1
|
Li WB, Du ZC, Liu YJ, Gao JX, Wang JG, Dai Q, Huang WH. Prediction of axillary lymph node metastasis in early breast cancer patients with ultrasonic videos based deep learning. Front Oncol 2023; 13:1219838. [PMID: 37719009 PMCID: PMC10503049 DOI: 10.3389/fonc.2023.1219838] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2023] [Accepted: 07/06/2023] [Indexed: 09/19/2023] Open
Abstract
Objective To develop a deep learning (DL) model for predicting axillary lymph node (ALN) metastasis using dynamic ultrasound (US) videos in breast cancer patients. Methods A total of 271 US videos from 271 early breast cancer patients collected from Xiang'an Hospital of Xiamen University andShantou Central Hospitabetween September 2019 and June 2021 were used as the training, validation, and internal testing set (testing set A). Additionally, an independent dataset of 49 US videos from 49 patients with breast cancer, collected from Shanghai 10th Hospital of Tongji University from July 2021 to May 2022, was used as an external testing set (testing set B). All ALN metastases were confirmed using pathological examination. Three different convolutional neural networks (CNNs) with R2 + 1D, TIN, and ResNet-3D architectures were used to build the models. The performance of the US video DL models was compared with that of US static image DL models and axillary US examination performed by ultra-sonographers. The performances of the DL models and ultra-sonographers were evaluated based on accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Additionally, gradient class activation mapping (Grad-CAM) technology was also used to enhance the interpretability of the models. Results Among the three US video DL models, TIN showed the best performance, achieving an AUC of 0.914 (95% CI: 0.843-0.985) in predicting ALN metastasis in testing set A. The model achieved an accuracy of 85.25% (52/61), with a sensitivity of 76.19% (16/21) and a specificity of 90.00% (36/40). The AUC of the US video DL model was superior to that of the US static image DL model (0.856, 95% CI: 0.753-0.959, P<0.05). The Grad-CAM technology confirmed the heatmap of the model, which highlighted important subregions of the keyframe for ultra-sonographers' review. Conclusion A feasible and improved DL model to predict ALN metastasis from breast cancer US video images was developed. The DL model in this study with reliable interpretability would provide an early diagnostic strategy for the appropriate management of axillary in the early breast cancer patients.
Collapse
Affiliation(s)
- Wei-Bin Li
- Cancer Center and Department of Breast and Thyroid Surgery, Xiang’an Hospital, School of Medicine, Xiamen University, Xiamen, China
- Fujian Key Laboratory of Precision Diagnosis and Treatment in Breast Cancer, Xiamen, China
- Xiamen Key Laboratory of Endocrine-Related Cancer Precision Medicine, Xiamen, China
- Xiamen Research Center of Clinical Medicine in Breast and Thyroid Cancers, Xiang’an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, China
- Department of Ultrasonic Medicine Affiliated Hospital of Xizang Minzu University, Xianyang, China
| | - Zhi-Cheng Du
- Cancer Center and Department of Breast and Thyroid Surgery, Xiang’an Hospital, School of Medicine, Xiamen University, Xiamen, China
- Fujian Key Laboratory of Precision Diagnosis and Treatment in Breast Cancer, Xiamen, China
- Xiamen Key Laboratory of Endocrine-Related Cancer Precision Medicine, Xiamen, China
- Xiamen Research Center of Clinical Medicine in Breast and Thyroid Cancers, Xiang’an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, China
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China
| | - Yue-Jie Liu
- Fujian Key Laboratory of Precision Diagnosis and Treatment in Breast Cancer, Xiamen, China
- Xiamen Key Laboratory of Endocrine-Related Cancer Precision Medicine, Xiamen, China
- Department of Ultrasonic Medicine, Xiang’an Hospital, School of Medicine, Xiamen University, Xiamen, China
| | - Jun-Xue Gao
- Fujian Key Laboratory of Precision Diagnosis and Treatment in Breast Cancer, Xiamen, China
- Xiamen Key Laboratory of Endocrine-Related Cancer Precision Medicine, Xiamen, China
- Department of Ultrasonic Medicine, Xiang’an Hospital, School of Medicine, Xiamen University, Xiamen, China
| | - Jia-Gang Wang
- Department of Ultrasonic Medicine of Shantou Central Hospital, Shantou, China
| | - Qian Dai
- School of Informatics, Xiamen University, Xiamen, China
| | - Wen-He Huang
- Cancer Center and Department of Breast and Thyroid Surgery, Xiang’an Hospital, School of Medicine, Xiamen University, Xiamen, China
- Fujian Key Laboratory of Precision Diagnosis and Treatment in Breast Cancer, Xiamen, China
- Xiamen Key Laboratory of Endocrine-Related Cancer Precision Medicine, Xiamen, China
- Xiamen Research Center of Clinical Medicine in Breast and Thyroid Cancers, Xiang’an Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, China
| |
Collapse
|
2
|
Ozaki J, Fujioka T, Yamaga E, Hayashi A, Kujiraoka Y, Imokawa T, Takahashi K, Okawa S, Yashima Y, Mori M, Kubota K, Oda G, Nakagawa T, Tateishi U. Deep learning method with a convolutional neural network for image classification of normal and metastatic axillary lymph nodes on breast ultrasonography. Jpn J Radiol 2022; 40:814-822. [DOI: 10.1007/s11604-022-01261-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2022] [Accepted: 02/25/2022] [Indexed: 10/18/2022]
|
3
|
Kataoka M, Honda M, Ohashi A, Yamaguchi K, Mori N, Goto M, Fujioka T, Mori M, Kato Y, Satake H, Iima M, Kubota K. Ultrafast Dynamic Contrast-enhanced MRI of the Breast: How Is It Used? Magn Reson Med Sci 2022; 21:83-94. [PMID: 35228489 PMCID: PMC9199976 DOI: 10.2463/mrms.rev.2021-0157] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/01/2023] Open
Abstract
Ultrafast dynamic contrast-enhanced (UF-DCE) MRI is a new approach to capture kinetic information in the very early post-contrast period with high temporal resolution while keeping reasonable spatial resolution. The detailed timing and shape of the upslope in the time–intensity curve are analyzed. New kinetic parameters obtained from UF-DCE MRI are useful in differentiating malignant from benign lesions and in evaluating prognostic markers of the breast cancers. Clinically, UF-DCE MRI contributes in identifying hypervascular lesions when the background parenchymal enhancement (BPE) is marked on conventional dynamic MRI. This review starts with the technical aspect of accelerated acquisition. Practical aspects of UF-DCE MRI include identification of target hypervascular lesions from marked BPE and diagnosis of malignant and benign lesions based on new kinetic parameters derived from UF-DCE MRI: maximum slope (MS), time to enhance (TTE), bolus arrival time (BAT), time interval between arterial and venous visualization (AVI), and empirical mathematical model (EMM). The parameters derived from UF-DCE MRI are compared in terms of their diagnostic performance and association with prognostic markers. Pitfalls of UF-DCE MRI in the clinical situation are also covered. Since UF-DCE MRI is an evolving technique, future prospects of UF-DCE MRI are discussed in detail by citing recent evidence. The topic covers prediction of treatment response, multiparametric approach using DWI-derived parameters, evaluation of tumor-related vessels, and application of artificial intelligence for UF-DCE MRI. Along with comprehensive literature review, illustrative clinical cases are used to understand the value of UF-DCE MRI.
Collapse
Affiliation(s)
- Masako Kataoka
- Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine
| | - Maya Honda
- Department of Diagnostic Radiology, Kansai Electric Power Hospital
| | - Akane Ohashi
- Department of Translational Medicine, Diagnostic Radiology, Lund University, Skåne University hospital
| | - Ken Yamaguchi
- Department of Radiology, Faculty of Medicine, Saga University
| | - Naoko Mori
- Department of Diagnostic Radiology, Tohoku University Graduate School of Medicine
| | - Mariko Goto
- Department of Radiology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine
| | - Tomoyuki Fujioka
- Department of Diagnostic Radiology, Tokyo Medical and Dental University
| | - Mio Mori
- Department of Diagnostic Radiology, Tokyo Medical and Dental University
| | - Yutaka Kato
- Department of Radiological Technology, Nagoya University Hospital
| | - Hiroko Satake
- Department of Radiology, Nagoya University Graduate School of Medicine
| | - Mami Iima
- Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine
| | - Kazunori Kubota
- Department of Radiology, Dokkyo Medical University Saitama Medical Center
| |
Collapse
|