# Approximating Intermediate Feature Maps of Self-Supervised Convolution Neural Network to Learn Hard Positive Representations in Chest Radiography

## TL;DR

This paper introduces a new loss function to improve contrastive learning in chest X-ray images by focusing on positive representations without extra data augmentation.

## Contribution

The novel IFA loss enhances contrastive learning by approximating intermediate features of positive pairs without additional augmentations.

## Key findings

- IFA loss improves performance in classification and object detection tasks.
- IFA loss helps overcome data imbalance and scarcity in medical imaging tasks.
- IFA loss serves as an effective perceptual loss encoder for GAN inversion.

## Abstract

Recent advances in contrastive learning have significantly improved the performance of deep learning models. In contrastive learning of medical images, dealing with positive representation is sometimes difficult because some strong augmentation techniques can disrupt contrastive learning owing to the subtle differences between other standardized CXRs compared to augmented positive pairs; therefore, additional efforts are required. In this study, we propose intermediate feature approximation (IFA) loss, which improves the performance of contrastive convolutional neural networks by focusing more on positive representations of CXRs without additional augmentations. The IFA loss encourages the feature maps of a query image and its positive pair to resemble each other by maximizing the cosine similarity between the intermediate feature outputs of the original data and the positive pairs. Therefore, we used the InfoNCE loss, which is commonly used loss to address negative representations, and the IFA loss, which addresses positive representations, together to improve the contrastive network. We evaluated the performance of the network using various downstream tasks, including classification, object detection, and a generative adversarial network (GAN) inversion task. The downstream task results demonstrated that IFA loss can improve the performance of effectively overcoming data imbalance and data scarcity; furthermore, it can serve as a perceptual loss encoder for GAN inversion. In addition, we have made our model publicly available to facilitate access and encourage further research and collaboration in the field.

The online version contains supplementary material available at 10.1007/s10278-024-01032-x.