{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:29:35Z","timestamp":1760059775861,"version":"build-2065373602"},"reference-count":42,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Breast cancer accounts for one in four new malignant tumors in women, and misdiagnosis can lead to severe consequences, including delayed treatment. Among patients classified with a BI-RADS 3 rating, the risk of very early-stage malignancy remains over 2%. However, due to the benign imaging characteristics of these lesions, radiologists often recommend follow-up rather than immediate biopsy, potentially missing critical early interventions. This study aims to develop a deep learning (DL) model to accurately identify very early-stage malignancies in BI-RADS 3 lesions using ultrasound (US) images, thereby improving diagnostic precision and clinical decision-making. A total of 852 lesions (256 malignant and 596 benign) from 685 patients who underwent biopsies or 3-year follow-up were collected by Southwest Hospital (SW) and Tangshan People\u2019s Hospital (TS) to develop and validate a deep learning model based on a novel transfer learning method. To further evaluate the performance of the model, six radiologists independently reviewed the external testing set on a web-based rating platform. The proposed model achieved an area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of 0.880, 0.786, and 0.833 in predicting BI-RADS 3 malignant lesions in the internal testing set. The proposed transfer learning method improves the clinical AUC of predicting BI-RADS 3 malignancy from 0.721 to 0.880. In the external testing set, the model achieved AUC, sensitivity, and specificity of 0.910, 0.875, and 0.786 and outperformed the radiologists with an average AUC of 0.653 (p = 0.021). The DL model could detect very early-stage malignancy of BI-RADS 3 lesions in US images and had higher diagnostic capability compared with experienced radiologists.<\/jats:p>","DOI":"10.3390\/jimaging11070240","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T08:04:41Z","timestamp":1752566681000},"page":"240","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting Very Early-Stage Breast Cancer in BI-RADS 3 Lesions of Large Population with Deep Learning"],"prefix":"10.3390","volume":"11","author":[{"given":"Congyu","family":"Wang","sequence":"first","affiliation":[{"name":"Cheeloo College of Medicine, Shandong University, Jinan 250012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changzhen","family":"Li","sequence":"additional","affiliation":[{"name":"Cheeloo College of Medicine, Shandong University, Jinan 250012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gengxiao","family":"Lin","sequence":"additional","affiliation":[{"name":"Cheeloo College of Medicine, Shandong University, Jinan 250012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"394","DOI":"10.3322\/caac.21492","article-title":"Global Cancer Statistics 2018: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries","volume":"68","author":"Bray","year":"2018","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","unstructured":"World Health Organization (2020). WHO Report on Cancer: Setting Priorities, Investing Wisely and Providing Care for All, World Health Organization."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1038\/s41591-022-01746-x","article-title":"The Future of Early Cancer Detection","volume":"28","author":"Fitzgerald","year":"2022","journal-title":"Nat. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.1016\/j.ultrasmedbio.2016.07.012","article-title":"Correlation of Breast Ultrasound Classifications with Breast Cancer in Chinese Women","volume":"42","author":"Hou","year":"2016","journal-title":"Ultrasound Med. Biol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1038\/bjc.2015.33","article-title":"A Multi-Centre Randomised Trial Comparing Ultrasound vs. Mammography for Screening Breast Cancer in High-Risk Chinese Women","volume":"112","author":"Shen","year":"2015","journal-title":"Br. J. Cancer"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1038\/s41551-021-00711-2","article-title":"Prospective Assessment of Breast Cancer Risk from Multimodal Multiview Ultrasound Images via Clinically Applicable Deep Learning","volume":"5","author":"Qian","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sun, Q., Lin, X., Zhao, Y., Li, L., Yan, K., Liang, D., Sun, D., and Li, Z.-C. (2020). Deep Learning vs. Radiomics for Predicting Axillary Lymph Node Metastasis of Breast Cancer Using Ultrasound Images: Don\u2019t Forget the Peritumoral Region. Front. Oncol., 10.","DOI":"10.3389\/fonc.2020.00053"},{"key":"ref_8","unstructured":"Magny, S.J., Shikhman, R., and Keppke, A.L. (2023). Breast Imaging Reporting and Data System. StatPearls, StatPearls Publishing."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1148\/radiol.11101285","article-title":"Use of BI-RADS 3\u2013Probably Benign Category in the American College of Radiology Imaging Network Digital Mammographic Imaging Screening Trial","volume":"260","author":"Baum","year":"2011","journal-title":"Radiology"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"20170787","DOI":"10.1259\/bjr.20170787","article-title":"Growing BI-RADS Category 3 Lesions on Follow-up Breast Ultrasound: Malignancy Rates and Worrisome Features","volume":"91","author":"Ha","year":"2018","journal-title":"Br. J. Radiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1148\/radiol.2020192641","article-title":"Cancer Yield and Patterns of Follow-up for BI-RADS Category 3 After Screening Mammography Recall in the National Mammography Database","volume":"296","author":"Berg","year":"2020","journal-title":"Radiology"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1093\/annonc\/mdh088","article-title":"Mammographic Features and Correlation with Biopsy Findings Using 11-Gauge Stereotactic Vacuum-Assisted Breast Biopsy (SVABB)","volume":"15","author":"Mendez","year":"2004","journal-title":"Ann. Oncol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/JPROC.2019.2932116","article-title":"Deep Learning in Ultrasound Imaging","volume":"108","author":"Cohen","year":"2020","journal-title":"Proc. IEEE"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.patcog.2017.12.017","article-title":"A Regularized Ensemble Framework of Deep Learning for Cancer Detection from Multi-Class, Imbalanced Training Data","volume":"77","author":"Yuan","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ribli, D., Horv\u00e1th, A., Unger, Z., Pollner, P., and Csabai, I. (2018). Detecting and Classifying Lesions in Mammograms with Deep Learning. Sci. Rep., 8.","DOI":"10.1038\/s41598-018-22437-z"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Adachi, M., Fujioka, T., Mori, M., Kubota, K., Kikuchi, Y., Xiaotong, W., Oyama, J., Kimura, K., Oda, G., and Nakagawa, T. (2020). Detection and Diagnosis of Breast Cancer Using Artificial Intelligence Based Assessment of Maximum Intensity Projection Dynamic Contrast-Enhanced Magnetic Resonance Images. Diagnostics, 10.","DOI":"10.3390\/diagnostics10050330"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wu, Y., Wu, J., Dou, Y., Rubert, N., Wang, Y., and Deng, J. (2022). A Deep Learning Fusion Model with Evidence-Based Confidence Level Analysis for Differentiation of Malignant and Benign Breast Tumors Using Dynamic Contrast Enhanced MRI. Biomed. Signal Process. Control, 72, Available online: https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S1746809421009162.","DOI":"10.1016\/j.bspc.2021.103319"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"20170576","DOI":"10.1259\/bjr.20170576","article-title":"Classification of Breast Cancer in Ultrasound Imaging Using a Generic Deep Learning Analysis Software: A Pilot Study","volume":"91","author":"Becker","year":"2018","journal-title":"Br. J. Radiol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5458","DOI":"10.1007\/s00330-019-06118-7","article-title":"Automatic Classification of Ultrasound Breast Lesions Using a Deep Convolutional Neural Network Mimicking Human Decision-Making","volume":"29","author":"Ciritsis","year":"2019","journal-title":"Eur. Radiol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","article-title":"Clinical-Grade Computational Pathology Using Weakly Supervised Deep Learning on Whole Slide Images","volume":"25","author":"Campanella","year":"2019","journal-title":"Nat. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1111\/j.1524-4741.1997.tb00188.x","article-title":"Stereotactic Core-Needle Biopsy of the Breast: A Report of the Joint Task Force of the American College of Radiology, American College of Surgeons, and College of American Pathologists","volume":"3","author":"Bassett","year":"1997","journal-title":"Breast J."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., and Lin, D. (2019, January 15\u201320). Libra R-CNN: Towards Balanced Learning for Object Detection. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref_23","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"104863","DOI":"10.1016\/j.dib.2019.104863","article-title":"Dataset of Breast Ultrasound Images","volume":"28","author":"Gomaa","year":"2020","journal-title":"Data Brief"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"710","DOI":"10.2214\/AJR.18.20866","article-title":"Comparison of Positive Predictive Values of Categorization of Suspicious Calcifications Using the 4th and 5th Editions of BI-RADS","volume":"213","author":"Park","year":"2019","journal-title":"Am. J. Roentgenol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2249","DOI":"10.1177\/0962280216679040","article-title":"A Novel Nonparametric Confidence Interval for Differences of Proportions for Correlated Binary Data","volume":"27","author":"Duan","year":"2018","journal-title":"Stat. Methods Med. Res."},{"key":"ref_28","unstructured":"Simonyan, K., and Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201323). Squeeze-and-Excitation Networks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_30","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1788","DOI":"10.2214\/ajr.184.6.01841788","article-title":"The Use of Unenhanced Doppler Sonography in the Evaluation of Solid Breast Lesions","volume":"184","author":"Elizagaray","year":"2005","journal-title":"Am. J. Roentgenol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.ultrasmedbio.2017.09.012","article-title":"Ultrasound Imaging Technologies for Breast Cancer Detection and Management: A Review","volume":"44","author":"Guo","year":"2018","journal-title":"Ultrasound Med. Biol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1200\/JCO.2009.24.9284","article-title":"Breast Cancer Subtypes and the Risk of Local and Regional Relapse","volume":"28","author":"Voduc","year":"2010","journal-title":"J. Clin. Oncol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1148\/radiol.2019182908","article-title":"A Deep Learning Model to Triage Screening Mammograms: A Simulation Study","volume":"293","author":"Yala","year":"2019","journal-title":"Radiology"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1148\/radiol.212877","article-title":"Deep Learning to Optimize Candidate Selection for Lung Cancer CT Screening: Advancing the 2021 USPSTF Recommendations","volume":"305","author":"Lee","year":"2022","journal-title":"Radiology"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1007\/s00259-022-06036-9","article-title":"Predicting Clinically Significant Prostate Cancer with a Deep Learning Approach: A Multicentre Retrospective Study","volume":"50","author":"Zhao","year":"2023","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1186\/s13244-022-01259-8","article-title":"Deep Learning Based on Ultrasound Images Assists Breast Lesion Diagnosis in China: A Multicenter Diagnostic Study","volume":"13","author":"Gu","year":"2022","journal-title":"Insights Imaging"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/s10549-022-06521-7","article-title":"Multi-Center Evaluation of Artificial Intelligent Imaging and Clinical Models for Predicting Neoadjuvant Chemotherapy Response in Breast Cancer","volume":"193","author":"Qi","year":"2022","journal-title":"Breast Cancer Res. Treat."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"5902","DOI":"10.1007\/s00330-020-07659-y","article-title":"A Deep Learning Model Integrating Mammography and Clinical Factors Facilitates the Malignancy Prediction of BI-RADS 4 Microcalcifications in Breast Cancer Screening","volume":"31","author":"Liu","year":"2021","journal-title":"Eur. Radiol."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Nastase, I.-N.A., Moldovanu, S., Biswas, K.C., and Moraru, L. (2024). Role of Inter- and Extra-Lesion Tissue, Transfer Learning, and Fine-Tuning in the Robust Classification of Breast Lesions. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-74316-5"},{"key":"ref_42","first-page":"28541","article-title":"Llava-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/7\/240\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:09:47Z","timestamp":1760033387000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/7\/240"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,15]]},"references-count":42,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["jimaging11070240"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11070240","relation":{},"ISSN":["2313-433X"],"issn-type":[{"type":"electronic","value":"2313-433X"}],"subject":[],"published":{"date-parts":[[2025,7,15]]}}}