Application of deep learning for automated diagnosis and classification of hip dysplasia on plain radiographs

TL;DR

This study shows that deep learning models can accurately distinguish between normal and dysplastic hips in X-rays, but struggle with more nuanced classifications.

Contribution

A deep learning approach for automated diagnosis and severity classification of hip dysplasia using plain radiographs is proposed and evaluated.

Findings

Models achieved high accuracy in distinguishing normal/borderline vs. dysplastic hips (92.2% and 83.3%).

Both models struggled with differentiating between normal and borderline hips.

Most misclassifications in severity grading were within one class of the correct label.

Abstract

Hip dysplasia is a condition where the acetabulum is too shallow to support the femoral head and is commonly considered a risk factor for hip osteoarthritis. The objective of this study was to develop a deep learning model to diagnose hip dysplasia from plain radiographs and classify dysplastic hips based on their severity.

We collected pelvic radiographs of 571 patients from two single-center cohorts and one multicenter cohort. The radiographs were split in half to create hip radiographs (n = 1022). One orthopaedic surgeon and one resident assessed the radiographs for hip dysplasia on either side. We used the center edge (CE) angle as the primary diagnostic criteria. Hips with a CE angle < 20°, 20° to 25°, and > 25° were labeled as dysplastic, borderline, and normal, respectively. The dysplastic hips were also classified with both Crowe and Hartofilakidis classification of dysplasia. The dataset was divided into train, validation, and test subsets using 80:10:10 split-ratio that were used to train two deep learning models to classify images into normal, borderline and (1) Crowe grade 1–4 or (2) Hartofilakidis grade 1–3. A pre-trained on Imagenet VGG16 convolutional neural network (CNN) was utilized by performing layer-wise fine-turning.

Both models struggled with distinguishing between normal and borderline hips. However, achieved high accuracy (Model 1: 92.2% and Model 2: 83.3%) in distinguishing between normal/borderline vs. dysplastic hips. The overall accuracy of Model 1 was 68% and for Model 2 73.5%. Most misclassifications for the Crowe and Hartofilakidis classifications were +/- 1 class from the correct class.

This pilot study shows promising results that a deep learning model distinguish between normal and dysplastic hips with high accuracy. Future research and external validation are warranted regarding the ability of deep learning models to perform complex tasks such as identifying and classifying disorders using plain radiographs.

Diagnostic level IV

Figures