Back to Search
Start Over
Semi-automatic classification of textures in thoracic CT scans
- Source :
- Physics in Medicine and Biology, 61(16), 5906. IOP Publishing Ltd., Kockelkorn, T T J P, de Jong, P A, Schaefer-Prokop, C M, Wittenberg, R, Tiehuis, A M, Gietema, H A, Grutters, J C, Viergever, M A & van Ginneken, B 2016, ' Semi-automatic classification of textures in thoracic CT scans ', Physics in Medicine and Biology, vol. 61, no. 16, pp. 5906-5924 . https://doi.org/10.1088/0031-9155/61/16/5906, Physics in Medicine and Biology, 61(16), 5906-5924. IOP Publishing Ltd., Physics in Medicine and Biology, 61, 5906-5924, Physics in Medicine and Biology, 61, 16, pp. 5906-5924
- Publication Year :
- 2016
-
Abstract
- Contains fulltext : 171478.pdf (Publisher’s version ) (Open Access) The textural patterns in the lung parenchyma, as visible on computed tomography (CT) scans, are essential to make a correct diagnosis in interstitial lung disease. We developed one automatic and two interactive protocols for classification of normal and seven types of abnormal lung textures. Lungs were segmented and subdivided into volumes of interest (VOIs) with homogeneous texture using a clustering approach. In the automatic protocol, VOIs were classified automatically by an extra-trees classifier that was trained using annotations of VOIs from other CT scans. In the interactive protocols, an observer iteratively trained an extra-trees classifier to distinguish the different textures, by correcting mistakes the classifier makes in a slice-by-slice manner. The difference between the two interactive methods was whether or not training data from previously annotated scans was used in classification of the first slice. The protocols were compared in terms of the percentages of VOIs that observers needed to relabel. Validation experiments were carried out using software that simulated observer behavior. In the automatic classification protocol, observers needed to relabel on average 58\% of the VOIs. During interactive annotation without the use of previous training data, the average percentage of relabeled VOIs decreased from 64\% for the first slice to 13\% for the second half of the scan. Overall, 21\% of the VOIs were relabeled. When previous training data was available, the average overall percentage of VOIs requiring relabeling was 20\%, decreasing from 56\% in the first slice to 13\% in the second half of the scan.
- Subjects :
- Adult
Lung Diseases
Male
Computed tomography
Pattern Recognition, Automated
030218 nuclear medicine & medical imaging
Young Adult
03 medical and health sciences
0302 clinical medicine
Image Processing, Computer-Assisted
Journal Article
Humans
Medicine
Thoracic ct
Radiology, Nuclear Medicine and imaging
Computer vision
Cluster analysis
Aged
Retrospective Studies
Medicine(all)
Training set
medicine.diagnostic_test
Radiological and Ultrasound Technology
business.industry
Supervised learning
Middle Aged
Homogeneous
Radiology Nuclear Medicine and imaging
030220 oncology & carcinogenesis
Female
Radiography, Thoracic
Artificial intelligence
Semi automatic
Tomography, X-Ray Computed
business
Classifier (UML)
Software
Rare cancers Radboud Institute for Health Sciences [Radboudumc 9]
Subjects
Details
- Language :
- English
- ISSN :
- 00319155
- Volume :
- 61
- Issue :
- 16
- Database :
- OpenAIRE
- Journal :
- Physics in Medicine and Biology
- Accession number :
- edsair.doi.dedup.....5137cb67e446e98be882fce4d2ae580c