Convolutional Neural Network-Based Approach for Cobb Angle Measurement Using Mask R-CNN.

Scoliosis is a disorder characterized by an abnormal spinal curvature, which can lead to negative effects on patients, affecting their quality of life. Given its progressive nature, the classification of the scoliosis severity requires an accurate diagnosis and effective monitoring. The Cobb angle measurement method has been widely considered as the gold standard for a scoliosis assessment. Commonly, an expert assesses scoliosis severity manually by identifying the most tilted vertebrae of the spine. However, this method requires time, effort, and presents limitations in measurement accuracy, such as the intra- and inter-observer variability. Artificial intelligence provides more objective tools that are less sensitive to manual intervention aiming to transform the diagnosis of scoliosis. The objective of this study was to address three key research questions regarding automated Cobb angle quantification: "Where is the spine in this radiograph?", "What is its exact shape?", and "Is the proposed method accurate?". We propose the use of Mask R-CNN architecture for spine detection and segmentation in response to the first two questions, and a set of algorithms to tackle the third. The network's detection and segmentation performance was evaluated through various metrics. An automated workflow for Cobb angle quantification and severity classification was developed. Finally, statistical methods provided the agreement between manual and automated measurements. A high segmentation accuracy was achieved, highlighting the following: mIoU of 0.8012, and a mean precision of 0.9145. MAE was 2.96° ± 2.60° demonstrating a high agreement. The results obtained in this study demonstrate the potential of the proposed automated approach in clinical scenarios, which provides experts with a clear visualization of each stage in the scoliosis assessment by overlaying the results onto the X-ray image.