Bag of Visual Words (BoVW) with Deep Features -- Patch Classification Model for Limited Dataset of Breast Tumours

TL;DR

This paper introduces a hybrid deep learning approach combining CNN features with Bag of Visual Words to improve patch classification of breast tumor images, especially under limited dataset conditions.

Contribution

It proposes a novel integration of BoVW with CNN features for enhanced patch-level classification in breast tumor images, addressing annotation limitations.

Findings

Outperforms ResNet50, DenseNet169, and InceptionV3 on BACH-2018 dataset.

Uses BoVW as a feature selector to improve discriminative power.

Provides an end-to-end pipeline without post-processing.

Abstract

Currently, the computational complexity limits the training of high resolution gigapixel images using Convolutional Neural Networks. Therefore, such images are divided into patches or tiles. Since, these high resolution patches are encoded with discriminative information therefore; CNNs are trained on these patches to perform patch-level predictions. However, the problem with patch-level prediction is that pathologist generally annotates at image-level and not at patch level. Due to this limitation most of the patches may not contain enough class-relevant features. Through this work, we tried to incorporate patch descriptive capability within the deep framework by using Bag of Visual Words (BoVW) as a kind of regularisation to improve generalizability. Using this hypothesis, we aim to build a patch based classifier to discriminate between four classes of breast biopsy image patches (normal, benign, \textit{In situ} carcinoma, invasive carcinoma). The task is to incorporate quality deep features using CNN to describe relevant information in the images while simultaneously discarding irrelevant information using Bag of Visual Words (BoVW). The proposed method passes patches obtained from WSI and microscopy images through pre-trained CNN to extract features. BoVW is used as a feature selector to select most discriminative features among the CNN features. Finally, the selected feature sets are classified as one of the four classes. The hybrid model provides flexibility in terms of choice of pre-trained models for feature extraction. The pipeline is end-to-end since it does not require post processing of patch predictions to select discriminative patches. We compared our observations with state-of-the-art methods like ResNet50, DenseNet169, and InceptionV3 on the BACH-2018 challenge dataset. Our proposed method shows better performance than all the three methods.