Knowledge-driven AI-generated data for accurate and interpretable breast ultrasound diagnoses

TL;DR

This paper introduces TAILOR, a knowledge-driven generative pipeline that creates synthetic breast ultrasound data to improve diagnosis accuracy, especially for rare cases, outperforming radiologists in specificity and interpretability.

Contribution

The study presents a novel knowledge-driven generative model that produces tailored synthetic data to enhance deep learning diagnosis of rare breast ultrasound cases.

Findings

Model outperforms nine radiologists in specificity by 33.5%.

Generated data significantly improves diagnosis accuracy for rare cases.

Model excels in diagnosing ductal carcinoma in situ (DCIS).

Abstract

Data-driven deep learning models have shown great capabilities to assist radiologists in breast ultrasound (US) diagnoses. However, their effectiveness is limited by the long-tail distribution of training data, which leads to inaccuracies in rare cases. In this study, we address a long-standing challenge of improving the diagnostic model performance on rare cases using long-tailed data. Specifically, we introduce a pipeline, TAILOR, that builds a knowledge-driven generative model to produce tailored synthetic data. The generative model, using 3,749 lesions as source data, can generate millions of breast-US images, especially for error-prone rare cases. The generated data can be further used to build a diagnostic model for accurate and interpretable diagnoses. In the prospective external evaluation, our diagnostic model outperforms the average performance of nine radiologists by 33.5% in specificity with the same sensitivity, improving their performance by providing predictions with an interpretable decision-making process. Moreover, on ductal carcinoma in situ (DCIS), our diagnostic model outperforms all radiologists by a large margin, with only 34 DCIS lesions in the source data. We believe that TAILOR can potentially be extended to various diseases and imaging modalities.