Publication Date

2022

Conference Title

Modeling, Simulation and Visualization Student Capstone Conference 2022

Conference Track

Medical Simulation

Document Type

Paper

Abstract

Segmentation of the chest region and breast tissues is essential for surgery planning and navigation. This paper proposes the foundation for preoperative segmentation based on two cascaded architectures of deep neural networks (DNN) based on the state-of-the-art nnU-Net. Additionally, this study introduces a polyvinyl alcohol cryogel (PVA-C) breast phantom based on the segmentation of the DNN automated approach, enabling the experiments of navigation system for robotic breast surgery. Multi-modality breast MRI datasets of T2W and STIR images were acquired from 10 patients. Segmentation evaluation utilized the Dice Similarity Coefficient (DSC), segmentation accuracy, sensitivity, and specificity. First, a single class labeling was used to segment the breast region. Then it was employed as an input for three-class labeling to segment fat, fibroglandular (FGT) tissues, and tumorous lesions. The first architecture has a 0.95 DCS, while the second has a 0.95, 0.83, and 0.41 for fat, FGT, and tumor classes, respectively.

Keywords:

MRI segmentation, Convolutional neural networks, Breast surgery, Surgery planning

Start Date

4-14-2022

End Date

4-14-2022

DOI

10.25776/zz2y-x338

Share

COinS
 
Apr 14th, 12:00 AM Apr 14th, 12:00 AM

Multi-Modality Breast MRI Segmentation Using nn-UNet for Preoperative Planning of Robotic Surgery Navigation

Segmentation of the chest region and breast tissues is essential for surgery planning and navigation. This paper proposes the foundation for preoperative segmentation based on two cascaded architectures of deep neural networks (DNN) based on the state-of-the-art nnU-Net. Additionally, this study introduces a polyvinyl alcohol cryogel (PVA-C) breast phantom based on the segmentation of the DNN automated approach, enabling the experiments of navigation system for robotic breast surgery. Multi-modality breast MRI datasets of T2W and STIR images were acquired from 10 patients. Segmentation evaluation utilized the Dice Similarity Coefficient (DSC), segmentation accuracy, sensitivity, and specificity. First, a single class labeling was used to segment the breast region. Then it was employed as an input for three-class labeling to segment fat, fibroglandular (FGT) tissues, and tumorous lesions. The first architecture has a 0.95 DCS, while the second has a 0.95, 0.83, and 0.41 for fat, FGT, and tumor classes, respectively.