Skip to main content

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

Wednesday, September 24, 2014 — Poster Session IV

10:00 a.m. –12:00 p.m.

FAES Academic Center



* FARE Award Winner


  • HR Roth
  • L Lu
  • A Seff
  • KM Cherry
  • J Hoffman
  • S Wang
  • J Liu
  • E Turkbey
  • RM Summers


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. 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 averaged 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. in mediastinum and abdomen respectively, which drastically improves over the previous state-of-the-art work.

back to top