Feasibility of infrared spectroscopy with pattern recognition techniques to identify a subpopulation of mares at risk of producing foals diagnosed with failure of transfer of passive immunity.

OBJECTIVE: To assess the feasibility of a serum-based test using infrared spectroscopy to identify a subpopulation of mares at risk of producing foals susceptible to failure of passive transfer of immunity (FPT) because of mare-associated factors. MATERIALS AND METHODS: Serum was collected from post-parturient mares (n = 126) and their foals at 24-72 h of age. A radial immunodiffusion IgG test was used to determine each foal's serum IgG concentration. Infrared absorbance spectra of dam sera were collected in the wave number range of 400-4000 cm(-1). Following data preprocessing, pattern recognition techniques were used to identify spectroscopic information capable of distinguishing between mares with FPT foals and those with normal foals. The sensitivity and specificity of infrared spectroscopy to detect risk-positive mares were calculated. RESULTS: Five wave number regions were identified as optimal for distinguishing between the two groups of mares: 740.9-785.2 cm(-1), 796.8-816.0 cm(-1), 970.4-993.5 cm(-1), 1371.6-1406.3 cm(-1) and 1632.0-1659.0 cm(-1). Based upon the infrared spectroscopic information within these discriminatory subregions, the spectra provided the risk status of the mares with a classification success rate of 81.0%. The sensitivity of the classification system was 85.7% and specificity was 80.0%. CONCLUSION: This preliminary study demonstrates that infrared spectra of dam serum have the potential to provide the basis for a new periparturient screening method for a subpopulation of mares at risk of having a foal susceptible to FPT. Further development may provide an economic and rapid technique for the pre-parturient assessment of mares.

Class proximity measures--dissimilarity-based classification and display of high-dimensional data.

For two-class problems, we introduce and construct mappings of high-dimensional instances into dissimilarity (distance)-based Class-Proximity Planes. The Class Proximity Projections are extensions of our earlier relative distance plane mapping, and thus provide a more general and unified approach to the simultaneous classification and visualization of many-feature datasets. The mappings display all L-dimensional instances in two-dimensional coordinate systems, whose two axes represent the two distances of the instances to various pre-defined proximity measures of the two classes. The Class Proximity mappings provide a variety of different perspectives of the dataset to be classified and visualized. We report and compare the classification and visualization results obtained with various Class Proximity Projections and their combinations on four datasets from the UCI data base, as well as on a particular high-dimensional biomedical dataset.

Potential of mid-infrared spectroscopy to aid the triage of patients with acute chest pain.

A total of 1,429 serum samples from 389 consecutive patients with acute chest pain were analyzed with the goal to aid the rapid diagnosis of acute myocardial infarction. To the best of our knowledge this is the largest and most comprehensive study on mid-infrared spectroscopy in cardiology. We were able to identify those signatures in the mid-infrared spectra of the samples, which were specific to either acute myocardial infarction or chest pain of other origin (angina pectoris, oesophagitis, etc). These characteristic spectral differences were used to distinguish between the cause of the donor's acute chest pain using robust linear discriminant analysis. A sensitivity of 88.5% and a specificity of 85.1% were achieved in a blind validation. The area under the receiver operating characteristics curve amounts to 0.921, which is comparable to the performance of routine cardiac laboratory markers within the same study population. The biochemical interpretation of the spectral signatures points towards an important role of carbohydrates and potentially glycation. Our studies indicate that the "Diagnostic Pattern Recognition (DPR)" method presented here has the potential to aid the diagnostic procedure as early as within the first 6 hours after the onset of chest pain.

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.

Detection of cholangiocarcinoma with magnetic resonance spectroscopy of bile in patients with and without primary sclerosing cholangitis.

BACKGROUND: Early detection of cholangiocarcinoma (CC) is very difficult, especially in patients with primary sclerosing cholangitis (PSC) who are at increased risk of developing CC. PURPOSE: To evaluate 1H magnetic resonance spectroscopy ((1)H-MRS) of bile as a diagnostic marker for CC in patients with and without PSC. MATERIAL AND METHODS: The institutional review board approved the study, and all patients gave informed consent. Bile from 49 patients was sampled and investigated using 1H-MRS. MR spectra of bile samples from 45 patients (18 female; age range 22-87 years, mean age 57 years) were analyzed both conventionally and using computerized multivariate analysis. Sixteen of the patients had CC, 18 had PSC, and 11 had other benign findings. RESULTS: The spectra of bile from CC patients differed from the benign group in the levels of phosphatidylcholine, bile acids, lipid, and cholesterol. It was possible to distinguish CC from benign conditions in all patients with malignancy. Two benign non-PSC patients were misclassified as malignant. The sensitivity, specificity, and accuracy were 88.9%, 87.1%, and 87.8%, respectively. CONCLUSION: With 1H-MRS of bile, cholangiocarcinoma could be discriminated from benign biliary conditions with or without PSC.

Direct classification of high-dimensional data in low-dimensional projected feature spaces--comparison of several classification methodologies.

Previously, we introduced a distance (similarity)-based mapping for the visualization of high-dimensional patterns and their relative relationships. The mapping preserves exactly the original distances from all points to any two reference patterns in a special two-dimensional coordinate system, the relative distance plane (RDP). We extend the RDP mapping's applicability from visualization to classification. Several of the classifiers use the RDP directly. These include the standard linear discriminant analysis (LDA), nearest neighbor classifiers, and a transvariation probabilities-based classification method that is natural in the RDP. Several reference directions can also be combined to create new coordinate systems in which arbitrary classifiers can be developed. We obtain increased confidence in the classification results by cycling through all possible reference pairs and computing a misclassification-based weighted accuracy. The classification results on several high-dimensional biomedical datasets are compared.

Mapping high-dimensional data onto a relative distance plane--an exact method for visualizing and characterizing high-dimensional patterns.

We introduce a distance (similarity)-based mapping for the visualization of high-dimensional patterns and their relative relationships. The mapping preserves exactly the original distances between points with respect to any two reference patterns in a special two-dimensional coordinate system, the relative distance plane (RDP). As only a single calculation of a distance matrix is required, this method is computationally efficient, an essential requirement for any exploratory data analysis. The data visualization afforded by this representation permits a rapid assessment of class pattern distributions. In particular, we can determine with a simple statistical test whether both training and validation sets of a 2-class, high-dimensional dataset derive from the same class distributions. We can explore any dataset in detail by identifying the subset of reference pairs whose members belong to different classes, cycling through this subset, and for each pair, mapping the remaining patterns. These multiple viewpoints facilitate the identification and confirmation of outliers. We demonstrate the effectiveness of this method on several complex biomedical datasets. Because of its efficiency, effectiveness, and versatility, one may use the RDP representation as an initial, data mining exploration that precedes classification by some classifier. Once final enhancements to the RDP mapping software are completed, we plan to make it freely available to researchers.

Classification of signatures of Bovine Spongiform Encephalopathy in serum using infrared spectroscopy.

Signatures of Bovine Spongiform Encephalopathy (BSE) have been identified in serum by means of "Diagnostic Pattern Recognition (DPR)". For DPR-analysis, mid-infrared spectroscopy of dried films of 641 serum samples was performed using disposable silicon sample carriers and a semi-automated DPR research system operating at room temperature. The combination of four mathematical classification approaches (principal component analysis plus linear discriminant analysis, robust linear discriminant analysis, artificial neural network, support vector machine) allowed for a reliable assignment of spectra to the class "BSE-positive" or "BSE-negative". An independent, blinded validation study was carried out on a second DPR research system at the Veterinary Laboratory Agency, Weybridge, UK. Out of 84 serum samples originating from terminally-ill, BSE-positive cattle, 78 were classified correctly. Similarly, 73 out of 76 BSE-negative samples were correctly identified by DPR such that, numerically, an accuracy of 94.4 % can be calculated. At a confidence level of 0.95 (alpha = 0.05) these results correspond to a sensitivity > 85% and a specificity > 90%. Identical class assignment by all four classifiers occurred in 75% of the cases while ambiguous results were obtained in only 8 of the 160 cases. With an area under the ROC (receiver operating charateristics) curve of 0.991, DPR may potentially supply a valuable surrogate marker for BSE even in cases in which a deliberate bias towards improved sensitivity or specificity is desired. To the best of our knowledge, DPR is the first and--up to now--only method which has demonstrated its capability of detecting BSE-related signatures in serum.

Class prediction and discovery using gene microarray and proteomics mass spectroscopy data: curses, caveats, cautions.

MOTIVATION: Two practical realities constrain the analysis of microarray data, mass spectra from proteomics, and biomedical infrared or magnetic resonance spectra. One is the 'curse of dimensionality': the number of features characterizing these data is in the thousands or tens of thousands. The other is the 'curse of dataset sparsity': the number of samples is limited. The consequences of these two curses are far-reaching when such data are used to classify the presence or absence of disease. RESULTS: Using very simple classifiers, we show for several publicly available microarray and proteomics datasets how these curses influence classification outcomes. In particular, even if the sample per feature ratio is increased to the recommended 5-10 by feature extraction/reduction methods, dataset sparsity can render any classification result statistically suspect. In addition, several 'optimal' feature sets are typically identifiable for sparse datasets, all producing perfect classification results, both for the training and independent validation sets. This non-uniqueness leads to interpretational difficulties and casts doubt on the biological relevance of any of these 'optimal' feature sets. We suggest an approach to assess the relative quality of apparently equally good classifiers.

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

BACKGROUND: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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.

Disease pattern recognition testing for rheumatoid arthritis using infrared spectra of human serum.

BACKGROUND: In view of the importance of the diagnosis of rheumatoid arthritis, a novel diagnostic method based on spectroscopic pattern recognition in combination with laboratory parameters such as the rheumatoid factor is described in the paper. Results of a diagnostic study of rheumatoid arthritis employing this method are presented. METHOD: The method uses classification of infrared (IR) spectra of serum samples by means of discriminant analysis. The spectroscopic pattern yielding the highest discriminatory power is found through a complex optimization procedure. In the study, IR spectra of 384 serum samples have been analyzed in this fashion with the objective of differentiating between rheumatoid arthritis and healthy subjects. In addition, the method integrates results from the classification with levels of the rheumatoid factor in the sample by optimized classifier weighting, in order to enhance classification accuracy, i.e. sensitivity and specificity. RESULTS: In independent validation, sensitivity and specificity of 84% and 88%, respectively, have been obtained purely on the basis of spectra classification employing a classifier designed specifically to provide robustness. Sensitivity and specificity are improved by 1% and 6%, respectively, upon inclusion of rheumatoid factor levels. Results for less robust methods are also presented and compared to the above numbers. CONCLUSION: The discrimination between RA and healthy by means of the pattern recognition approach presented here is feasible for IR spectra of serum samples. The method is sufficiently robust to be used in a clinical setting. A particular advantage of the method is its potential use in RA diagnosis at early stages of the disease.

The use of 1H magnetic resonance spectroscopy in inflammatory bowel diseases: distinguishing ulcerative colitis from Crohn's disease.

OBJECTIVES: The distinction between the two major forms of inflammatory bowel diseases (IBD), i.e., ulcerative colitis (UC) and Crohn's disease is sometimes difficult and may lead to a diagnosis of indeterminate colitis. We have used 1H magnetic resonance spectroscopy (MRS) combined with multivariate methods of spectral data analysis to differentiate UC from Crohn's disease and to evaluate normal-appearing mucosa in IBD. METHODS: Colon mucosal biopsies (45 UC and 31 Crohn's disease) were submitted to 1H MRS, and multivariate analysis was applied to distinguish the two diseases. A second study was performed to test endoscopically and histologically normal biopsies from IBD patients. A classifier was developed by training on 101 spectra (76 inflamed IBD tissues and 25 normal control tissues). The spectra of 38 biopsies obtained from endoscopically and histologically normal areas of the colons of patients with IBD were put into the validation test set. RESULTS: The classification accuracy between UC and Crohn's disease was 98.6%, with only one case of Crohn's disease and no cases of UC misclassified. The diagnostic spectral regions identified by our algorithm included those for taurine, lysine, and lipid. In the second study, the classification accuracy between normal controls and IBD was 97.9%. Only 47.4% of the endoscopically and histologically normal IBD tissue spectra were classified as true normals; 34.2% showed "abnormal" magnetic resonance spectral profiles, and the remaining 18.4% could not be classified unambiguously. CONCLUSIONS: There is a strong potential for MRS to be used in the accurate diagnosis of indeterminate colitis; it may also be sensitive in detecting preclinical inflammatory changes in the colon.

Disease pattern recognition in infrared spectra of human sera with diabetes mellitus as an example.

To benefit from the full information content of the mid-IR spectra of human sera, we directly related the overall shape of the spectra to the donors' disease states. For this approach of disease pattern recognition we applied cluster analysis and discriminant analysis to the example of the disease states diabetes type 1, diabetes type 2, and healthy. In a binary, supervised classification of any pair of these disease states we achieved specificities and sensitivities of approximately 80% within our data set.

Classification of breast tumors by grade and steroid receptor status using pattern recognition analysis of infrared spectra.

Infrared (IR) spectroscopy applied to tissue sections yields complex spectra that provide a molecular fingerprint of the tissue. We have studied a cohort of 77 breast tumors by IR spectroscopy to develop an objective method for the assignment of grade of breast tumors. Although the major variations between spectra from different tumors were in absorptions arising from triglycerides (adipose tissue) and collagen, subtle changes in spectra could be detected that were independent of cellularity and tissue composition. Using a specific multivariate pattern recognition strategy to associate these changes in spectra with different tumor grades, we then were able to accurately reclassify tumors by grade (87% accuracy; kappa = 0.835). A similar approach allowed classification of steroid receptor status (93% accuracy; kappa = 0.852). We conclude that IR spectroscopy may have clinical utility in the objective assignment of breast tumor grade.

Near-optimal region selection for feature space reduction: novel preprocessing methods for classifying MR spectra.

We introduce a global feature extraction method specifically designed to preprocess magnetic resonance spectra of biomedical origin. Such preprocessing is essential for the accurate and reliable classification of diseases or disease stages manifest in the spectra. The new method is genetic algorithm-guided. It is compared with our enhanced version of the standard forward selection algorithm. Both seek and select optimal spectral subregions. These subregions necessarily retain spectral information, thus aiding the eventual identification of the biochemistry of disease presence and progression. The power of the methods is demonstrated on two biomedical examples: the discrimination between meningioma and astrocytoma in brain tissue biopsies, and the classification of colorectal biopsies into normal and tumour classes. Both preprocessing methods lead to classification accuracies over 97% for the two examples.

Classification of 1H MR spectra of human brain neoplasms: the influence of preprocessing and computerized consensus diagnosis on classification accuracy.

We study how classification accuracy can be improved when both different data preprocessing methods and computerized consensus diagnosis (CCD) are applied to 1H magnetic resonance (MR) spectra of astrocytomas, meningiomas, and epileptic brain tissue. The MR spectra (360 MHz, 37 degrees C) of tissue specimens (biopsies) from subjects with meningiomas (95; 26 cases), astrocytomas (74; 26 cases), and epilepsy (37; 8 cases) were preprocessed by several methods. Each data set was partitioned into training and validation sets. Robust classification was carried out via linear discriminant analysis (LDA), artificial neural nets (NN), and CCD, and the results were compared with histopathological diagnosis of the MR specimens. Normalization of the relevant spectral regions affects classification accuracy significantly. The spectra-based average three-class classification accuracies of LDA and NN increased from 81.7% (unnormalized data sets) to 89.9% (normalized). CCD increased the classification accuracy of the normalized sets to an average of 91.8%. CCD invariably decreases the fraction of unclassifiable spectra. The same trends prevail, with improved results, for case-based classification. Preprocessing the 1H MR spectra is essential for accurate and reliable classification of astrocytomas, meningiomas, and nontumorous epileptic brain tissue. CCD improves classification accuracy, with an attendant decrease in the fraction of unclassifiable spectra or cases.

Computerized consensus diagnosis: a classification strategy for the robust analysis of MR spectra. I. Application to 1H spectra of thyroid neoplasms.

We introduce and apply a new classification strategy we call computerized consensus diagnosis (CCD). Its purpose is to provide robust, reliable classification of biomedical data. The strategy involves the cross-validated training of several classifiers of diverse conceptual and methodological origin on the same data, and appropriately combining their outcomes. The strategy is tested on proton magnetic resonance spectra of human thyroid biopsies, which are successfully allocated to normal or carcinoma classes. We used Linear Discriminant Analysis, a Neural Net-based method, and Genetic Programming as independent classifiers on two spectral regions, and chose the median of the six classification outcomes as the consensus. This procedure yielded 100% specificity and 100% sensitivity on the training sets, and 100% specificity and 98% sensitivity on samples of known malignancy in the test sets. We discuss the necessary steps any classification approach must take to guarantee reliability, and stress the importance of fuzziness and undecidability in robust classification.

Tolerance to analog hardware of on-chip learning in backpropagation networks.

In this paper we present results of simulations performed assuming both forward and backward computation are done on-chip using analog components. Aspects of analog hardware studied are component variability, limited voltage ranges, components (multipliers) that only approximate the computations in the backpropagation algorithm, and capacitive weight decay. It is shown that backpropagation networks can learn to compensate for all these shortcomings of analog circuits except for zero offsets, and the latter are correctable with minor circuit complications. Variability in multiplier gains is not a problem, and learning is still possible despite limited voltage ranges and function approximations. Fixed component variation from fabrication is shown to be less detrimental to learning than component variation due to noise. Weight decay is tolerable provided it is sufficiently small, which implies frequent refreshing by rehearsal on the training data or modest cooling of the circuits. The former approach allows for learning nonstationary problem sets.