S. Bessa et al., "Personalized 3D Breast Cancer Models with Automatic Image Segmentation and Registration", Proc. of 3DBODY.TECH 2020 - 11th Int. Conf. and Exh. on 3D Body Scanning and Processing Technologies, Online/Virtual, 17-18 Nov. 2020, #15, https://doi.org/10.15221/20.15.
Personalized 3D Breast Cancer Models with Automatic Image Segmentation and Registration
Silvia BESSA 1,2, Joao F. TEIXEIRA 1,2, Pedro H. CARVALHO 1, Pedro F. GOUVEIA 3,4, Helder P. OLIVEIRA 1,2
1 INESC TEC, Porto, Portugal;
2 University of Porto, Porto, Portugal;
3 Champalimaud Foundation, Lisbon, Portugal;
4 Medical School, University of Lisbon, Lisbon, Portugal
Breast conservative surgery (BCS) combined with radiotherapy has become the treatment of choice for the majority of women suffering from breast cancer. Every year approximately 2.1million new cases arise worldwide, but fortunately the 10-year survival rate now exceeds 80% mostly due to the early detection of non-palpable breast cancer. The accurate localization of the tumor is of utmost importance to decrease the re-excision rate and necessity of a second surgery, and also pivotal to the minimization of unaesthetic outcomes caused by these interventions. Nevertheless, 7 out of 10 patients will need invasive pre-operative localization and women will live long lives with the dire consequences of cancer treatments. Currently, it is up to the physicians to correlate multimodal 2-dimensial (2D) sectional images to the 3D space for surgical planning. The challenge is now focused on the technology to create an alternative non-invasive tumor location procedure that can be ethical and fit to the clinical set. This paper describes an automatic image segmentation and registration algorithm that fuses 3D optical scans of the breast surface, with interior radiological data for tumor characterization, to build a personalized digital breast model that can potentially be used as a non-invasive digital pre-operative localization technique, improving tumor visualization and surgery planning.
breast cancer, 3D breast model, fusion, multimodal registration, automatic segmentation, magnetic resonance image, surface, tumor location
© Hometrica Consulting - Dr. Nicola D'Apuzzo, Switzerland, www.hometrica.ch.
Reproduction of the proceedings or any parts thereof (excluding short quotations for the use in the preparation of reviews and technical and scientific papers) may be made only after obtaining the specific approval of the publisher. The papers appearing in the proceedings reflect the author's opinions. Their inclusion in these publications does not necessary constitute endorsement by the editor or by the publisher. Authors retain all rights to individual papers.
Note: click the + on the top left of the page to open/close the menu.