Longitudinal detection of radiological abnormalities with time-modulated LSTM

TL;DR

This paper introduces a time-modulated LSTM model that leverages sequential radiological data and reports to improve abnormality detection in chest x-rays, outperforming traditional methods by accounting for irregular sampling intervals.

Contribution

The study presents a novel modification to LSTM architecture that explicitly incorporates time intervals between observations, enhancing classification accuracy in medical imaging sequences.

Findings

Improved detection of cardiomegaly, consolidation, pleural effusion, and hiatus hernia.

Time-aware LSTM outperforms standard LSTM on simulated and real datasets.

Explicit modeling of time intervals boosts performance in irregularly sampled medical data.

Abstract

Convolutional neural networks (CNNs) have been successfully employed in recent years for the detection of radiological abnormalities in medical images such as plain x-rays. To date, most studies use CNNs on individual examinations in isolation and discard previously available clinical information. In this study we set out to explore whether Long-Short-Term-Memory networks (LSTMs) can be used to improve classification performance when modelling the entire sequence of radiographs that may be available for a given patient, including their reports. A limitation of traditional LSTMs, though, is that they implicitly assume equally-spaced observations, whereas the radiological exams are event-based, and therefore irregularly sampled. Using both a simulated dataset and a large-scale chest x-ray dataset, we demonstrate that a simple modification of the LSTM architecture, which explicitly takes into account the time lag between consecutive observations, can boost classification performance. Our empirical results demonstrate improved detection of commonly reported abnormalities on chest x-rays such as cardiomegaly, consolidation, pleural effusion and hiatus hernia.