Classification of lung cancer from histopathology Images using a deep ensemble classifier

Singh, Onkar and Singh, Koushlendra Kumar and Das, Saikat and Akbari, Akbar Sheikh and Abd Manap, Nurulfajar (2023) Classification of lung cancer from histopathology Images using a deep ensemble classifier. In: 2023 IEEE International Conference on Imaging Systems and Techniques, IST 2023, 17 October 2023through 19 October 2023, Copenhagen.

Text Classification of lung cancer from histopathology Images using a deep ensemble classifier.pdf Restricted to Repository staff only Download (1MB)

Abstract

Lung cancer continues to be the leading disease of patient death and disability all over the world. Many metabolic abnormalities and genetic illnesses, including cancer, can be fatal. Histological diagnosis one of the important part to determine form of malignancy. Thus, one of the most significant research challenges is explore the classification of lung cancer based on histopathology images. The proposed method encompasses the ensemble learning for classification of lung cancer and its subtype which employing pre-train deep learning models (EfficientNetB3, InceptionNetV2, ResNet50, and VGG16). The ensemble model has been created utilizing VotingClassifier in soft voting mode. The ensemble model is fit using the extracted features (features_train) and training labels (y_train). The LC25000 database's images of lung tissues are utilized to train and evaluate the ensemble classifiers. Our proposed method has an average F_I score of 99.33%, recall of 99.33%, precision of 99.33%, and accuracy of 99.00% for lung cancer detection. The findings of the analysis demonstrate that our proposed approach performs noticeably better compared to existing models. This technology is more suited to handle a wide range of classification challenges than using a single classifier alone and could improve the accuracy of predictions.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Deep learning, EfficientNetB3, Histopathology images, InceptionNetV2, Lung cancer, Resnet50, VGG16
Divisions:	Faculty Of Electronics And Computer Technology And Engineering
Depositing User:	Maizatul Najwa Ahmad
Date Deposited:	16 Oct 2024 16:41
Last Modified:	16 Oct 2024 16:41
URI:	http://eprints.utem.edu.my/id/eprint/27997
Statistic Details:	View Download Statistic

Actions (login required)

View Item