Deep learning radiomics of ultrasonography: Identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer
Background: Completion axillary lymph node dissection is overtreatment for patients with sentinel lymph node (SLN) metastasis in whom the metastatic risk of residual non-SLN (NSLN) is low. However, the National Comprehensive Cancer Network panel posits that none of the previous studies has successfu...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-10-01
|
| Series: | EBioMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352396420303947 |
| _version_ | 1819045219500294144 |
|---|---|
| author | Xu Guo Zhenyu Liu Caixia Sun Lei Zhang Ying Wang Ziyao Li Jiaxin Shi Tong Wu Hao Cui Jing Zhang Jie Tian Jiawei Tian |
| author_facet | Xu Guo Zhenyu Liu Caixia Sun Lei Zhang Ying Wang Ziyao Li Jiaxin Shi Tong Wu Hao Cui Jing Zhang Jie Tian Jiawei Tian |
| author_sort | Xu Guo |
| collection | DOAJ |
| description | Background: Completion axillary lymph node dissection is overtreatment for patients with sentinel lymph node (SLN) metastasis in whom the metastatic risk of residual non-SLN (NSLN) is low. However, the National Comprehensive Cancer Network panel posits that none of the previous studies has successfully identified such subset patients. Here, we develop a multicentre deep learning radiomics of ultrasonography model (DLRU) to predict the risk of SLN and NSLN metastasis. Methods: In total, 937 eligible breast cancer patients with ultrasound images were enrolled from two hospitals as the training set (n = 542) and independent test set (n = 395) respectively. Using the images, we developed and validated a prediction model combined with deep learning radiomics and axillary ultrasound to sequentially identify the metastatic risk of SLN and NSLN, thereby, classifying patients to relevant axillary management groups. Findings: In the test set, the DLRU yields the best performance in identifying patients with metastatic disease in SLNs (sensitivity=98.4%, 95% CI 96.6–100) and NSLNs (sensitivity=98.4%, 95% CI 95.6–99.9). The DLRU also accurately stratifies patients without metastasis in SLN or NSLN into the corresponding low-risk (LR)-SLN and high-risk (HR)-SLN&LR-NSLN category with the negative predictive value of 97% (95% CI 94.2–100) and 91.7% (95% CI 88.8–97.9), respectively. Moreover, compared with the current clinical management, DLRU appropriately assigned 51% (39.6%/77.4%) of overtreated patients in the entire study cohort into the LR group, perhaps avoiding overtreatment. Interpretation: The performance of the DLRU indicates that it may offer a simple preoperative tool to promote personalized axillary management of breast cancer. Funding: The National Nature Science Foundation of China; The National Outstanding Youth Science Fund Project of National Natural Science Foundation of China; The Scientific research project of Heilongjiang Health Committee; The Postgraduate Research &Practice Innovation Program of Harbin Medical University. |
| first_indexed | 2024-12-21T10:25:06Z |
| format | Article |
| id | doaj.art-9d6544b64f4e47c49f5476b4213eb590 |
| institution | Directory Open Access Journal |
| issn | 2352-3964 |
| language | English |
| last_indexed | 2024-12-21T10:25:06Z |
| publishDate | 2020-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EBioMedicine |
| spelling | doaj.art-9d6544b64f4e47c49f5476b4213eb5902022-12-21T19:07:20ZengElsevierEBioMedicine2352-39642020-10-0160103018Deep learning radiomics of ultrasonography: Identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancerXu Guo0Zhenyu Liu1Caixia Sun2Lei Zhang3Ying Wang4Ziyao Li5Jiaxin Shi6Tong Wu7Hao Cui8Jing Zhang9Jie Tian10Jiawei Tian11Department of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, China; CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaCAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, ChinaCAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China; Beijing Advanced Innovation Centre for Big Data-Based Precision Medicine, School of Medicine and Engineering, Beihang University, Beijing, China; Key Laboratory of Big Data-Based Precision Medicine, Ministry of Industry and Information Technology, Beihang University, Beijing, ChinaDepartment of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, ChinaDepartment of general surgery, The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei, China.Department of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, ChinaDepartment of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, ChinaDepartment of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, ChinaDepartment of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, ChinaDepartment of MRI Diagnosis, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, ChinaCAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China; Beijing Advanced Innovation Centre for Big Data-Based Precision Medicine, School of Medicine and Engineering, Beihang University, Beijing, China; Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi'an, Shanxi, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China; Key Laboratory of Big Data-Based Precision Medicine, Ministry of Industry and Information Technology, Beihang University, Beijing, China; Corresponding author at: Jie Tian, PhD, CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, No.95 Zhongguancun East road, Beijing, China.Department of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, China; Correspondence to: Jiawei Tian, MD, Department of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, No.246 Xuefu Road, Nan Gang Dist., Harbin, Heilongjiang, China.Background: Completion axillary lymph node dissection is overtreatment for patients with sentinel lymph node (SLN) metastasis in whom the metastatic risk of residual non-SLN (NSLN) is low. However, the National Comprehensive Cancer Network panel posits that none of the previous studies has successfully identified such subset patients. Here, we develop a multicentre deep learning radiomics of ultrasonography model (DLRU) to predict the risk of SLN and NSLN metastasis. Methods: In total, 937 eligible breast cancer patients with ultrasound images were enrolled from two hospitals as the training set (n = 542) and independent test set (n = 395) respectively. Using the images, we developed and validated a prediction model combined with deep learning radiomics and axillary ultrasound to sequentially identify the metastatic risk of SLN and NSLN, thereby, classifying patients to relevant axillary management groups. Findings: In the test set, the DLRU yields the best performance in identifying patients with metastatic disease in SLNs (sensitivity=98.4%, 95% CI 96.6–100) and NSLNs (sensitivity=98.4%, 95% CI 95.6–99.9). The DLRU also accurately stratifies patients without metastasis in SLN or NSLN into the corresponding low-risk (LR)-SLN and high-risk (HR)-SLN&LR-NSLN category with the negative predictive value of 97% (95% CI 94.2–100) and 91.7% (95% CI 88.8–97.9), respectively. Moreover, compared with the current clinical management, DLRU appropriately assigned 51% (39.6%/77.4%) of overtreated patients in the entire study cohort into the LR group, perhaps avoiding overtreatment. Interpretation: The performance of the DLRU indicates that it may offer a simple preoperative tool to promote personalized axillary management of breast cancer. Funding: The National Nature Science Foundation of China; The National Outstanding Youth Science Fund Project of National Natural Science Foundation of China; The Scientific research project of Heilongjiang Health Committee; The Postgraduate Research &Practice Innovation Program of Harbin Medical University.http://www.sciencedirect.com/science/article/pii/S2352396420303947Deep learning radiomicsUltrasonographyPrimary breast cancerAxillary managementNSLN metastasis in the axilla |
| spellingShingle | Xu Guo Zhenyu Liu Caixia Sun Lei Zhang Ying Wang Ziyao Li Jiaxin Shi Tong Wu Hao Cui Jing Zhang Jie Tian Jiawei Tian Deep learning radiomics of ultrasonography: Identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer EBioMedicine Deep learning radiomics Ultrasonography Primary breast cancer Axillary management NSLN metastasis in the axilla |
| title | Deep learning radiomics of ultrasonography: Identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer |
| title_full | Deep learning radiomics of ultrasonography: Identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer |
| title_fullStr | Deep learning radiomics of ultrasonography: Identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer |
| title_full_unstemmed | Deep learning radiomics of ultrasonography: Identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer |
| title_short | Deep learning radiomics of ultrasonography: Identifying the risk of axillary non-sentinel lymph node involvement in primary breast cancer |
| title_sort | deep learning radiomics of ultrasonography identifying the risk of axillary non sentinel lymph node involvement in primary breast cancer |
| topic | Deep learning radiomics Ultrasonography Primary breast cancer Axillary management NSLN metastasis in the axilla |
| url | http://www.sciencedirect.com/science/article/pii/S2352396420303947 |
| work_keys_str_mv | AT xuguo deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT zhenyuliu deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT caixiasun deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT leizhang deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT yingwang deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT ziyaoli deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT jiaxinshi deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT tongwu deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT haocui deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT jingzhang deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT jietian deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer AT jiaweitian deeplearningradiomicsofultrasonographyidentifyingtheriskofaxillarynonsentinellymphnodeinvolvementinprimarybreastcancer |