Deep Volumetric Universal Lesion Detection using Light-Weight Pseudo 3D Convolution and Surface Point Regression

TL;DR

This paper introduces a lightweight, deep learning framework for 3D lesion detection in CT scans that leverages pseudo 3D convolutions and surface point regression, achieving state-of-the-art results on large and small datasets.

Contribution

It presents a novel anchor-free, one-stage VULD framework combining P3DC operators and SPR for improved 3D lesion detection from CT scans.

Findings

Achieved state-of-the-art performance on NIH DeepLesion dataset.

Demonstrated effective generalization on in-house liver tumor dataset.

Performed well on both large-scale and small-sized tumor detection.

Abstract

Identifying, measuring and reporting lesions accurately and comprehensively from patient CT scans are important yet time-consuming procedures for physicians. Computer-aided lesion/significant-findings detection techniques are at the core of medical imaging, which remain very challenging due to the tremendously large variability of lesion appearance, location and size distributions in 3D imaging. In this work, we propose a novel deep anchor-free one-stage VULD framework that incorporates (1) P3DC operators to recycle the architectural configurations and pre-trained weights from the off-the-shelf 2D networks, especially ones with large capacities to cope with data variance, and (2) a new SPR method to effectively regress the 3D lesion spatial extents by pinpointing their representative key points on lesion surfaces. Experimental validations are first conducted on the public large-scale NIH DeepLesion dataset where our proposed method delivers new state-of-the-art quantitative performance. We also test VULD on our in-house dataset for liver tumor detection. VULD generalizes well in both large-scale and small-sized tumor datasets in CT imaging.