s awarded to radiology as compared to a 31.7% increase in R01s awarded to ACDs. There was a 69.0% increase in the number of R01<sup>+</sup>s awarded to radiology as compared to a 34.4% increase in R01<sup>+</sup>s awarded to ACDs during this same period.</div></div><div><h3>Conclusion</h3><div>Since FY2014, there has been an increase in funding from the NIH to ACDs and specifically to radiology, but departments of radiology are outpacing ACDs in several key R01 and R01<sup>+</sup> funding metrics, including greater increases in the number of awards.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"33 1","pages":"Pages 15-19"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145304239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Challenges in Imaging-Based Nomogram Models for ALNM in TNBC: Commentary on Mammography and Ultrasound Approaches TNBC中ALNM基于成像的Nomogram模型所面临的挑战：关于乳腺x线摄影和超声方法的评论。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-01-01 DOI: 10.1016/j.acra.2025.09.042

Deniz Esin Tekcan Sanli , Ahmet Necati Sanli

引用次数: 0

Advancing MRI-Based Machine Learning Models for Breast Cancer Subtyping: Clarifications, Subtype Refinements, and Future Directions 推进基于mri的乳腺癌亚型机器学习模型：澄清、亚型改进和未来方向。

IF 3.9 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Academic Radiology

Pub Date : 2026-01-01 DOI: 10.1016/j.acra.2025.09.046

Yi Zhou , Shuzheng Chen MD, PhD

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Academic Radiology

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.

﹀