Transfer learning for cancer diagnosis in histopathological images

TL;DR

This study compares 14 pre-trained ImageNet models for histopathologic cancer detection, analyzing their performance in terms of precision and recall, and demonstrates that transfer learning accelerates model convergence.

Contribution

It provides a comprehensive comparison of various transfer learning architectures on a cancer detection dataset, highlighting their strengths and practical applications.

Findings

Densenet161 achieves high precision

Resnet101 has high recall

Transfer learning speeds up model convergence

Abstract

Transfer learning allows us to exploit knowledge gained from one task to assist in solving another but relevant task. In modern computer vision research, the question is which architecture performs better for a given dataset. In this paper, we compare the performance of 14 pre-trained ImageNet models on the histopathologic cancer detection dataset, where each model has been configured as a naive model, feature extractor model, or fine-tuned model. Densenet161 has been shown to have high precision whilst Resnet101 has a high recall. A high precision model is suitable to be used when follow-up examination cost is high, whilst low precision but a high recall/sensitivity model can be used when the cost of follow-up examination is low. Results also show that transfer learning helps to converge a model faster.