High-accuracy detection of supraspinatus fatty infiltration in shoulder MRI using convolutional neural network algorithms

Juan Pablo Saavedra; Guillermo Droppelmann; Nicolás García; Carlos Jorquera; Felipe Feijoo

doi:10.3389/fmed.2023.1070499

High-accuracy detection of supraspinatus fatty infiltration in shoulder MRI using convolutional neural network algorithms

Front Med (Lausanne). 2023 May 25:10:1070499. doi: 10.3389/fmed.2023.1070499. eCollection 2023.

Authors

Juan Pablo Saavedra¹, Guillermo Droppelmann^{2

3

4}, Nicolás García², Carlos Jorquera⁵, Felipe Feijoo¹

Affiliations

¹ School of Industrial Engineering, Pontificia Universidad Católica de Valparaíso, Valparaíso, Chile.
² Research Center on Medicine, Exercise, Sport and Health, MEDS Clinic, Santiago, Chile.
³ Health Sciences PhD Program, Universidad Católica de Murcia UCAM, Murcia, Spain.
⁴ Principles and Practice of Clinical Research (PPCR), Harvard T. H. Chan School of Public Health, Boston, MA, United States.
⁵ Facultad de Ciencias, Escuela de Nutrición y Dietética, Universidad Mayor, Santiago, Chile.

Abstract

Background: The supraspinatus muscle fatty infiltration (SMFI) is a crucial MRI shoulder finding to determine the patient's prognosis. Clinicians have used the Goutallier classification to diagnose it. Deep learning algorithms have been demonstrated to have higher accuracy than traditional methods.

Aim: To train convolutional neural network models to categorize the SMFI as a binary diagnosis based on Goutallier's classification using shoulder MRIs.

Methods: A retrospective study was performed. MRI and medical records from patients with SMFI diagnosis from January 1st, 2019, to September 20th, 2020, were selected. 900 T2-weighted, Y-view shoulder MRIs were evaluated. The supraspinatus fossa was automatically cropped using segmentation masks. A balancing technique was implemented. Five binary classification classes were developed into two as follows, A: 0, 1 v/s 3, 4; B: 0, 1 v/s 2, 3, 4; C: 0, 1 v/s 2; D: 0, 1, 2, v/s 3, 4; E: 2 v/s 3, 4. The VGG-19, ResNet-50, and Inception-v3 architectures were trained as backbone classifiers. An average of three 10-fold cross-validation processes were developed to evaluate model performance. AU-ROC, sensitivity, and specificity with 95% confidence intervals were used.

Results: Overall, 606 shoulders MRIs were analyzed. The Goutallier distribution was presented as follows: 0 = 403; 1 = 114; 2 = 51; 3 = 24; 4 = 14. Case A, VGG-19 model demonstrated an AU-ROC of 0.991 ± 0.003 (accuracy, 0.973 ± 0.006; sensitivity, 0.947 ± 0.039; specificity, 0.975 ± 0.006). B, VGG-19, 0.961 ± 0.013 (0.925 ± 0.010; 0.847 ± 0.041; 0.939 ± 0.011). C, VGG-19, 0.935 ± 0.022 (0.900 ± 0.015; 0.750 ± 0.078; 0.914 ± 0.014). D, VGG-19, 0.977 ± 0.007 (0.942 ± 0.012; 0.925 ± 0.056; 0.942 ± 0.013). E, VGG-19, 0.861 ± 0.050 (0.779 ± 0.054; 0.706 ± 0.088; 0.831 ± 0.061).

Conclusion: Convolutional neural network models demonstrated high accuracy in MRIs SMFI diagnosis.

Keywords: MRI; classification; deep learning; fatty infiltration; supraspinatus.