A1 Journal article (refereed)
An efficient memory reserving-and-fading strategy for vector quantization based 3D brain segmentation and tumor extraction using an unsupervised deep learning network (2024)


De, A., Wang, X., Zhang, Q., Wu, J., & Cong, F. (2024). An efficient memory reserving-and-fading strategy for vector quantization based 3D brain segmentation and tumor extraction using an unsupervised deep learning network. Cognitive Neurodynamics, 18(3), 1097-1118. https://doi.org/10.1007/s11571-023-09965-9


JYU authors or editors


Publication details

All authors or editorsDe, Ailing; Wang, Xiulin; Zhang, Qing; Wu, Jianlin; Cong, Fengyu

Journal or seriesCognitive Neurodynamics

ISSN1871-4080

eISSN1871-4099

Publication year2024

Publication date26/04/2023

Volume18

Issue number3

Pages range1097-1118

PublisherSpringer

Publication countryNetherlands

Publication languageEnglish

DOIhttps://doi.org/10.1007/s11571-023-09965-9

Publication open accessNot open

Publication channel open access


Abstract

Deep learning networks are state-of-the-art approaches for 3D brain image segmentation, and the radiological characteristics extracted from tumors are of great significance for clinical diagnosis, treatment planning, and treatment outcome evaluation. However, two problems have been the hindering factors in brain image segmentation techniques. One is that deep learning networks require large amounts of manually annotated data. Another issue is the computational efficiency of 3D deep learning networks. In this study, we propose a vector quantization (VQ)-based 3D segmentation method that employs a novel unsupervised 3D deep embedding clustering (3D-DEC) network and an efficiency memory reserving-and-fading strategy. The VQ-based 3D-DEC network is trained on volume data in an unsupervised manner to avoid manual data annotation. The memory reserving-and-fading strategy beefs up model efficiency greatly. The designed methodology makes deep learning-based model feasible for biomedical image segmentation. The experiment is divided into two parts. First, we extensively evaluate the effectiveness and robustness of the proposed model on two authoritative MRI brain tumor databases (i.e., IBSR and BrainWeb). Second, we validate the model using real 3D brain tumor data collected from our institute for clinical practice significance. Results show that our method (without data manual annotation) has superior accuracy (0.74±0.040.74±0.04 Tanimoto coefficient on IBSR, 97.5% TP and 97.7% TN on BrainWeb, and 91% Dice, 88% sensitivity and 87% specificity on real brain data) and remarkable efficiency (speedup ratio is 18.72 on IBSR, 31.16 on BrainWeb, 31.00 on real brain data) compared to the state-of-the-art methods. The results show that our proposed model can address the lacks of manual annotations, and greatly increase computation speedup with competitive segmentation accuracy compared to other state-of-the-art 3D CNN models. Moreover, the proposed model can be used for tumor treatment follow-ups every 6 months, providing critical details for surgical and postoperative treatment by correctly extracting numerical radiomic features of tumors.


Keywordsbrain researchtumoursmagnetic resonance imagingThree-dimensional imagingsegmentationmachine learningdeep learning

Free keywords3D data segmentation; unsupervised deep learning; codebook design; vector quantization; DEC network


Contributing organizations


Ministry reportingYes

Reporting Year2023

JUFO rating1


Last updated on 2024-03-07 at 00:06