Artificial-Intelligence-Aided Radiographic Diagnostic of Knee Osteoarthritis Leads to a Higher Association of Clinical Findings with Diagnostic Ratings.

BACKGROUND: Radiographic knee osteoarthritis (OA) severity and clinical severity are often dissociated. Artificial intelligence (AI) aid was shown to increase inter-rater reliability in radiographic OA diagnosis. Thus, AI-aided radiographic diagnoses were compared against AI-unaided diagnoses with regard to their correlations with clinical severity. METHODS: Seventy-one DICOMs (m/f = 27:42, mean age: 27.86 ± 6.5) (X-ray format) were used for AI analysis (KOALA software, IB Lab GmbH). Subjects were recruited from a physiotherapy trial (MLKOA). At baseline, each subject received (i) a knee X-ray and (ii) an assessment of five main scores (Tegner Scale (TAS); Knee Injury and Osteoarthritis Outcome Score (KOOS); International Physical Activity Questionnaire; Star Excursion Balance Test; Six-Minute Walk Test). Clinical assessments were repeated three times (weeks 6, 12 and 24). Three physicians analyzed the presented X-rays both with and without AI via KL grading. Analyses of the (i) inter-rater reliability (IRR) and (ii) Spearman's Correlation Test for the overall KL score for each individual rater with clinical score were performed. RESULTS: We found that AI-aided diagnostic ratings had a higher association with the overall KL score and the KOOS. The amount of improvement due to AI depended on the individual rater. CONCLUSION: AI-guided systems can improve the ratings of knee radiographs and show a stronger association with clinical severity. These results were shown to be influenced by individual readers. Thus, AI training amongst physicians might need to be increased. KL might be insufficient as a single tool for knee OA diagnosis.

Artificial intelligence-based computer-aided system for knee osteoarthritis assessment increases experienced orthopaedic surgeons' agreement rate and accuracy.

PURPOSE: The aims of this study were to (1) analyze the impact of an artificial intelligence (AI)-based computer system on the accuracy and agreement rate of board-certified orthopaedic surgeons (= senior readers) to detect X-ray features indicative of knee OA in comparison to unaided assessment and (2) compare the results to those of senior residents (= junior readers). METHODS: One hundred and twenty-four unilateral knee X-rays from the OAI study were analyzed regarding Kellgren-Lawrence grade, joint space narrowing (JSN), sclerosis and osteophyte OARSI grade by computerized methods. Images were rated for these parameters by three senior readers using two modalities: plain X-ray (unaided) and X-ray presented alongside reports from a computer-assisted detection system (aided). After exclusion of nine images with incomplete annotation, intraclass correlations between readers were calculated for both modalities among 115 images, and reader performance was compared to ground truth (OAI consensus). Accuracy, sensitivity and specificity were also calculated and the results were compared to those from a previous study on junior readers. RESULTS: With the aided modality, senior reader agreement rates for KL grade (2.0-fold), sclerosis (1.42-fold), JSN (1.37-fold) and osteophyte OARSI grades (3.33-fold) improved significantly. Reader specificity and accuracy increased significantly for all features when using the aided modality compared to the gold standard. On the other hand, sensitivity only increased for OA diagnosis, whereas it decreased (without statistical significance) for all other features. With aided analysis, senior readers reached similar agreement and accuracy rates as junior readers, with both surpassing AI performance. CONCLUSION: The introduction of AI-based computer-aided assessment systems can increase the agreement rate and overall accuracy for knee OA diagnosis among board-certified orthopaedic surgeons. Thus, use of this software may improve the standard of care for knee OA detection and diagnosis in the future. LEVEL OF EVIDENCE: Level II.

Artificial intelligence-generated hip radiological measurements are fast and adequate for reliable assessment of hip dysplasia : an external validation study.

AIMS: Hip dysplasia (HD) leads to premature osteoarthritis. Timely detection and correction of HD has been shown to improve pain, functional status, and hip longevity. Several time-consuming radiological measurements are currently used to confirm HD. An artificial intelligence (AI) software named HIPPO automatically locates anatomical landmarks on anteroposterior pelvis radiographs and performs the needed measurements. The primary aim of this study was to assess the reliability of this tool as compared to multi-reader evaluation in clinically proven cases of adult HD. The secondary aims were to assess the time savings achieved and evaluate inter-reader assessment. METHODS: A consecutive preoperative sample of 130 HD patients (256 hips) was used. This cohort included 82.3% females (n = 107) and 17.7% males (n = 23) with median patient age of 28.6 years (interquartile range (IQR) 22.5 to 37.2). Three trained readers' measurements were compared to AI outputs of lateral centre-edge angle (LCEA), caput-collum-diaphyseal (CCD) angle, pelvic obliquity, Tönnis angle, Sharp's angle, and femoral head coverage. Intraclass correlation coefficients (ICC) and Bland-Altman analyses were obtained. RESULTS: Among 256 hips with AI outputs, all six hip AI measurements were successfully obtained. The AI-reader correlations were generally good (ICC 0.60 to 0.74) to excellent (ICC > 0.75). There was lower agreement for CCD angle measurement. Most widely used measurements for HD diagnosis (LCEA and Tönnis angle) demonstrated good to excellent inter-method reliability (ICC 0.71 to 0.86 and 0.82 to 0.90, respectively). The median reading time for the three readers and AI was 212 (IQR 197 to 230), 131 (IQR 126 to 147), 734 (IQR 690 to 786), and 41 (IQR 38 to 44) seconds, respectively. CONCLUSION: This study showed that AI-based software demonstrated reliable radiological assessment of patients with HD with significant interpretation-related time savings.Cite this article: Bone Jt Open 2022;3(11):877-884.

Trabecular bone texture analysis of conventional radiographs in the assessment of knee osteoarthritis: review and viewpoint.

BACKGROUND: Trabecular bone texture analysis (TBTA) has been identified as an imaging biomarker that provides information on trabecular bone changes due to knee osteoarthritis (KOA). Consequently, it is important to conduct a comprehensive review that would permit a better understanding of this unfamiliar image analysis technique in the area of KOA research. We examined how TBTA, conducted on knee radiographs, is associated to (i) KOA incidence and progression, (ii) total knee arthroplasty, and (iii) KOA treatment responses. The primary aims of this study are twofold: to provide (i) a narrative review of the studies conducted on radiographic KOA using TBTA, and (ii) a viewpoint on future research priorities. METHOD: Literature searches were performed in the PubMed electronic database. Studies published between June 1991 and March 2020 and related to traditional and fractal image analysis of trabecular bone texture (TBT) on knee radiographs were identified. RESULTS: The search resulted in 219 papers. After title and abstract scanning, 39 studies were found eligible and then classified in accordance to six criteria: cross-sectional evaluation of osteoarthritis and non-osteoarthritis knees, understanding of bone microarchitecture, prediction of KOA progression, KOA incidence, and total knee arthroplasty and association with treatment response. Numerous studies have reported the relevance of TBTA as a potential bioimaging marker in the prediction of KOA incidence and progression. However, only a few studies have focused on the association of TBTA with both OA treatment responses and the prediction of knee joint replacement. CONCLUSION: Clear evidence of biological plausibility for TBTA in KOA is already established. The review confirms the consistent association between TBT and important KOA endpoints such as KOA radiographic incidence and progression. TBTA could provide markers for enrichment of clinical trials enhancing the screening of KOA progressors. Major advances were made towards a fully automated assessment of KOA.

Automated Knee Osteoarthritis Assessment Increases Physicians' Agreement Rate and Accuracy: Data from the Osteoarthritis Initiative.

Objective. To assess the impact of a computerized system on physicians' accuracy and agreement rate, as compared with unaided diagnosis. Methods. A set of 124 unilateral knee radiographs from the Osteoarthritis Initiative (OAI) study were analyzed by a computerized method with regard to Kellgren-Lawrence (KL) grade, as well as joint space narrowing, osteophytes, and sclerosis Osteoarthritis Research Society International (OARSI) grades. Physicians scored all images, with regard to osteophytes, sclerosis, joint space narrowing OARSI grades and KL grade, in 2 modalities: through a plain radiograph (unaided) and a radiograph presented together with the report from the computer assisted detection system (aided). Intraclass correlation between the physicians was calculated for both modalities. Furthermore, physicians' performance was compared with the grading of the OAI study, and accuracy, sensitivity, and specificity were calculated in both modalities for each of the scored features. Results. Agreement rates for KL grade, sclerosis, and osteophyte OARSI grades, were statistically increased in the aided versus the unaided modality. Readings for joint space narrowing OARSI grade did not show a statistically difference between the 2 modalities. Readers' accuracy and specificity for KL grade >0, KL >1, sclerosis OARSI grade >0, and osteophyte OARSI grade >0 was significantly increased in the aided modality. Reader sensitivity was high in both modalities. Conclusions. These results show that the use of an automated knee OA software increases consistency between physicians when grading radiographic features of OA. The use of the software also increased accuracy measures as compared with the OAI study, mostly through increases in specificity.

Assessing the effects of long-term osteoporosis treatment by using conventional spine radiographs: results from a pilot study in a sub-cohort of a large randomized controlled trial.

OBJECTIVE: To evaluate the clinical applicability of a software tool developed to extract bone textural information from conventional lumbar spine radiographs, and to test it in a subset of postmenopausal women treated for osteoporosis with the fully human monoclonal antibody denosumab. METHODS: The software was developed based on the principles of a fractal model using pixel grey-level variations together with a specific machine-learning algorithm. The obtained dimensionless parameter, termed bone structure value (BSV), was then tested and compared to bone mineral density (BMD) in a sub-cohort of postmenopausal women with osteoporosis who were treated with the monoclonal antibody denosumab, within the framework of a large randomized controlled trial and its open-label extension phase. RESULTS: After 3 years and after 8 years of treatment with denosumab, mean lumbar spine BMD as well as mean lumbar BSV were significantly higher compared to study entry (one-way repeated measures ANOVA for DXA: F = 108.2, p < 0.00001; and for BSV: F = 84.3, p < 0.00001). The overall increase in DXA-derived lumbar spine BMD at year 8 was + 42% (mean ± SD; 0.725 ± 0.038 g/cm2 to 1.031 ± 0.092 g/cm2; p < 0.0001), and the overall increase of BSV was 255% (mean ± SD; 0.076 ± 0.022 to 0.270 ± 0.09, p < 0.0001). Overall, BMD and BSV were significantly correlated (R = 0.51; p < 0.0001). CONCLUSIONS: This pilot study provides evidence that lumbar spine BSV as obtained from conventional radiographs constitutes a useful means for the assessment of bone-specific treatment effects in postmenopausal women with osteoporosis.