Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort studyResearch in context
Summary: Background: Early diagnosis of breast cancer has always been a difficult clinical challenge. We developed a deep-learning model EDL-BC to discriminate early breast cancer with ultrasound (US) benign findings. This study aimed to investigate how the EDL-BC model could help radiologists impr...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-06-01
|
| Series: | EClinicalMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589537023001785 |
| _version_ | 1797819879145865216 |
|---|---|
| author | Jianwei Liao Yu Gui Zhilin Li Zijian Deng Xianfeng Han Huanhuan Tian Li Cai Xingyu Liu Chengyong Tang Jia Liu Ya Wei Lan Hu Fengling Niu Jing Liu Xi Yang Shichao Li Xiang Cui Xin Wu Qingqiu Chen Andi Wan Jun Jiang Yi Zhang Xiangdong Luo Peng Wang Zhigang Cai Li Chen |
| author_facet | Jianwei Liao Yu Gui Zhilin Li Zijian Deng Xianfeng Han Huanhuan Tian Li Cai Xingyu Liu Chengyong Tang Jia Liu Ya Wei Lan Hu Fengling Niu Jing Liu Xi Yang Shichao Li Xiang Cui Xin Wu Qingqiu Chen Andi Wan Jun Jiang Yi Zhang Xiangdong Luo Peng Wang Zhigang Cai Li Chen |
| author_sort | Jianwei Liao |
| collection | DOAJ |
| description | Summary: Background: Early diagnosis of breast cancer has always been a difficult clinical challenge. We developed a deep-learning model EDL-BC to discriminate early breast cancer with ultrasound (US) benign findings. This study aimed to investigate how the EDL-BC model could help radiologists improve the detection rate of early breast cancer while reducing misdiagnosis. Methods: In this retrospective, multicentre cohort study, we developed an ensemble deep learning model called EDL-BC based on deep convolutional neural networks. The EDL-BC model was trained and internally validated on B-mode and color Doppler US image of 7955 lesions from 6795 patients between January 1, 2015 and December 31, 2021 in the First Affiliated Hospital of Army Medical University (SW), Chongqing, China. The model was assessed by internal and external validations, and outperformed radiologists. The model performance was validated in two independent external validation cohorts included 448 lesions from 391 patients between January 1 to December 31, 2021 in the Tangshan People's Hospital (TS), Chongqing, China, and 245 lesions from 235 patients between January 1 to December 31, 2021 in the Dazu People's Hospital (DZ), Chongqing, China. All lesions in the training and total validation cohort were US benign findings during screening and biopsy-confirmed malignant, benign, and benign with 3-year follow-up records. Six radiologists performed the clinical diagnostic performance of EDL-BC, and six radiologists independently reviewed the retrospective datasets on a web-based rating platform. Findings: The area under the receiver operating characteristic curve (AUC) of the internal validation cohort and two independent external validation cohorts for EDL-BC was 0.950 (95% confidence interval [CI]: 0.909–0.969), 0.956 (95% [CI]: 0.939–0.971), and 0.907 (95% [CI]: 0.877–0.938), respectively. The sensitivity values were 94.4% (95% [CI]: 72.7%–99.9%), 100% (95% [CI]: 69.2%–100%), and 80% (95% [CI]: 28.4%–99.5%), respectively, at 0.76. The AUC for accurate diagnosis of EDL-BC (0.945 [95% [CI]: 0.933–0.965]) and radiologists with artificial intelligence (AI) assistance (0.899 [95% [CI]: 0.883–0.913]) was significantly higher than that of the radiologists without AI assistance (0.716 [95% [CI]: 0.693–0.738]; p < 0.0001). Furthermore, there were no significant differences between the EDL-BC model and radiologists with AI assistance (p = 0.099). Interpretation: EDL-BC can identify subtle but informative elements on US images of breast lesions and can significantly improve radiologists' diagnostic performance for identifying patients with early breast cancer and benefiting the clinical practice. Funding: The National Key R&D Program of China. |
| first_indexed | 2024-03-13T09:29:07Z |
| format | Article |
| id | doaj.art-5054abf59f3344279d467fdd6f67cf1f |
| institution | Directory Open Access Journal |
| issn | 2589-5370 |
| language | English |
| last_indexed | 2024-03-13T09:29:07Z |
| publishDate | 2023-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EClinicalMedicine |
| spelling | doaj.art-5054abf59f3344279d467fdd6f67cf1f2023-05-26T04:21:57ZengElsevierEClinicalMedicine2589-53702023-06-0160102001Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort studyResearch in contextJianwei Liao0Yu Gui1Zhilin Li2Zijian Deng3Xianfeng Han4Huanhuan Tian5Li Cai6Xingyu Liu7Chengyong Tang8Jia Liu9Ya Wei10Lan Hu11Fengling Niu12Jing Liu13Xi Yang14Shichao Li15Xiang Cui16Xin Wu17Qingqiu Chen18Andi Wan19Jun Jiang20Yi Zhang21Xiangdong Luo22Peng Wang23Zhigang Cai24Li Chen25Department of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, China; College of Computer and Information Science, Southwest University, Chongqing, 400715, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaCollege of Computer and Information Science, Southwest University, Chongqing, 400715, ChinaCollege of Computer and Information Science, Southwest University, Chongqing, 400715, ChinaCollege of Computer and Information Science, Southwest University, Chongqing, 400715, ChinaCollege of Computer and Information Science, Southwest University, Chongqing, 400715, ChinaCollege of Computer and Information Science, Southwest University, Chongqing, 400715, ChinaCollege of Computer and Information Science, Southwest University, Chongqing, 400715, ChinaCollege of Computer and Information Science, Southwest University, Chongqing, 400715, ChinaDepartment of Gastroenterology, The First Affiliated Hospital (Southwest Hospital) of Third Military Medical University (Army Medical University), Chongqing, 40038, ChinaThe Third Department of General Surgery, Anyang Cancer Hospital, Henan, 455001, ChinaDepartment of General Surgery, The People's Hospital of Dazu, Chongqing, 402360, ChinaBreast Surgery Department, Tangshan People's Hospital, Tangshan, 063001, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaDepartment of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, ChinaCentre for Medical Big Data and Artificial Intelligence, Southwest Hospital of Third Military Medical University, Chongqing, 400038, China; Corresponding author. Centre for Medical Big Data and Artificial Intelligence, Southwest Hospital of Third Military Medical University, Chongqing, China.College of Computer and Information Science, Southwest University, Chongqing, 400715, China; Corresponding author. College of Computer and Information Science, Southwest University, Chongqing, China.Department of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, 40038, China; Corresponding author. Department of Breast and Thyroid Surgery, Southwest Hospital of Third Military Medical University, Chongqing, China.Summary: Background: Early diagnosis of breast cancer has always been a difficult clinical challenge. We developed a deep-learning model EDL-BC to discriminate early breast cancer with ultrasound (US) benign findings. This study aimed to investigate how the EDL-BC model could help radiologists improve the detection rate of early breast cancer while reducing misdiagnosis. Methods: In this retrospective, multicentre cohort study, we developed an ensemble deep learning model called EDL-BC based on deep convolutional neural networks. The EDL-BC model was trained and internally validated on B-mode and color Doppler US image of 7955 lesions from 6795 patients between January 1, 2015 and December 31, 2021 in the First Affiliated Hospital of Army Medical University (SW), Chongqing, China. The model was assessed by internal and external validations, and outperformed radiologists. The model performance was validated in two independent external validation cohorts included 448 lesions from 391 patients between January 1 to December 31, 2021 in the Tangshan People's Hospital (TS), Chongqing, China, and 245 lesions from 235 patients between January 1 to December 31, 2021 in the Dazu People's Hospital (DZ), Chongqing, China. All lesions in the training and total validation cohort were US benign findings during screening and biopsy-confirmed malignant, benign, and benign with 3-year follow-up records. Six radiologists performed the clinical diagnostic performance of EDL-BC, and six radiologists independently reviewed the retrospective datasets on a web-based rating platform. Findings: The area under the receiver operating characteristic curve (AUC) of the internal validation cohort and two independent external validation cohorts for EDL-BC was 0.950 (95% confidence interval [CI]: 0.909–0.969), 0.956 (95% [CI]: 0.939–0.971), and 0.907 (95% [CI]: 0.877–0.938), respectively. The sensitivity values were 94.4% (95% [CI]: 72.7%–99.9%), 100% (95% [CI]: 69.2%–100%), and 80% (95% [CI]: 28.4%–99.5%), respectively, at 0.76. The AUC for accurate diagnosis of EDL-BC (0.945 [95% [CI]: 0.933–0.965]) and radiologists with artificial intelligence (AI) assistance (0.899 [95% [CI]: 0.883–0.913]) was significantly higher than that of the radiologists without AI assistance (0.716 [95% [CI]: 0.693–0.738]; p < 0.0001). Furthermore, there were no significant differences between the EDL-BC model and radiologists with AI assistance (p = 0.099). Interpretation: EDL-BC can identify subtle but informative elements on US images of breast lesions and can significantly improve radiologists' diagnostic performance for identifying patients with early breast cancer and benefiting the clinical practice. Funding: The National Key R&D Program of China.http://www.sciencedirect.com/science/article/pii/S2589537023001785Artificial intelligenceUltrasoundEarly breast cancer |
| spellingShingle | Jianwei Liao Yu Gui Zhilin Li Zijian Deng Xianfeng Han Huanhuan Tian Li Cai Xingyu Liu Chengyong Tang Jia Liu Ya Wei Lan Hu Fengling Niu Jing Liu Xi Yang Shichao Li Xiang Cui Xin Wu Qingqiu Chen Andi Wan Jun Jiang Yi Zhang Xiangdong Luo Peng Wang Zhigang Cai Li Chen Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort studyResearch in context EClinicalMedicine Artificial intelligence Ultrasound Early breast cancer |
| title | Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort studyResearch in context |
| title_full | Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort studyResearch in context |
| title_fullStr | Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort studyResearch in context |
| title_full_unstemmed | Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort studyResearch in context |
| title_short | Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort studyResearch in context |
| title_sort | artificial intelligence assisted ultrasound image analysis to discriminate early breast cancer in chinese population a retrospective multicentre cohort studyresearch in context |
| topic | Artificial intelligence Ultrasound Early breast cancer |
| url | http://www.sciencedirect.com/science/article/pii/S2589537023001785 |
| work_keys_str_mv | AT jianweiliao artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT yugui artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT zhilinli artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT zijiandeng artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT xianfenghan artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT huanhuantian artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT licai artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT xingyuliu artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT chengyongtang artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT jialiu artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT yawei artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT lanhu artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT fenglingniu artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT jingliu artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT xiyang artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT shichaoli artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT xiangcui artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT xinwu artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT qingqiuchen artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT andiwan artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT junjiang artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT yizhang artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT xiangdongluo artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT pengwang artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT zhigangcai artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext AT lichen artificialintelligenceassistedultrasoundimageanalysistodiscriminateearlybreastcancerinchinesepopulationaretrospectivemulticentrecohortstudyresearchincontext |