A New 2.5D Representation for Lymph Node Detection using Random Sets of Deep Convolutional Neural Network Observations

TL;DR

This paper introduces a novel 2.5D deep learning approach using random views for lymph node detection in CT scans, significantly improving sensitivity over previous methods.

Contribution

The study proposes a 2.5D representation with random view sampling and deep CNN classification, enhancing lymph node detection accuracy in CT images.

Findings

Achieved 70-83% sensitivity at 3 false positives per volume.

Achieved 84-90% sensitivity at 6 false positives per volume.

Outperformed previous state-of-the-art methods in lymph node detection.

Abstract

Automated Lymph Node (LN) detection is an important clinical diagnostic task but very challenging due to the low contrast of surrounding structures in Computed Tomography (CT) and to their varying sizes, poses, shapes and sparsely distributed locations. State-of-the-art studies show the performance range of 52.9% sensitivity at 3.1 false-positives per volume (FP/vol.), or 60.9% at 6.1 FP/vol. for mediastinal LN, by one-shot boosting on 3D HAAR features. In this paper, we first operate a preliminary candidate generation stage, towards 100% sensitivity at the cost of high FP levels (40 per patient), to harvest volumes of interest (VOI). Our 2.5D approach consequently decomposes any 3D VOI by resampling 2D reformatted orthogonal views N times, via scale, random translations, and rotations with respect to the VOI centroid coordinates. These random views are then used to train a deep Convolutional Neural Network (CNN) classifier. In testing, the CNN is employed to assign LN probabilities for all N random views that can be simply averaged (as a set) to compute the final classification probability per VOI. We validate the approach on two datasets: 90 CT volumes with 388 mediastinal LNs and 86 patients with 595 abdominal LNs. We achieve sensitivities of 70%/83% at 3 FP/vol. and 84%/90% at 6 FP/vol. in mediastinum and abdomen respectively, which drastically improves over the previous state-of-the-art work.