SVM Optimization for Brain Tumor Identification Using Infrared Spectroscopic Samples.
Ontology highlight
ABSTRACT:
SUBMITTER: Fabelo H
PROVIDER: S-EPMC6308411 | biostudies-literature | 2018 Dec
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Cell cycle progression plays a vital role in regulating proliferation, metabolism, and apoptosis. Three-dimensional (3D) cell cultures have emerged as an important class of in vitro disease models, and incorporating the variation occurring from cell cycle progression in these systems is critical. Here, we report the use of Fourier transform infrared (FT-IR) spectroscopic imaging to identify subtle biochemical changes within cells, indicative of the G1/S and G2/M phases of the cell cycle. Following previous studies, we first synchronized samples from two-dimensional (2D) cell cultures, confirmed their states by flow cytometry and DNA quantification, and recorded spectra. We determined two critical wavenumbers (1059 and 1219 cm-1) as spectral indicators of the cell cycle for a set of isogenic breast cancer cell lines (MCF10AT series). These two simple spectral markers were then applied to distinguish cell cycle stages in a 3D cell culture model using four cell lines that represent the main stages of cancer progression from normal cells to metastatic disease. Temporal dependence of spectral biomarkers during acini maturation validated the hypothesis that the cells are more proliferative in the early stages of acini development; later stages of the culture showed stability in the overall composition but unique spatial differences in cells in the two phases. Altogether, this study presents a computational and quantitative approach for cell phase analysis in tissue-like 3D structures without any biomarker staining and provides a means to characterize the impact of the cell cycle on 3D biological systems and disease diagnostic studies using IR imaging.
| S-EPMC10214899 | biostudies-literature
Project description:BackgroundRecent advances and automation in DNA sequencing technology has created a vast amount of DNA sequence data. This increasing growth of sequence data demands better and efficient analysis methods. Identifying genes in this newly accumulated data is an important issue in bioinformatics, and it requires the prediction of the complete gene structure. Accurate identification of splice sites in DNA sequences plays one of the central roles of gene structural prediction in eukaryotes. Effective detection of splice sites requires the knowledge of characteristics, dependencies, and relationship of nucleotides in the splice site surrounding region. A higher-order Markov model is generally regarded as a useful technique for modeling higher-order dependencies. However, their implementation requires estimating a large number of parameters, which is computationally expensive.ResultsThe proposed method for splice site detection consists of two stages: a first order Markov model (MM1) is used in the first stage and a support vector machine (SVM) with polynomial kernel is used in the second stage. The MM1 serves as a pre-processing step for the SVM and takes DNA sequences as its input. It models the compositional features and dependencies of nucleotides in terms of probabilistic parameters around splice site regions. The probabilistic parameters are then fed into the SVM, which combines them nonlinearly to predict splice sites. When the proposed MM1-SVM model is compared with other existing standard splice site detection methods, it shows a superior performance in all the cases.ConclusionWe proposed an effective pre-processing scheme for the SVM and applied it for the identification of splice sites. This is a simple yet effective splice site detection method, which shows a better classification accuracy and computational speed than some other more complex methods.
| S-EPMC1764471 | biostudies-literature
Project description:Fast and accurate fault classification is essential to power system operations. In this paper, in order to classify electrical faults in radial distribution systems, a particle swarm optimization (PSO) based support vector machine (SVM) classifier has been proposed. The proposed PSO based SVM classifier is able to select appropriate input features and optimize SVM parameters to increase classification accuracy. Further, a time-domain reflectometry (TDR) method with a pseudorandom binary sequence (PRBS) stimulus has been used to generate a dataset for purposes of classification. The proposed technique has been tested on a typical radial distribution network to identify ten different types of faults considering 12 given input features generated by using Simulink software and MATLAB Toolbox. The success rate of the SVM classifier is over 97%, which demonstrates the effectiveness and high efficiency of the developed method.
| S-EPMC5525094 | biostudies-other
Project description:Tumor grade assessment is critical to the treatment of cancers. A pathologist typically evaluates grade by examining morphologic organization in tissue using hematoxylin and eosin (H&E) stained tissue sections. Fourier transform infrared spectroscopic (FT-IR) imaging provides an alternate view of tissue in which spatially specific molecular information from unstained tissue can be utilized. Here, we examine the potential of IR imaging for grading colon cancer in biopsy samples. We used a 148-patient cohort to develop a deep learning classifier to estimate the tumor grade using IR absorption. We demonstrate that FT-IR imaging can be a viable tool to determine colorectal cancer grades, which we validated on an independent cohort of surgical resections. This work demonstrates that harnessing molecular information from FT-IR imaging and coupling it with morphometry is a potential path to develop clinically relevant grade prediction models.
| S-EPMC9202565 | biostudies-literature
Project description:Numerous classification and regression problems have extensively used Support Vector Machines (SVMs). However, the SVM approach is less practical for large datasets because of its processing cost. This is primarily due to the requirement of optimizing a quadratic programming problem to determine the decision boundary during training. As a result, methods for selecting data instances that have a better likelihood of being chosen as support vectors by the SVM algorithm have been developed to help minimize the bulk of training data. This paper presents a density-based method, called Density-based Border Identification (DBI), in addition to four different variations of the method, for the lessening of the SVM training data through the extraction of a layer of border instances. For higher-dimensional datasets, the extraction is performed on lower-dimensional embeddings obtained by Uniform Manifold Approximation and Projection (UMAP), and the resulting subset can be repetitively used for SVM training in higher dimensions. Experimental findings on different datasets, such as Banana, USPS, and Adult9a, have shown that the best-performing variations of the proposed method effectively reduced the size of the training data and achieved acceptable training and prediction speedups while maintaining an adequate classification accuracy compared to training on the original dataset. These results, as well as comparisons to a selection of related state-of-the-art methods from the literature, such as Border Point extraction based on Locality-Sensitive Hashing (BPLSH), Clustering-Based Convex Hull (CBCH), and Shell Extraction (SE), suggest that our proposed methods are effective and potentially useful.
| S-EPMC10990207 | biostudies-literature
Project description:Glandular tumors arising in epithelial cells comprise the majority of solid human cancers. Glands are supported by stroma, which is activated in the proximity of a tumor. Activated stroma is often characterized by the molecular expression of ?-smooth muscle actin (?-SMA) within fibroblasts. However, the precise spatial and temporal evolution of chemical changes in fibroblasts upon epithelial tumor signaling is poorly understood. Here we report a label-free method to characterize fibroblast changes by using Fourier transform infrared spectroscopic imaging and comparing spectra with ?-SMA expression in primary normal human fibroblasts. We recorded the fibroblast activation process by spectroscopic imaging using increasingly tissue-like conditions: 1), stimulation with the growth factor TGF?1; 2), coculture with MCF-7 human breast cancerous epithelial cells in Transwell coculture; and 3), coculture with MCF-7 in three-dimensional cell culture. Finally, we compared the spectral signatures of stromal transformation with normal and malignant human breast tissue biopsies. The results indicate that this approach reveals temporally complex spectral changes and thus provides a richer assessment than simple molecular imaging based on ?-SMA expression. Some changes are conserved across culture conditions and in human tissue, providing a label-free method to monitor stromal transformations.
| S-EPMC3177049 | biostudies-literature
Project description:Brain haemorrhages often require urgent treatment with a consequent need for quick and accurate diagnosis. Therefore, in this study, we investigate Support Vector Machine (SVM) classifiers for detecting brain haemorrhages using Electrical Impedance Tomography (EIT) measurement frames. A 2-layer model of the head, along with a series of haemorrhages, is designed as both numerical models and physical phantoms. EIT measurement frames, taken from an electrode array placed on the head surface, are used to train and test linear SVM classifiers. Various scenarios are implemented on both platforms to examine the impact of variables such as noise level, lesion location, lesion size, variation in electrode positioning, and variation in anatomy, on the classifier performance. The classifier performed well in numerical models (sensitivity and specificity of 90%+) with signal-to-noise ratios of 60 dB+, was independent of lesion location, and could detect lesions reliably down to the tested minimum volume of 5 ml. Slight variations in electrode layout did not affect performance. Performance was affected by variations in anatomy however, emphasising the need for large training sets covering different anatomies. The phantom models proved more challenging, with maximal sensitivity and specificity of 75% when used with the linear SVM. Finally, the performance of two more complex classifiers is briefly examined and compared to the linear SVM classifier. These results demonstrate that a radial basis function (RBF) SVM classifier and a neural network classifier can improve detection accuracy. Classifiers applied to EIT measurement frames is a novel approach for lesion detection and may offer an effective diagnostic tool clinically. A challenge is to translate the strong results from numerical models into real world phantoms and ultimately human patients, as well as the selection and development of optimal classifiers for this application.
| S-EPMC6042738 | biostudies-other
Project description:Interventions: 0.5 ml ICG was injected the mucosa into the submucosal space of the bowel wall at just the distal side of the tumor preoperative endoscopically. We identified the colonic tumor site in the PINPOINT Endoscopic Fluorescence Imaging System, in which NIR fluorescence is superimposed in pseudo-color (green) on a white light image.
Primary outcome(s): The intraoperative visibility rate of tumor site
Study Design: Single arm Non-randomized
| 2636552 | ecrin-mdr-crc
Project description:Renal transplants have not seen a significant improvement in their 10-year graft life. Chronic damage accumulation often leads to interstitial fibrosis and tubular atrophy (IF/TA) and thus graft function loss over time. For this reason, IF/TA has been the chief suspect for a potential prognostic marker for long term outcomes. In this study, we have used infrared spectroscopic (IR) imaging to interrogate the biochemistry of regions of fibrosis from renal transplant biopsies to identify a biochemical signature that can predict rapid progression of fibrosis. IR imaging represents an approach that permits label-free biochemical imaging of human tissues towards identifying novel biomarkers for disease diagnosis or prognosis. Two cohorts were identified as progressors (n?=?5,?>?50% fibrosis increase between time points) and non-progressors (n?=?5,?<?5% increase between time points). Each patient had an early time point and late time point biopsy. Collagen associated carbohydrate moieties (?(C-O), 1035?cm-1 and ?(C-O-C),1079?cm-1) spectral ratios demonstrated good separation between the two cohorts (p?=?0.001). This was true for late and early time point biopsies suggesting the regions of fibrosis are biochemically altered in cases undergoing progressive fibrosis. Thus, IR imaging can potentially predict rapid progression of fibrosis using histologically normal early time point biopsies.
| S-EPMC5766495 | biostudies-literature
Project description:Enveloped viruses, such as HIV, Ebola and Influenza, are among the most deadly known viruses. Cellular membrane penetration of enveloped viruses is a critical step in the cascade of events that lead to entry into the host cell. Conventional ensemble fusion assays rely on collective responses to membrane fusion events, and do not allow direct and quantitative studies of the subtle and intricate fusion details. Such details are accessible via single particle investigation techniques, however. Here, we implement nano-infrared spectroscopic imaging to investigate the chemical and structural modifications that occur prior to membrane fusion in the single archetypal enveloped virus, influenza X31. We traced in real-space structural and spectroscopic alterations that occur during environmental pH variations in single virus particles. In addition, using nanospectroscopic imaging we quantified the effectiveness of an antiviral compound in stopping viral membrane disruption (a novel mechanism for inhibiting viral entry into cells) during environmental pH variations.
| S-EPMC5997350 | biostudies-literature