Semi-automated contour recognition using DICOMautomaton

17th International Conference on the Use of Computers in Radiation Therapy

物理学;计算机科学

Clark, H.^1,2 ; Wu, J.^2 ; Moiseenko, V.^2,3 ; Lee, R.^2 ; Gill, B.^2 ; Duzenli, C.^1,2 ; Thomas, S.^4

University of British Columbia, Vancouver, BC, Canada^1

British Columbia Cancer Agency, Vancouver Centre, Vancouver, BC, Canada^2

University of California San Diego, San Diego, CA, United States^3

British Columbia Cancer Agency, Fraser Valley Centre, Surrey, BC, Canada^4

关键词: Additional structures;    Digital imaging and communication in medicines;    Fourier descriptors;    Geometric analysis;    Human intervention;    Lexicographic methods;    Rule-based techniques;    Word and characters;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/489/1/012088/pdf
DOI  :  10.1088/1742-6596/489/1/012088

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

Purpose: A system has been developed which recognizes and classifies Digital Imaging and Communication in Medicine contour data with minimal human intervention. It allows researchers to overcome obstacles which tax analysis and mining systems, including inconsistent naming conventions and differences in data age or resolution. Methods: Lexicographic and geometric analysis is used for recognition. Well-known lexicographic methods implemented include Levenshtein-Damerau, bag-of-characters, Double Metaphone, Soundex, and (word and character)-N-grams. Geometrical implementations include 3D Fourier Descriptors, probability spheres, boolean overlap, simple feature comparison (e.g. eccentricity, volume) and rule-based techniques. Both analyses implement custom, domain-specific modules (e.g. emphasis differentiating left/right organ variants). Contour labels from 60 head and neck patients are used for cross-validation. Results: Mixed-lexicographical methods show an effective improvement in more than 10% of recognition attempts compared with a pure Levenshtein-Damerau approach when withholding 70% of the lexicon. Domain-specific and geometrical techniques further boost performance. Conclusions: DICOMautomaton allows users to recognize contours semi-automatically. As usage increases and the lexicon is filled with additional structures, performance improves, increasing the overall utility of the system.