Cancer image classification based on DenseNet model

TL;DR

This paper introduces a DenseNet-based model for metastatic cancer image classification, demonstrating improved accuracy over classical methods on the PCam dataset, with insights into data augmentation and training dynamics.

Contribution

The paper proposes a novel DenseNet Block model specifically designed for small patch metastatic cancer detection, outperforming traditional models like ResNet34 and VGG19.

Findings

Model outperforms ResNet34 and VGG19

Data augmentation improves model robustness

Training loss correlates with batch processing

Abstract

Computer-aided diagnosis establishes methods for robust assessment of medical image-based examination. Image processing introduced a promising strategy to facilitate disease classification and detection while diminishing unnecessary expenses. In this paper, we propose a novel metastatic cancer image classification model based on DenseNet Block, which can effectively identify metastatic cancer in small image patches taken from larger digital pathology scans. We evaluate the proposed approach to the slightly modified version of the PatchCamelyon (PCam) benchmark dataset. The dataset is the slightly modified version of the PatchCamelyon (PCam) benchmark dataset provided by Kaggle competition, which packs the clinically-relevant task of metastasis detection into a straight-forward binary image classification task. The experiments indicated that our model outperformed other classical methods like Resnet34, Vgg19. Moreover, we also conducted data augmentation experiment and study the relationship between Batches processed and loss value during the training and validation process.