A deep learning pipeline for localization, differentiation, and uncertainty estimation of liver lesions using multi-phasic and multi-sequence MRI

TL;DR

This paper presents a fully-automatic deep learning pipeline for liver lesion detection and classification in multi-sequence MRI, with confidence estimation, outperforming some radiologists in certain metrics.

Contribution

It introduces a novel deep learning CAD system that localizes liver lesions and estimates diagnostic uncertainty from multi-phasic MRI scans.

Findings

Achieves a mean F1 score of 0.62, outperforming an abdominal radiologist.

Provides confidence measures that improve diagnostic metrics when focusing on high-confidence cases.

Matches the performance of a junior hepatology radiologist and approaches senior radiologist accuracy.

Abstract

Objectives: to propose a fully-automatic computer-aided diagnosis (CAD) solution for liver lesion characterization, with uncertainty estimation. Methods: we enrolled 400 patients who had either liver resection or a biopsy and was diagnosed with either hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma, or secondary metastasis, from 2006 to 2019. Each patient was scanned with T1WI, T2WI, T1WI venous phase (T2WI-V), T1WI arterial phase (T1WI-A), and DWI MRI sequences. We propose a fully-automatic deep CAD pipeline that localizes lesions from 3D MRI studies using key-slice parsing and provides a confidence measure for its diagnoses. We evaluate using five-fold cross validation and compare performance against three radiologists, including a senior hepatology radiologist, a junior hepatology radiologist and an abdominal radiologist. Results: the proposed CAD solution achieves a mean F1 score of 0.62, outperforming the abdominal radiologist (0.47), matching the junior hepatology radiologist (0.61), and underperforming the senior hepatology radiologist (0.68). The CAD system can informatively assess its diagnostic confidence, i.e., when only evaluating on the 70% most confident cases the mean f1 score and sensitivity at 80% specificity for HCC vs. others are boosted from 0.62 to 0.71 and 0.84 to 0.92, respectively. Conclusion: the proposed fully-automatic CAD solution can provide good diagnostic performance with informative confidence assessments in finding and discriminating liver lesions from MRI studies.