Scoring Osteoarthritis Reliably in Large Joints and the Spine Using Whole-Body CT: OsteoArthritis Computed Tomography-Score (OACT-Score)

Gielis, Willem Paul; Weinans, Harrie; Nap, Frank J.; Roemer, Frank W.; Foppen, Wouter

doi:10.3390/jpm11010005

Cited by 12 publications

(31 citation statements)

References 41 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model-5 was trained solely on the CT-AP images PR AUC , area under the precision recall curve; ROC AUC , area under the receiver operating characteristics curve; CI, confidence interval thin-slab maximum intensity projection technique [18]. Turmezei et al based their hip OA grading on three separate assessments of joint space narrowing, osteophytes, and subchondral cysts [10,11]. Their scoring system was diverse, and they reported high reliability, especially for their composite three-class scoring system [11].…”

Section: Discussionmentioning

confidence: 99%

“…The most common assessment method of radiographic hip OA (rHOA) is the Kellgren and Lawrence (KL) severity grading [ 1 , 2 ]. Clinical computed tomography (CT) has lower resolution than plain radiographs but provides detailed three-dimensional (3-D) information on the joint bones [ 10 , 11 ]. Consequently, due to the differences between the 3-D CT and two-dimensional (2-D) X-ray images, the KL grading is not directly applicable to CT.…”

Section: Introductionmentioning

confidence: 99%

“…Consequently, due to the differences between the 3-D CT and two-dimensional (2-D) X-ray images, the KL grading is not directly applicable to CT. Although there have been some previous attempts to introduce CT-based hip OA severity grading [ 10 , 11 ], there is still no widely accepted gold standard. Furthermore, grading hip OA severity on CTs can prove to be difficult and time consuming [ 11 ] especially for pelvic and hip studies that use clinical CTs, e.g., to investigate the relationship between proximal femur or acetabular fractures and hip OA.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detecting hip osteoarthritis on clinical CT: a deep learning application based on 2-D summation images derived from CT

et al. 2021

View full text Add to dashboard Cite

We developed and compared deep learning models to detect hip osteoarthritis on clinical CT. The CT-based summation images, CT-AP, that resemble X-ray radiographs can detect radiographic hip osteoarthritis and in the absence of large training data, a reliable deep learning model can be optimized by combining CT-AP and X-ray images. Introduction In this study, we aimed to investigate the applicability of deep learning (DL) to assess radiographic hip osteoarthritis (rHOA) on computed tomography (CT). Methods The study data consisted of 94 abdominopelvic clinical CTs and 5659 hip X-ray images collected from Cohort Hip and Cohort Knee (CHECK). The CT slices were sequentially summed to create radiograph-like 2-D images named CT-AP. X-ray and CT-AP images were classified as rHOA if they had osteoarthritic changes corresponding to Kellgren-Lawrence grade 2 or higher. The study data was split into 55% training, 30% validation, and 15% test sets. A pretrained ResNet18 was optimized for a classification task of rHOA vs. no-rHOA. Five models were trained using (1) X-rays, (2) downsampled X-rays, (3) combination of CT-AP and X-ray images, (4) combination of CT-AP and downsampled X-ray images, and (5) CT-AP images. Results Amongst the five models, Model-3 and Model-5 performed best in detecting rHOA from the CT-AP images. Model-3 detected rHOA on the test set of CT-AP images with a balanced accuracy of 82.2% and was able to discriminate rHOA from no-rHOA with an area under the receiver operating characteristic curve (ROC AUC) of 0.93 [0.75-0.99]. Model-5 detected rHOA on the test set at a balanced accuracy of 82.2% and classified rHOA from no-rHOA with an ROC AUC of 0.89 [0.67-0.97]. Conclusion CT-based summation images that resemble radiographs can be used to detect rHOA. In addition, in the absence of large training data, a reliable DL model can be optimized by combining CT-AP and X-ray images.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detecting hip osteoarthritis on clinical CT: a deep learning application based on 2-D summation images derived from CT

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Consistent with the previous study, another study using ultrasound found that rectus femoris and vastus lateralis muscle echogenicity, representing fat content and fibrosis, was associated with mobility performance in women with knee OA, while, muscle thickness and subcutaneous fat thickness were not 46 . CT-based grading system to evaluate OA in large joints and the spine, the OsteoArthritis Computed Tomography (OACT) score 47 . This score calculate a person's total OA burden by summing scores of individual joints.…”

Section: Imaging Of Peri-articular Tissues In Oamentioning

confidence: 99%

Osteoarthritis year in review 2021: imaging

Oei

Hirvasniemi

Zadelhoff

et al. 2022

Osteoarthritis and Cartilage

View full text Add to dashboard Cite

“…Multiple joints are often affected by osteoarthritis, and this may hamper interpretation of the contribution of a specific joint in patients’ quality of life, physical performance, or biochemical markers. Gielis et al developed and tested the reproducibility of the OsteoArthritis Computed Tomography-Score in order to assess osteoarthritis burden throughout the body in large joints and the spine [ 8 ]. Abnormal new bone formation was observed in patients with diffuse idiopathic skeletal hyperostosis (DISH), especially in the spine near the anterior longitudinal ligament, resulting in an increased risk of spinal fractures.…”

mentioning

confidence: 99%