Domain Knowledge Based Brain Tumor Segmentation and Overall Survival Prediction

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

5 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationBrainlesion
Subtitle of host publicationGlioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries
EditorsAlessandro Crimi, Spyridon Bakas
PublisherSpringer Nature Switzerland AG
Pages285-295
ISBN (Electronic)9783030466435
ISBN (Print)9783030466428
Publication statusPublished - 2020

Publication series

NameLecture Notes in Computer Science
Volume11993
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Title5th International MICCAI Brainlesion Workshop, BrainLes 2019, held in conjunction with the Medical Image Computing for Computer Assisted Intervention, MICCAI 2019
PlaceChina
CityShenzhen
Period13 - 17 October 2019

Abstract

Automatically segmenting sub-regions of gliomas (necrosis, edema and enhancing tumor) and accurately predicting overall survival (OS) time from multimodal MRI sequences have important clinical significance in diagnosis, prognosis and treatment of gliomas. However, due to the high degree variations of heterogeneous appearance and individual physical state, the segmentation of sub-regions and OS prediction are very challenging. To deal with these challenges, we utilize a 3D dilated multi-fiber network (DMFNet) with weighted dice loss for brain tumor segmentation, which incorporates prior volume statistic knowledge and obtains a balance between small and large objects in MRI scans. For OS prediction, we propose a DenseNet based 3D neural network with position encoding convolutional layer (PECL) to extract meaningful features from T1 contrast MRI, T2 MRI and previously segmented sub-regions. Both labeled data and unlabeled data are utilized to prevent over-fitting for semi-supervised learning. Those learned deep features along with handcrafted features (such as ages, volume of tumor) and position encoding segmentation features are fed to a Gradient Boosting Decision Tree (GBDT) to predict a specific OS day.

Citation Format(s)

Domain Knowledge Based Brain Tumor Segmentation and Overall Survival Prediction. / Guo, Xiaoqing; Yang, Chen; Lam, Pak Lun; Woo, Peter Y. M.; Yuan, Yixuan.

Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. ed. / Alessandro Crimi; Spyridon Bakas. Springer Nature Switzerland AG, 2020. p. 285-295 (Lecture Notes in Computer Science; Vol. 11993).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review