预测不确定肺结节消失的综合和仅图像深度学习模型的比较

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics Pub Date : 2025-04-11 DOI:10.1016/j.compmedimag.2025.102553

Jingxuan Wang , Jiali Cai , Wei Tang , Ivan Dudurych , Marcel van Tuinen , Rozemarijn Vliegenthart , Peter van Ooijen

{"title":"预测不确定肺结节消失的综合和仅图像深度学习模型的比较","authors":"Jingxuan Wang , Jiali Cai , Wei Tang , Ivan Dudurych , Marcel van Tuinen , Rozemarijn Vliegenthart , Peter van Ooijen","doi":"10.1016/j.compmedimag.2025.102553","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Indeterminate pulmonary nodules (IPNs) require follow-up CT to assess potential growth; however, benign nodules may disappear. Accurately predicting whether IPNs will resolve is a challenge for radiologists. Therefore, we aim to utilize deep-learning (DL) methods to predict the disappearance of IPNs.</div></div><div><h3>Material and methods</h3><div>This retrospective study utilized data from the Dutch-Belgian Randomized Lung Cancer Screening Trial (NELSON) and Imaging in Lifelines (ImaLife) cohort. Participants underwent follow-up CT to determine the evolution of baseline IPNs. The NELSON data was used for model training. External validation was performed in ImaLife. We developed integrated DL-based models that incorporated CT images and demographic data (age, sex, smoking status, and pack years). We compared the performance of integrated methods with those limited to CT images only and calculated sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). From a clinical perspective, ensuring high specificity is critical, as it minimizes false predictions of non-resolving nodules that should be monitored for evolution on follow-up CTs. Feature importance was calculated using SHapley Additive exPlanations (SHAP) values.</div></div><div><h3>Results</h3><div>The training dataset included 840 IPNs (134 resolving) in 672 participants. The external validation dataset included 111 IPNs (46 resolving) in 65 participants. On the external validation set, the performance of the integrated model (sensitivity, 0.50; 95 % CI, 0.35–0.65; specificity, 0.91; 95 % CI, 0.80–0.96; AUC, 0.82; 95 % CI, 0.74–0.90) was comparable to that solely trained on CT image (sensitivity, 0.41; 95 % CI, 0.27–0.57; specificity, 0.89; 95 % CI, 0.78–0.95; AUC, 0.78; 95 % CI, 0.69–0.86; P = 0.39). The top 10 most important features were all image related.</div></div><div><h3>Conclusion</h3><div>Deep learning-based models can predict the disappearance of IPNs with high specificity. Integrated models using CT scans and clinical data had comparable performance to those using only CT images.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"123 ","pages":"Article 102553"},"PeriodicalIF":5.4000,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A comparison of an integrated and image-only deep learning model for predicting the disappearance of indeterminate pulmonary nodules\",\"authors\":\"Jingxuan Wang , Jiali Cai , Wei Tang , Ivan Dudurych , Marcel van Tuinen , Rozemarijn Vliegenthart , Peter van Ooijen\",\"doi\":\"10.1016/j.compmedimag.2025.102553\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><div>Indeterminate pulmonary nodules (IPNs) require follow-up CT to assess potential growth; however, benign nodules may disappear. Accurately predicting whether IPNs will resolve is a challenge for radiologists. Therefore, we aim to utilize deep-learning (DL) methods to predict the disappearance of IPNs.</div></div><div><h3>Material and methods</h3><div>This retrospective study utilized data from the Dutch-Belgian Randomized Lung Cancer Screening Trial (NELSON) and Imaging in Lifelines (ImaLife) cohort. Participants underwent follow-up CT to determine the evolution of baseline IPNs. The NELSON data was used for model training. External validation was performed in ImaLife. We developed integrated DL-based models that incorporated CT images and demographic data (age, sex, smoking status, and pack years). We compared the performance of integrated methods with those limited to CT images only and calculated sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). From a clinical perspective, ensuring high specificity is critical, as it minimizes false predictions of non-resolving nodules that should be monitored for evolution on follow-up CTs. Feature importance was calculated using SHapley Additive exPlanations (SHAP) values.</div></div><div><h3>Results</h3><div>The training dataset included 840 IPNs (134 resolving) in 672 participants. The external validation dataset included 111 IPNs (46 resolving) in 65 participants. On the external validation set, the performance of the integrated model (sensitivity, 0.50; 95 % CI, 0.35–0.65; specificity, 0.91; 95 % CI, 0.80–0.96; AUC, 0.82; 95 % CI, 0.74–0.90) was comparable to that solely trained on CT image (sensitivity, 0.41; 95 % CI, 0.27–0.57; specificity, 0.89; 95 % CI, 0.78–0.95; AUC, 0.78; 95 % CI, 0.69–0.86; P = 0.39). The top 10 most important features were all image related.</div></div><div><h3>Conclusion</h3><div>Deep learning-based models can predict the disappearance of IPNs with high specificity. Integrated models using CT scans and clinical data had comparable performance to those using only CT images.</div></div>\",\"PeriodicalId\":50631,\"journal\":{\"name\":\"Computerized Medical Imaging and Graphics\",\"volume\":\"123 \",\"pages\":\"Article 102553\"},\"PeriodicalIF\":5.4000,\"publicationDate\":\"2025-04-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computerized Medical Imaging and Graphics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S089561112500062X\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, BIOMEDICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computerized Medical Imaging and Graphics","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S089561112500062X","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}

引用次数: 0

摘要

背景不确定的肺结节（IPN）需要进行 CT 随访，以评估其生长的可能性；然而，良性结节可能会消失。准确预测 IPN 是否会消失对放射科医生来说是一项挑战。因此，我们希望利用深度学习（DL）方法来预测 IPN 的消失。材料和方法这项回顾性研究利用了荷兰-比利时随机肺癌筛查试验（NELSON）和生命线成像（ImaLife）队列的数据。参与者接受了随访CT检查，以确定基线IPN的变化情况。NELSON 数据用于模型训练。外部验证在 ImaLife 中进行。我们开发了基于 DL 的集成模型，其中包含 CT 图像和人口统计学数据（年龄、性别、吸烟状况和包年）。我们比较了综合方法与仅局限于 CT 图像的方法的性能，并计算了灵敏度、特异性和接收器工作特征曲线下面积 (AUC)。从临床角度来看，确保高特异性至关重要，因为它能最大限度地减少对未溶解结节的错误预测，而这些结节应在后续 CT 检查中监测其演变情况。训练数据集包括 672 名参与者的 840 个 IPN（134 个正在消融）。外部验证数据集包括 65 名参与者的 111 个 IPN（46 个解析）。在外部验证集上，综合模型的性能（灵敏度，0.50；95 % CI，0.35-0.65；特异性，0.91；95 % CI，0.80-0.96；AUC，0.82；95 % CI，0.74-0.90）与单纯模型的性能（灵敏度，0.50；95 % CI，0.35-0.65；特异性，0.91；95 % CI，0.80-0.96）相当。90）与仅在 CT 图像上训练的结果相当（灵敏度，0.41；95 % CI，0.27-0.57；特异性，0.89；95 % CI，0.78-0.95；AUC，0.78；95 % CI，0.69-0.86；P = 0.39）。结论基于深度学习的模型可以预测 IPN 的消失，特异性很高。使用 CT 扫描和临床数据的综合模型与仅使用 CT 图像的模型性能相当。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A comparison of an integrated and image-only deep learning model for predicting the disappearance of indeterminate pulmonary nodules

Background

Indeterminate pulmonary nodules (IPNs) require follow-up CT to assess potential growth; however, benign nodules may disappear. Accurately predicting whether IPNs will resolve is a challenge for radiologists. Therefore, we aim to utilize deep-learning (DL) methods to predict the disappearance of IPNs.

Material and methods

This retrospective study utilized data from the Dutch-Belgian Randomized Lung Cancer Screening Trial (NELSON) and Imaging in Lifelines (ImaLife) cohort. Participants underwent follow-up CT to determine the evolution of baseline IPNs. The NELSON data was used for model training. External validation was performed in ImaLife. We developed integrated DL-based models that incorporated CT images and demographic data (age, sex, smoking status, and pack years). We compared the performance of integrated methods with those limited to CT images only and calculated sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). From a clinical perspective, ensuring high specificity is critical, as it minimizes false predictions of non-resolving nodules that should be monitored for evolution on follow-up CTs. Feature importance was calculated using SHapley Additive exPlanations (SHAP) values.

Results

The training dataset included 840 IPNs (134 resolving) in 672 participants. The external validation dataset included 111 IPNs (46 resolving) in 65 participants. On the external validation set, the performance of the integrated model (sensitivity, 0.50; 95 % CI, 0.35–0.65; specificity, 0.91; 95 % CI, 0.80–0.96; AUC, 0.82; 95 % CI, 0.74–0.90) was comparable to that solely trained on CT image (sensitivity, 0.41; 95 % CI, 0.27–0.57; specificity, 0.89; 95 % CI, 0.78–0.95; AUC, 0.78; 95 % CI, 0.69–0.86; P = 0.39). The top 10 most important features were all image related.

Conclusion

Deep learning-based models can predict the disappearance of IPNs with high specificity. Integrated models using CT scans and clinical data had comparable performance to those using only CT images.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Computerized Medical Imaging and Graphics 医学-核医学

CiteScore

10.70

自引率

3.50%

发文量

审稿时长

26 days

期刊介绍： The purpose of the journal Computerized Medical Imaging and Graphics is to act as a source for the exchange of research results concerning algorithmic advances, development, and application of digital imaging in disease detection, diagnosis, intervention, prevention, precision medicine, and population health. Included in the journal will be articles on novel computerized imaging or visualization techniques, including artificial intelligence and machine learning, augmented reality for surgical planning and guidance, big biomedical data visualization, computer-aided diagnosis, computerized-robotic surgery, image-guided therapy, imaging scanning and reconstruction, mobile and tele-imaging, radiomics, and imaging integration and modeling with other information relevant to digital health. The types of biomedical imaging include: magnetic resonance, computed tomography, ultrasound, nuclear medicine, X-ray, microwave, optical and multi-photon microscopy, video and sensory imaging, and the convergence of biomedical images with other non-imaging datasets.