Efficient Identification of Melanocytic Nuclei in Pathology Images for Melanoma Diagnosis Using A Weakly-Supervised Deep Learning Framework

Madan Parajuli; Mohamed Shaban; Thuy Phung; IEEE

doi:10.1109/SoutheastCon48659.2022.9764004

Back

Conference proceeding

Efficient Identification of Melanocytic Nuclei in Pathology Images for Melanoma Diagnosis Using A Weakly-Supervised Deep Learning Framework

Madan Parajuli, Mohamed Shaban, Thuy Phung and IEEE

SoutheastCon 2022, pp.255-260

26/03/2022

DOI: https://doi.org/10.1109/SoutheastCon48659.2022.9764004

Abstract

Deep learning

Gradient-Weighted Class Activation Mapping (Grad-CAM)

Heating systems

Histopathology

Histopathology Images

Image resolution

Image segmentation

Melanoma

Reliability

Weakly-Supervised Learning

In this paper, we introduce a weakly-supervised deep learning framework that detects atypical melanocytic nuclei in histopathology images for the diagnosis of Melanoma with a nuclei detection accuracy of 92% surpassing the-state-of-the-art fully automated techniques. The proposed method will support pathologists in providing an objective, accurate and reliable diagnosis of Melanoma and minimizes the missed detection rate of the tumor. This will accordingly enhance the disease prognosis and improve the treatment efficacy.

Metrics

1 Record Views

Details

Title: Efficient Identification of Melanocytic Nuclei in Pathology Images for Melanoma Diagnosis Using A Weakly-Supervised Deep Learning Framework
Creators - without role: Madan Parajuli - University of South Alabama
Mohamed Shaban - University of South Alabama
Thuy Phung - University of South Alabama
IEEE
Publication Details: SoutheastCon 2022, pp.255-260
Publisher: IEEE
Identifiers: 9916739708331
Academic Unit: Islamic University of Al Madinah
Language: English
Resource Type: Conference proceeding