Michael Z Liu1, Simukayi Mutasa2, Peter Chang3, Maham Siddique4, Sachin Jambawalikar5, Richard Ha6. 1. Department of Medical Physics, Columbia University Medical Center, 177 Ft. Washington Ave., Milstein Bldg Room 3-124B, New York, NY, United States of America. Electronic address: mzl2104@cumc.columbia.edu. 2. Department of Radiology, Columbia University Medical Center, 622 West 168th Street, PB-1-301, New York, NY, United States of America. Electronic address: stm9116@nyp.org. 3. Department of Radiological Sciences, Center for Artificial Intelligence in Diagnostic Medicine (CAIDM), University of California, Irvine, Calit2 Building, Suite 4500, 4100 E. Peltason Drive, Irvine, CA, United States of America. Electronic address: changp6@uci.edu. 4. Department of Radiology, Columbia University Medical Center, 622 West 168th Street, PB-1-301, New York, NY, United States of America. Electronic address: ms5270@cumc.columbia.edu. 5. Department of Medical Physics, Columbia University Medical Center, 177 Ft. Washington Ave., Milstein Bldg Room 3-124B, New York, NY, United States of America. Electronic address: sj2532@cumc.columbia.edu. 6. Breast Imaging Section, New York Presbyterian Hospital, Columbia University Medical Center, 622 West 168th Street, PB-1-301, New York, NY 10032, United States of America. Electronic address: rh2616@columbia.edu.
Abstract
PURPOSE: To apply our convolutional neural network (CNN) algorithm to predict neoadjuvant chemotherapy (NAC) response using the I-SPY TRIAL breast MRI dataset. METHODS: From the I-SPY TRIAL breast MRI database, 131 patients from 9 institutions were successfully downloaded for analysis. First post-contrast MRI images were used for 3D segmentation using 3D slicer. Our CNN was implemented entirely of 3 × 3 convolutional kernels and linear layers. The convolutional kernels consisted of 6 residual layers, totaling 12 convolutional layers. Dropout with a 0.5 keep probability and L2 normalization was utilized. Training was implemented by using the Adam optimizer. A 5-fold cross validation was used for performance evaluation. Software code was written in Python using the TensorFlow module on a Linux workstation with one NVidia Titan X GPU. RESULTS: Of 131 patients, 40 patients achieved pCR following NAC (group 1) and 91 patients did not achieve pCR following NAC (group 2). Diagnostic accuracy of our CNN two classification model distinguishing patients with pCR vs non-pCR was 72.5 (SD ± 8.4), with sensitivity 65.5% (SD ± 28.1) and specificity of 78.9% (SD ± 15.2). The area under a ROC Curve (AUC) was 0.72 (SD ± 0.08). CONCLUSION: It is feasible to use our CNN algorithm to predict NAC response in patients using a multi-institution dataset.
PURPOSE: To apply our convolutional neural network (CNN) algorithm to predict neoadjuvant chemotherapy (NAC) response using the I-SPY TRIAL breast MRI dataset. METHODS: From the I-SPY TRIAL breast MRI database, 131 patients from 9 institutions were successfully downloaded for analysis. First post-contrast MRI images were used for 3D segmentation using 3D slicer. Our CNN was implemented entirely of 3 × 3 convolutional kernels and linear layers. The convolutional kernels consisted of 6 residual layers, totaling 12 convolutional layers. Dropout with a 0.5 keep probability and L2 normalization was utilized. Training was implemented by using the Adam optimizer. A 5-fold cross validation was used for performance evaluation. Software code was written in Python using the TensorFlow module on a Linux workstation with one NVidia Titan X GPU. RESULTS: Of 131 patients, 40 patients achieved pCR following NAC (group 1) and 91 patients did not achieve pCR following NAC (group 2). Diagnostic accuracy of our CNN two classification model distinguishing patients with pCR vs non-pCR was 72.5 (SD ± 8.4), with sensitivity 65.5% (SD ± 28.1) and specificity of 78.9% (SD ± 15.2). The area under a ROC Curve (AUC) was 0.72 (SD ± 0.08). CONCLUSION: It is feasible to use our CNN algorithm to predict NAC response in patients using a multi-institution dataset.
Authors: Yousef Mazaheri; Sunitha B Thakur; Almir Gv Bitencourt; Roberto Lo Gullo; Andreas M Hötker; David D B Bates; Oguz Akin Journal: BJR Open Date: 2022-06-22