Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods

• Published in: PloS one 2017-08, Vol.12 (8), p.e0184059-e0184059
• Main Authors: Burlina, Philippe, Billings, Seth, Joshi, Neil, Albayda, Jemima
• Format: Article
• Language: English
• Subjects: Adult; Aged; Aged, 80 and over; Algorithms; Applied physics; Artificial intelligence; Artificial neural networks; Biology and Life Sciences; Biomarkers; Care and treatment; Classification; Computer and Information Sciences; Deep learning; Delineation; Dermatomyositis; Dermatomyositis - diagnostic imaging; Design; Diagnosis; Diagnostic systems; Disease; Edema; Female; Humans; Image acquisition; Inflammatory diseases; International conferences; Laboratories; Learning algorithms; Machine Learning; Magnetic resonance imaging; Male; Mathematical functions; Medical diagnosis; Medicine and Health Sciences; Middle Aged; Muscles; Muscles - diagnostic imaging; Musculoskeletal diseases; Myositis; Myositis - diagnostic imaging; Myositis, Inclusion Body - diagnostic imaging; Neural networks; Neural Networks, Computer; Neuromuscular diseases; Polymyositis; Polymyositis - diagnostic imaging; Research and Analysis Methods; Ultrasonography - methods; Ultrasound; Young Adult
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0184059

To evaluate the use of ultrasound coupled with machine learning (ML) and deep learning (DL) techniques for automated or semi-automated classification of myositis. Eighty subjects comprised of 19 with inclusion body myositis (IBM), 14 with polymyositis (PM), 14 with dermatomyositis (DM), and 33 normal (N) subjects were included in this study, where 3214 muscle ultrasound images of 7 muscles (observed bilaterally) were acquired. We considered three problems of classification including (A) normal vs. affected (DM, PM, IBM); (B) normal vs. IBM patients; and (C) IBM vs. other types of myositis (DM or PM). We studied the use of an automated DL method using deep convolutional neural networks (DL-DCNNs) for diagnostic classification and compared it with a semi-automated conventional ML method based on random forests (ML-RF) and "engineered" features. We used the known clinical diagnosis as the gold standard for evaluating performance of muscle classification. The performance of the DL-DCNN method resulted in accuracies ± standard deviation of 76.2% ± 3.1% for problem (A), 86.6% ± 2.4% for (B) and 74.8% ± 3.9% for (C), while the ML-RF method led to accuracies of 72.3% ± 3.3% for problem (A), 84.3% ± 2.3% for (B) and 68.9% ± 2.5% for (C). This study demonstrates the application of machine learning methods for automatically or semi-automatically classifying inflammatory muscle disease using muscle ultrasound. Compared to the conventional random forest machine learning method used here, which has the drawback of requiring manual delineation of muscle/fat boundaries, DCNN-based classification by and large improved the accuracies in all classification problems while providing a fully automated approach to classification.