BACH: Grand challenge on breast cancer histology images

Aresta, Guilherme; Araújo, Teresa; Kwok, Scotty; Chennamsetty, Sai Saketh; Safwan, Mohammed; Alex, Varghese; Marami, Bahram; Prastawa, Marcel; Chan, Monica S.M.; Donovan, Michael; Fernández, Gerardo; Zeineh, Jack; Kohl, Matthias; Walz, Christoph; Ludwig, F.; Braunewell, Stefan; Baust, Maximilian; Vu, Quoc Dang; To, Minh Nguyen Nhat; Kim, Eal; Kwak, Jin Tae; Galal, Sameh; Sánchez-Freire, Verónica; Brancati, Nadia; Frucci, Maria; Riccio, Daniel; Wang, Yaqi; Sun, Lingling; Ma, Kebo; Fang, Jiannan; Koné, Ismaël; Boulmane, Lahsen; Campilho, Aurélio; Eloy, Catarina; Polónia, António; Aguiar, Paulo

doi:10.1016/j.media.2019.05.010

Cited by 439 publications

(308 citation statements)

References 56 publications

Supporting

Mentioning

301

Contrasting

Unclassified

Order By: Relevance

“…Dataset We validate the effectiveness of CPC + MIL on the weakly supervised classification of H&E stained breast cancer image data. The ICIAR 2018 BACH dataset [15] has a total of 400 labeled images of size 2048 × 1536. We consider the binary classification of carcinoma (in situ or Invasive) vs. non-carcinoma (Nomral or Benign).…”

Section: Experiments and Resultsmentioning

confidence: 99%

Semi-supervised breast cancer histology classification using deep multiple instance learning and contrast predictive coding (Conference Presentation)

Chen

Mahmood

2020

Medical Imaging 2020: Digital Pathology

View full text Add to dashboard Cite

Convolutional neural networks can be trained to perform histology slide classification using weak annotations with multiple instance learning (MIL). However, given the paucity of labeled histology data, direct application of MIL can easily suffer from overfitting and the network is unable to learn rich feature representations due to the weak supervisory signal. We propose to overcome such limitations with a two-stage semi-supervised approach that combines the power of data-efficient self-supervised feature learning via contrastive predictive coding (CPC) and the interpretability and flexibility of regularized attention-based MIL. We apply our two-stage CPC + MIL semi-supervised pipeline to the binary classification of breast cancer histology images. Across five random splits, we report state-of-theart performance with a mean validation accuracy of 95% and an area under the ROC curve of 0.968. We further evaluate the quality of features learned via CPC relative to simple transfer learning and show that strong classification performance using CPC features can be efficiently leveraged under the MIL framework even with the feature encoder frozen.However, direct application of deep MIL to histopathogical image analysis carries many challenges. Notably, it is common to have limited number of slides available for training, especially for rare conditions. This makes it difficult for a MIL network to adequately learn useful feature representations and as a result we found that MIL tends to drastically overfit. Another challenge is the need to process a bag of many instances at a time, usually in a single batch. This makes backpropagation infeasible due to the large size of tissue microarrays and whole slides and the memory constraints of modern GPUs. As a result, patches need to be sampled, resulting in noisy bag labels [12], or the feature network needs to remain fixed during training to save memory.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Semi-supervised breast cancer histology classification using deep multiple instance learning and contrast predictive coding (Conference Presentation)

Chen

Mahmood

2020

Medical Imaging 2020: Digital Pathology

View full text Add to dashboard Cite

show abstract

“…The BreAst Cancer Histology Dataset (BACH) 3 [3] comprises over 400 labeled microscopy images with ten pixel-wise labeled and 20 non-labeled whole-slide images with an ultrahigh resolution of 42,113×62,625 pixels. The microscopy images were annotated by two expert clinicians into four classes: normal, benign, in situ carcinoma, and invasive carcinoma according to the preponderant cancer.…”

Section: A Datasetsmentioning

confidence: 99%

A Question-Centric Model for Visual Question Answering in Medical Imaging

Löfstedt

Nyholm

et al. 2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Deep learning methods have proven extremely effective at performing a variety of medical image analysis tasks. With their potential use in clinical routine, their lack of transparency has however been one of their few weak points, raising concerns regarding their behavior and failure modes. While most research to infer model behavior has focused on indirect strategies that estimate prediction uncertainties and visualize model support in the input image space, the ability to explicitly query a prediction model regarding its image content offers a more direct way to determine the behavior of trained models. To this end, we present a novel Visual Question Answering approach that allows an image to be queried by means of a written question. Experiments on a variety of medical and natural image datasets show that by fusing image and question features in a novel way, the proposed approach achieves an equal or higher accuracy compared to current methods.

show abstract

“…We used publically available datasets, BreakHis [1], and BACH [12] for our analysis. BreakHis dataset contains 7909 images of four different magnification levels divided into two major classes viz.…”

Section: A Datasetsmentioning

confidence: 99%

Breast Cancer Histopathology Image Classification and Localization using Multiple Instance Learning

Patil

Tamboli

Sundaram

et al. 2019

2019 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE)

View full text Add to dashboard Cite

Breast cancer has the highest mortality among cancers in women. Computer-aided pathology to analyze microscopic histopathology images for diagnosis with an increasing number of breast cancer patients can bring the cost and delays of diagnosis down. Deep learning in histopathology has attracted attention over the last decade of achieving state-of-the-art performance in classification and localization tasks. The convolutional neural network, a deep learning framework, provides remarkable results in tissue images analysis, but lacks in providing interpretation and reasoning behind the decisions. We aim to provide a better interpretation of classification results by providing localization on microscopic histopathology images. We frame the image classification problem as weakly supervised multiple instance learning problem where an image is collection of patches i.e. instances. Attention-based multiple instance learning (A-MIL) learns attention on the patches from the image to localize the malignant and normal regions in an image and use them to classify the image. We present classification and localization results on two publicly available BreakHIS and BACH dataset. The classification and visualization results are compared with other recent techniques. The proposed method achieves better localization results without compromising classification accuracy.

show abstract

BACH: Grand challenge on breast cancer histology images

Cited by 439 publications

References 56 publications

Semi-supervised breast cancer histology classification using deep multiple instance learning and contrast predictive coding (Conference Presentation)

Semi-supervised breast cancer histology classification using deep multiple instance learning and contrast predictive coding (Conference Presentation)

A Question-Centric Model for Visual Question Answering in Medical Imaging

Breast Cancer Histopathology Image Classification and Localization using Multiple Instance Learning

Contact Info

Product

Resources

About