Automatic Segmentation of Corpus Callosum in Midsagittal Based on Bayesian Inference Consisting of Sparse Representation Error and Multi-Atlas Voting

A method framework of automatic localization and quantitative segmentation for the cavum septum pellucidum complex and the cerebellar vermis in fetal brain ultrasound images

Background

Early detection of central nervous system (CNS) anomalies in human embryos through prenatal screening is crucial for timely intervention and improved patient outcomes. Fetal brain mid-sagittal ultrasound images (FBMUIs) play a pivotal role as a diagnostic tool for detecting structural abnormalities. However, the automatic localization and quantitative segmentation of complex anatomical structures such as the corpus callosum-cavum septum pellucidum complex (CCC) and cerebellar vermis (CV) in FBMUIs present significant challenges.

Methods

To address this issue, we propose an integrated framework that combines anatomical knowledge with computer vision techniques. Our framework comprises four steps: (I) generation of average templates for CCC and CV local images using a variational autoencoder (VAE); (II) localizing the CCC by using the "Initial Localization-Accurate Localization-Result Detection" strategy, followed by segmenting it based on morphological characteristics using the "Initial Contour Fitting-Contour Iteration" strategy; (III) applying a similar strategy as CCC localization and CV segmentation; and (IV) leveraging spatial and morphological characteristics to achieve accurate localization and segmentation.

Results

Our CCC and CV localization and segmentation methods were validated by using 140 FBMUIs from various perspectives. The accuracy and effectiveness of our approach were demonstrated through data statistics and comparative analysis. Currently, clinical trials are being conducted on our method at Shengjing Hospital of China Medical University.

Conclusions

Our proposed integrated framework presents a novel solution for the automatic localization and quantitative segmentation of the CCC and CV in FBMUIs. It shows promise for early diagnosis of CNS anomalies in human embryos, offering significant clinical implications.

Classification of Preschoolers with Low-Functioning Autism Spectrum Disorder Using Multimodal MRI Data

Multimodal imaging studies targeting preschoolers and low-functioning autism spectrum disorder (ASD) patients are scarce. We applied machine learning classifiers to parameters from T1-weighted MRI and DTI data of 58 children with ASD (age 3-6 years) and 48 typically developing controls (TDC). Classification performance reached an accuracy, sensitivity, and specificity of 88.8%, 93.0%, and 83.8%, respectively. The most prominent features were the cortical thickness of the right inferior occipital gyrus, mean diffusivity of the middle cerebellar peduncle, and nodal efficiency of the left posterior cingulate gyrus. Machine learning-based analysis of MRI data was useful in distinguishing low-functioning ASD preschoolers from TDCs. Combination of T1 and DTI improved classification accuracy about 10%, and large-scale multi-modal MRI studies are warranted for external validation.

Deep Learning Corpus Callosum Segmentation as a Neurodegenerative Marker in Multiple Sclerosis

BACKGROUND AND PURPOSE

Corpus callosum atrophy is a sensitive biomarker of multiple sclerosis (MS) neurodegeneration but typically requires manual 2D or volumetric 3D-based segmentations. We developed a supervised machine learning algorithm, DeepnCCA, for corpus callosum segmentation and relate callosal morphology to clinical disability using conventional MRI scans collected in clinical routine.

METHODS

In a prospective study of 553 MS patients with 704 acquisitions, 200 unique 2D T₂ -weighted MRI scans were delineated to develop, train, and validate DeepnCCA. Comparative FreeSurfer segmentations were obtained in 504 3D T₁ -weighted scans. Both FreeSurfer and DeepnCCA outputs were correlated with clinical disability. Using principal component analysis of the DeepnCCA output, the morphological changes were explored in relation to clinical disease burden.

RESULTS

DeepnCCA and manual segmentations had high similarity (Dice coefficients 98.1 ± .11%, 89.3 ± .76%, for intracranial and corpus callosum area, respectively through 10-fold cross-validation). DeepnCCA had numerically stronger correlations with cognitive and physical disability as compared to FreeSurfer: Expanded disability status scale (EDSS) ±6 months (r = -.22 P = .002; r = -.17, P = .013), future EDSS (r = -.26, P<.001; r = -.17, P = .012), and future symbol digit modalities test (r = .26, P = .001; r = .24, P = .003). The corpus callosum became thinner with increasing cognitive and physical disability. Increasing physical disability, additionally, significantly correlated with a more angled corpus callosum.

CONCLUSIONS

DeepnCCA (https://github.com/plattenmichael/DeepnCCA/) is an openly available tool that can provide fast and accurate corpus callosum measurements applicable to large MS cohorts, potentially suitable for monitoring disease progression and therapy response.