Learning directional relative positions between mediastinal lymph node stations and organs. Issue 6 (14th May 2014)

• Record Type: Journal Article
• Authors: Sarrut, David; Rit, Simon; Claude, Line; Pinho, Romulo; Pitson, Graham; Bouilhol, Gauthier; Lynch, Rod
• Is Part Of: Medical physics. Volume 41:Issue 6(2014)Part 1
• Page Start: n/a
• Page End: n/a
• Publication Date: 2014-05-14
• Subjects: Computed tomography -- Segmentation -- Neural networks, fuzzy logic, artificial intelligence; biological organs -- biological tissues -- computerised tomography -- feature extraction -- fuzzy reasoning -- image matching -- image segmentation -- learning (artificial intelligence) -- medical image processing -- visual databases; mediastinal lymph stations segmentation -- machine learning -- directional relative position; Computerised tomographs -- Biological material, e.g. blood, urine; Haemocytometers -- In which a programme is changed according to experience gained by the computer itself during a complete run; Learning machines -- Information retrieval; Database structures therefor -- Digital computing or data processing equipment or methods, specially adapted for specific applications -- Image data processing or generation, in general -- Inference methods or devices; Medical image segmentation -- Databases -- Cancer -- Computed tomography -- Lungs -- Radiation treatment -- Image registration -- Vascular system; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1118/1.4873677
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: To automatically learn directional relative positions (DRP) between mediastinal lymph node stations and anatomical organs. Those spatial relationships are used to semiautomatically segment the stations in thoracic CT images. Methods: Fuzzy maps of DRP were automatically extracted by a learning procedure from a database composed of images with stations and anatomical structures manually segmented by consensus between experts. Spatial relationships common to all patients were retained. The segmentation of a new image used an initial rough delineation of anatomical organs and applied the DRP operators. The algorithm was tested with a leave‐one‐out approach on a database of 5 patients with 10 lymph stations and 30 anatomical structures each. Results were compared to expert delineations with dice similarity coefficient (DSC) and bidirectional local distance (BLD). Results: The overall mean DSC was 66% and the mean BLD was 1.7 mm. Best matches were obtained from stations S3P or S4R while lower matches were obtained for stations 1R and 1L. On average, more than 30 spatial relationships were automatically extracted for each station. Conclusions: This feasibility study suggests that mediastinal lymph node stations could be satisfactory segmented from thoracic CT using automatically extracted positional relationships with anatomical organs. This approach requires the anatomical structures to be initially roughly delineated. A similar approach could be applied to other sites where spatial relationships exists between anatomical structures. The complete database of the five reference cases is made publicly available.