Parsing radiographs by integrating landmark set detection and multi-object active appearance models

Albert Montillo, Qi Song, Xiaoming Liu, James V. Miller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

This work addresses the challenging problem of parsing 2D radiographs into salient anatomical regions such as the left and right lungs and the heart. We propose the integration of an automatic detection of a constellation of landmarks via rejection cascade classifiers and a learned geometric constellation subset detector model with a multi-object active appearance model (MO-AAM) initialized by the detected landmark constellation subset. Our main contribution is twofold. First, we propose a recovery method for false positive and negative landmarks which allows to handle extreme ranges of anatomical and pathological variability. Specifically we (1) recover false negative (missing) landmarks through the consensus of inferences from subsets of the detected landmarks, and (2) choose one from multiple false positives for the same landmark by learning Gaussian distributions for the relative location of each landmark. Second, we train a MO-AAM using the true landmarks for the detectors and during test, initialize the model using the detected landmarks. Our model fitting allows simultaneous localization of multiple regions by encoding the shape and appearance information of multiple objects in a single model. The integration of landmark detection method and MO-AAM reduces mean distance error of the detected landmarks from 20.0mm to 12.6mm. We assess our method using a database of scout CT scans from 80 subjects with widely varying pathology.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2013
Subtitle of host publicationImage Processing
DOIs
StatePublished - Jun 3 2013
EventMedical Imaging 2013: Image Processing - Lake Buena Vista, FL, United States
Duration: Feb 10 2013Feb 12 2013

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume8669
ISSN (Print)1605-7422

Other

OtherMedical Imaging 2013: Image Processing
CountryUnited States
CityLake Buena Vista, FL
Period2/10/132/12/13

Keywords

  • Active appearance model
  • Automatic landmark localization
  • Image parsing
  • Organ localization
  • Radiograph
  • Rejection cascade

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'Parsing radiographs by integrating landmark set detection and multi-object active appearance models'. Together they form a unique fingerprint.

  • Cite this

    Montillo, A., Song, Q., Liu, X., & Miller, J. V. (2013). Parsing radiographs by integrating landmark set detection and multi-object active appearance models. In Medical Imaging 2013: Image Processing [86690H] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 8669). https://doi.org/10.1117/12.2007138