Phase Recognition in Contrast-Enhanced CT Scans based on Deep Learning and Random Sampling

TL;DR

This paper introduces a novel deep learning method with random sampling and majority voting for accurate, fast phase recognition in abdominal contrast-enhanced CT scans, achieving high accuracy and outperforming existing 3D methods.

Contribution

The study presents a new slice-wise classification approach using CNNs combined with random sampling and majority voting, improving speed and accuracy over prior 3D methods.

Findings

Achieved 92.09% F1-score on internal test set.

Maintained high accuracy with 76.79% and 86.94% F1-scores on external datasets.

Outperformed state-of-the-art 3D approaches in speed and accuracy.

Abstract

A fully automated system for interpreting abdominal computed tomography (CT) scans with multiple phases of contrast enhancement requires an accurate classification of the phases. This work aims at developing and validating a precise, fast multi-phase classifier to recognize three main types of contrast phases in abdominal CT scans. We propose in this study a novel method that uses a random sampling mechanism on top of deep CNNs for the phase recognition of abdominal CT scans of four different phases: non-contrast, arterial, venous, and others. The CNNs work as a slice-wise phase prediction, while the random sampling selects input slices for the CNN models. Afterward, majority voting synthesizes the slice-wise results of the CNNs, to provide the final prediction at scan level. Our classifier was trained on 271,426 slices from 830 phase-annotated CT scans, and when combined with majority voting on 30% of slices randomly chosen from each scan, achieved a mean F1-score of 92.09% on our internal test set of 358 scans. The proposed method was also evaluated on 2 external test sets: CTPAC-CCRCC (N = 242) and LiTS (N = 131), which were annotated by our experts. Although a drop in performance has been observed, the model performance remained at a high level of accuracy with a mean F1-score of 76.79% and 86.94% on CTPAC-CCRCC and LiTS datasets, respectively. Our experimental results also showed that the proposed method significantly outperformed the state-of-the-art 3D approaches while requiring less computation time for inference.