Prediction of relative position of CT slices using a computational intelligence system
Graphical abstract
Section snippets
Background
Scanning large parts of a patient's body with computerized tomography (CT) is common practice in radiology. As reported in [1], the amount of image data resulting from a full body scan varies between 40 MB to more than 1 GB, which has to be stored in a medical picture archiving and communication system (PACS). The increasing amount of data poses various problems for physicians and the PACS. A clinician often needs to compare different scans of the same body region for differential diagnoses or
Method
The field of evolutionary computation is devoted to the development of search and optimization algorithms based on the core principles of Neo-Darwinian evolutionary theory [11]. Evolutionary algorithms are population-based meta-heuristics, where candidate solutions are stochastically selected and modified to produce new, and possibly better, solutions for a particular problem. In particular, in standard GP each individual is encoded using a tree structure, also known as a program tree, which
Data set information
Each CT slice is described by a compound radial image descriptor, which is generated using the following steps: unifying the image resolutions, extracting the patient's body and combining the two image descriptors to a single radial descriptor. The complete process used to build the dataset is explained with rigorous detail in [21], but can be summarized as follows. The data was retrieved from 53,500 CT images taken from 74 different patients (43 male, 31 female). Each CT slice is described by
Conclusions
This paper proposes a computational intelligence system to automatically determine the relative position of a single CT slice within a full body scan. Knowing the relative position in a scan allows the efficient retrieval of similar slices from the same body region in other volume scans. Moreover, the relative position is often important information for a non-expert user that only has access to a single CT slice of a scan.
The proposed system is based on a variant of GP. In particular, the GP
Acknowledgments
The authors acknowledge project MassGP (PTDC/EEI-CTP/2975/2012), FCT, Portugal.
References (26)
- et al.
Comparing axial ct slices in quantized n-dimensional surf descriptor space to estimate the visible body region
Comput. Med. Imaging Graph.
(2011) - et al.
CT slice localization via instance-based regression
- DICOM standard, 2015,...
Human-competitive results produced by genetic programming
Genet. Programm. Evol. Mach.
(2010)- et al.
Quality of DICOM header information for image categorization
- et al.
Automatic segmentation of thoracic and pelvic CT images for radiotherapy planning using implicit anatomic knowledge and organ-specific segmentation strategies
Phys. Med. Biol.
(2008) - et al.
Hierarchical parsing and semantic navigation of full body CT data
Automatic Localisation of Body Regions in CT Topograms
(2008)- et al.
A boosting framework for visuality-preserving distance metric learning and its application to medical image retrieval
IEEE Trans. Pattern Anal. Mach. Intell.
(2010) - et al.
Medical image analysis: progress over two decades and the challenges ahead
IEEE Trans. Pattern Anal. Mach. Intell.
(2000)