Search

Over the past decade rapid advancements in molecular imaging (MI) and artificial intelligence (AI) have revolutionized traditional musculoskeletal radiology. Molecular imaging refers to the ability of various methods to in vivo characterize and quantify biological processes, at a molecular level. The extracted information provides the tools to understand the pathophysiology of diseases and thus to early detect, to accurately evaluate the extend and to apply and evaluate targeted treatments. At present, molecular imaging mainly involves CT, MRI, radionuclide, US, and optical imaging and has been reported in many clinical and preclinical studies. Although originally MI techniques targeted at central nervous system disorders, later on their value on musculoskeletal disorders was also studied in depth. Meaningful exploitation of the large volume of imaging data generated by molecular and conventional imaging techniques, requires state-of-the-art computational methods that enable rapid handling of large volumes of information. AI allows end-to-end training of computer algorithms to perform tasks encountered in everyday clinical practice including diagnosis, disease severity classification and image optimization. Notably, the development of deep learning algorithms has offered novel methods that enable intelligent processing of large imaging datasets in an attempt to automate decision-making in a wide variety of settings related to musculoskeletal trauma. Current applications of AI include the diagnosis of bone and soft tissue injuries, monitoring of the healing process and prediction of injuries in the professional sports setting. This review presents the current applications of novel MI techniques and methods and the emerging role of AI regarding the diagnosis and evaluation of musculoskeletal trauma., Competing Interests: Declaration of Competing Interest No conflict of interest to disclose for all authors, (Copyright © 2020 Elsevier Ltd. All rights reserved.)

Purpose: Subchondral insufficiency fractures (SIF) and advanced osteoarthritis (OA) of the knee are usually seen in conjunction with bone marrow lesions (BMLs) and their differentiation may pose a significant diagnostic challenge. We aimed to develop a convolutional neural network (CNN) ensemble which could successfully differentiate between these two entities.Materials and Methods: A total of 212 knees with SIF and 102 knees with advanced OA with BMLs were retrospectively included. Coronal fat suppressed PD-w images were augmented, resized and normalized, reaching a total of 1174 images. Data was used to fine-tune three ImageNet-pretrained CNNs (VGG-16, InceptionV3 and Inception-ResNet-V2). Agreement of at least two networks was recorded as the decision of the network ensemble. Ensemble performance was compared to that of two MSK radiologists on the validation set. Receiver operating characteristics (ROC) curves and the respective areas under the curve (AUC) were used to evaluate human and machine performance.Results: InceptionV3 achieved the highest AUC (93.68%) and VGG-16 the lowest AUC (82.18%) among individual CNNs. CNN ensemble achieved the highest overall performance with an AUC of 95.97%. The first of the two MSK radiologists achieved a performance similar to the ensemble, reaching an AUC of 91.95%. The second radiologist achieved lower AUC of 82.76% which was lower than both the other specialist and the ensemble (P < 0.001).Conclusion: A CNN ensemble was highly accurate in differentiating between SIF and OA, achieving a higher or equal performance to MSK radiologists. [ABSTRACT FROM AUTHOR]