Application value of a deep learning model based on 3D ultrasound videos in assisting radiologists of different experience levels to differentiate benign and malignant breast masses
Objective To establish a deep learning model based on 3D ultrasound videos (DL-3DUV) and investigate its application value in assisting radiologists with different levels of experience to differentiate benign and malignant breast masses. Methods The ResNet50 model was employed to develop DL-3DUV for...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Diagnostics Concepts & Practice
2025-06-01
|
| Series: | Zhenduanxue lilun yu shijian |
| Subjects: | |
| Online Access: | https://www.qk.sjtu.edu.cn/jdcp/fileup/1671-2870/PDF/1756094170110-2050325757.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849222948745904128 |
|---|---|
| author | GUO Yuqing, WANG Changyan, LIU Yinchun, PANG Yun, ZHU Xia, GE Rui, LI Weiping, ZHANG Qi, CHEN Lin |
| author_facet | GUO Yuqing, WANG Changyan, LIU Yinchun, PANG Yun, ZHU Xia, GE Rui, LI Weiping, ZHANG Qi, CHEN Lin |
| author_sort | GUO Yuqing, WANG Changyan, LIU Yinchun, PANG Yun, ZHU Xia, GE Rui, LI Weiping, ZHANG Qi, CHEN Lin |
| collection | DOAJ |
| description | Objective To establish a deep learning model based on 3D ultrasound videos (DL-3DUV) and investigate its application value in assisting radiologists with different levels of experience to differentiate benign and malignant breast masses. Methods The ResNet50 model was employed to develop DL-3DUV for the classification of benign and malignant breast masses. A retrospective study was conducted using automated breast volume scanner (ABVS) dynamic videos from 400 patients with breast masses (a total of 525 lesions), which were randomly divided into training and testing sets at an 8∶2 ratio. The diagnostic performance of DL-3DUV was compared with that of senior and junior radiologists, both independently and in combination. Results When diagnosing independently, DL-3DUV demonstrated comparable sensitivi-ty (83.33% vs. 81.77%), accuracy (82.50% vs. 84.60%), and area under the curve (AUC) (0.83 vs. 0.85) compared to senior radiologists (all P>0.05), though its specificity was significantly lower (81.58% vs. 87.73%, P<0.05). Compared with junior radiologists, DL-3DUV showed significantly higher sensitivity (83.33% vs. 78.60%), specificity (81.58% vs. 57.00%), accuracy (82.50% vs. 68.37%), and AUC (0.83 vs. 0.68) (P<0.05). The combination of senior radiologists and DL-3DUV achieved higher sensitivity (89.70% vs. 81.77%) and AUC (0.91 vs. 0.85) than senior radiologists alone (all P<0.05), with no significant differences in specificity (91.23% vs. 87.73%) or accuracy (89.17% vs. 84.60%) (all P>0.05). Similarly, the combination of junior radiologists and DL-3DUV significantly improved diagnostic performance compared to junior radiologists alone, with statistically significant differences in sensitivity (88.10% vs. 78.60%), specificity (82.47% vs. 57.00%), accuracy (85.47% vs. 68.37%), and AUC (0.85 vs. 0.68) (all P<0.05). Conclusions DL-3DUV exhibits significant value in differentiating benign and malignant breast masses and is expected to become a useful tool to assist ultrasonographers, particularly for junior radiologists. |
| format | Article |
| id | doaj-art-eb7acad0a5be453aa78cc5ec812908ca |
| institution | Kabale University |
| issn | 1671-2870 |
| language | zho |
| publishDate | 2025-06-01 |
| publisher | Editorial Office of Journal of Diagnostics Concepts & Practice |
| record_format | Article |
| series | Zhenduanxue lilun yu shijian |
| spelling | doaj-art-eb7acad0a5be453aa78cc5ec812908ca2025-08-26T01:50:28ZzhoEditorial Office of Journal of Diagnostics Concepts & PracticeZhenduanxue lilun yu shijian1671-28702025-06-01240331231910.16150/j.1671-2870.2025.03.010Application value of a deep learning model based on 3D ultrasound videos in assisting radiologists of different experience levels to differentiate benign and malignant breast massesGUO Yuqing, WANG Changyan, LIU Yinchun, PANG Yun, ZHU Xia, GE Rui, LI Weiping, ZHANG Qi, CHEN Lin01a. Department of Ultrasound, 1b.Department of Pathology, 1c.Department of Surgery, Huadong Hospital, Fudan University, Shanghai 200040, China;2. School of Communication and Information Engineering, Shanghai University, Shanghai 200444, ChinaObjective To establish a deep learning model based on 3D ultrasound videos (DL-3DUV) and investigate its application value in assisting radiologists with different levels of experience to differentiate benign and malignant breast masses. Methods The ResNet50 model was employed to develop DL-3DUV for the classification of benign and malignant breast masses. A retrospective study was conducted using automated breast volume scanner (ABVS) dynamic videos from 400 patients with breast masses (a total of 525 lesions), which were randomly divided into training and testing sets at an 8∶2 ratio. The diagnostic performance of DL-3DUV was compared with that of senior and junior radiologists, both independently and in combination. Results When diagnosing independently, DL-3DUV demonstrated comparable sensitivi-ty (83.33% vs. 81.77%), accuracy (82.50% vs. 84.60%), and area under the curve (AUC) (0.83 vs. 0.85) compared to senior radiologists (all P>0.05), though its specificity was significantly lower (81.58% vs. 87.73%, P<0.05). Compared with junior radiologists, DL-3DUV showed significantly higher sensitivity (83.33% vs. 78.60%), specificity (81.58% vs. 57.00%), accuracy (82.50% vs. 68.37%), and AUC (0.83 vs. 0.68) (P<0.05). The combination of senior radiologists and DL-3DUV achieved higher sensitivity (89.70% vs. 81.77%) and AUC (0.91 vs. 0.85) than senior radiologists alone (all P<0.05), with no significant differences in specificity (91.23% vs. 87.73%) or accuracy (89.17% vs. 84.60%) (all P>0.05). Similarly, the combination of junior radiologists and DL-3DUV significantly improved diagnostic performance compared to junior radiologists alone, with statistically significant differences in sensitivity (88.10% vs. 78.60%), specificity (82.47% vs. 57.00%), accuracy (85.47% vs. 68.37%), and AUC (0.85 vs. 0.68) (all P<0.05). Conclusions DL-3DUV exhibits significant value in differentiating benign and malignant breast masses and is expected to become a useful tool to assist ultrasonographers, particularly for junior radiologists.https://www.qk.sjtu.edu.cn/jdcp/fileup/1671-2870/PDF/1756094170110-2050325757.pdf|automated breast volume scanner|breast cancer|deep learning |
| spellingShingle | GUO Yuqing, WANG Changyan, LIU Yinchun, PANG Yun, ZHU Xia, GE Rui, LI Weiping, ZHANG Qi, CHEN Lin Application value of a deep learning model based on 3D ultrasound videos in assisting radiologists of different experience levels to differentiate benign and malignant breast masses Zhenduanxue lilun yu shijian |automated breast volume scanner|breast cancer|deep learning |
| title | Application value of a deep learning model based on 3D ultrasound videos in assisting radiologists of different experience levels to differentiate benign and malignant breast masses |
| title_full | Application value of a deep learning model based on 3D ultrasound videos in assisting radiologists of different experience levels to differentiate benign and malignant breast masses |
| title_fullStr | Application value of a deep learning model based on 3D ultrasound videos in assisting radiologists of different experience levels to differentiate benign and malignant breast masses |
| title_full_unstemmed | Application value of a deep learning model based on 3D ultrasound videos in assisting radiologists of different experience levels to differentiate benign and malignant breast masses |
| title_short | Application value of a deep learning model based on 3D ultrasound videos in assisting radiologists of different experience levels to differentiate benign and malignant breast masses |
| title_sort | application value of a deep learning model based on 3d ultrasound videos in assisting radiologists of different experience levels to differentiate benign and malignant breast masses |
| topic | |automated breast volume scanner|breast cancer|deep learning |
| url | https://www.qk.sjtu.edu.cn/jdcp/fileup/1671-2870/PDF/1756094170110-2050325757.pdf |
| work_keys_str_mv | AT guoyuqingwangchangyanliuyinchunpangyunzhuxiageruiliweipingzhangqichenlin applicationvalueofadeeplearningmodelbasedon3dultrasoundvideosinassistingradiologistsofdifferentexperiencelevelstodifferentiatebenignandmalignantbreastmasses |