Enhancing Mobile Acute Lymphoblastic Cancer Detection: Transfer Learning from YOLOv9 to TensorFlow for Real-Time Applications

Abstract

The detection of acute lymphoblastic cancer (ALL) is critical for timely diagnosis and treatment. In this study, we propose a novel approach to enhance ALL detection using transfer learning techniques from YOLOv9 to TensorFlow, facilitating real-time application on mobile devices. Leveraging the robustness of YOLOv9 and the versatility of TensorFlow, we fine-tune the pre-trained model to optimize performance for ALL detection. The adapted model is then integrated into a mobile application, enabling users to perform real-time ALL detection using their smartphones. Our results demonstrate the efficacy of the proposed system in accurately identifying ALL cells, with a detection rate of 98% in one scenario and 100% in another. This research represents a significant step forward in leveraging advanced computer vision technologies for mobile healthcare applications, ultimately improving patient outcomes and healthcare accessibility.

Keywords

• acute lymphoblastic cancer detection
• transfer learning
• yolov9
• tensorflow
• mobile application
• real-time detection