Towards Intelligent Robust Detection of Anatomical Structures in Incomplete Volumetric Data

Ghesu FC, Georgescu B, Grbic S, Maier A, Hornegger J, Comaniciu D (2018)

Publication Type: Journal article

Publication year: 2018

Journal

Medical Image Analysis Elsevier

Publisher: Elsevier B.V.

Book Volume: 1

Pages Range: 203-213

Journal Issue: 48

DOI: 10.1016/j.media.2018.06.007

Abstract

Robust and fast detection of anatomical structures represents an important component of medical image analysis technologies. Current solutions for anatomy detection are based on machine learning, and are generally driven by suboptimal and exhaustive search strategies. In particular, these techniques do not effectively address cases of incomplete data, i.e., scans acquired with a partial field-of-view. We address these challenges by following a new paradigm, which reformulates the detection task to teaching an intelligent artificial agent how to actively search for an anatomical structure. Using the principles of deep reinforcement learning with multi-scale image analysis, artificial agents are taught optimal navigation paths in the scale-space representation of an image, while accounting for structures that are missing from the field-of-view. The spatial coherence of the observed anatomical landmarks is ensured using elements from statistical shape modeling and robust estimation theory. Experiments show that our solution outperforms marginal space deep learning, a powerful deep learning method, at detecting different anatomical structures without any failure. The dataset contains 5043 3D-CT volumes from over 2000 patients, totaling over 2,500,000 image slices. In particular, our solution achieves 0% false-positive and 0% false-negative rates at detecting whether the landmarks are captured in the field-of-view of the scan (excluding all border cases), with an average detection accuracy of 2.78 mm. In terms of runtime, we reduce the detection-time of the marginal space deep learning method by 20–30 times to under 40 ms, an unmatched performance for high resolution incomplete 3D-CT data.

Authors with CRIS profile

Florin-Cristian Ghesu Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung) Joachim Hornegger Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung)

Involved external institutions

Siemens AG, Healthcare Sector DE Germany (DE) Siemens AG, Sector Corporate Technology DE Germany (DE)

How to cite

APA:

Ghesu, F.-C., Georgescu, B., Grbic, S., Maier, A., Hornegger, J., & Comaniciu, D. (2018). Towards Intelligent Robust Detection of Anatomical Structures in Incomplete Volumetric Data. Medical Image Analysis, 1(48), 203-213. https://doi.org/10.1016/j.media.2018.06.007

MLA:

Ghesu, Florin-Cristian, et al. "Towards Intelligent Robust Detection of Anatomical Structures in Incomplete Volumetric Data." Medical Image Analysis 1.48 (2018): 203-213.

BibTeX: Download