Giovanna Medina1, Colleen G Buckless2, Eamon Thomasson2, Luke S Oh1, Martin Torriani3. 1. Department of Orthopedics, Massachusetts General Hospital, Harvard Medical School, Boston, MA, 02114, USA. 2. Division of Musculoskeletal Imaging and Intervention, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street - YAW 6048, Boston, MA, 02114, USA. 3. Division of Musculoskeletal Imaging and Intervention, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street - YAW 6048, Boston, MA, 02114, USA. mtorriani@mgh.harvard.edu.
Abstract
OBJECTIVE: To develop and validate a deep convolutional neural network (CNN) method capable of (1) selecting a specific shoulder sagittal MR image (Y-view) and (2) automatically segmenting rotator cuff (RC) muscles on a Y-view. We hypothesized a CNN approach can accurately perform both tasks compared with manual reference standards. MATERIAL AND METHODS: We created 2 models: model A for Y-view selection and model B for muscle segmentation. For model A, we manually selected shoulder sagittal T1 Y-views from 258 cases as ground truth to train a classification CNN (Keras/Tensorflow, Inception v3, 16 batch, 100 epochs, dropout 0.2, learning rate 0.001, RMSprop). A top-3 success rate evaluated model A on 100 internal and 50 external test cases. For model B, we manually segmented subscapularis, supraspinatus, and infraspinatus/teres minor on 1048 sagittal T1 Y-views. After histogram equalization and data augmentation, the model was trained from scratch (U-Net, 8 batch, 50 epochs, dropout 0.25, learning rate 0.0001, softmax). Dice (F1) score determined segmentation accuracy on 105 internal and 50 external test images. RESULTS: Model A showed top-3 accuracy > 98% to select an appropriate Y-view. Model B produced accurate RC muscle segmentations with mean Dice scores > 0.93. Individual muscle Dice scores on internal/external datasets were as follows: subscapularis 0.96/0.93, supraspinatus 0.97/0.96, and infraspinatus/teres minor 0.97/0.95. CONCLUSIONS: Our results show overall accurate Y-view selection and automated RC muscle segmentation using a combination of deep CNN algorithms.
OBJECTIVE: To develop and validate a deep convolutional neural network (CNN) method capable of (1) selecting a specific shoulder sagittal MR image (Y-view) and (2) automatically segmenting rotator cuff (RC) muscles on a Y-view. We hypothesized a CNN approach can accurately perform both tasks compared with manual reference standards. MATERIAL AND METHODS: We created 2 models: model A for Y-view selection and model B for muscle segmentation. For model A, we manually selected shoulder sagittal T1 Y-views from 258 cases as ground truth to train a classification CNN (Keras/Tensorflow, Inception v3, 16 batch, 100 epochs, dropout 0.2, learning rate 0.001, RMSprop). A top-3 success rate evaluated model A on 100 internal and 50 external test cases. For model B, we manually segmented subscapularis, supraspinatus, and infraspinatus/teres minor on 1048 sagittal T1 Y-views. After histogram equalization and data augmentation, the model was trained from scratch (U-Net, 8 batch, 50 epochs, dropout 0.25, learning rate 0.0001, softmax). Dice (F1) score determined segmentation accuracy on 105 internal and 50 external test images. RESULTS: Model A showed top-3 accuracy > 98% to select an appropriate Y-view. Model B produced accurate RC muscle segmentations with mean Dice scores > 0.93. Individual muscle Dice scores on internal/external datasets were as follows: subscapularis 0.96/0.93, supraspinatus 0.97/0.96, and infraspinatus/teres minor 0.97/0.95. CONCLUSIONS: Our results show overall accurate Y-view selection and automated RC muscle segmentation using a combination of deep CNN algorithms.
Authors: Olivier Q Groot; Michiel E R Bongers; Colleen G Buckless; Peter K Twining; Neal D Kapoor; Stein J Janssen; Joseph H Schwab; Martin Torriani; Miriam A Bredella Journal: J Surg Oncol Date: 2022-01-13 Impact factor: 2.885
Authors: Justus Schock; Daniel Truhn; Darius Nürnberger; Stefan Conrad; Marc Sebastian Huppertz; Sebastian Keil; Christiane Kuhl; Dorit Merhof; Sven Nebelung Journal: Sci Rep Date: 2021-12-01 Impact factor: 4.379
Authors: Stephan G Bodkin; Andrew C Smith; Bryan C Bergman; Donglai Huo; Kenneth A Weber; Simona Zarini; Darcy Kahn; Amanda Garfield; Emily Macias; Michael O Harris-Love Journal: Front Rehabil Sci Date: 2022-03-24