Efficient Chromosome Abnormal Detection using Yolo-V8 model

Human chromosomes exhibit complex and intricate patterns, making their analysis and data interpretation challenging. Studying chromosomes is crucial for identifying genetic disorders, such as Down syndrome, and various types of cancer. Traditional karyotyping methods depend heavily on manual method, which causes human error and high cost. To address these challenges, a deep learning-based approach is proposed to automate the karyotyping process, improving both accuracy and efficiency while minimizing human involvement and errors. This research leverages advanced deep learning techniques, specifically the YOLOv8 object detection framework, to enhance chromosomal analysis. From experiments, the proposed YOLO V8 model achieves a 95.2% accuracy, surpassing other models such as DCNN, CNN, and VGG-19. This work represents a significant step toward developing a more reliable and efficient diagnostic tool for detecting genetic disorders.