Dataset Information

Robust and fast characterization of OCT-based optical attenuation using a novel frequency-domain algorithm for brain cancer detection.

ABSTRACT: Cancer is known to alter the local optical properties of tissues. The detection of OCT-based optical attenuation provides a quantitative method to efficiently differentiate cancer from non-cancer tissues. In particular, the intraoperative use of quantitative OCT is able to provide a direct visual guidance in real time for accurate identification of cancer tissues, especially these without any obvious structural layers, such as brain cancer. However, current methods are suboptimal in providing high-speed and accurate OCT attenuation mapping for intraoperative brain cancer detection. In this paper, we report a novel frequency-domain (FD) algorithm to enable robust and fast characterization of optical attenuation as derived from OCT intensity images. The performance of this FD algorithm was compared with traditional fitting methods by analyzing datasets containing images from freshly resected human brain cancer and from a silica phantom acquired by a 1310?nm swept-source OCT (SS-OCT) system. With graphics processing unit (GPU)-based CUDA C/C++ implementation, this new attenuation mapping algorithm can offer robust and accurate quantitative interpretation of OCT images in real time during brain surgery.

SUBMITTER: Yuan W

PROVIDER: S-EPMC5361149 | biostudies-literature | 2017 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Robust and fast characterization of OCT-based optical attenuation using a novel frequency-domain algorithm for brain cancer detection.

Yuan Wu W Kut Carmen C Liang Wenxuan W Li Xingde X

Scientific reports 20170322

Cancer is known to alter the local optical properties of tissues. The detection of OCT-based optical attenuation provides a quantitative method to efficiently differentiate cancer from non-cancer tissues. In particular, the intraoperative use of quantitative OCT is able to provide a direct visual guidance in real time for accurate identification of cancer tissues, especially these without any obvious structural layers, such as brain cancer. However, current methods are suboptimal in providing hi ...[more]

PMID: 28327613

Similar Datasets

Project description:Optical coherence tomography (OCT) is a new type of tomography that has experienced rapid development and potential in recent years. It is playing an increasingly important role in retinopathy diagnoses. At present, due to the uneven distributions of medical resources in various regions, the uneven proficiency levels of doctors in grassroots and remote areas, and the development needs of rare disease diagnosis and precision medicine, artificial intelligence technology based on deep learning can provide fast, accurate, and effective solutions for the recognition and diagnosis of retinal OCT images. To prevent vision damage and blindness caused by the delayed discovery of retinopathy, a fusion network (FN)-based retinal OCT classification algorithm (FN-OCT) is proposed in this paper to improve upon the adaptability and accuracy of traditional classification algorithms. The InceptionV3, Inception-ResNet, and Xception deep learning algorithms are used as base classifiers, a convolutional block attention mechanism (CBAM) is added after each base classifier, and three different fusion strategies are used to merge the prediction results of the base classifiers to output the final prediction results (choroidal neovascularization (CNV), diabetic macular oedema (DME), drusen, normal). The results show that in a classification problem involving the UCSD common retinal OCT dataset (108,312 OCT images from 4,686 patients), compared with that of the InceptionV3 network model, the prediction accuracy of FN-OCT is improved by 5.3% (accuracy = 98.7%, area under the curve (AUC) = 99.1%). The predictive accuracy and AUC achieved on an external dataset for the classification of retinal OCT diseases are 92 and 94.5%, respectively, and gradient-weighted class activation mapping (Grad-CAM) is used as a visualization tool to verify the effectiveness of the proposed FNs. This finding indicates that the developed fusion algorithm can significantly improve the performance of classifiers while providing a powerful tool and theoretical support for assisting with the diagnosis of retinal OCT.

Project description:Neointimal infiltration with foamy macrophages is recognized as an early and important sign of de-novo atherosclerosis after stent implantation (neoatherosclerosis). Recent histopathological studies have proven that automated quantification of signal attenuation using intravascular optical coherence tomography (OCT) imaging allows for sensitive identification of macrophages in native atherosclerotic disease. Whether this is true for neointimal foam cells in the setting of neoatherosclerosis remains unknown. Autopsy samples of stented coronary arteries (n = 13 cases) were evaluated by histology and OCT. After co-registration with histology, the attenuation rate of emitted laser light was measured in regions with and without neointimal foamy macrophages relative to its peak intensity at the blood-tissue interface. Attenuation index was subsequently determined as slope of a regression curve fitted to individual data points. Receiver operating curve (ROC) analysis was used to establish an optimal cut-off for detecting foamy macrophages in homogenous and non-homogenous neointima, respectively. Finally, the tissue attenuation index was applied to confirm or exclude the presence of neointimal foamy macrophages in symptomatic patients presenting with in-stent restenosis and undergoing intravascular OCT imaging (n = 29 cases). Tissue attenuation index derived from post-mortem samples differed significantly between histologically confirmed regions with and without neointimal foamy macrophages (- 1.23 ± 1.42 vs. - 0.52 ± 1.79, p < 0.05). ROC analysis was able to distinguish neointima with foamy macrophage infiltration from neointima without (93% sensitivity, 73% specificity, cut-off - 0.79, AUC 0.87 for homogenous neointima and 40% sensitivity, 95% specificity, cut-off - 1.93, AUC 0.69 for non-homogenous neointima). In symptomatic patients presenting with in-stent restenosis after stent implantation and undergoing intravascular imaging with OCT, neointimal foamy macrophages were detected in 34.2% of homogenous and 43.6% of non-homogenous neointimal ROI's evaluated. OCT-derived and histopathologically validated tissue attenuation index enables identification of neointimal foamy macrophages in stented coronary arteries. Such image-based post-processing software algorithm may help discern and triage subjects at increased risk for device-related events.

Project description:BackgroundImproving accuracy and efficiency of computational methods that predict pseudoknotted RNA secondary structures is an ongoing challenge. Existing methods based on free energy minimization tend to be very slow and are limited in the types of pseudoknots that they can predict. Incorporating known structural information can improve prediction accuracy; however, there are not many methods for prediction of pseudoknotted structures that can incorporate structural information as input. There is even less understanding of the relative robustness of these methods with respect to partial information.ResultsWe present a new method, Iterative HFold, for pseudoknotted RNA secondary structure prediction. Iterative HFold takes as input a pseudoknot-free structure, and produces a possibly pseudoknotted structure whose energy is at least as low as that of any (density-2) pseudoknotted structure containing the input structure. Iterative HFold leverages strengths of earlier methods, namely the fast running time of HFold, a method that is based on the hierarchical folding hypothesis, and the energy parameters of HotKnots V2.0.Our experimental evaluation on a large data set shows that Iterative HFold is robust with respect to partial information, with average accuracy on pseudoknotted structures steadily increasing from roughly 54% to 79% as the user provides up to 40% of the input structure.Iterative HFold is much faster than HotKnots V2.0, while having comparable accuracy. Iterative HFold also has significantly better accuracy than IPknot on our HK-PK and IP-pk168 data sets.ConclusionsIterative HFold is a robust method for prediction of pseudoknotted RNA secondary structures, whose accuracy with more than 5% information about true pseudoknot-free structures is better than that of IPknot, and with about 35% information about true pseudoknot-free structures compares well with that of HotKnots V2.0 while being significantly faster. Iterative HFold and all data used in this work are freely available at http://www.cs.ubc.ca/~hjabbari/software.php.

Dataset Information

Robust and fast characterization of OCT-based optical attenuation using a novel frequency-domain algorithm for brain cancer detection.

Publications

Robust and fast characterization of OCT-based optical attenuation using a novel frequency-domain algorithm for brain cancer detection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets