Xianwen Yu , Yao Ai , Wanyu Su , Ziqing Xiang , Jianping Wu , Yiran Mu , Yifan Yang , Long Zhang , Wenliang Yu , Weihua Ni , Juebin Jin , Congying Xie , Xiance Jin
{"title":"剂量组学指导下的深度学习用于肺癌放射性食管炎预测:通过多分支融合辅助学习确定最佳感兴趣区域。","authors":"Xianwen Yu , Yao Ai , Wanyu Su , Ziqing Xiang , Jianping Wu , Yiran Mu , Yifan Yang , Long Zhang , Wenliang Yu , Weihua Ni , Juebin Jin , Congying Xie , Xiance Jin","doi":"10.1016/j.radonc.2025.111121","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Accurate delineation of regions of interest (ROIs) is critical for feature extraction and selection in radiomics-based prediction models.</div></div><div><h3>Purpose</h3><div>To develop a combined dosiomics and deep learning (DL) model for predicting grade ≥ 2 radiation esophagitis (RE) in lung cancer patients undergoing radiotherapy, we propose a multi-task auxiliary learning approach to define accurate and objective ROIs based on radiation dose distribution (RDD) images.</div></div><div><h3>Materials and Methods</h3><div>Lung cancer patients who underwent radiotherapy were gathered retrospectively from hospital 1 (January 2020 and December 2022) for model development. Two external validation sets were obtained retrospectively from hospital 2 (January 2021 and December 2022) and hospital 3 (January 2022 and December 2023), respectively. A dosiomics-guided deep learning (DGD) network using multi-task auxiliary learning to define accurate and objective ROIs was introduced by integrating dosiomic features with high-dimensional DL features for RE prediction.</div></div><div><h3>Results</h3><div>This study enrolled 488 patients from three hospitals: 235 in the training set, 101 in the internal validation set, 57 in the external validation set 1 and 95 in the external validation set 2, respectively. The dosiomics −guided ResNet34 combined with contrastive learning and auxiliary segmentation module achieved the best AUCs of 0.88 [95% CI: 0.76–0.95], 0.82 [95% CI: 0.65–0.96], 0.83 [95% CI: 0.74–0.92] in the internal validation set, external validation set 1, and external validation set 2, respectively.</div></div><div><h3>Conclusion</h3><div>The proposed DGD model leverages multi-task auxiliary learning to automatically define ROIs and effectively predict RE in lung cancer patients undergoing radiotherapy.</div></div>","PeriodicalId":21041,"journal":{"name":"Radiotherapy and Oncology","volume":"212 ","pages":"Article 111121"},"PeriodicalIF":5.3000,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Dosiomics-guided deep learning for radiation esophagitis prediction in lung cancer: optimal region of interest definition via multi-branch fusion auxiliary learning\",\"authors\":\"Xianwen Yu , Yao Ai , Wanyu Su , Ziqing Xiang , Jianping Wu , Yiran Mu , Yifan Yang , Long Zhang , Wenliang Yu , Weihua Ni , Juebin Jin , Congying Xie , Xiance Jin\",\"doi\":\"10.1016/j.radonc.2025.111121\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><div>Accurate delineation of regions of interest (ROIs) is critical for feature extraction and selection in radiomics-based prediction models.</div></div><div><h3>Purpose</h3><div>To develop a combined dosiomics and deep learning (DL) model for predicting grade ≥ 2 radiation esophagitis (RE) in lung cancer patients undergoing radiotherapy, we propose a multi-task auxiliary learning approach to define accurate and objective ROIs based on radiation dose distribution (RDD) images.</div></div><div><h3>Materials and Methods</h3><div>Lung cancer patients who underwent radiotherapy were gathered retrospectively from hospital 1 (January 2020 and December 2022) for model development. Two external validation sets were obtained retrospectively from hospital 2 (January 2021 and December 2022) and hospital 3 (January 2022 and December 2023), respectively. A dosiomics-guided deep learning (DGD) network using multi-task auxiliary learning to define accurate and objective ROIs was introduced by integrating dosiomic features with high-dimensional DL features for RE prediction.</div></div><div><h3>Results</h3><div>This study enrolled 488 patients from three hospitals: 235 in the training set, 101 in the internal validation set, 57 in the external validation set 1 and 95 in the external validation set 2, respectively. The dosiomics −guided ResNet34 combined with contrastive learning and auxiliary segmentation module achieved the best AUCs of 0.88 [95% CI: 0.76–0.95], 0.82 [95% CI: 0.65–0.96], 0.83 [95% CI: 0.74–0.92] in the internal validation set, external validation set 1, and external validation set 2, respectively.</div></div><div><h3>Conclusion</h3><div>The proposed DGD model leverages multi-task auxiliary learning to automatically define ROIs and effectively predict RE in lung cancer patients undergoing radiotherapy.</div></div>\",\"PeriodicalId\":21041,\"journal\":{\"name\":\"Radiotherapy and Oncology\",\"volume\":\"212 \",\"pages\":\"Article 111121\"},\"PeriodicalIF\":5.3000,\"publicationDate\":\"2025-09-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiotherapy and Oncology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0167814025046250\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiotherapy and Oncology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167814025046250","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
Dosiomics-guided deep learning for radiation esophagitis prediction in lung cancer: optimal region of interest definition via multi-branch fusion auxiliary learning
Background
Accurate delineation of regions of interest (ROIs) is critical for feature extraction and selection in radiomics-based prediction models.
Purpose
To develop a combined dosiomics and deep learning (DL) model for predicting grade ≥ 2 radiation esophagitis (RE) in lung cancer patients undergoing radiotherapy, we propose a multi-task auxiliary learning approach to define accurate and objective ROIs based on radiation dose distribution (RDD) images.
Materials and Methods
Lung cancer patients who underwent radiotherapy were gathered retrospectively from hospital 1 (January 2020 and December 2022) for model development. Two external validation sets were obtained retrospectively from hospital 2 (January 2021 and December 2022) and hospital 3 (January 2022 and December 2023), respectively. A dosiomics-guided deep learning (DGD) network using multi-task auxiliary learning to define accurate and objective ROIs was introduced by integrating dosiomic features with high-dimensional DL features for RE prediction.
Results
This study enrolled 488 patients from three hospitals: 235 in the training set, 101 in the internal validation set, 57 in the external validation set 1 and 95 in the external validation set 2, respectively. The dosiomics −guided ResNet34 combined with contrastive learning and auxiliary segmentation module achieved the best AUCs of 0.88 [95% CI: 0.76–0.95], 0.82 [95% CI: 0.65–0.96], 0.83 [95% CI: 0.74–0.92] in the internal validation set, external validation set 1, and external validation set 2, respectively.
Conclusion
The proposed DGD model leverages multi-task auxiliary learning to automatically define ROIs and effectively predict RE in lung cancer patients undergoing radiotherapy.
期刊介绍:
Radiotherapy and Oncology publishes papers describing original research as well as review articles. It covers areas of interest relating to radiation oncology. This includes: clinical radiotherapy, combined modality treatment, translational studies, epidemiological outcomes, imaging, dosimetry, and radiation therapy planning, experimental work in radiobiology, chemobiology, hyperthermia and tumour biology, as well as data science in radiation oncology and physics aspects relevant to oncology.Papers on more general aspects of interest to the radiation oncologist including chemotherapy, surgery and immunology are also published.