Dataset Information

Standardization of size, shape and internal structure of spinal cord images: comparison of three transformation methods.

ABSTRACT: Functional fluorescence imaging has been widely applied to analyze spatio-temporal patterns of cellular dynamics in the brain and spinal cord. However, it is difficult to integrate spatial information obtained from imaging data in specific regions of interest across multiple samples, due to large variability in the size, shape and internal structure of samples. To solve this problem, we attempted to standardize transversely sectioned spinal cord images focusing on the laminar structure in the gray matter. We employed three standardization methods, the affine transformation (AT), the angle-dependent transformation (ADT) and the combination of these two methods (AT+ADT). The ADT is a novel non-linear transformation method developed in this study to adjust an individual image onto the template image in the polar coordinate system. We next compared the accuracy of these three standardization methods. We evaluated two indices, i.e., the spatial distribution of pixels that are not categorized to any layer and the error ratio by the leave-one-out cross validation method. In this study, we used neuron-specific marker (NeuN)-stained histological images of transversely sectioned cervical spinal cord slices (21 images obtained from 4 rats) to create the standard atlas and also to serve for benchmark tests. We found that the AT+ADT outperformed other two methods, though the accuracy of each method varied depending on the layer. This novel image standardization technique would be applicable to optical recording such as voltage-sensitive dye imaging, and will enable statistical evaluations of neural activation across multiple samples.

SUBMITTER: Fujiki Y

PROVIDER: S-EPMC3818318 | biostudies-literature | 2013

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Standardization of size, shape and internal structure of spinal cord images: comparison of three transformation methods.

Fujiki Yasuhisa Y Yokota Shigefumi S Okada Yasumasa Y Oku Yoshitaka Y Tamura Yoshiyasu Y Ishiguro Makio M Miwakeichi Fumikazu F

PloS one 20131105 11

Functional fluorescence imaging has been widely applied to analyze spatio-temporal patterns of cellular dynamics in the brain and spinal cord. However, it is difficult to integrate spatial information obtained from imaging data in specific regions of interest across multiple samples, due to large variability in the size, shape and internal structure of samples. To solve this problem, we attempted to standardize transversely sectioned spinal cord images focusing on the laminar structure in the gr ...[more]

PMID: 24223702

Similar Datasets

Project description:BackgroundMeasuring the physical condition of long-lasting insecticidal nets (LLINs) under field conditions is of great importance for malaria control programmes to guide decisions on how frequently to replace LLINs. Current guidelines by the World Health Organization Pesticide Evaluation Scheme (WHOPES) propose a proportionate hole index (pHI) for assessing LLIN condition by counting the number of holes the size of a thumb, fist, head, and larger than a head. However, this method does not account for irregular hole shapes or exact hole sizes which could result in inaccurate decisions about when to replace LLINs.MethodsLLINs were collected during a 2013 health facility-based malaria case control study in Machinga District, Malawi. To evaluate the accuracy of the pHI, the physical condition of 277 LLINs was estimated by the WHOPES method and then compared with two more thorough measurement methods: image analysis of digital photographs of each LLIN side; and for 10 nets, ruler measurements of the length, width, and location of each hole. Total hole counts and areas per net were estimated by each method, and detailed results of hole shapes and composite pictures of hole locations were generated using image analysis.ResultsThe WHOPES method and image analysis resulted in similar estimates of total hole counts, each with a median of 10 (inter-quartile range (IQR) 4-24 and 4-23, respectively; p = 0.004); however, estimated hole areas were significantly larger using the WHOPES method (median 162 cm2, IQR 28-793) than image analysis (median 13 cm2, IQR 3-101; p < 0.0001). The WHOPES method classified fewer LLINs in 'good condition' compared to image analysis (42% vs 74%). The ruler method detected significantly more holes than image analysis did (p = 0.002) in 10 LLINs; however, total hole area was not significantly different (p = 0.16). Most holes were not circular but roughly 2-5 times longer in one direction. The lower quarter of LLIN sides was found to have the most holes.ConclusionsThe WHOPES method overestimated total hole area, likely because holes are elongated rather than circular, suggesting further adjustments to the pHI formula may be warranted when considering LLIN replacement strategies.

Project description:Deep Learning based Convolutional Neural Networks (CNNs) are the state-of-the-art machine learning technique with medical image data. They have the ability to process large amounts of data and learn image features directly from the raw data. Based on their training, these networks are ultimately able to classify unknown data and make predictions. Magnetic resonance imaging (MRI) is the imaging modality of choice for many spinal cord disorders. Proper interpretation requires time and expertise from radiologists, so there is great interest in using artificial intelligence to more quickly interpret and diagnose medical imaging data. In this study, a CNN was trained and tested using thoracolumbar MR images from 500 dogs. T1- and T2-weighted MR images in sagittal and transverse planes were used. The network was trained with unremarkable images as well as with images showing the following spinal cord pathologies: intervertebral disc extrusion (IVDE), intervertebral disc protrusion (IVDP), fibrocartilaginous embolism (FCE)/acute non-compressive nucleus pulposus extrusion (ANNPE), syringomyelia and neoplasia. 2,693 MR images from 375 dogs were used for network training. The network was tested using 7,695 MR images from 125 dogs. The network performed best in detecting IVDPs on sagittal T1-weighted images, with a sensitivity of 100% and specificity of 95.1%. The network also performed very well in detecting IVDEs, especially on sagittal T2-weighted images, with a sensitivity of 90.8% and specificity of 98.98%. The network detected FCEs and ANNPEs with a sensitivity of 62.22% and a specificity of 97.90% on sagittal T2-weighted images and with a sensitivity of 91% and a specificity of 90% on transverse T2-weighted images. In detecting neoplasms and syringomyelia, the CNN did not perform well because of insufficient training data or because the network had problems differentiating different hyperintensities on T2-weighted images and thus made incorrect predictions. This study has shown that it is possible to train a CNN in terms of recognizing and differentiating various spinal cord pathologies on canine MR images. CNNs therefore have great potential to act as a "second eye" for imagers in the future, providing a faster focus on the altered image area and thus increasing workflow in radiology.

Project description:Long-term morphine treatment leads to tolerance which attenuates analgesic effect and hampers clinical utilization. Recent studies have sought to reveal the mechanism of opioid receptors and neuroinflammation by observing morphological changes of cells in the rat spinal cord. This work proposes a high-content screening (HCS) based computational method, HCS-Morph, for predicting neuroinflammation in morphine tolerance to facilitate the development of tolerance therapy using immunostaining images for astrocytes, microglia, and neurons in the spinal cord. HCS-Morph first extracts numerous HCS-based features of cellular phenotypes. Next, an inheritable bi-objective genetic algorithm is used to identify a minimal set of features by maximizing the prediction accuracy of neuroinflammation. Finally, a mathematic model using a support vector machine with the identified features is established to predict drug-treated images to assess the effects of tolerance therapy. The dataset consists of 15 saline controls (1 μl/h), 15 morphine-tolerant rats (15 μg/h), and 10 rats receiving a co-infusion of morphine (15 μg/h) and gabapentin (15 μg/h, Sigma). The three individual models of astrocytes, microglia, and neurons for predicting neuroinflammation yielded respective Jackknife test accuracies of 96.67%, 90.00%, and 86.67% on the 30 rats, and respective independent test accuracies of 100%, 90%, and 60% on the 10 co-infused rats. The experimental results suggest that neuroinflammation activity expresses more predominantly in astrocytes and microglia than in neuron cells. The set of features for predicting neuroinflammation from images of astrocytes comprises mean cell intensity, total cell area, and second-order geometric moment (relating to cell distribution), relevant to cell communication, cell extension, and cell migration, respectively. The present investigation provides the first evidence for the role of gabapentin in the attenuation of morphine tolerance from phenotypic changes of astrocytes and microglia. Based on neuroinflammation prediction, the proposed computer-aided image diagnosis system can greatly facilitate the development of tolerance therapy with anti-inflammatory drugs.

Dataset Information

Standardization of size, shape and internal structure of spinal cord images: comparison of three transformation methods.

Publications

Standardization of size, shape and internal structure of spinal cord images: comparison of three transformation methods.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets