Classification of breast cancer histology images using Convolutional Neural Networks

By Teresa Araújo, Guilherme Aresta, E. Castro, José Rouco, Paulo Aguiar, C. Eloy, A. Polónia, Aurélio J. C. Campilho. PLoS ONE, 2017

914 citations recorded by the source corpus.

Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on the final diagnosis. Computer-aided Diagnosis systems contribute to reduce the cost and increase the efficiency of this process. Conventional classification approaches rely on feature extraction methods designed for a specific problem based on field-knowledge. To overcome the many difficulties of the feature-based approaches, deep learning methods are becoming important alternatives. A method for the classification of hematoxylin and eosin stained breast biopsy images using Convolutional Neural Networks (CNNs) is proposed. Images are classified in four classes, normal tissue, benign lesion, in situ carcinoma and invasive carcinoma, and in two classes, carcinoma and non-carcinoma. The architecture of the network is designed to retrieve information at different scales, including both nuclei and overall tissue organization. This design allows the extension of the proposed system to whole-slide histology images. The features extracted by the CNN are also used for training a Support Vector Machine classifier. Accuracies of 77.8% for four class and 83.3% for carcinoma/non-carcinoma are achieved. The sensitivity of our method for cancer cases is 95.6%.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/61244d24d769fb6c9626becd58204e766c059513

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Emerging role of deep learning‐based artificial intelligence in tumor pathology (2020, methodology): “Diagnosis Carcinoma/Non-carcinoma Accuracy: 83.3% [18] Normal/Benign/Carcinoma in situ/Invasive carcinoma Accuracy: 77.8% [18] Non-malignant/Malignant AUC: 0.962 [19] Benign/Ductal carcinoma in situ/Invasive ductal carcinoma Accuracy: 81.3% [19] Invasive cancer/Benign lesion based on both tumor…”
Understanding Deep Learning Techniques for Image Segmentation (2019, neutral): “Natural Berkeley Segmentation Dataset [140] Scenes PASCAL VOC [54] Stanford Background Dataset [72] Microsoft COCO [122] MIT Scene parsing data(ADE20K) [222, 223] Semantic Boundaries Dataset [75] Microsoft Research Cambridge Object Recognition Image Database (MSRC) [188] Video Densely Annotated Vide”
BACH: Grand challenge on breast cancer histology images (2018, methodology): “[10], which reported an overall 4-class accuracy of 77.”
Causability and explainability of artificial intelligence in medicine (2019, background): “We propose to extract from both benign and malign single cell nuclei and to classify chromatin organization (Araujo et al., 2017) within the nuclei to correlate these to histopathological features and molecular markers.”
Brain Tumor Detection Based on Deep Learning Approaches and Magnetic Resonance Imaging (2023, methodology): “Another CNN-based architecture was presented for breast cancer picture categorization [33].”
Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural Network (2018, methodology): “are considered for testing, per the work in [17].”
Deep learning-based breast cancer classification through medical imaging modalities: state of the art and research challenges (2019, methodology): “Therefore, many researchers employed HP images to classify BrC multi-class accurately (Abdullah-Al et al. 2017; Araujo et al. 2017; Bardou et al. 2018; Bayramoglu et al. 2017; Bejnordi et al. 2017b; Cao et al. 2016; Chang et al. 2017; Feng et al. 2018; Gandomkar et al. 2018; Han et al. 2017b;…”
The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis (2020, methodology): “This post-processing strategy achieved a 6% improvement in accuracy compared to the baseline score [116].”
Breast Tumor Cellularity Assessment using Deep Neural Networks (2019, methodology): “As such, they have successfully been utilized for digital pathology image analysis and have demonstrated great potential for improving breast cancer diagnostics [38, 4, 5, 32].”