[OA216] Development of breast tumours models database. (August 2018)

• Record Type: Journal Article
• Authors: Bliznakova, Kristina; Buliev, Ivan; Bosmans, Hilde; Russo, Paolo; Mettivier, Giovanni; Bliznakov, Zhivko
• Is Part Of: Physica medica. Volume 52(2018)Supplement 1
• Page Start: 82
• Publication Date: 2018-08
• Subjects: Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2018.06.288
• Languages: English
• ISSNs: 1120-1797

Abstract

Abstract : Purpose: We present the development and the current state of the MaXIMA Breast Tumours Models' Database, which is intended to provide researchers with both segmented and mathematically modelled realistic in shape computer-based breast tumours. Methods: The database contains various 3D images of breast cancers of irregular shapes, collected from routine patient examinations or dedicated scientific experiments. It also contains images of simulated tumour models. To extract the 3D shapes of the breast cancers from patient images, an in–house developed and well evaluated segmentation algorithm was applied on 60 tomosynthesis sets from patients diagnosed with malignant and benign lesions. In addition, three breast mastectomy cases scanned at a CT system were added. This algorithm includes a series of image processing operations and region-growing techniques with minimal interaction from the user to find and segment the areas of the lesions. Modelled computational breast tumours are generated following different approaches and also stored in the database. Each record in the database is supported with relevant information, e.g. voxel size and resolution, matrix size, geometrical centre, etc. Results: The MaXIMA Imaging Database currently contains 68 unique breast cancer models obtained by segmentation of 3D patient breast tomosynthesis images; 8 models obtained by segmentation of 3D micro CT images of biopsy specimens; and 20 models based on mathematical algorithm. An application of the tumour models is to insert them into computationally generated healthy breast phantom generated with dedicated software tools (e.g. the BreastSimulator tool). The resulted combined computational breast models are used to study the visibility of breast tumours in 3D breast imaging techniques. This approach allows implementation of multiple scenarios and unlimited number of cases, which can be used for further software modelling and investigation of breast imaging techniques. The database interface is web-based, i.e. is platform independent, user friendly and is indented to be made freely accessible through internet after the completion of the MaXIMA project. Conclusions: The developed database serves as an imaging data source for researchers, working on breast imaging and early breast cancer detection with the help of existing or newly developed imaging modalities.