PORTALE DELLA DIDATTICA

Ricerca CERCA
  KEYWORD

GR-09 - GRAphics and INtelligent Systems - GRAINS

Deep learning techniques for breast cancer characterization in magnetic resonance images

Reference persons FABRIZIO LAMBERTI

External reference persons LIA MORRA

Research Groups GR-09 - GRAphics and INtelligent Systems - GRAINS

Thesis type RESEARCH THESIS

Description Neo-adjuvant chemotherapy (NAC) is the standard of care and is widely used in patients with locally advanced breast cancer offering several advantages such as reduction of tumor and enabling breast-conservation surgery instead of mastectomy, as well as response-guided NAC approaches. In patients undergoing NAC for breast cancer the achievement of a pathological complete response (pCR) is associated with a significantly improved disease-free and overall survival. However a pCR is achieved in only 30% of the patients after the completion of NAC and clinical studies have shown that the therapeutic outcome can be improved after treatment modifications during NAC.
Predicting the pathological response after NAC in breast cancer patients is crucial and quantitative computerized methods represent an important step towards an accurate and effective breast cancer treatment.

The goal of this thesis proposal is to use deep learning techniques to improve NAC outcome prediction in breast cancer patients. We will develop a novel pipeline for quantitative feature extraction based on deep convolutional neural networks, and use advanced classification techniques (such as multiple-instance learning) for feature selection and NAC-outcome prediction. Experimental comparison with hand-crafted features used at the state-of-the-art will be performed to demonstrate the superiority of the proposed approach. Integration with other sources of data, including pathology images, may also be considered. The thesis work will be carried out at the Department of Scientific Computing at Florida State University (Prof. Anke Meyer-Baese), also in collaboration with the Medical University of Vienna (Prof. Hellbich).

Essential pre-requesites are good problem solving and programming skills, and a background in image analysis and/or pattern classification. Previous experience with deep learning is preferred but not required.

See also  http://grains.polito.it/work.php


Deadline 23/07/2020      PROPONI LA TUA CANDIDATURA




© Politecnico di Torino
Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY
Contatti