Towards a Case-Based Reasoning System for Predicting Aesthetic Outcomes of Breast Reconstruction - 13.279

J. Lee et al., "Towards a Case-Based Reasoning System for Predicting Aesthetic Outcomes of Breast Reconstruction", in Proc. of 4th Int. Conf. on 3D Body Scanning Technologies, Long Beach CA, USA, 2013, pp. 279-284, https://doi.org/10.15221/13.279.

Title:

Towards a Case-Based Reasoning System for Predicting Aesthetic Outcomes of Breast Reconstruction

Authors:

Juhun LEE 1,2, Clement S. SUN 1,2, Gregory P. REECE 2, Michelle C. FINGERET 2, Mia K. MARKEY 1,2

1 The University of Texas at Austin, Austin TX, USA;
2 The University of Texas MD Anderson Cancer Center, Houston TX, USA

Abstract:

As many breast cancer survivors are candidates for multiple types of breast reconstruction, they need help visualizing possible outcomes to make optimal decisions about breast reconstruction. The purpose of this study was to develop a prototype of a system that could help women visualize possible breast reconstruction surgery results by displaying examples of reconstruction outcomes achieved by patients with similar pre-operative features. We present a prototype case-based reasoning (CBR) system that queries a database of women who have already undergone breast reconstruction surgery to retrieve a subset of cases that were pre-operatively similar to the test patient. Similarity is assessed in terms of features such as breast volume, patient age, and body mass index (BMI). In our prototype CBR system, the prior cases are reused in a straightforward manner; we simply present the post-operative 3D images of the cases that were pre-operatively similar to the test patient. The prototype CBR system was built on the data obtained from 47 patients. For each patient, we obtained 3D images before and six months after the initial breast reconstruction surgery. From these images, we quantified left and right pre-operative breast volumes. In order to retrieve cases that were pre-operatively similar to a given test patient, we applied the k-nearest neighbor algorithm (based on Euclidean distance) on the pre-operative features. We demonstrated the usefulness of our CBR system by presenting the sample query, which showed visually similar reconstructed breasts compared to the real reconstruction outcome.

Keywords:

case-based reasoning, k-nearest neighbor, recommender system, breast cancer, breast reconstruction

Details:

Full paper: 13.279.pdf
Proceedings: 3DBST 2013, 19-20 Nov. 2013, Long Beach California, USA
Pages: 279-284
DOI: https://doi.org/10.15221/13.279

License/Copyright notice:

Proceedings: © Hometrica Consulting - Dr. Nicola D'Apuzzo, Switzerland, hometrica.ch.
Authors retain all rights to individual papers, which are licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
The papers appearing in the proceedings reflect the author's opinions. Their inclusion in the proceedings does not necessary constitute endorsement by the editor or by the publisher.

Note: click the + on the top left of the page to open/close the menu.