FEA-based simulation of breast deformation in real-time using artificial neural network

Treatment of breast cancer involves two stages: diagnosis and treatment. It is difficult to correlate the imaging results at the two stages because as the patient’s posture changes during treatment, the images captured during diagnosis do not represent the tumor location during the treatment. In the absence of real-time imaging during treatment, the visualization of tumor location is challenging for surgeons. There are many challenges for breast deformation simulation. For example, material properties are very important to simulate the deformation accurately. The simulation speed will decide whether the technology is applicable for clinical use. But because of the limit of hardware, achieving real time simulation is difficult. This thesis focuses on investigating visualization of breast deformation for different patient’s positions. We utilized magnetic resonance imaging (MRI) of a patient collected during diagnosis for this study. This data was preprocessed to form a 3D reconstructed model that was used to run a finite element analysis (FEA) simulation. FEA simulates the deformation of breast tissues for different constraints, such as glandular ratio and gravity angle. However, FEA simulation of such deformation can take a few minutes to as much as 40 minutes to complete using a 8 cores computer. To obtain real-time visualization, we constructed a neural network (NN) model that takes breast gravity angle and glandular / fat ratio (breast material) as input to estimate breast deformation for different patient’s positions offline. This NN is used to predict the deformation of the breast and provide visualization in real-time (5 ms prediction time). To further validate our result, we carried out MRI of a breast phantom in several angles (to mimic various patient postures). We also implemented an iterative technique to estimate material properties. This data was used to simulate breast deformations at different posture angles. A similar approach was implemented to build an NN model. Our results show that NN has the ability to map the gravity direction to the breast shape and tumor location accurately, while, keeping run time to a minimum.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Systems & Entrepreneurial Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2022

Author dc:creator

• Wang, Kuocheng

Contributors dc:contributor

• Sreenivas, Ramavarapu S
• Masud, Arif
• Sutton, Brad
• Kesavadas, Thenkurussi

• Engineering

Statement dc:rights

• Copyright 2021 Kuocheng Wang

Language dc:language

en, eng

Handle dc:identifier

http://hdl.handle.net/2142/113842

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F113842