Classifying Breast Cytological Images using Deep Learning Architectures

Zerouaoui, Hasnae; Idri, Ali

doi:10.5220/0010850000003123

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Owing to the lack of studies that investigate the importance of the magnification-independent approach for the binary classification of BreakHis histopathological images, this study explores the performance of transfer learning and late fusion to construct multi-scale ensembles that fuse different magnification-specific DL models for predicting the class of the slides based on the class predicted for each MF. Unlike existing studies, this paper investigated three different pretrained DL models (DenseNet 201, MobileNet v2 and Inception v3), which were selected based on their performances for the binary classification of breast pathological images over the BreakHis and Fine Needle Aspiration Cytology datasets in comparison with four other DL models (VGG 16, VGG 19, Inception ResNet v2 and ResNet 50) (Zerouaoui et al , 2022). Moreover, according to Sun and Binder (2017) who recommended that the weights should not be determined with blind or equal assignments, the current study proposes combining the scores corresponding to each magnification by averaging the weights estimated based on the accuracy of the models.…”

Section: Introductionmentioning

confidence: 99%

Binary classification of multi-magnification histopathological breast cancer images using late fusion and transfer learning

Nakach

Zerouaoui²,

Idri³

2023

DTA

View full text Add to dashboard Cite

PurposeHistopathology biopsy imaging is currently the gold standard for the diagnosis of breast cancer in clinical practice. Pathologists examine the images at various magnifications to identify the type of tumor because if only one magnification is taken into account, the decision may not be accurate. This study explores the performance of transfer learning and late fusion to construct multi-scale ensembles that fuse different magnification-specific deep learning models for the binary classification of breast tumor slides.Design/methodology/approachThree pretrained deep learning techniques (DenseNet 201, MobileNet v2 and Inception v3) were used to classify breast tumor images over the four magnification factors of the Breast Cancer Histopathological Image Classification dataset (40×, 100×, 200× and 400×). To fuse the predictions of the models trained on different magnification factors, different aggregators were used, including weighted voting and seven meta-classifiers trained on slide predictions using class labels and the probabilities assigned to each class. The best cluster of the outperforming models was chosen using the Scott–Knott statistical test, and the top models were ranked using the Borda count voting system.FindingsThis study recommends the use of transfer learning and late fusion for histopathological breast cancer image classification by constructing multi-magnification ensembles because they perform better than models trained on each magnification separately.Originality/valueThe best multi-scale ensembles outperformed state-of-the-art integrated models and achieved an accuracy mean value of 98.82 per cent, precision of 98.46 per cent, recall of 100 per cent and F1-score of 99.20 per cent.

show abstract

Section: Introductionmentioning

confidence: 99%