Performance analysis of a deep-learning algorithm to detect the presence of inflammation in MRI of sacroiliac joints in patients with axial spondyloarthritis.

OBJECTIVES: To assess the ability of a previously trained deep-learning algorithm to identify the presence of inflammation on MRI of sacroiliac joints (SIJ) in a large external validation set of patients with axial spondyloarthritis (axSpA). METHODS: Baseline SIJ MRI scans were collected from two prospective randomised controlled trials in patients with non-radiographic (nr-) and radiographic (r-) axSpA (RAPID-axSpA: NCT01087762 and C-OPTIMISE: NCT02505542) and were centrally evaluated by two expert readers (and adjudicator in case of disagreement) for the presence of inflammation by the 2009 Assessment of SpondyloArthritis International Society (ASAS) definition. Scans were processed by the deep-learning algorithm, blinded to clinical information and central expert readings. RESULTS: Pooling the patients from RAPID-axSpA (n=152) and C-OPTIMISE (n=579) yielded a validation set of 731 patients (mean age: 34.2 years, SD: 8.6; 505/731 (69.1%) male), of which 326/731 (44.6%) had nr-axSpA and 436/731 (59.6%) had inflammation on MRI per central readings. Scans were obtained from over 30 scanners from 5 manufacturers across over 100 clinical sites. Comparing the trained algorithm with the human central readings yielded a sensitivity of 70% (95% CI 66% to 73%), specificity of 81% (95% CI 78% to 84%), positive predictive value of 84% (95% CI 82% to 87%), negative predictive value of 64% (95% CI 61% to 68%), Cohen's kappa of 0.49 (95% CI 0.43 to 0.55) and absolute agreement of 74% (95% CI 72% to 77%). CONCLUSION: The algorithm enabled acceptable detection of inflammation according to the 2009 ASAS MRI definition in a large external validation cohort.

Detection and characterization of pancreatic lesion with artificial intelligence: The SFR 2023 artificial intelligence data challenge.

PURPOSE: The purpose of the 2023 SFR data challenge was to invite researchers to develop artificial intelligence (AI) models to identify the presence of a pancreatic mass and distinguish between benign and malignant pancreatic masses on abdominal computed tomography (CT) examinations. MATERIALS AND METHODS: Anonymized abdominal CT examinations acquired during the portal venous phase were collected from 18 French centers. Abdominal CT examinations were divided into three groups including CT examinations with no lesion, CT examinations with benign pancreatic mass, or CT examinations with malignant pancreatic mass. Each team included at least one radiologist, one data scientist, and one engineer. Pancreatic lesions were annotated by expert radiologists. CT examinations were distributed in balanced batches via a Health Data Hosting certified platform. Data were distributed into four batches, two for training, one for internal evaluation, and one for the external evaluation. Training used 83 % of the data from 14 centers and external evaluation used data from the other four centers. The metric (i.e., final score) used to rank the participants was a weighted average of mean sensitivity, mean precision and mean area under the curve. RESULTS: A total of 1037 abdominal CT examinations were divided into two training sets (including 500 and 232 CT examinations), an internal evaluation set (including 139 CT examinations), and an external evaluation set (including 166 CT examinations). The training sets were distributed on September 7 and October 13, 2023, and evaluation sets on October 15, 2023. Ten teams with a total of 93 members participated to the data challenge, with the best final score being 0.72. CONCLUSION: This SFR 2023 data challenge based on multicenter CT data suggests that the use of AI for pancreatic lesions detection is possible on real data, but the distinction between benign and malignant pancreatic lesions remains challenging.

Artificial intelligence in musculoskeletal oncology imaging: A critical review of current applications.

Artificial intelligence (AI) is increasingly being studied in musculoskeletal oncology imaging. AI has been applied to both primary and secondary bone tumors and assessed for various predictive tasks that include detection, segmentation, classification, and prognosis. Still, in the field of clinical research, further efforts are needed to improve AI reproducibility and reach an acceptable level of evidence in musculoskeletal oncology. This review describes the basic principles of the most common AI techniques, including machine learning, deep learning and radiomics. Then, recent developments and current results of AI in the field of musculoskeletal oncology are presented. Finally, limitations and future perspectives of AI in this field are discussed.

A deep learning model for the diagnosis of sacroiliitis according to Assessment of SpondyloArthritis International Society classification criteria with magnetic resonance imaging.

PURPOSE: The purpose of this study was to develop and evaluate a deep learning model to detect bone marrow edema (BME) in sacroiliac joints and predict the MRI Assessment of SpondyloArthritis International Society (ASAS) definition of active sacroiliitis in patients with chronic inflammatory back pain. MATERIALS AND METHODS: MRI examinations of patients from the French prospective multicenter DESIR cohort (DEvenir des Spondyloarthropathies Indifférenciées Récentes) were used for training, validation and testing. Patients with inflammatory back pain lasting three months to three years were recruited. Test datasets were from MRI follow-ups at five years and ten years. The model was evaluated using an external test dataset from the ASAS cohort. A neuronal network classifier (mask-RCNN) was trained and evaluated for sacroiliac joints detection and BME classification. Diagnostic capabilities of the model to predict ASAS MRI active sacroiliitis (BME in at least two half-slices) were assessed using Matthews correlation coefficient (MCC), sensitivity, specificity, accuracy and AUC. The gold standard was experts' majority decision. RESULTS: A total of 256 patients with 362 MRI examinations from the DESIR cohort were included, with 27% meeting the ASAS definition for experts. A total of 178 MRI examinations were used for the training set, 25 for the validation set and 159 for the evaluation set. MCCs for DESIR baseline, 5-years, and 10-years follow-up were 0.90 (n = 53), 0.64 (n = 70), and 0.61 (n = 36), respectively. AUCs for predicting ASAS MRI were 0.98 (95% CI: 0.93-1), 0.90 (95% CI: 0.79-1), and 0.80 (95% CI: 0.62-1), respectively. The ASAS external validation cohort included 47 patients (mean age 36 ± 10 [SD] years; women, 51%) with 19% meeting the ASAS definition. MCC was 0.62, sensitivity 56% (95% CI: 42-70), specificity 100% (95% CI: 100-100) and AUC 0.76 (95% CI: 0.57-0.95). CONCLUSION: The deep learning model achieves performance close to those of experts for BME detection in sacroiliac joints and determination of active sacroiliitis according to the ASAS definition.