Classification of lung cancer from histopathology Images using a deep ensemble classifier
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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2023
|
| Online Access: | http://eprints.utem.edu.my/id/eprint/27997/1/Classification%20of%20lung%20cancer%20from%20histopathology%20Images%20using%20a%20deep%20ensemble%20classifier.pdf http://eprints.utem.edu.my/id/eprint/27997/ https://eprints.leedsbeckett.ac.uk/id/eprint/10472/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | 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. |
|---|