Format

Send to

Choose Destination
Neuroinformatics. 2018 Oct;16(3-4):325-337. doi: 10.1007/s12021-018-9365-1.

Automated Pathogenesis-Based Diagnosis of Lumbar Neural Foraminal Stenosis via Deep Multiscale Multitask Learning.

Han Z1,2,3,4, Wei B5,6, Leung S4, Nachum IB4, Laidley D4, Li S7,8.

Author information

1
College of Science and Technology, Shandong University of Traditional Chinese Medicine, Jinan, 250355, China.
2
Computational Medicine Lab, Shandong University of Traditional Chinese Medicine, Jinan, 250355, China.
3
Department of Medical Imaging, Western University, London, N6A 4V2, Canada.
4
Digital Image Group (DIG), London, ON, N6A 4V2, Canada.
5
College of Science and Technology, Shandong University of Traditional Chinese Medicine, Jinan, 250355, China. wbz99@sina.com.
6
Computational Medicine Lab, Shandong University of Traditional Chinese Medicine, Jinan, 250355, China. wbz99@sina.com.
7
Department of Medical Imaging, Western University, London, N6A 4V2, Canada. slishuo@gmail.com.
8
Digital Image Group (DIG), London, ON, N6A 4V2, Canada. slishuo@gmail.com.

Abstract

Pathogenesis-based diagnosis is a key step to prevent and control lumbar neural foraminal stenosis (LNFS). It conducts both early diagnosis and comprehensive assessment by drawing crucial pathological links between pathogenic factors and LNFS. Automated pathogenesis-based diagnosis would simultaneously localize and grade multiple spinal organs (neural foramina, vertebrae, intervertebral discs) to diagnose LNFS and discover pathogenic factors. The automated way facilitates planning optimal therapeutic schedules and relieving clinicians from laborious workloads. However, no successful work has been achieved yet due to its extreme challenges since 1) multiple targets: each lumbar spine has at least 17 target organs, 2) multiple scales: each type of target organ has structural complexity and various scales across subjects, and 3) multiple tasks, i.e., simultaneous localization and diagnosis of all lumbar organs, are extremely difficult than individual tasks. To address these huge challenges, we propose a deep multiscale multitask learning network (DMML-Net) integrating a multiscale multi-output learning and a multitask regression learning into a fully convolutional network. 1) DMML-Net merges semantic representations to reinforce the salience of numerous target organs. 2) DMML-Net extends multiscale convolutional layers as multiple output layers to boost the scale-invariance for various organs. 3) DMML-Net joins a multitask regression module and a multitask loss module to prompt the mutual benefit between tasks. Extensive experimental results demonstrate that DMML-Net achieves high performance (0.845 mean average precision) on T1/T2-weighted MRI scans from 200 subjects. This endows our method an efficient tool for clinical LNFS diagnosis.

KEYWORDS:

Deep learning; Multiscale learning; Multitask learning; Neural foraminal stenosis

PMID:
29450848
DOI:
10.1007/s12021-018-9365-1
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center