Dataset Information

Automated dendritic spine detection using convolutional neural networks on maximum intensity projected microscopic volumes.

ABSTRACT: BACKGROUND:Dendritic spines are structural correlates of excitatory synapses in the brain. Their density and structure are shaped by experience, pointing to their role in memory encoding. Dendritic spine imaging, followed by manual analysis, is a primary way to study spines. However, an approach that analyses dendritic spines images in an automated and unbiased manner is needed to fully capture how spines change with normal experience, as well as in disease. NEW METHOD:We propose an approach based on fully convolutional neural networks (FCNs) to detect dendritic spines in two-dimensional maximum-intensity projected images from confocal fluorescent micrographs. We experiment on both fractionally strided convolution and efficient sub-pixel convolutions. Dendritic spines far from the dendritic shaft are pruned by extraction of the shaft to reduce false positives. Performance of the proposed method is evaluated by comparing predicted spine positions to those manually marked by experts. RESULTS:The averaged distance between predicted and manually annotated spines is 2.81?±?2.63 pixels (0.082?±?0.076 microns) and 2.87?±?2.33 pixels (0.084?±?0.068 microns) based on two different experts. FCN-based detection achieves F scores > 0.80 for both sets of expert annotations. COMPARISON WITH EXISTING METHODS:Our method significantly outperforms two well-known software, NeuronStudio and Neurolucida (p-value < 0.02). CONCLUSIONS:FCN architectures used in this work allow for automated dendritic spine detection. Superior outcomes are possible even with small training data-sets. The proposed method may generalize to other datasets on larger scales.

SUBMITTER: Xiao X

PROVIDER: S-EPMC6402488 | biostudies-literature | 2018 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated dendritic spine detection using convolutional neural networks on maximum intensity projected microscopic volumes.

Xiao Xuerong X Djurisic Maja M Hoogi Assaf A Sapp Richard W RW Shatz Carla J CJ Rubin Daniel L DL

Journal of neuroscience methods 20180818

<h4>Background</h4>Dendritic spines are structural correlates of excitatory synapses in the brain. Their density and structure are shaped by experience, pointing to their role in memory encoding. Dendritic spine imaging, followed by manual analysis, is a primary way to study spines. However, an approach that analyses dendritic spines images in an automated and unbiased manner is needed to fully capture how spines change with normal experience, as well as in disease.<h4>New method</h4>We propose ...[more]

PMID: 30130608

Similar Datasets

Project description:Positron emission tomography (PET) of lung tumors suffers from breathing-motion induced blurring. Respiratory-correlated PET ameliorates motion blurring and enables visualization of lung tumor functional uptake throughout the breathing cycle but has achieved limited clinical use in radiotherapy planning. In this work, the authors propose a process for generating a gated PET maximum intensity projection (MIP), a breathing-phase projection of the 4D image set comprising gated PET images, as a technique to quantitatively and efficiently incorporate respiratory-correlated PET information into radiotherapy treatment planning.4D-CT and respiratory-gated PET using [(18)F]fluorodeoxyglucose (FDG) were acquired of three patients with a total of four small (4-18 cc), clearly defined lower-lobe lung tumors. Internal target volumes (ITVs) for the lung tumors were generated by threshold-based segmentation of PET-MIP images and ungated PET images (ITV(PET-MIP) and ITV(3D-PET), respectively), and by manual contouring of CT-MIP and end-exhale and end-inhale phases of 4D-CT (ITV(CT-MIP)) by a radiation oncologist. Because of the sensitivity of tumor segmentation to threshold value, several different thresholds were tested for ITV generation, including 40%, 30%, and 20% of maximum standardized uptake value (SUV(max)) for FDG as well as absolute SUV thresholds of 2.5 and 3.0. The normalized overlap and relative volumes of ITV(PET-MIP) and ITV(3D-PET) with respect to ITV(CT-MIP) were compared. The images were also visually compared. ITV(CT-MIP) was considered a gold standard for these tumors with CT-visible morphology.The mean and standard deviation normalized overlap and relative volumes between ITV(PET-MIP) and ITV(CT-MIP) were 0.68 ± 0.07 and 1.07 ± 0.42, respectively, averaged over all four tumors and all five threshold values. The mean and standard deviation normalized overlap and relative volumes of ITV(3D-PET) and ITV(CT-MIP) were 0.47 ± 0.12 and 0.69 ± 0.56, respectively.PET-MIP images better match CT-MIP images for this sample of four small CT-visible tumors as compared to ungated PET images, based on the metrics of volumetric overlap and relative volumes as well as visual interpretation. The PET-MIP is a way to incorporate 4D-PET imaging into the process of lung tumor contouring that is time-efficient for the radiation oncologist and involves minimal effort to implement in treatment planning software, because it requires only a single PET image beyond contouring on CT alone.

Project description:Cardiovascular resonance (CMR) imaging is a standard imaging modality for assessing cardiovascular diseases (CVDs), the leading cause of death globally. CMR enables accurate quantification of the cardiac chamber volume, ejection fraction and myocardial mass, providing information for diagnosis and monitoring of CVDs. However, for years, clinicians have been relying on manual approaches for CMR image analysis, which is time consuming and prone to subjective errors. It is a major clinical challenge to automatically derive quantitative and clinically relevant information from CMR images.Deep neural networks have shown a great potential in image pattern recognition and segmentation for a variety of tasks. Here we demonstrate an automated analysis method for CMR images, which is based on a fully convolutional network (FCN). The network is trained and evaluated on a large-scale dataset from the UK Biobank, consisting of 4,875 subjects with 93,500 pixelwise annotated images. The performance of the method has been evaluated using a number of technical metrics, including the Dice metric, mean contour distance and Hausdorff distance, as well as clinically relevant measures, including left ventricle (LV) end-diastolic volume (LVEDV) and end-systolic volume (LVESV), LV mass (LVM); right ventricle (RV) end-diastolic volume (RVEDV) and end-systolic volume (RVESV).By combining FCN with a large-scale annotated dataset, the proposed automated method achieves a high performance in segmenting the LV and RV on short-axis CMR images and the left atrium (LA) and right atrium (RA) on long-axis CMR images. On a short-axis image test set of 600 subjects, it achieves an average Dice metric of 0.94 for the LV cavity, 0.88 for the LV myocardium and 0.90 for the RV cavity. The mean absolute difference between automated measurement and manual measurement is 6.1 mL for LVEDV, 5.3 mL for LVESV, 6.9 gram for LVM, 8.5 mL for RVEDV and 7.2 mL for RVESV. On long-axis image test sets, the average Dice metric is 0.93 for the LA cavity (2-chamber view), 0.95 for the LA cavity (4-chamber view) and 0.96 for the RA cavity (4-chamber view). The performance is comparable to human inter-observer variability.We show that an automated method achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures.

Project description:PurposeAccurate segmentation of gross target volume (GTV) from computed tomography (CT) images is a prerequisite in radiotherapy for nasopharyngeal carcinoma (NPC). However, this task is very challenging due to the low contrast at the boundary of the tumor and the great variety of sizes and morphologies of tumors between different stages. Meanwhile, the data source also seriously affect the results of segmentation. In this paper, we propose a novel three-dimensional (3D) automatic segmentation algorithm that adopts cascaded multiscale local enhancement of convolutional neural networks (CNNs) and conduct experiments on multi-institutional datasets to address the above problems.Materials and methodsIn this study, we retrospectively collected CT images of 257 NPC patients to test the performance of the proposed automatic segmentation model, and conducted experiments on two additional multi-institutional datasets. Our novel segmentation framework consists of three parts. First, the segmentation framework is based on a 3D Res-UNet backbone model that has excellent segmentation performance. Then, we adopt a multiscale dilated convolution block to enhance the receptive field and focus on the target area and boundary for segmentation improvement. Finally, a central localization cascade model for local enhancement is designed to concentrate on the GTV region for fine segmentation to improve the robustness. The Dice similarity coefficient (DSC), positive predictive value (PPV), sensitivity (SEN), average symmetric surface distance (ASSD) and 95% Hausdorff distance (HD95) are utilized as qualitative evaluation criteria to estimate the performance of our automated segmentation algorithm.ResultsThe experimental results show that compared with other state-of-the-art methods, our modified version 3D Res-UNet backbone has excellent performance and achieves the best results in terms of the quantitative metrics DSC, PPR, ASSD and HD95, which reached 74.49 ± 7.81%, 79.97 ± 13.90%, 1.49 ± 0.65 mm and 5.06 ± 3.30 mm, respectively. It should be noted that the receptive field enhancement mechanism and cascade architecture can have a great impact on the stable output of automatic segmentation results with high accuracy, which is critical for an algorithm. The final DSC, SEN, ASSD and HD95 values can be increased to 76.23 ± 6.45%, 79.14 ± 12.48%, 1.39 ± 5.44mm, 4.72 ± 3.04mm. In addition, the outcomes of multi-institution experiments demonstrate that our model is robust and generalizable and can achieve good performance through transfer learning.ConclusionsThe proposed algorithm could accurately segment NPC in CT images from multi-institutional datasets and thereby may improve and facilitate clinical applications.

Project description:PurposeTo develop a fast and accurate convolutional neural network based method for segmentation of thalamic nuclei.MethodsA 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.ResultsSegmentation 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).ConclusionThe 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.

Dataset Information

Automated dendritic spine detection using convolutional neural networks on maximum intensity projected microscopic volumes.

Publications

Automated dendritic spine detection using convolutional neural networks on maximum intensity projected microscopic volumes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets