Bing Yu, Huijuan He, Qiao Zheng, Yao Ai, Xianwen Yu, Sunjun Li, Ji Zhang, Juebin Jin, Xiance Jin, Wenliang Yu
{"title":"Integrating Deep Learning and Radiomics in Differentiating Papillary Thyroid Microcarcinoma from Papillary Thyroid Carcinoma with Ultrasound Images.","authors":"Bing Yu, Huijuan He, Qiao Zheng, Yao Ai, Xianwen Yu, Sunjun Li, Ji Zhang, Juebin Jin, Xiance Jin, Wenliang Yu","doi":"10.2147/CMAR.S507943","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>The feasibility and accuracy of ultrasound-based radiomics, deep learning, and combined deep learning radiomics models were investigated in the differentiation of papillary thyroid carcinoma and papillary thyroid microcarcinoma to decrease the risk of overtreatment of papillary thyroid microcarcinoma.</p><p><strong>Methods: </strong>A total of 549 patients with confirmed 180 papillary thyroid carcinoma and 436 papillary thyroid microcarcinoma nodules from Hospital One were enrolled and randomly divided into training and validation cohorts at a ratio of 8:2 with 56 patients left as independent testing set 1. Fifty patients from Hospital Two were enrolled as independent testing set 2. Radiomics signature and five deep learning networks, such as visual geometry group 13 (VGG13), VGG16, VGG19, AlexNet, and EfficientNet, were generated for papillary thyroid carcinoma and papillary thyroid microcarcinoma differentiation. Combined deep learning and radiomics models were constructed to further improve the differentiation ability.</p><p><strong>Results: </strong>An area under curves of 0.826 and 0.822 was achieved with radiomics model for papillary thyroid carcinoma and papillary thyroid microcarcinoma differentiation in the independent testing set 1 and set 2, respectively. VGG19 achieved the best area under curves of 0.890 and EfficientNet achieved the best accuracy of 0.867. The best accuracy and area under curves of 0.904, 0.900, and 0.931, 0.946 were achieved with the combination of VGG + radiomics (R_V_Combined) and EffiecientNet + radiomics (R_E_Combined) in the independent testing set 1 and set 2, respectively.</p><p><strong>Conclusion: </strong>Deep learning and radiomics combination models are promising in the noninvasively preoperative differentiation of papillary thyroid microcarcinoma and papillary thyroid carcinoma to decrease the overtreatment of patients with papillary thyroid microcarcinoma and to minimize the complications caused by overtreatment.</p>","PeriodicalId":9479,"journal":{"name":"Cancer Management and Research","volume":"17 ","pages":"1339-1349"},"PeriodicalIF":2.5000,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12255253/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cancer Management and Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2147/CMAR.S507943","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose: The feasibility and accuracy of ultrasound-based radiomics, deep learning, and combined deep learning radiomics models were investigated in the differentiation of papillary thyroid carcinoma and papillary thyroid microcarcinoma to decrease the risk of overtreatment of papillary thyroid microcarcinoma.
Methods: A total of 549 patients with confirmed 180 papillary thyroid carcinoma and 436 papillary thyroid microcarcinoma nodules from Hospital One were enrolled and randomly divided into training and validation cohorts at a ratio of 8:2 with 56 patients left as independent testing set 1. Fifty patients from Hospital Two were enrolled as independent testing set 2. Radiomics signature and five deep learning networks, such as visual geometry group 13 (VGG13), VGG16, VGG19, AlexNet, and EfficientNet, were generated for papillary thyroid carcinoma and papillary thyroid microcarcinoma differentiation. Combined deep learning and radiomics models were constructed to further improve the differentiation ability.
Results: An area under curves of 0.826 and 0.822 was achieved with radiomics model for papillary thyroid carcinoma and papillary thyroid microcarcinoma differentiation in the independent testing set 1 and set 2, respectively. VGG19 achieved the best area under curves of 0.890 and EfficientNet achieved the best accuracy of 0.867. The best accuracy and area under curves of 0.904, 0.900, and 0.931, 0.946 were achieved with the combination of VGG + radiomics (R_V_Combined) and EffiecientNet + radiomics (R_E_Combined) in the independent testing set 1 and set 2, respectively.
Conclusion: Deep learning and radiomics combination models are promising in the noninvasively preoperative differentiation of papillary thyroid microcarcinoma and papillary thyroid carcinoma to decrease the overtreatment of patients with papillary thyroid microcarcinoma and to minimize the complications caused by overtreatment.
期刊介绍：
Cancer Management and Research is an international, peer reviewed, open access journal focusing on cancer research and the optimal use of preventative and integrated treatment interventions to achieve improved outcomes, enhanced survival, and quality of life for cancer patients. Specific topics covered in the journal include:
◦Epidemiology, detection and screening
◦Cellular research and biomarkers
◦Identification of biotargets and agents with novel mechanisms of action
◦Optimal clinical use of existing anticancer agents, including combination therapies
◦Radiation and surgery
◦Palliative care
◦Patient adherence, quality of life, satisfaction
The journal welcomes submitted papers covering original research, basic science, clinical & epidemiological studies, reviews & evaluations, guidelines, expert opinion and commentary, and case series that shed novel insights on a disease or disease subtype.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
