Deep Learning Methods and Applications for Region of Interest Detection in Dermoscopic Images

TL;DR

This paper explores deep learning architectures for detecting skin lesion regions in dermoscopic images, compares their performance with segmentation methods, and develops a smartphone app for real-time diagnosis, aiming to improve skin cancer detection accuracy.

Contribution

It introduces the use of Faster R-CNN and SSD architectures for ROI detection in dermoscopic images and integrates data augmentation to enhance segmentation performance.

Findings

Deep learning models effectively detect skin lesion ROIs.

ROI detection improves the accuracy of skin lesion segmentation.

The smartphone app enables real-time skin lesion detection.

Abstract

Rapid growth in the development of medical imaging analysis technology has been propelled by the great interest in improving computer-aided diagnosis and detection (CAD) systems for three popular image visualization tasks: classification, segmentation, and Region of Interest (ROI) detection. However, a limited number of datasets with ground truth annotations are available for developing segmentation and ROI detection of lesions, as expert annotations are laborious and expensive. Detecting the ROI is vital to locate lesions accurately. In this paper, we propose the use of two deep object detection meta-architectures (Faster R-CNN Inception-V2 and SSD Inception-V2) to develop robust ROI detection of skin lesions in dermoscopic datasets (2017 ISIC Challenge, PH2, and HAM10000), and compared the performance with state-of-the-art segmentation algorithm (DeeplabV3+). To further demonstrate the potential of our work, we built a smartphone application for real-time automated detection of skin lesions based on this methodology. In addition, we developed an automated natural data-augmentation method from ROI detection to produce augmented copies of dermoscopic images, as a pre-processing step in the segmentation of skin lesions to further improve the performance of the current state-of-the-art deep learning algorithm. Our proposed ROI detection has the potential to more appropriately streamline dermatology referrals and reduce unnecessary biopsies in the diagnosis of skin cancer.