Unsupervised Hybrid framework for ANomaly Detection (HAND) -- applied to Screening Mammogram

TL;DR

This paper introduces HAND, an unsupervised hybrid CNN-transformer framework for detecting out-of-distribution anomalies in mammogram screening, improving accuracy with synthetic data and adversarial training.

Contribution

The novel HAND model combines CNNs and transformers with synthetic OOD samples and a parallel discriminator, advancing unsupervised OOD detection in mammography.

Findings

HAND outperforms existing encoder and GAN-based methods.

It surpasses hybrid CNN+transformer baselines in OOD detection.

The model provides efficient domain-specific quality checks.

Abstract

Out-of-distribution (OOD) detection is crucial for enhancing the generalization of AI models used in mammogram screening. Given the challenge of limited prior knowledge about OOD samples in external datasets, unsupervised generative learning is a preferable solution which trains the model to discern the normal characteristics of in-distribution (ID) data. The hypothesis is that during inference, the model aims to reconstruct ID samples accurately, while OOD samples exhibit poorer reconstruction due to their divergence from normality. Inspired by state-of-the-art (SOTA) hybrid architectures combining CNNs and transformers, we developed a novel backbone - HAND, for detecting OOD from large-scale digital screening mammogram studies. To boost the learning efficiency, we incorporated synthetic OOD samples and a parallel discriminator in the latent space to distinguish between ID and OOD samples. Gradient reversal to the OOD reconstruction loss penalizes the model for learning OOD reconstructions. An anomaly score is computed by weighting the reconstruction and discriminator loss. On internal RSNA mammogram held-out test and external Mayo clinic hand-curated dataset, the proposed HAND model outperformed encoder-based and GAN-based baselines, and interestingly, it also outperformed the hybrid CNN+transformer baselines. Therefore, the proposed HAND pipeline offers an automated efficient computational solution for domain-specific quality checks in external screening mammograms, yielding actionable insights without direct exposure to the private medical imaging data.