Deep Learning-Based Classification of Inflammatory Arthritis by Identification of Joint Shape Patterns—How Neural Networks Can Tell Us Where to “Deep Dive” Clinically

Abstract

Objective:We investigated whether a neural network based on the shape of joints can differentiate between rheumatoid arthritis (RA), psoriatic arthritis (PsA), and healthy controls (HC), which class patients with undifferentiated arthritis (UA) are assigned to, and whether this neural network is able to identify disease-specific regions in joints.MethodsWe trained a novel neural network on 3D articular bone shapes of hand joints of RA and PsA patients as well as HC. Bone shapes were created from high-resolution peripheral-computed-tomography (HR-pQCT) data of the second metacarpal bone head. Heat maps of critical spots were generated using GradCAM. After training, we fed shape patterns of UA into the neural network to classify them into RA, PsA, or HC.ResultsHand bone shapes from 932 HR-pQCT scans of 617 patients were available. The network could differentiate the classes with an area-under-receiver-operator-curve of 82% for HC, 75% for RA, and 68% for PsA. Heat maps identified anatomical regions such as bare area or ligament attachments prone to erosions and bony spurs. When feeding UA data into the neural network, 86% were classified as “RA,” 11% as “PsA,” and 3% as “HC” based on the joint shape.ConclusionWe investigated neural networks to differentiate the shape of joints of RA, PsA, and HC and extracted disease-specific characteristics as heat maps on 3D joint shapes that can be utilized in clinical routine examination using ultrasound. Finally, unspecific diseases such as UA could be grouped using the trained network based on joint shape.

DeepNAPSI multi-reader nail psoriasis prediction using deep learning

“…classify CT scans for the presence of a disease 7 . Lately, neural networks also were applied to challenges in the rheumatology, such as image-based classification of rheumatic diseases via data from magnetic resonance imaging or computed tomography 8 , 9 .…”

Application of clinical and molecular profiling data to improve patient outcomes in psoriatic arthritis

“…Modern imaging techniques such as ultrasound, MRI, positron emission tomography (PET) -computed tomography (CT) and high-resolution peripheral quantitative CT (HR-pQCT) are diagnostic tools with high resolution and accuracy for the assessment of synovio-entheseal damage and are major assets for the current diagnostic approach to psoriatic disease. [37][38][39][40][41] The first results of HIPPOCRATES in this field were promising, showing that these imaging technologies can be further developed [42][43][44] to allow assessment of damage progression in PsA at a new level. The use of molecular approaches for damage characterization in PsA is a growing area of research and one of the main focuses of HIPPOCRATES.…”

Artificial intelligence, machine learning and deep learning in musculoskeletal imaging: Current applications

“…Different authors also investigated whether a neural network based on the shape of joints could differentiate between rheumatoid arthritis (RA) and psoriatic arthritis, from healthy controls, by identifying diseasespecific regions in joints. 21 The novel neural network was trained on 3D articular bone shapes from high-resolution CT images of the second metacarpal bone head. Heat maps identified anatomical regions such as bare areas or ligament attachments prone to erosions and bony spurs.…”