Dataset Information

Reproducibility of automated habenula segmentation via deep learning in major depressive disorder and normal controls with 7 Tesla MRI.

ABSTRACT: The habenula is one of the most important brain regions for investigating the etiology of psychiatric diseases such as major depressive disorder (MDD). However, the habenula is challenging to delineate with the naked human eye in brain imaging due to its low contrast and tiny size, and the manual segmentation results vary greatly depending on the observer. Therefore, there is a great need for automatic quantitative analytic methods of the habenula for psychiatric research purposes. Here we propose an automated segmentation and volume estimation method for the habenula in 7 Tesla magnetic resonance imaging based on a deep learning-based semantic segmentation network. The proposed method, using the data of 69 participants (33 patients with MDD and 36 normal controls), achieved an average precision, recall, and dice similarity coefficient of 0.869, 0.865, and 0.852, respectively, in the automated segmentation task. Moreover, the intra-class correlation coefficient reached 0.870 in the volume estimation task. This study demonstrates that this deep learning-based method can provide accurate and quantitative analytic results of the habenula. By providing rapid and quantitative information on the habenula, we expect our proposed method will aid future psychiatric disease studies.

SUBMITTER: Lim SH

PROVIDER: S-EPMC8241874 | biostudies-literature | 2021 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Reproducibility of automated habenula segmentation via deep learning in major depressive disorder and normal controls with 7 Tesla MRI.

Lim Sang-Heon SH Yoon Jihyun J Kim Young Jae YJ Kang Chang-Ki CK Cho Seo-Eun SE Kim Kwang Gi KG Kang Seung-Gul SG

Scientific reports 20210629 1

The habenula is one of the most important brain regions for investigating the etiology of psychiatric diseases such as major depressive disorder (MDD). However, the habenula is challenging to delineate with the naked human eye in brain imaging due to its low contrast and tiny size, and the manual segmentation results vary greatly depending on the observer. Therefore, there is a great need for automatic quantitative analytic methods of the habenula for psychiatric research purposes. Here we propo ...[more]

PMID: 34188141

Similar Datasets

Project description:IntroductionAbnormalities in myelin are believed to be one of the important causes of major depressive disorder, and it is becoming important to more accurately quantify myelin in in vivo magnetic resonance imaging of major depressive disorder patients. We aimed to investigate the difference in myelin concentration in the white matter and subcortical areas using new quantitative myelin-related maps of high-resolution 7 Tesla (7 T) magnetic resonance imaging between patients with major depressive disorder and healthy controls.MethodsMyelin-related comparisons of the white matter and nearby subcortical regions were conducted between healthy controls (n = 36) and patients with major depressive disorder (n = 34). Smoothed quantitative ratio (sq-Ratio) myelin-related maps were created using the multi-echo magnetization-prepared two rapid gradient echoes (ME-MP2RAGE) sequence of the T1 and T2* images of 7 T magnetic resonance imaging. Differences in the myelin-related values of the regions of interest between the two groups were analyzed using a two-sample t-test, and multiple comparison corrections were performed using the false discovery rate.ResultsThe average sq-Ratio myelin-related values were 2.62% higher in the white matter and 2.26% higher in the subcortical regions of the healthy controls group than in the major depressive disorder group. In the group analysis of the healthy control and major depressive disorder groups, the sq-Ratio myelin-related values were significantly different in the fornix area of the white matter (false discovery rate-corrected p = 0.012). In addition, significant differences were observed in both the left (false discovery rate-corrected p = 0.04) and right thalamus (false discovery rate-corrected p = 0.040) among the subcortical regions.DiscussionThe average sq-ratio myelin-related value and sq-ratio myelin-related values in the fornix of the white matter and both thalami were higher in the healthy controls group than in the major depressive disorder group. We look forward to replicating our findings in other populations using larger sample sizes.

Project description:PurposeTo investigate reproducibility of myocardial radiomic features with cardiac MRI.Materials and methodsTest-retest studies were performed with a 3-T MRI system using commonly used cardiac MRI sequences of cine balanced steady-state free precession (cine bSSFP), T1-weighted and T2-weighted imaging, and quantitative T1 and T2 mapping in phantom experiments and 10 healthy participants (mean ± standard deviation age, 29 years ± 13). In addition, this study assessed repeatability in 51 patients (56 years ± 14) who underwent imaging twice during the same session. Three readers independently delineated the myocardium to investigate inter- and intraobserver reproducibility of radiomic features. A total of 1023 radiomic features were extracted by using PyRadiomics (https://pyradiomics.readthedocs.io/) with 11 image filters and six feature families. The intraclass correlation coefficient (ICC) was estimated to assess reproducibility and repeatability, and features with ICCs greater than or equal to 0.8 were considered reproducible.ResultsDifferent reproducibility patterns were observed among sequences in in vivo test-retest studies. In cine bSSFP, the gray-level run-length matrix was the most reproducible feature family, and the wavelet low-pass filter applied horizontally and vertically was the most reproducible image filter. In T1 and T2 maps, intensity-based statistics (first-order) and gray-level co-occurrence matrix features were the most reproducible feature families, without a dominant reproducible image filter. Across all sequences, gray-level nonuniformity was the most frequently identified reproducible feature name. In inter- and intraobserver reproducibility studies, respectively, only 32%-47% and 61%-73% of features were identified as reproducible.ConclusionOnly a small subset of myocardial radiomic features was reproducible, and these reproducible radiomic features varied among different sequences. Supplemental material is available for this article. © RSNA, 2020See also the commentary by Leiner in this issue.

Dataset Information

Reproducibility of automated habenula segmentation via deep learning in major depressive disorder and normal controls with 7 Tesla MRI.

Publications

Reproducibility of automated habenula segmentation via deep learning in major depressive disorder and normal controls with 7 Tesla MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets