MPBD-LSTM: A Predictive Model for Colorectal Liver Metastases Using Time Series Multi-phase Contrast-Enhanced CT Scans

TL;DR

This paper introduces MPBD-LSTM, a novel deep learning model utilizing multi-plane 3D bi-directional LSTM for early detection of colorectal liver metastases from complex multi-phase CT scans, achieving promising but improvable results.

Contribution

The paper develops a new dataset and proposes MPBD-LSTM, a multi-plane 3D bi-directional LSTM model, to handle the five-dimensional data for early CRLM prediction.

Findings

MPBD-LSTM achieved an AUC of 0.79.

Multi-plane architecture outperformed other models.

Significant room for improvement remains.

Abstract

Colorectal cancer is a prevalent form of cancer, and many patients develop colorectal cancer liver metastasis (CRLM) as a result. Early detection of CRLM is critical for improving survival rates. Radiologists usually rely on a series of multi-phase contrast-enhanced computed tomography (CECT) scans done during follow-up visits to perform early detection of the potential CRLM. These scans form unique five-dimensional data (time, phase, and axial, sagittal, and coronal planes in 3D CT). Most of the existing deep learning models can readily handle four-dimensional data (e.g., time-series 3D CT images) and it is not clear how well they can be extended to handle the additional dimension of phase. In this paper, we build a dataset of time-series CECT scans to aid in the early diagnosis of CRLM, and build upon state-of-the-art deep learning techniques to evaluate how to best predict CRLM. Our experimental results show that a multi-plane architecture based on 3D bi-directional LSTM, which we call MPBD-LSTM, works best, achieving an area under curve (AUC) of 0.79. On the other hand, analysis of the results shows that there is still great room for further improvement.