Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu

INESC TEC researcher proposes deep learning model for the aesthetic evaluation of breast cancer treatment

Wilson Silva, INESC TEC researcher, won the “Best Student Paper Award” at IbPRIA 2022, an Iberian conference in the field of pattern recognition and image analysis, thanks to his paper “Deep Aesthetic Assessment and Retrieval of Breast Cancer Treatment Outcomes”. This is the first paper that uses deep learning methodologies (a recent paradigm in Artificial Intelligence to evaluate the aesthetic result of treatments associated with breast cancer.

30th May 2022

As the researcher explained, there is neither a reference methodology for performing an aesthetic assessment of the outcome of breast cancer treatments, nor a way to show patients the potential outcome of surgery. “In this sense, the presentation of results from similar cases is of greater relevance to manage the expectations of patients regarding the possible aesthetic results of the treatment”, added Wilson Silva.

Moreover, the work presented proposes an innovative neural network to perform the aesthetic evaluation, and focused on the development, as a proof of concept, of a binary aesthetic evaluation solution. “In addition to the classification, the proposed model can also be used to find similar previous cases”, explained the researcher, stating that the testing phase included a set of data consisting of more than 140 photographs of women who’ve undergone breast-conserving treatments. “The results showed a superior performance of the proposed model considering the state of the art in the aesthetic evaluation of this type of treatments,” he concluded.

Following this award, Wilson Silva will now publish an extension of the paper in one of the leading scientific journals in the field: Pattern Recognition Letters. This work is also related to the European project Cinderella, coordinated by the Champalimaud Breast Unit with INESC TEC participation, towards optimising the prediction of the aesthetic results of reconstructive surgeries in patients with breast cancer.

The IbPRIA 2022 Conference took place in early May, in Aveiro. This is an international event promoted by APRP – Portuguese Association for Recognition of Standards and AERFAI – Spanish Association for Recognition of Standards and Image Analysis.

The INESC TEC researcher mentioned in the news piece is associated with INESC TEC, UP-FEUP and FCT.