AUTHOR=Imran Muhammad , Islam Tiwana Mohsin , Mohsan Mashood Mohammad , Alghamdi Norah Saleh , Akram Muhammad Usman 

TITLE=Transformer-based framework for multi-class segmentation of skin cancer from histopathology images

JOURNAL=Frontiers in Medicine

VOLUME=Volume 11 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2024.1380405

DOI=10.3389/fmed.2024.1380405

ISSN=2296-858X

ABSTRACT=This work is an attempt to automate the segmentation of the most occurring non-melanoma skin cancer using a transformer-based deep learning technique applied to histopathology skin images. Since non-melanoma skin cancer comprising Basal cell carcinoma (BCC), Squamous cell carcinoma (SCC) and Intraepidermal carcinoma (IEC) have the highest incidence rate among skin cancers therefore, successful implementation of the proposed method implies that most skin cancer segmentation related tasks can be automated thus providing swift diagnosis and early detection. This work may address the issue of the limited number of subject experts and help in mitigating the parity of health services between urban centres and remote areas. In this research, we propose a transformer-based model for the segmentation of histopathology images not only into inflammation and cancers like BCC, SCC, and IEC but also to identify skin tissues and boundaries that are important in decision-making. Accurate segmentation of these tissue types will eventually lead to accurate detection and classification of non-melanoma skin cancer.The segmentation according to tissue types and their visual representation before classification enhances the trust of pathologists and doctors being relatable to how most pathologists approach this problem. The visualization of the confidence of the model in its prediction through uncertainty maps is also what distinguishes this work from most deep learning methods. Highly accurate segmentation and visual representation of histopathology images according to tissue types by the proposed system implies that the system can be used for skin-related routine pathology tasks including cancer and other anomaly detection, their classification, and measurement of surgical margins in case of cancer cases. The application of our proposed segmentation system demonstrated excellent performance with an F1 score of 0.908, mean intersection over union (mIoU) of 0.653, and average accuracy of 83.1% advocating that the system can be used as a decision support system successfully and has the potential of subsequently maturing into a fully automated system.