Τετάρτη 18 Αυγούστου 2021

Segmentation of Brain Tumor in 3D Intraoperative Ultrasound Imaging

xlomafota13 shared this article with you from Inoreader

Abstract

Background

Intraoperative Ultrasound (iUS), using a navigation system and preoperative magnetic resonance imaging (pMRI), supports the surgeon intraoperatively in identifying tumor margins. Therefore, visual tumor enhancement can be supported by efficient segmentation methods.

Methods

A semi-automatic and two registration-based segmentation methods are evaluated to extract brain tumors from 3D-iUS data. The registration-based methods estimated the brain deformation after craniotomy based on pMRI and 3D-iUS data. Both approaches use the Normalized Gradient Field (NGF) and Linear Correlation of Linear Combinations (LC2) metrics. Proposed methods were evaluated on 66 B-mode and contrast-mode 3D-iUS data with metastasis and glioblastoma.

Results

The semi-automatic segmentation achieved superior results with Dice Similarity Index (DSI) values between [85.34, 86.79] % and Contour Mean Distance (CMD) values between [1.05, 1.11] mm for both modalities and tumor classes.

Conclusions

Better segmentation results were obtained for metastasis detection than glioblastoma, preferring 3D-intraoperative B-mode over 3D-intraoperative contrast-mode.

This article is protected by copyright. All rights reserved.

View on the web

Δεν υπάρχουν σχόλια:

Δημοσίευση σχολίου