Yasemin Kayadibi1, Burak Kocak2, Nese Ucar3, Yesim Namdar Akan4, Emine Yildirim5, Sibel Bektas6. 1. Department of Radiology, Istanbul University-Cerrahpasa, Cerrahpasa Medical Faculty, Kocamustafapasa, Istanbul, Turkey. Electronic address: ysmnkayadibi@gmail.com. 2. Department of Radiology, Basaksehir Cam and Sakura City Hospital, Basaksehir, Istanbul, Turkey. Electronic address: drburakkocak@gmail.com. 3. Department of Radiology, Gaziosmanspasa Education and Research Hospital,Gaziosmanpasa, Istanbul, Turkey. Electronic address: neseyigit@hotmail.com. 4. Department of Radiology, Gaziosmanspasa Education and Research Hospital, Gaziosmanpasa, Istanbul, Turkey. Electronic address: namdaryesim@gmail.com. 5. Department of General Surgery, Gaziosmanspasa Education and Research Hospital, Gaziosmanpasa, Istanbul, Turkey. Electronic address: opdreyildirim@gmail.com. 6. Department of Pathology, Gaziosmanspasa Education and Research Hospital, Gaziosmanpasa, Istanbul, Turkey. Electronic address: sibel_bektas@yahoo.com.
Abstract
RATIONALE AND OBJECTIVES: In patients with breast cancer (BC), lymphovascular invasion (LVI) status is considered an important prognostic factor. We aimed to develop machine learning (ML)-based radiomics models for the prediction of LVI status in patients with BC, using preoperative MRI images. MATERIALS AND METHODS: This retrospective study included patients with BC with known LVI status and preoperative MRI. The dataset was split into training and unseen testing sets by stratified sampling with a 2:1 ratio. 2D and 3D radiomic features were extracted from contrast-enhanced T1 weighted images (C+T1W) and apparent diffusion coefficient (ADC) maps. The reliability of the features was assessed with two radiologists' segmentation data. Dimension reduction was done with reliability analysis, multi-collinearity analysis, removal of low-variance features, and feature selection. ML models were created with base, tuned, and boosted random forest algorithms. RESULT: A total of 128 lesions (LVI-positive, 76; LVI-negative, 52) were included. The best model performance was achieved with tunning and boosting model based on 3D ADC maps and selected four radiomic features. The area under the curve and accuracy were 0.726 and 63.5% in the training data, 0.732 and 76.7% in the test data, respectively. The overall sensitivity and positive predictive values were 68% and 69.6% in the training data, 84.6% and 78.6% in the test data, respectively. CONCLUSION: ML and radiomics based on 3D segmentation of ADC maps can be used to predict LVI status in BC, with satisfying performance.
RATIONALE AND OBJECTIVES: In patients with breast cancer (BC), lymphovascular invasion (LVI) status is considered an important prognostic factor. We aimed to develop machine learning (ML)-based radiomics models for the prediction of LVI status in patients with BC, using preoperative MRI images. MATERIALS AND METHODS: This retrospective study included patients with BC with known LVI status and preoperative MRI. The dataset was split into training and unseen testing sets by stratified sampling with a 2:1 ratio. 2D and 3D radiomic features were extracted from contrast-enhanced T1 weighted images (C+T1W) and apparent diffusion coefficient (ADC) maps. The reliability of the features was assessed with two radiologists' segmentation data. Dimension reduction was done with reliability analysis, multi-collinearity analysis, removal of low-variance features, and feature selection. ML models were created with base, tuned, and boosted random forest algorithms. RESULT: A total of 128 lesions (LVI-positive, 76; LVI-negative, 52) were included. The best model performance was achieved with tunning and boosting model based on 3D ADC maps and selected four radiomic features. The area under the curve and accuracy were 0.726 and 63.5% in the training data, 0.732 and 76.7% in the test data, respectively. The overall sensitivity and positive predictive values were 68% and 69.6% in the training data, 84.6% and 78.6% in the test data, respectively. CONCLUSION: ML and radiomics based on 3D segmentation of ADC maps can be used to predict LVI status in BC, with satisfying performance.