Simultaneous brain structure segmentation in magnetic resonance images using deep convolutional neural networks

Maruyama, Tomoko; Hayashi, Norio; Sato, Yusuke; Ogura, Toshihiro; Uehara, Masayuki; Ogura, Akio; Watanabe, H.; Kitoh, Yoshihiro; Initiative, Alzheimer’s Disease Neuroimaging

doi:10.1007/s12194-021-00633-3

Cited by 10 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…with a Dice of .89, 14 and Maruyama et al. with a Dice of .79 (Jaccard index of .652) 13 . Overall, the segmentations performed on T1w data were shown to be significantly more accurate than those performed on FLAIR data (independently from the type of segmentation network used).…”

Section: Discussionmentioning

confidence: 83%

“…27 Our Dice coefficient varied depending on the patient's atrophy level (.85-.94) but was overall at least on par, or better, with similar studies applying CNNs to segment the CC, such as Platten et al with a Dice of .89, 14 and Maruyama et al with a Dice of .79 (Jaccard index of .652). 13 Overall, the segmentations performed on T1w data were shown to be significantly more accurate than those performed on FLAIR data (independently from the type of segmentation network used). This difference is likely secondary to unsuppressed cerebrospinal fluid directly inferior to the CC, making its delineation inherently more difficult.…”

Section: Discussionmentioning

confidence: 87%

“…with a Dice of .79 (Jaccard index of .652). 13 Overall, the segmentations performed on T1w data were shown to be significantly more accurate than those performed on FLAIR data (independently from the type of segmentation network used). This difference is likely secondary to unsuppressed cerebrospinal fluid directly inferior to the CC, making its delineation inherently more difficult.…”

Section: Discussionmentioning

confidence: 87%

“…12 Previous studies have applied CNNs to segment the CC in 2 dimensions in healthy volunteers as well as in MS but on older sagittal two-dimensional T2-weighted (T2w) and T1-weighted (T1w) images. 13,14 Meanwhile, the current MAGNIMS-CMSC-NAIMS consensus guidelines recommend that 3-dimensional T2w fluid-attenuated inversion recovery (FLAIR) and T1w images are acquired for diagnosis and monitoring in MS. 15,16 Therefore, we developed a fully automatic, computationally efficient deep learning-based segmentation tool tailored for modern 3dimensional FLAIR and T1w scans in MS. The aim was to provide a biomarker of neurodegeneration in MS feasible to be run on large datasets.…”

Section: Introductionmentioning

confidence: 99%

“…In small sample sizes, a U‐net architecture is popular and it is often combined with effective image augmentation for improved classification 12 . Previous studies have applied CNNs to segment the CC in 2 dimensions in healthy volunteers as well as in MS but on older sagittal two‐dimensional T2‐weighted (T2w) and T1‐weighted (T1w) images 13,14 . Meanwhile, the current MAGNIMS‐CMSC‐NAIMS consensus guidelines recommend that 3‐dimensional T2w fluid‐attenuated inversion recovery (FLAIR) and T1w images are acquired for diagnosis and monitoring in MS 15,16 …”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automatic deep learning multicontrast corpus callosum segmentation in multiple sclerosis

Brusini

Plattén

Ouellette

et al. 2022

Journal of Neuroimaging

View full text Add to dashboard Cite

Background and Purpose Corpus callosum (CC) atrophy is predictive of future disability in multiple sclerosis (MS). However, current segmentation methods are either labor‐ or computationally intensive. We therefore developed an automated deep learning‐based CC segmentation tool and hypothesized that its output would correlate with disability. Methods A cohort of 631 MS patients (449 females, baseline age 41 ± 11 years) with both 3‐dimensional T1‐weighted and T2‐weighted fluid‐attenuated inversion recovery (FLAIR) MRI was used for the development. Data from 204 patients were manually segmented to train convolutional neural networks in extracting the midsagittal intracranial and CC areas. Remaining data were used to compare segmentations with FreeSurfer and benchmark the outputs with regard to clinical correlations. A 1.5 and 3 Tesla reproducibility cohort of 9 MS patients evaluated the segmentation robustness. Results The deep learning‐based tool was accurate in selecting the appropriate slice for segmentation (98% accuracy within 3 mm of the manual ground truth) and segmenting the CC (Dice coefficient .88‐.91) and intracranial areas (.97‐.98). The accuracy was lower with higher atrophy. Reproducibility was excellent (intraclass correlation coefficient > .90) for T1‐weighted scans and moderate‐good for FLAIR (.74‐.75). Segmentations were associated with baseline and future (average follow‐up time 6‐7 years) Expanded Disability Status Scale (ρ = –.13 to –.24) and Symbol Digit Modalities Test (r = .18‐.29) scores. Conclusions We present a fully automatic deep learning‐based CC segmentation tool optimized to modern imaging in MS with clinical correlations on par with computationally expensive alternatives.

show abstract

Section: Discussionmentioning

confidence: 83%