Biology subjects

Ntiri, E. E.

Publications and source records attributed to Ntiri, E. E..

3 recordsLinked to original sources

bioRxiv2025

A self-supervised deep learning pipeline for segmentation in two-photon fluorescence microscopy

Two-photon fluorescence microscopy (TPFM) allows in situ investigation of the structure and function of the brain at a cellular level, but the conventional image analyses of TPFM data are labour-intensive. Automated deep learning (DL)-based image processing pipelines used to analyze TPFM data require large labeled training datasets. Here, we developed a self supervised learning (SSL) pipeline to test whether unlabeled data can be used to boost the accuracy and generalizability of DL models for image segmentation in TPFM. We specifically developed four pretext tasks, including shuffling, rotation, axis rotation, and reconstruction, to train models without supervision using the UNet architecture. We validated our pipeline on two tasks (neuronal soma and vasculature segmentation), using large 3D microscopy datasets. We introduced a novel density-based metric, which provided more sensitive evaluation to downstream analysis tasks. We further determined the amount of labeled data required to reach performance on par with fully supervised learning (FSL) models. SSL-based models that were fine-tuned with only 50% of data were on par or superior (e.g., Dice increase of 3% for neuron segmentation and Dice score of 0.88 {+/-} 0.09 for vessel segmentation) to FSL models. We demonstrated that segmentation maps generated by SSL models pretrained on the reconstruction and rotation tasks can be better translated to downstream tasks than can other SSL tasks. Finally, we benchmarked all models on a publicly available out-of-distribution dataset, demonstrating that SSL models outperform FSL when trained with clean data, and are more robust than FSL models when trained with noisy data.

neuroscience↗

bioRxiv2021

Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation

White matter hyperintensities (WMH) are frequently observed on structural neuroimaging of elderly populations and are associated with cognitive decline and increased risk of dementia. Many existing WMH segmentation algorithms produce suboptimal results in populations with vascular lesions or brain atrophy, or require parameter tuning and are computationally expensive. Additionally, most algorithms do not generate a confidence estimate of segmentation quality, limiting their interpretation. MRI-based segmentation methods are often sensitive to acquisition protocols, scanners, noise-level, and image contrast, failing to generalize to other populations and out-of-distribution datasets. Given these concerns, we propose a novel Bayesian 3D Convolutional Neural Network (CNN) with a U-Net architecture that automatically segments WMH, provides uncertainty estimates of the segmentation output for quality control and is robust to changes in acquisition protocols. We also provide a second model to differentiate deep and periventricular WMH. 432 subjects were recruited to train the CNNs from four multi-site imaging studies. A separate test set of 158 subjects was used for evaluation, including an unseen multi-site study. We compared our model to two established state-of-the-art techniques (BIANCA and DeepMedic), highlighting its accuracy and efficiency. Our Bayesian 3D U-Net achieved the highest Dice similarity coefficient of 0.89 {+/-} 0.08 and the lowest modified Hausdorff distance of 2.98 {+/-} 4.40 mm. We further validated our models highlighting their robustness on clinical adversarial cases simulating data with low signal-to-noise ratio, low resolution, and different contrast (stemming from MRI sequences with different parameters). Our pipeline and models are available at: https://hypermapp3r.readthedocs.io

neuroscience↗

bioRxiv2020

Improved segmentation of the intracranial and ventricular volumes in populations with cerebrovascular lesions and atrophy using 3D CNNs

Successful segmentation of the total intracranial vault (ICV) and ventricles is of critical importance when studying neurodegeneration through neuroimaging. We present iCVMapper and VentMapper, robust algorithms that use a convolutional neural network (CNN) to segment the ICV and ventricles from both single and multi-contrast MRI data. Our models were trained on a large dataset from two multi-site studies (N=528 subjects for ICV, N=501 for ventricular segmentation) consisting of older adults with varying degrees of cerebrovascular lesions and atrophy, which pose significant challenges for most segmentation approaches. The models were tested on 238 participants, including subjects with vascular cognitive impairment and high white matter hyperintensity burden. Two of the three test sets came from studies not used in the training dataset. We assessed our algorithms relative to four state-of-the-art ICV extraction methods (MONSTR, BET, Deep Extraction, FreeSurfer), as well as a ventricular segmentation tool (FreeSurfer). Our multi-contrast models outperformed other methods across all evaluation metrics, with average Dice coefficients of 0.98 and 0.94 for ICV and ventricular segmentation respectively. Both models were also the most time efficient, segmenting the structures in orders of magnitude faster than some of the other available methods. Our networks showed an increased accuracy with the use of a conditional random field (CRF) as a post-processing step. We further validated both segmentation models, highlighting their robustness to images with lower resolution and signal-to-noise ratio, compared to tested techniques. The pipeline and models are available at: https://icvmapp3r.readthedocs.io and https://ventmapp3r.readthedocs.io to enable further investigation of the roles of ICV and ventricles in relation to normal aging and neurodegeneration in large multi-site studies.

neuroscience↗