Improved Classification of Cancerous Histopathology Images using Color Channel Separation and Deep Learning

Abstract

Oral cancer is ranked second most diagnosed cancer among Indian population and ranked sixth all around the world. Oral cancer is one of the deadliest cancers with high mortality rate and very less 5-year survival rates even after treatment. It becomes necessary to detect oral malignancies as early as possible so that timely treatment may be given to patient and increase the survival chances. In recent years deep learning based frameworks have been proposed by many researchers that can detect malignancies from medical images. In this paper we have proposed a deep learning-based framework which detects oral cancer from histopathology images very efficiently. We have designed our model to split the color channels and extract deep features from these individual channels rather than single combined channel with the help of Efficient NET B3. These features from different channels are fused by using feature fusion module designed as a layer and placed before dense layers of Efficient NET. The experiments were performed on our own dataset collected from hospitals. We also performed experiments of BreakHis, and ICML datasets to evaluate our model. The results produced by our model are very good as compared to previously reported results.

Ranking Loss and Sequestering Learning for Reducing Image Search Bias in Histopathology

“…Later, the EfficientNet models have been commonly used in several studies for medical image processing. Gupta and Manhas [50] in 2021 proposed a model based on EfficientNet-B3 topology that can efficiently detect oral cancer in histopathology images. Sun et al [51] proposed a model based on the EfficientNet-B6 architecture for histopathologic cancer detection.…”

Sailfish Optimization with Deep Learning Based Oral Cancer Classification Model

“…Eventually, machine learning (ML) technique (shallow learning) has been reported to provide better prognostication of OC. Note that, the usage of ML technique has been reported to offer a better prognostication when compared to the conventional statistical analysis [7]. The ML technique can exhibit promising outcomes since it can discern the complicated relations among the variables included in the dataset [8].…”

Hyperparameter Tuning Bidirectional Gated Recurrent Unit Model for Oral Cancer Classification

“…The authors in the literature [13] presented a Deep Learning (DL)-based structure that detects oral cancer using histopathology images in a highly effective manner. In this method, the color channel was split, deep features were extracted and categorized under individual channels instead of single integrated channel using EfficientNetB3.…”