Evaluating Scoliosis Severity Based on Posturographic X-ray Images Using a Contrastive Language–Image Pretraining Model

Abstract

Assessing severe scoliosis requires the analysis of posturographic X-ray images. One way to analyse these images may involve the use of open-source artificial intelligence models (OSAIMs), such as the contrastive language–image pretraining (CLIP) system, which was designed to combine images with text. This study aims to determine whether the CLIP model can recognise visible severe scoliosis in posturographic X-ray images. This study used 23 posturographic images of patients diagnosed with severe scoliosis that were evaluated by two independent neurosurgery specialists. Subsequently, the X-ray images were input into the CLIP system, where they were subjected to a series of questions with varying levels of difficulty and comprehension. The predictions obtained using the CLIP models in the form of probabilities ranging from 0 to 1 were compared with the actual data. To evaluate the quality of image recognition, true positives, false negatives, and sensitivity were determined. The results of this study show that the CLIP system can perform a basic assessment of X-ray images showing visible severe scoliosis with a high level of sensitivity. It can be assumed that, in the future, OSAIMs dedicated to image analysis may become commonly used to assess X-ray images, including those of scoliosis.

Artificial Intelligence in Scoliosis: Current Applications and Future Directions

“…CLIP is designed to process and understand both text and images simultaneously, allowing it to perform tasks such as image classification, object detection, and image generation. Fabijan et al [26] used 23 postural images of patients with severe scoliosis, evaluated by two neurosurgery experts. The images are fed into the CLIP system and the predictions obtained are compared with the actual data.…”

Artificial Intelligence in Scoliosis Classification: An Investigation of Language-Based Models

“…Our previous study sheds light on the capabilities of the publicly accessible contrastive language-image pretraining (CLIP) system in recognizing severe cases of single-curve scoliosis. The results showed that although some AI models possess the ability to partially recognize scoliosis based on visual data, their effectiveness is limited [21]. Consequently, in our article, we delve into the current state of research on the application of AI models in medicine, highlighting that they are rarely considered in the context of scoliosis, despite the potential to offer new, valuable diagnostic perspectives.…”

Artificial Intelligence in Medical Imaging: Analyzing the Performance of ChatGPT and Microsoft Bing in Scoliosis Detection and Cobb Angle Assessment

“…In the context of dynamic advancements in language models, our current research aims to extend our understanding of the capabilities of ChatGPT and Microsoft Bing in analyzing posturographic images of patients diagnosed with scoliosis. Expanding on our previous studies, which evaluated the CLIP system's ability to analyze X-ray images of scoliosis [28] and assessed ChatGPT and other AI models in classifying single-curve scoliosis from radiological descriptions [29], our current research delves deeper into the capabilities of ChatGPT and Microsoft Bing for more complex image analysis tasks. Specifically, we selected images depicting severe single-curve scoliosis, which are considered to be relatively simpler for specialists in spinal pathology to assess.…”