A Novel Approach for Fully Automatic Intra-Tumor Segmentation With 3D U-Net Architecture for Gliomas

Frontiers in Computational Neuroscience
Ujjwal BaidAbhishek Mahajan

Abstract

Purpose: Gliomas are the most common primary brain malignancies, with varying degrees of aggressiveness and prognosis. Understanding of tumor biology and intra-tumor heterogeneity is necessary for planning personalized therapy and predicting response to therapy. Accurate tumoral and intra-tumoral segmentation on MRI is the first step toward understanding the tumor biology through computational methods. The purpose of this study was to design a segmentation algorithm and evaluate its performance on pre-treatment brain MRIs obtained from patients with gliomas. Materials and Methods: In this study, we have designed a novel 3D U-Net architecture that segments various radiologically identifiable sub-regions like edema, enhancing tumor, and necrosis. Weighted patch extraction scheme from the tumor border regions is proposed to address the problem of class imbalance between tumor and non-tumorous patches. The architecture consists of a contracting path to capture context and the symmetric expanding path that enables precise localization. The Deep Convolutional Neural Network (DCNN) based architecture is trained on 285 patients, validated on 66 patients and tested on 191 patients with Glioma from Brain Tumor Segmentation (BraTS) 2018 c...Continue Reading

References

Oct 23, 2002·Human Brain Mapping·Stephen M Smith
Sep 29, 2004·Medical Image Analysis·Marcel PrastawaGuido Gerig
Jul 10, 2007·Acta Neuropathologica·David N LouisPaul Kleihues
Apr 10, 2010·IEEE Transactions on Medical Imaging·Nicholas J TustisonJames C Gee
Jun 8, 2013·Physics in Medicine and Biology·Stefan BauerMauricio Reyes
Aug 3, 2013·Medical Image Analysis·Anders EklundStephen M LaConte
Sep 30, 2014·IEEE Journal of Biomedical and Health Informatics·Ayse DemirhanInan Guler
Dec 11, 2014·IEEE Transactions on Medical Imaging·Bjoern H MenzeKoen Van Leemput
Dec 24, 2014·Medical Image Analysis·Erik SmistadFrank Lindseth
Aug 13, 2015·BMC Medical Imaging·Abdel Aziz Taha, Allan Hanbury
Dec 20, 2015·IEEE Transactions on Medical Imaging·Nicolas CordierNicholas Ayache
Mar 10, 2016·IEEE Transactions on Medical Imaging·Sergio PereiraCarlos A Silva
Apr 6, 2016·IEEE Transactions on Medical Imaging·Pim MoeskopsIvana Isgum
Jun 17, 2016·Medical Image Analysis·Mohammad HavaeiHugo Larochelle
Nov 20, 2016·Medical Image Analysis·Konstantinos KamnitsasBen Glocker
Jan 18, 2019·JCO Clinical Cancer Informatics·Okyaz EminagaBernhard Breil

❮ Previous
Next ❯

Citations

Aug 28, 2020·Frontiers in Computational Neuroscience·Ujjwal BaidAbhishek Mahajan
Jun 16, 2021·Journal of Zhejiang University. Science. B·Xiaobing ZhangShengdong Nie
Aug 18, 2021·Journal of Radiation Research·Yosuke KanoAkihiro Haga
Aug 28, 2021·Healthcare·Wenyin ZhangSahraoui Dhelimd
Aug 28, 2021·Brain Sciences·Ali FawziBahari Belaton

❮ Previous
Next ❯

Methods Mentioned

BETA
imaging techniques
light microscopy

Software Mentioned

N4ITK
Tensorflow library
cuDNN
CBICA Image Processing
skimage
CUDA
smal
BraTS

Related Concepts

Related Feeds

Cancer Imaging

Imaging techniques, including CT and MR, have become essential to tumor detection, diagnosis, and monitoring. Here is the latest research on cancer imaging.

Brain Injury & Trauma

brain injury after impact to the head is due to both immediate mechanical effects and delayed responses of neural tissues.