Universal Lesion Detection in CT Scans using Neural Network Ensembles

TL;DR

This paper introduces an ensemble of neural networks for detecting lesions in CT scans, achieving high sensitivity and precision, which enhances clinical lesion detection and sizing accuracy.

Contribution

The study develops a neural network ensemble with a bounding box fusion technique to improve lesion detection accuracy in CT scans, outperforming existing methods.

Findings

Achieved 65.17% precision and 91.67% sensitivity at 4 false positives per image.

Improved lesion detection accuracy over current state-of-the-art methods.

Demonstrated robustness in detecting small and challenging lesions.

Abstract

In clinical practice, radiologists are reliant on the lesion size when distinguishing metastatic from non-metastatic lesions. A prerequisite for lesion sizing is their detection, as it promotes the downstream assessment of tumor spread. However, lesions vary in their size and appearance in CT scans, and radiologists often miss small lesions during a busy clinical day. To overcome these challenges, we propose the use of state-of-the-art detection neural networks to flag suspicious lesions present in the NIH DeepLesion dataset for sizing. Additionally, we incorporate a bounding box fusion technique to minimize false positives (FP) and improve detection accuracy. Finally, to resemble clinical usage, we constructed an ensemble of the best detection models to localize lesions for sizing with a precision of 65.17% and sensitivity of 91.67% at 4 FP per image. Our results improve upon or maintain the performance of current state-of-the-art methods for lesion detection in challenging CT scans.