Deep Learning-Based Detection of Bone Tumors around the Knee in X-rays of Children

Abstract

Even though tumors in children are rare, they cause the second most deaths under the age of 18 years. More often than in other age groups, underage patients suffer from malignancies of the bones, and these mostly occur in the area around the knee. One problem in the treatment is the early detection of bone tumors, especially on X-rays. The rarity and non-specific clinical symptoms further prolong the time to diagnosis. Nevertheless, an early diagnosis is crucial and can facilitate the treatment and therefore improve the prognosis of affected children. A new approach to evaluating X-ray images using artificial intelligence may facilitate the detection of suspicious lesions and, hence, accelerate the referral to a specialized center. We implemented a Vision Transformer model for image classification of healthy and pathological X-rays. To tackle the limited amount of data, we used a pretrained model and implemented extensive data augmentation. Discrete parameters were described by incidence and percentage ratio and continuous parameters by median, standard deviation and variance. For the evaluation of the model accuracy, sensitivity and specificity were computed. The two-entity classification of the healthy control group and the pathological group resulted in a cross-validated accuracy of 89.1%, a sensitivity of 82.2% and a specificity of 93.2% for test groups. Grad-CAMs were created to ensure the plausibility of the predictions. The proposed approach, using state-of-the-art deep learning methodology to detect bone tumors on knee X-rays of children has achieved very good results. With further improvement of the algorithm, enlargement of the dataset and removal of potential biases, this could become a useful additional tool, especially to support general practitioners for early, accurate and specific diagnosis of bone lesions in young patients.

Machine Learning–Assisted Decision Making in Orthopaedic Oncology

“…One illustrative example by Park et al showed ML classification of bone tumors using proximal femur plain radiographs with diagnostic accuracy of 0.853 compared with 0.794 for physicians 39 . Another study by Breden et al reported accuracy of 89.1% in detected radiographic tumors around the knee 41 . This demonstrates the effectiveness of radiographs as they present higher contrast for bony structures facilitating more straightforward feature extraction for ML algorithms.…”

Deep learning for differentiation of osteolytic osteosarcoma and giant cell tumor around the knee joint on radiographs: a multicenter study

“…As an emerging machine learning technology, deep learning (DL) has been widely applied to medical image analysis of bone tumors [ 15 – 17 ], which can distinguish benign and malignant bone tumors [ 11 , 12 , 14 , 18 – 21 ]. A recent study has highlighted DL’s potential in effectively classifying healthy and pathological X-rays in children [ 22 ]. However, previous studies have primarily focused on the benign and malignant classification of various bone tumors at different sites throughout the body [ 15 , 18 , 21 ], rather than specifically addressing the differential diagnosis of osteolytic OS and GCT around the knee joint.…”