Deep Learning Augmented Osteoarthritis Grading Standardization

Abstract

Manual grading of cartilage histology images for investigating the extent and severity of osteoarthritis (OA) involves critical examination of the cell characteristics, which makes this task tiresome, tedious, and error prone. This results in wide interobserver variation, causing ambiguities in OA grade prediction. Such drawbacks of manual assessment can be overcome by implementing artificial intelligence–based automated image classification techniques such as deep learning (DL). Hence, we present the feasibility of training a deep neural network with cartilage histology images, which can grade the extent and severity of knee OA based on modified Mankin scoring system. The grading system used here for automating OA grading was simplified and modified based on the microscopic observations from the histology images, where three parameters (Safranin-O staining intensity, chondrocyte distribution and arrangement, and morphology) were considered for evaluating the OA progression. The histology images were tiled, labeled, and grouped together based on the developed grading system (Grade 0–3). Four different DL architectures were tried for image classification and the best performing model was selected by fivefold validation method. With a validation accuracy of ∼84%, 0.632 Cohen's kappa score, and an excellent receiver operating characteristic (ROC)–area under the ROC curve ranging between 0.89 and 0.99, DenseNet121 was selected among the four models as the best performing model, and was used for inferencing on new data. Final grades obtained from the models were in accordance with the grades provided by the medical experts. We hereby demonstrate that a DL architecture can be taught to interpret the degree of cartilage degradation, with excellent discriminatory ability across all four classes of OA severity. Unlike other works where radiographic images have been considered for grading of OA, we have considered histology images, which is a fundamental approach for grading OA extent and severity. This would bring a paradigm shift in histology-based assessment of OA, making this automated approach to be explored as an option for OA grading standardization. Ethical approval number-IAH-BMR-018/10-19.

Impact statement

1. 1.

   Feasibility of training a deep neural network with human knee osteoarthritic histology images to grade the extent and severity of osteoarthritis (OA) has not been reported yet anywhere to the best of our knowledge.

2. 2.

   Among the four deep learning models tried ResNet50, DenseNet121, VGG16, and InceptionV3, DenseNet121 was found to be the best performing model with a validation accuracy of ∼84%, and the grades presented were in accordance with the grades given by medical experts (pathologists and orthopedic surgeons).

3. 3.

   This work would be of great interest to the researchers who work on distinguishing the subsets of OA, defining the end points for clinical trials, evaluation of characteristic features and disease markers of OA, and evaluation of animal OA models.

4. 4.

   Such automated grading systems help in transforming the tiresome and error-prone grading process to swift, precise, and unbiased grading, thereby reducing the demand for pathologists with years of experience