Statistical Classification Strategy Research Articles

Footprint removal from seismic data with residual dictionary learning

Dictionary learning (DL) is a machine learning technique that can be used to find a sparse representation of a given data set by means of a relatively small set of atoms, which are learned from the input data. DL allows for the removal of random noise from seismic data very effectively. However, when seismic data are contaminated with footprint noise, the atoms of the learned dictionary are often a mixture of data and coherent noise patterns. In this scenario, DL requires carrying out a morphological attribute classification of the atoms to separate the noisy atoms from the dictionary. Instead, we have developed a novel DL strategy for the removal of footprint patterns in 3D seismic data that is based on an augmented dictionary built upon appropriately filtering the learned atoms. The resulting augmented dictionary, which contains the filtered atoms and their residuals, has a high discriminative power in separating signal and footprint atoms, thus precluding the use of any statistical classification strategy to segregate the atoms of the learned dictionary. We filter the atoms using a domain transform filtering approach, a very efficient edge-preserving smoothing algorithm. As in the so-called coherence-constrained DL method, the proposed DL strategy does not require the user to know or adjust the noise level or the sparsity of the solution for each data set. Furthermore, it only requires one pass of DL and is shown to produce successful transfer learning. This increases the speed of the denoising processing because the augmented dictionary does not need to be calculated for each time slice of the input data volume. Results on synthetic and 3D public-domain poststack field data demonstrate effective footprint removal with accurate edge preservation.

MRS-based Metabolomics in Cancer Research.

Metabolomics is a relatively new technique that is gaining importance very rapidly. MRS-based metabolomics, in particular, is becoming a useful tool in the study of body fluids, tissue biopsies and whole organisms. Advances in analytical techniques and data analysis methods have opened a new opportunity for such technology to contribute in the field of diagnostics. In the MRS approach to the diagnosis of disease, it is important that the analysis utilizes all the essential information in the spectra, is robust, and is non-subjective. Although some of the data analytic methods widely used in chemical and biological sciences are sketched, a more extensive discussion is given of a 5-stage Statistical Classification Strategy. This proposes powerful feature selection methods, based on, for example, genetic algorithms and novel projection techniques. The applications of MRS-based metabolomics in breast cancer, prostate cancer, colorectal cancer, pancreatic cancer, hepatobiliary cancers, gastric cancer, and brain cancer have been reviewed. While the majority of these applications relate to body fluids and tissue biopsies, some in vivo applications have also been included. It should be emphasized that the number of subjects studied must be sufficiently large to ensure a robust diagnostic classification. Before MRS-based metabolomics can become a widely used clinical tool, however, certain challenges need to be overcome. These include manufacturing user-friendly commercial instruments with all the essential features, and educating physicians and medical technologists in the acquisition, analysis, and interpretation of metabolomics data.

Deriving biomedical diagnostics from NMR spectroscopic data.

Biomedical spectroscopic experiments generate large volumes of data. For accurate, robust diagnostic tools the data must be analyzed for only a few characteristic observations per subject, and a large number of subjects must be studied. We describe here two of the current data analytic approaches applied to this problem: SIMCA (principal component analysis, partial least squares), and the statistical classification strategy (SCS). We demonstrate the application of the SCS by three examples of its use in analyzing 1H NMR spectra: screening for colon cancer, characterization of thyroid cancer, and distinguishing cancer from cholangitis in the biliary tract.

Potential of Magnetic Resonance Spectroscopy in Assessing the Effect of Fatty Acids on Inflammatory Bowel Disease in an Animal Model

People with inflammatory bowel disease (IBD) are at risk for developing colorectal cancer, and this risk increases at a rate of 1% per year after 8-10 years of having the disease. Saturated and omega-6 polyunsaturated fatty acids (PUFAs) have been implicated in its causation. Conversely, omega-3 PUFAs may have the potential to confer therapeutic benefit. Since proton magnetic resonance spectroscopy ((1)H MRS) combined with pattern recognition methods could be a valuable adjunct to histology, the objective of this study was to analyze the potential of (1)H MRS in assessing the effect of dietary fatty acids on colonic inflammation. Forty male Sprague-Dawley rats were administered one of the following dietary regimens for 2 weeks: low-fat corn oil (omega-6), high-fat corn oil (omega-6), high-fat flaxseed oil (omega-3) or high-fat beef tallow (saturated fatty acids). Half of the animals were fed 2% carrageenan to induce colonic inflammation similar to IBD. (1)H MRS and histology were performed on ex vivo colonic samples, and the (1)H MR spectra were analyzed using a statistical classification strategy (SCS). The histological and/or MRS studies revealed that different dietary fatty acids modulate colonic inflammation differently, with high-fat corn oil being the most inflammatory and high-fat flaxseed oil the least inflammatory. (1)H MRS is capable of identifying the biochemical changes in the colonic tissue as a result of inflammation, and when combined with SCS, this technique accurately differentiated the inflamed colonic mucosa based on the severity of the inflammation. This indicates that MRS could serve as a valuable adjunct to histology in accurately assessing colonic inflammation. Our data also suggest that both the type and the amount of fatty acids in the diet are critical in modulating IBD.

Creating robust, reliable, clinically relevant classifiers from spectroscopic data.

I describe in detail the intimately connected feature extraction and classifier development stages of the data-driven Statistical Classification Strategy (SCS) and compare them with current practice used in MR spectroscopy. We initially created the SCS for the analysis of MR and IR spectra of biofluids and tissues, and subsequently extended it to analyze biomedical data in general. I focus on explaining how to extract discriminatory spectral features and create robust classifiers that can reliably discriminate diseases and disease states. I discuss our approach to identifying features that retain spectral identity and provisionally relate these features, averaged subregions of the spectra, to specific chemical entities ("metabolites"). Particular emphasis is placed on describing the steps required to help create classifiers whose accuracy doesn't deteriorate significantly when presented with new, unknown samples. A simple but powerful extension of the discovered features to detect metabolite-metabolite (feature-feature) interactions is also sketched. I contrast the advantages and disadvantages of using either spectral signatures or explicit metabolite concentrations derived from the spectra as sets of discriminatory features. At present, no clear-cut preference is obvious and more objective comparisons will be needed. Finally, I argue that clinical requirements and exigencies strongly suggest adopting a two-phase approach to diagnosis/prognosis. In the first phase the emphasis ought to be on providing as accurate a diagnosis as possible, without any attempt to identify "biomarkers." That should be the goal of the second, research phase, with a view of providing prognosis on disease progression.

Rapid Etiological Classification of Meningitis by NMR Spectroscopy Based on Metabolite Profiles and Host Response

Bacterial meningitis is an acute disease with high mortality that is reduced by early treatment. Identification of the causative microorganism by culture is sensitive but slow. Large volumes of cerebrospinal fluid (CSF) are required to maximise sensitivity and establish a provisional diagnosis.We have utilised nuclear magnetic resonance (NMR) spectroscopy to rapidly characterise the biochemical profile of CSF from normal rats and animals with pneumococcal or cryptococcal meningitis. Use of a miniaturised capillary NMR system overcame limitations caused by small CSF volumes and low metabolite concentrations. The analysis of the complex NMR spectroscopic data by a supervised statistical classification strategy included major, minor and unidentified metabolites.Reproducible spectral profiles were generated within less than three minutes, and revealed differences in the relative amounts of glucose, lactate, citrate, amino acid residues, acetate and polyols in the three groups. Contributions from microbial metabolism and inflammatory cells were evident. The computerised statistical classification strategy is based on both major metabolites and minor, partially unidentified metabolites. This data analysis proved highly specific for diagnosis (100% specificity in the final validation set), provided those with visible blood contamination were excluded from analysis; 6–8% of samples were classified as indeterminate.This proof of principle study suggests that a rapid etiologic diagnosis of meningitis is possible without prior culture. The method can be fully automated and avoids delays due to processing and selective identification of specific pathogens that are inherent in DNA-based techniques.

Detecting colorectal cancer by 1H magnetic resonance spectroscopy of fecal extracts

Colorectal cancer is one of the most common cancers in the western world. Its early detection has been found to improve the prognosis of the patient, providing a wide window of opportunity for successful therapeutic interventions. However, current diagnostic techniques all have some limitations; there is a need to develop a better technique for routine screening purposes. We present a new methodology based on magnetic resonance spectroscopy of fecal extracts for the non-invasive detection of colorectal cancer. Five hundred twenty-three human subjects (412 with no colonic neoplasia and 111 with colorectal cancer, who were scheduled for colonoscopy or surgery) were recruited to donate a single sample of stool. One-dimensional (1)H magnetic resonance spectroscopy (MRS) experiments were performed on the supernatant of aqueous dispersions of the stool samples. Using a statistical classification strategy, several multivariate classifiers were developed. Applying the preprocessing, feature selection and classifier development stages of the Statistical Classification Strategy led to approximately 87% average balanced sensitivity and specificity for both training and monitoring sets, improving to approximately 92% when only crisp results, i.e. class assignment probabilities > or =75%, are considered. These results indicate that (1)H magnetic resonance spectroscopy of human fecal extracts, combined with appropriate data analysis methodology, has the potential to detect colorectal neoplasia accurately and reliably, and could be a useful addition to the current screening tools.

Magnetic Resonance Spectroscopy Detects Biochemical Changes in the Brain Associated with Chronic Low Back Pain: A Preliminary Report

Magnetic resonance (MR) spectroscopy is a noninvasive technique that can be used to detect and measure the concentration of metabolites and neurotransmitters in the brain and other organs. We used in vivo (1)H MR spectroscopy in subjects with low back pain compared with control subjects to detect alterations in biochemistry in three brain regions associated with pain processing. A pattern recognition approach was used to determine whether it was possible to discriminate accurately subjects with low back pain from control subjects based on MR spectroscopy. MR spectra were obtained from the prefrontal cortex, anterior cingulate cortex, and thalamus of 32 subjects with low back pain and 33 control subjects without pain. Spectra were analyzed and compared between groups using a pattern recognition method (Statistical Classification Strategy). Using this approach, it was possible to discriminate between subjects with low back pain and control subjects with accuracies of 100%, 99%, and 97% using spectra obtained from the anterior cingulate cortex, thalamus, and prefrontal cortex, respectively. These results demonstrate that MR spectroscopy, in combination with an appropriate pattern recognition approach, is able to detect brain biochemical changes associated with chronic pain with a high degree of accuracy.

A rapid screening test to distinguish between Candida albicans and Candida dubliniensis using NMR spectroscopy

Nuclear magnetic resonance (NMR) spectroscopy combined with a statistical classification strategy (SCS) successfully distinguished between Candida albicans and Candida dubliniensis. 96% of the isolates from an independent test set were identified correctly. This proves that this rapid approach is a valuable method for the identification and chemotaxonomic characterisation of closely related taxa. Most discriminatory regions were correlated with metabolite profiles, indicating biochemical differences between the two species.

Identification ofStaphylococcus aureusBrain Abscesses: Rat and Human Studies with1H MR Spectroscopy

To determine the feasibility of a statistical classification strategy (SCS) and the identity of metabolites of bacterial and host origins that potentially contributed to the most discriminatory regions of magnetic resonance (MR) spectra from Staphylococcus aureus abscesses of biopsy material from controls, gliomas, and staphylococcal abscesses. Human and animal study received ethics committee approval, and informed patient consent was obtained. A rat model of S aureus brain abscess was developed. Histologic and microbiologic examination was performed to assess abscess development 3-4, 6-8, and 10-15 days after initiation. Metabolite profiles in pus (n = 62) and controls (n = 37) were characterized with ex vivo MR spectroscopy and compared with data from rat gliomas (n = 27). SCS, optimal region selection, and development of pairwise classifiers allowed MR spectra of abscesses (n = 42, day 6-8) to be distinguished from those of glioblastoma multiforme and controls. MR spectroscopy profiles of pus from animal abscesses were compared with in vivo MR spectra from patients with staphylococcal brain abscesses (n = 7, aged 6-67 years) and ex vivo pus MR spectra from patients with S aureus abscesses. Histologically confirmed abscesses were present 6-8 days after stereotactic injection of S aureus in 42 of 47 rats (89%). MR spectra of abscesses and glioblastoma multiforme in the animal model were similar. Typical metabolites of abscesses due to anaerobe bacteria (acetate, succinate, amino acids) were not detectable in S aureus abscesses in rats or humans. MR spectroscopic findings from controls, abscesses, and gliomas were distinguished by means of SCS with an accuracy of 99%. Analysis of the most discriminatory regions with two-dimensional correlation spectra indicated that glutamine and/or glutamate and aspartate potentially contributed to successful classification. S aureus is detectable in abscesses with a non-culture-based method in an animal model.

Diagnosis of cerebral cryptococcoma using a computerized analysis of 1H NMR spectra in an animal model

Viable cryptococci load in biopsy material from an animal model of cerebral cryptococcoma were correlated with 1H NMR spectra and metabolite profiles. A statistical classification strategy was applied to distinguish among high-resolution 1H NMR spectra acquired from cryptococcomas, glioblastomas, and normal brain tissue. The overall classification accuracy was 100% when a genetic-algorithm-based optimal region selection preceded the development of linear discriminant analysis-based classifiers. The method remained robust despite differences in the microbial load of the cryptococcoma group when harvested at different time points. These results indicate the feasibility of the method for diagnosis without isolation of the pathogenic microorganism and its potential for in vivo diagnosis based on computerized analysis of magnetic resonance spectra.

Práctica docente en el aula multigrado rural de una población mexicana

Con el objeto de presentar el escenario del aula multigrado en la zona rural en pobreza extrema se emplea una estrategia de clasificación estadística con el procedimiento por conglomerados. La muestra poblacional fue de 206 docentes que se clasificaron en base a datos de observación y reporte verbal de estrategias didácticas, control de grupo, planeación, evaluación y apoyo al aprendizaje, identificándose 5 tipos en la práctica docente. Los grupos se contrastan con los resultados en competencias académicas básicas de sus alumnos. Se señala la importancia de la diversidad en las estrategias didácticas y de manejo grupal, así como la variedad de elementos que los docentes emplean en su planificación y evaluación como la característica que permite identificar la diferencia entre los resultados de los alumnos. En la perspectiva de la política educativa vigente se analiza el impacto de los mecanismos de incentivos y capacitación docente como elementos para promover habilidades cognitivas sobre el proceso enseñanza-aprendizaje. Se resaltan las condiciones de la enseñanza multigrado en zona rural como elemento primordial para mediar la regulación de estrategias de control disciplinario y planeación de la práctica docente. Se crítica los sistemas actuales de compensación por la preponderancia de una visión administrativa de la enseñanza. Finalmente se enfatiza la utilidad de la clasificación de la práctica docente para posteriores acciones de capacitación específica a las condiciones de la zona rural, así como a distintos niveles de pericia de los profesores.

Determination of Grade and Receptor Status from the Primary Breast Lesion by Magnetic Resonance Spectroscopy

Magnetic resonance spectra (MRS) from fine needle aspiration biopsies (FNAB) from primary breast lesions were analysed using a pattern recognition method, Statistical Classification Strategy, to assess tumor grade and oestrogen receptor (ER) and progesterone receptor (PgR) status. Grade 1 and 2 breast cancers were separated from grade 3 cancers with a sensitivity and specificity of 96% and 95%, respectively. The ER status was predicted with a sensitivity of 91% and a specificity of 90%, and the PgR status with a sensitivity of 91% and a specificity of 86%. These classifiers provide rapid and reliable, computerized information and may offer an objective method for determining these prognostic indicators simultaneously with the diagnosis of primary pathology and lymph node involvement.

Detection of melanoma lymph node metastases by proton magnetic resonance spectroscopy of fine-needle aspirates

Introduction Non-surgical sentinel node (SN) evaluation offers advantages over SN removal. Proton Magnetic Resonance Spectroscopy (MRS) of lymph node needle aspirates accurately identifies the presence of metabolites associated with melanoma micrometastases. Validation of this technique would reduce the morbidity and costs of SN evaluation. Methods Fine needle aspiration biopsies (FNAB) from 70 malignant and 42 benign nodes from patients undergoing node resection for metastatic melanoma were obtained. Proton MRS (8.5 T) was carried out using standard protocols (4). Four 5~tm sections from each node block (3mm thick) were stained with H&E (2 sections) and for S 100 protein and HMB45. MR spectra and histopathology were correlated using a statistical classification strategy (SCS) (3). Results Proton MRS of FNAB from benign and metastatic nodes are shown in Figure 1. Resonances include those from lipid (Lip), amino acids, lactate, creatine (Cre), phosphocreatine, choline (Chol) metabolites and inositol. An SCS-based classifier was generated for benign and metastatic nodes. In four random training sets, spectra from 47 metastatic and 28 benign nodes were subjected to SCS. Using five optimally discriminatory spectral regions, metastases was predicted with a sensitivity of 97.3%, a specificity of 90.2% and an accuracy of 94.7%. In independent validation sets (samples not in training sets), including 23 metastatic and 14 benign nodes, the presence of metastases was predicted with a sensitivity of 93.5%, a specificity of 87.5% and an accuracy of 91.2%. The crispness of the data (% samples with a class probability >75%) was ~88% for training and validation sets. These data indicate that SN staging of melanoma may be achieved without surgical biopsy and histopathology. Conclusions Pro- ton MRS of FNAB of lymph nodes provides robust, accurate diagnosis of metastatic disease in nodes from melanoma patients.

Rapid identification of Candida species by using nuclear magnetic resonance spectroscopy and a statistical classification strategy.

Nuclear magnetic resonance (NMR) spectra were acquired from suspensions of clinically important yeast species of the genus Candida to characterize the relationship between metabolite profiles and species identification. Major metabolites were identified by using two-dimensional correlation NMR spectroscopy. One-dimensional proton NMR spectra were analyzed by using a staged statistical classification strategy. Analysis of NMR spectra from 442 isolates of Candida albicans, C. glabrata, C. krusei, C. parapsilosis, and C. tropicalis resulted in rapid, accurate identification when compared with conventional and DNA-based identification. Spectral regions used for the classification of the five yeast species revealed species-specific differences in relative amounts of lipids, trehalose, polyols, and other metabolites. Isolates of C. parapsilosis and C. glabrata with unusual PCR fingerprinting patterns also generated atypical NMR spectra, suggesting the possibility of intraspecies discontinuity. We conclude that NMR spectroscopy combined with a statistical classification strategy is a rapid, nondestructive, and potentially valuable method for identification and chemotaxonomic characterization that may be broadly applicable to fungi and other microorganisms.

Pathology of Barrett’s esophagus by proton magnetic resonance spectroscopy and a statistical classification strategy

Background Barrett’s esophagus is thought to be a precursor of adenocarcinoma. The incidence of adenocarcinoma of the lower esophagus in the Western world is rising and accounts for more than 40% of esophageal carcinomas in males. It is not possible to identify which Barrett’s patients are at high risk of developing malignancy. Here we applied a statistical classification strategy to the analysis of magnetic resonance spectroscopy and histopathological data from esophageal biopsies to ascertain whether this risk could be identified in Barrett’s patients. Methods Tissue specimens from 72 patients (29 noncancer-bearing and 43 cancer-bearing) were analyzed by one-dimensional proton magnetic resonance spectroscopy at 8.5 Tesla. Diagnostic correlation was performed between the magnetic resonance spectra and histopathology. The magnetic resonance magnitude spectra were preprocessed, followed by identification of optimal spectral regions, and were then classified by cross-validated linear discriminant analysis of rank orders of the first derivative of magnetic resonance spectra. Results Magnetic resonance spectroscopy combined with a statistical classification strategy analysis distinguished normal esophagus from adenocarcinoma and Barrett’s epithelium with an accuracy of 100%. Barrett’s epithelium and adenocarcinoma were distinguished with an accuracy of 98.6% but only when 4 of the Barrett’s specimens and 7 of the carcinoma specimens, determined to be “fuzzy” (ie, unable to be accurately assigned to either class) were withdrawn. The 7 cancer and 4 Barrett’s specimens, determined to be “fuzzy” using the Barrett’s versus cancer (B versus C) classifier, were submitted to the other two classifiers (Barrett’s versus normal [B versus N] and normal versus cancer [N versus C], respectively). The 4 Barrett’s specimens were assigned to Barrett’s by the N versus B classifier and to normal (n = 2) or cancer (n = 2) classes by the N versus C classifer. The 7 cancer specimens were crisply assigned to the cancer class (N versus C), or for the B versus N classifier, to the Barrett’s class (ie, more similar to Barrett’s than to normal tissue). Visual inspection of the spectra from histologically identified Barrett’s epithelium showed a gradation from normal to carcinoma. Conclusions Proton magnetic resonance spectroscopy of esophageal biopsies combined with a statistical classification strategy data analysis provides a robust diagnosis with a high degree of accuracy for discriminating normal epithelium from esophageal adenocarcinoma and Barrett’s esophagus. Different spectral categories of Barrett’s epithelium were identified both by visual inspection and by statistical classification strategy, possibly reflecting the risk of future malignant transformation.

Statistical Classification Strategy for Proton Magnetic ResonanceSpectra of Soft Tissue Sarcoma: An Exploratory Study withPotential Clinical Utility

Purpose: Histological grading is currently one of the best predictors of tumor behavior and outcome in soft tissue sarcoma. However, occasionally there is significant disagreement even among expert pathologists. An alternative method that gives more reliable and non-subjective diagnostic information is needed. The potential use of proton magnetic resonance spectroscopy in combination with an appropriate statistical classification strategy was tested here in differentiating normal mesenchymal tissue from soft tissue sarcoma. Methods: Fifty-four normal and soft tissue sarcoma specimens of various histological types were obtained from 15 patients. One-dimensional proton magnetic resonance spectra were acquired at 360 MHz. Spectral data were analyzed by using both the conventional peak area ratios and a specific statistical classification strategy. Results: The statistical classification strategy gave much better results than the conventional analysis. The overall classification accuracy (based on the histopathology of the MRS specimens) in differentiating normal mesenchymal from soft tissue sarcoma was 93%, with a sensitivity of 100% and specificity of 88%.The results in the test set were 83, 92 and 76%, respectively. Our optimal region selection algorithm identified six spectral regions with discriminating potential, including those assigned to choline, creatine, glutamine, glutamic acid and lipid. Conclusion: Proton magnetic resonance spectroscopy combined with a statistical classification strategy gave good results in differentiating normal mesenchymal tissue from soft tissue sarcoma specimens ex vivo. Such an approach may also differentiate benign tumors from malignant ones and this will be explored in future studies.

Pathology of hepatocellular carcinoma and its precursors using proton magnetic resonance spectroscopy and a statistical classification strategy

Apply the statistical classification strategy (SCS) to magnetic resonance spectroscopy (MRS) data from liver biopsies and test its potential to discriminate between normal liver, cirrhotic nodules and nodules of hepatocellular carcinoma with a high degree of accuracy. Liver tissue specimens from 54 patients undergoing either partial (hemi) or total hepatectomy were analysed by one-dimensional proton MRS at 8.5 Tesla. Histologically, these specimens were confirmed as normal (n=31), cirrhotic (n=59), and hepatocellular carcinoma (HCC, n=32). Diagnostic correlation was performed between the MR spectra and histopathology. An SCS was applied consisting of pre-processing MR magnitude spectra to identify spectral regions of maximal discriminatory value, and cross-validated linear discriminant analysis. SCS applied to MRS data distinguished normal liver tissue from HCC with an accuracy of 100%. Normal liver tissue was distinguished from cirrhotic liver with an accuracy of 92% and cirrhotic liver was distinguished from HCC with an accuracy of 98%. SCS applied to proton MRS of liver biopsies provides a robust method to distinguish, with a high degree of accuracy, HCC from both cirrhotic and normal liver.

Diagnosis and prognosis of breast cancer by magnetic resonance spectroscopy of fine-needle aspirates analysed using a statistical classification strategy.

The aim was to develop robust classifiers to analyse magnetic resonance spectroscopy (MRS) data of fine-needle aspirates taken from breast tumours. The resulting data could provide computerized, classification-based diagnosis and prognostic indicators. Fine-needle aspirate biopsies obtained at the time of surgery for both benign and malignant breast diseases were analysed by one-dimensional proton MRS at 8.5 Tesla. Diagnostic correlation was performed between the spectra and standard pathology reports, including the presence of vascular invasion by the primary cancer and involvement of the excised axillary lymph nodes. Malignant tissue was distinguished from benign lesions with an overall accuracy of 93 per cent. From the same spectra, lymph node involvement was predicted with an overall accuracy of 95 per cent, and tumour vascular invasion with an overall accuracy of 94 per cent. The pathology, nodal involvement and tumour vascular invasion were predicted by computerized statistical classification of the proton MRS spectrum from a fine-needle aspirate biopsy taken from the primary breast lesion.