A hybrid multi-panel image segmentation framework for improved medical image retrieval system

Multi-panel images play an essential role in medical diagnostics and represent approximately 50% of the medical literature. These images serve as important tools for physicians to align various medical data (e.g., X-rays, MRIs, CT scans) of a patient into a consolidated image. This consolidated multi-panel image, represented by its component sub-images, contributes to a thorough representation of the patient's case during diagnosis. However, extracting sub-images from the multi-panel images poses significant challenges for medical image retrieval systems, especially when dealing with regular and irregular image layouts. To address these challenges, this paper presents a novel hybrid framework that significantly enhances sub-image retrieval. The framework classifies medical images, employs advanced computer vision and image processing techniques including image projection profiles and morphological operations, and performs efficient segmentation of various multi-panel image types including regular and irregular medical images. The hybrid approach ensures accurate indexing and facilitates fast retrieval of sub-images by medical image retrieval systems. To validate the proposed framework, experiments were conducted on a set of medical images from publicly available datasets, including ImageCLEFmed 2013 to ImageCLEFmed 2016. The results show better performance compared to other methods, attaining an accuracy of 90.50% in image type identification and 91% and 92% in regular and irregular multi-panel image segmentation tasks, respectively. By achieving accurate and efficient segmentation across diverse multi-panel image types, our framework demonstrates significant potential to improve the performance of medical image retrieval systems.