A novel online Variance Based Instance Selection (VBIS) method for efficient atypicality detection in chest radiographs

Mohammad Alzubaidi, Vineeth Balasubramanian, Ameet Patel, Sethuraman Panchanathan, John A. Black

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

1 Scopus citations


Chest radiographs are complex, heterogeneous medical images that depict many different types of tissues, and many different types of abnormalities. A radiologist develops a sense of what visual textures are typical for each anatomic region within chest radiographs by viewing a large set of "normal" radiographs over a period of years. As a result, an expert radiologist is able to readily detect atypical features. In our previous research, we modeled this type of learning by (1) collecting a large set of "normal" chest radiographs, (2) extracting local textural and contour features from anatomical regions within these radiographs, in the form of high-dimensional feature vectors, (3) using a distance-based transductive machine learning method to learn what it typical for each anatomical region, and (4) computing atypicality scores for the anatomical regions in test radiographs. That research demonstrated that the transductive One-Nearest-Neighbor (1NN) method was effective for identifying atypical regions in chest radiographs. However, the large set of training instances (and the need to compute a distance to each of these instances in a high dimensional space) made the transductive method computationally expensive. This paper discusses a novel online Variance Based Instance Selection (VBIS) method for use with the Nearest Neighbor classifier, that (1) substantially reduced the computational cost of the transductive 1NN method, while maintaining a high level of effectiveness in identifying regions of chest radiographs with atypical content, and (2) allowed the incremental incorporation of training data from new informative chest radiographs as they are encountered in day-to-day clinical work.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2012
Subtitle of host publicationImage Processing
ISBN (Print)9780819489630
StatePublished - 2012
Externally publishedYes
EventMedical Imaging 2012: Image Processing - San Diego, CA, United States
Duration: Feb 6 2012Feb 9 2012

Publication series

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


OtherMedical Imaging 2012: Image Processing
Country/TerritoryUnited States
CitySan Diego, CA


  • Anomaly detection
  • Atypicality detection
  • Chest x-rays
  • Computer aided diagnosis
  • Instance selection
  • Machine learning
  • Nearest neighbor
  • Radiology training

ASJC Scopus subject areas

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


Dive into the research topics of 'A novel online Variance Based Instance Selection (VBIS) method for efficient atypicality detection in chest radiographs'. Together they form a unique fingerprint.

Cite this