Title: Artificial Intelligence for Intelligent Medical Image Sorting and Diagnostic Workflow Optimization
Authors: Mohammed Asem Abdul-Shakour Al-Tawil, Samy S. Abu-Naser
Volume: 10
Issue: 7
Pages: 79-83
Publication Date: 2026/07/28
Abstract:
Medical imaging departments worldwide are experiencing an unprecedented increase in diagnostic imaging volume due to the widespread adoption of digital radiology, computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound technologies. Conventional Picture Archiving and Communication Systems (PACS) generally process examinations using First-In, First-Out (FIFO) scheduling, which does not account for the clinical severity of individual cases. Consequently, patients with life-threatening conditions may experience unnecessary delays before radiological review. This paper proposes an intelligent image-sorting framework that combines deep learning-based medical image analysis with a Max-Heap Priority Queue to dynamically prioritize examinations according to predicted clinical urgency. A lightweight Convolutional Neural Network (CNN) assigns each incoming image an urgency score reflecting the probability of critical pathology. The assigned score serves as the priority key for insertion into a heap-based scheduling structure, enabling efficient retrieval of the most urgent examination in logarithmic time complexity. The proposed framework is analytically compared with traditional FIFO queues, unsorted lists, and fully sorted lists in terms of computational complexity and scalability. Complexity analysis demonstrates that the proposed approach reduces retrieval operations from O(n) to O(log n) while maintaining efficient insertion performance suitable for high-volume imaging environments. Theoretical workload evaluation indicates that the number of comparisons required to retrieve the highest-priority examination decreases by more than 99% for large imaging queues. The proposed framework illustrates how integrating artificial intelligence with classical data structures can improve diagnostic workflow efficiency, reduce waiting times for critically ill patients, and provide a scalable foundation for intelligent medical imaging pipelines.