Dataset Information

Automated thalamic nuclei segmentation using multi-planar cascaded convolutional neural networks.

ABSTRACT:

Purpose

To develop a fast and accurate convolutional neural network based method for segmentation of thalamic nuclei.

Methods

A cascaded multi-planar scheme with a modified residual U-Net architecture was used to segment thalamic nuclei on conventional and white-matter-nulled (WMn) magnetization prepared rapid gradient echo (MPRAGE) data. A single network was optimized to work with images from healthy controls and patients with multiple sclerosis (MS) and essential tremor (ET), acquired at both 3 T and 7 T field strengths. WMn-MPRAGE images were manually delineated by a trained neuroradiologist using the Morel histological atlas as a guide to generate reference ground truth labels. Dice similarity coefficient and volume similarity index (VSI) were used to evaluate performance. Clinical utility was demonstrated by applying this method to study the effect of MS on thalamic nuclei atrophy.

Results

Segmentation of each thalamus into twelve nuclei was achieved in under a minute. For 7 T WMn-MPRAGE, the proposed method outperforms current state-of-the-art on patients with ET with statistically significant improvements in Dice for five nuclei (increase in the range of 0.05-0.18) and VSI for four nuclei (increase in the range of 0.05-0.19), while performing comparably for healthy and MS subjects. Dice and VSI achieved using 7 T WMn-MPRAGE data are comparable to those using 3 T WMn-MPRAGE data. For conventional MPRAGE, the proposed method shows a statistically significant Dice improvement in the range of 0.14-0.63 over FreeSurfer for all nuclei and disease types. Effect of noise on network performance shows robustness to images with SNR as low as half the baseline SNR. Atrophy of four thalamic nuclei and whole thalamus was observed for MS patients compared to healthy control subjects, after controlling for the effect of parallel imaging, intracranial volume, gender, and age (p < 0.004).

Conclusion

The proposed segmentation method is fast, accurate, performs well across disease types and field strengths, and shows great potential for improving our understanding of thalamic nuclei involvement in neurological diseases.

SUBMITTER: Majdi MS

PROVIDER: S-EPMC7530079 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Thalamic nuclei have been implicated in several neurological diseases. Thalamic nuclei parcellation from structural MRI is challenging due to poor intra-thalamic nuclear contrast while methods based on diffusion and functional MRI are affected by limited spatial resolution and image distortion. Existing multi-atlas based techniques are often computationally intensive and time-consuming. In this work, we propose a 3D convolutional neural network (CNN) based framework for thalamic nuclei parcellation using T1-weighted Magnetization Prepared Rapid Gradient Echo (MPRAGE) images. Transformation of images to an efficient representation has been proposed to improve the performance of subsequent classification tasks especially when working with limited labeled data. We investigate this by transforming the MPRAGE images to White-Matter-nulled MPRAGE (WMn-MPRAGE) contrast, previously shown to exhibit good intra-thalamic nuclear contrast, prior to the segmentation step. We trained two 3D segmentation frameworks using MPRAGE images (n = 35 subjects): (a) a native contrast segmentation (NCS) on MPRAGE images and (b) a synthesized contrast segmentation (SCS) where synthesized WMn-MPRAGE representation generated by a contrast synthesis CNN were used. Thalamic nuclei labels were generated using THOMAS, a multi-atlas segmentation technique proposed for WMn-MPRAGE images. The segmentation accuracy and clinical utility were evaluated on a healthy cohort (n = 12) and a cohort (n = 45) comprising of healthy subjects and patients with alcohol use disorder (AUD), respectively. Both the segmentation CNNs yielded comparable performances on most thalamic nuclei with Dice scores greater than 0.84 for larger nuclei and at least 0.7 for smaller nuclei. However, for some nuclei, the SCS CNN yielded significant improvements in Dice scores (medial geniculate nucleus, P = 0.003, centromedian nucleus, P = 0.01) and percent volume difference (ventral anterior, P = 0.001, ventral posterior lateral, P = 0.01) over NCS. In the AUD cohort, the SCS CNN demonstrated a significant atrophy in ventral lateral posterior nucleus in AUD patients compared to healthy age-matched controls (P = 0.01), agreeing with previous studies on thalamic atrophy in alcoholism, whereas the NCS CNN showed spurious atrophy of the ventral posterior lateral nucleus. CNN-based segmentation of thalamic nuclei provides a fast and automated technique for thalamic nuclei prediction in MPRAGE images. The transformation of images to an efficient representation, such as WMn-MPRAGE, can provide further improvements in segmentation performance.

Project description:In this study, we developed a multi-scale Convolutional neural network based Automated hippocampal subfield Segmentation Toolbox (CAST) for automated segmentation of hippocampal subfields. Although training CAST required approximately three days on a single workstation with a high-quality GPU card, CAST can segment a new subject in less than 1 min even with GPU acceleration disabled, thus this method is more time efficient than current automated methods and manual segmentation. This toolbox is highly flexible with either a single modality or multiple modalities and can be easily set up to be trained with a researcher's unique data. A 3D multi-scale deep convolutional neural network is the key algorithm used in the toolbox. The main merit of multi-scale images is the capability to capture more global structural information from down-sampled images without dramatically increasing memory and computational burden. The original images capture more local information to refine the boundary between subfields. Residual learning is applied to alleviate the vanishing gradient problem and improve the performance with a deeper network. We applied CAST with the same settings on two datasets, one 7T dataset (the UMC dataset) with only the T2 image and one 3T dataset (the MNI dataset) with both T1 and T2 images available. The segmentation accuracy of both CAST and the state-of-the-art automated method ASHS, in terms of the dice similarity coefficient (DSC), were comparable. CAST significantly improved the reliability of segmenting small subfields, such as CA2, CA3, and the entorhinal cortex (ERC), in terms of the intraclass correlation coefficient (ICC). Both ASHS and manual segmentation process some subfields (e.g. CA2 and ERC) with high DSC values but low ICC values, consequently increasing the difficulty of judging segmentation quality. CAST produces very consistent DSC and ICC values, with a maximal discrepancy of 0.01 (DSC-ICC) across all subfields. The pre-trained model, source code, and settings for the CAST toolbox are publicly available.

Project description:BackgroundAutomated segmentation of nuclei in microscopic images has been conducted to enhance throughput in pathological diagnostics and biological research. Segmentation accuracy and speed has been significantly enhanced with the advent of convolutional neural networks. A barrier in the broad application of neural networks to nuclei segmentation is the necessity to train the network using a set of application specific images and image labels. Previous works have attempted to create broadly trained networks for universal nuclei segmentation; however, such networks do not work on all imaging modalities, and best results are still commonly found when the network is retrained on user specific data. Stochastic optical reconstruction microscopy (STORM) based super-resolution fluorescence microscopy has opened a new avenue to image nuclear architecture at nanoscale resolutions. Due to the large size and discontinuous features typical of super-resolution images, automatic nuclei segmentation can be difficult. In this study, we apply commonly used networks (Mask R-CNN and UNet architectures) towards the task of segmenting super-resolution images of nuclei. First, we assess whether networks broadly trained on conventional fluorescence microscopy datasets can accurately segment super-resolution images. Then, we compare the resultant segmentations with results obtained using networks trained directly on our super-resolution data. We next attempt to optimize and compare segmentation accuracy using three different neural network architectures.ResultsResults indicate that super-resolution images are not broadly compatible with neural networks trained on conventional bright-field or fluorescence microscopy images. When the networks were trained on super-resolution data, however, we attained nuclei segmentation accuracies (F1-Score) in excess of 0.8, comparable to past results found when conducting nuclei segmentation on conventional fluorescence microscopy images. Overall, we achieved the best results utilizing the Mask R-CNN architecture.ConclusionsWe found that convolutional neural networks are powerful tools capable of accurately and quickly segmenting localization-based super-resolution microscopy images of nuclei. While broadly trained and widely applicable segmentation algorithms are desirable for quick use with minimal input, optimal results are still found when the network is both trained and tested on visually similar images. We provide a set of Colab notebooks to disseminate the software into the broad scientific community ( https://github.com/YangLiuLab/Super-Resolution-Nuclei-Segmentation ).