Deep Implicit Statistical Shape Models for 3D Medical Image Delineation

Authors

  • Ashwin Raju University of Texas at Arlington, Arlington, TX, USA
  • Shun Miao PAII Inc, Bethesda, MD, USA
  • Dakai Jin PAII Inc, Bethesda, MD, USA
  • Le Lu PAII Inc, Bethesda, MD, USA
  • Junzhou Huang University of Texas at Arlington, Arlington, TX, USA
  • Adam P. Harrison PAII Inc, Bethesda, MD, USA

DOI:

https://doi.org/10.1609/aaai.v36i2.20110

Keywords:

Computer Vision (CV)

Abstract

3D delineation of anatomical structures is a cardinal goal in medical imaging analysis. Prior to deep learning, statistical shape models (SSMs) that imposed anatomical constraints and produced high quality surfaces were a core technology. Today’s fully-convolutional networks (FCNs), while dominant, do not offer these capabilities. We present deep implicit statistical shape models (DISSMs), a new approach that marries the representation power of deep networks with the benefits of SSMs. DISSMs use an implicit representation to produce compact and descriptive deep surface embeddings that permit statistical models of anatomical variance. To reliably fit anatomically plausible shapes to an image, we introduce a novel rigid and non-rigid pose estimation pipeline that is modelled as a Markov decision process (MDP). Intra-dataset experiments on the task of pathological liver segmentation demonstrate that DISSMs can perform more robustly than four leading FCN models, including nnU-Net + an adversarial prior: reducing the mean Hausdorff distance (HD) by 7.5-14.3 mm and improving the worst case Dice-Sørensen coefficient (DSC) by 1.2-2.3%. More critically, cross-dataset experiments on an external and highly challenging clinical dataset demonstrate that DISSMs improve the mean DSC and HD by 2.1-5.9% and 9.9-24.5 mm, respectively, and the worst-case DSC by 5.4-7.3%. Supplemental validation on a highly challenging and low-contrast larynx dataset further demonstrate DISSM’s improvements. These improvements are over and above any benefits from representing delineations with high-quality surfaces.

Downloads

Published

2022-06-28

How to Cite

Raju, A., Miao, S., Jin, D., Lu, L., Huang, J., & Harrison, A. P. (2022). Deep Implicit Statistical Shape Models for 3D Medical Image Delineation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(2), 2135-2143. https://doi.org/10.1609/aaai.v36i2.20110

Issue

Section

AAAI Technical Track on Computer Vision II