Automated diagnosis of brain tumours astrocytomas using probabilistic neural network clustering and support vector machines

Plasma protein biomarkers for the detection of pancreatic neuroendocrine tumors and differentiation from small intestinal neuroendocrine tumors

There is an unmet need for novel biomarkers to diagnose and monitor patients with neuroendocrine neoplasms. The EXPLAIN study explores a multi-plasma protein and supervised machine learning strategy to improve the diagnosis of pancreatic neuroendocrine tumors (PanNET) and differentiate them from small intestinal neuroendocrine tumors (SI-NET). At time of diagnosis, blood samples were collected and analyzed from 39 patients with PanNET, 135 with SI-NET (World Health Organization Grade 1-2) and 144 controls. Exclusion criteria were other malignant diseases, chronic inflammatory diseases, reduced kidney or liver function. Prosed Oncology-II (i.e., OLink) was used to measure 92 cancer related plasma proteins. Chromogranin A was analyzed separately. Median age in all groups was 65-67 years and with a similar sex distribution (females: PanNET, 51%; SI-NET, 42%; controls, 42%). Tumor grade (G1/G2): PanNET, 39/61%; SI-NET, 46/54%. Patients with liver metastases: PanNET, 78%; SI-NET, 63%. The classification model of PanNET versus controls provided a sensitivity (SEN) of 0.84, specificity (SPE) 0.98, positive predictive value (PPV) of 0.92 and negative predictive value (NPV) of 0.95, and area under the receiver operating characteristic curve (AUROC) of 0.99; the model for the discrimination of PanNET versus SI-NET providing a SEN 0.61, SPE 0.96, PPV 0.83, NPV 0.90 and AUROC 0.98. These results suggest that a multi-plasma protein strategy can significantly improve diagnostic accuracy of PanNET and SI-NET.

A Plasma Protein Biomarker Strategy for Detection of Small Intestinal Neuroendocrine Tumors

BACKGROUND

Small intestinal neuroendocrine tumors (SI-NETs) are difficult to diagnose in the early stage of disease. Current blood biomarkers such as chromogranin A (CgA) and 5-hydroxyindolacetic acid have low sensitivity (SEN) and specificity (SPE). This is a first preplanned interim analysis (Nordic non-interventional, prospective, exploratory, EXPLAIN study [NCT02630654]). Its objective is to investigate if a plasma protein multi-biomarker strategy can improve diagnostic accuracy (ACC) in SI-NETs.

METHODS

At the time of diagnosis, before any disease-specific treatment was initiated, blood was collected from patients with advanced SI-NETs and 92 putative cancer-related plasma proteins from 135 patients were analyzed and compared with the results of age- and sex-matched controls (n = 143), using multiplex proximity extension assay and machine learning techniques.

RESULTS

Using a random forest model including 12 top ranked plasma proteins in patients with SI-NETs, the multi-biomarker strategy showed SEN and SPE of 89 and 91%, respectively, with negative predictive value (NPV) and positive predictive value (PPV) of 90 and 91%, respectively, to identify patients with regional or metastatic disease with an area under the receiver operator characteristic curve (AUROC) of 99%. In 30 patients with normal CgA concentrations, the model provided a diagnostic SPE of 98%, SEN of 56%, and NPV 90%, PPV of 90%, and AUROC 97%, regardless of proton pump inhibitor intake.

CONCLUSION

This interim analysis demonstrates that a multi-biomarker/machine learning strategy improves diagnostic ACC of patients with SI-NET at the time of diagnosis, especially in patients with normal CgA levels. The results indicate that this multi-biomarker strategy can be useful for early detection of SI-NETs at presentation and conceivably detect recurrence after radical primary resection.

ENRICHING STATISTICAL INFERENCES ON BRAIN CONNECTIVITY FOR ALZHEIMER'S DISEASE ANALYSIS VIA LATENT SPACE GRAPH EMBEDDING

We develop a graph node embedding Deep Neural Network that leverages statistical outcome measure and graph structure given in the data. The objective is to identify regions of interests (ROIs) in the brain that are affected by topological changes of brain connectivity due to specific neurodegenerative diseases by enriching statistical group analysis. We tackle this problem by learning a latent space where statistical inference can be made more effectively. Our experiments on a large-scale Alzheimer's Disease dataset show promising result identifying ROIs that show statistically significant group differences separating even early and late Mild Cognitive Impairment (MCI) groups whose effect sizes are very subtle.

Investigating the Behaviour of Machine Learning Techniques to Segment Brain Metastases in Radiation Therapy Planning

This work aimed to investigate whether automated classifiers belonging to feature-based and deep learning may approach brain metastases segmentation successfully. Support Vector Machine and V-Net Convolutional Neural Network are selected as representatives of the two approaches. In the experiments, we consider several configurations of the two methods to segment brain metastases on contrast-enhanced T1-weighted magnetic resonance images. Performances were evaluated and compared under critical conditions imposed by the clinical radiotherapy domain, using in-house dataset and public dataset created for the Multimodal Brain Tumour Image Segmentation (BraTS) challenge. Our results showed that the feature-based and the deep network approaches are promising for the segmentation of Magnetic Resonance Imaging (MRI) brain metastases achieving both an acceptable level of performance. Experimental results also highlight different behaviour between the two methods. Support vector machine (SVM) improves performance with a smaller training set, but it is unable to manage a high level of heterogeneity in the data and requires post-processing refinement stages. The V-Net model shows good performances when trained on multiple heterogeneous cases but requires data augmentations and transfer learning procedures to optimise its behaviour. The paper illustrates a software package implementing an integrated set of procedures for active support in segmenting brain metastases within the radiotherapy workflow.

A fully automated image analysis method to quantify lung fibrosis in the bleomycin-induced rat model

Intratracheal administration of bleomycin induces fibrosis in the lung, which is mainly assessed by histopathological grading that is subjective. Current literature highlights the need of reproducible and quantitative pulmonary fibrosis analysis. If some quantitative studies looked at fibrosis parameters separately, none of them quantitatively assessed both aspects: lung tissue remodeling and collagenization. To ensure reliable quantification, support vector machine learning was used on digitalized images to design a fully automated method that analyzes two important aspects of lung fibrosis: (i) areas having substantial tissue remodeling with appearance of dense fibrotic masses and (ii) collagen deposition. Fibrotic masses were identified on low magnification images and collagen detection was performed at high magnification. To insure a fully automated application the tissue classifier was trained on several independent studies that were performed over a period of four years. The detection method generates two different values that can be used to quantify lung fibrosis development: (i) percent area of fibrotic masses and (ii) percent of alveolar collagen. These two parameters were validated using independent studies from bleomycin- and saline-treated animals. A significant change of these lung fibrosis quantification parameters- increased amount of fibrotic masses and increased collagen deposition- were observed upon intratracheal administration of bleomycin and subsequent significant beneficial treatments effects were observed with BIBF-1120 and pirfenidone.

Convergent Time-Varying Regression Models for Data Streams: Tracking Concept Drift by the Recursive Parzen-Based Generalized Regression Neural Networks

One of the greatest challenges in data mining is related to processing and analysis of massive data streams. Contrary to traditional static data mining problems, data streams require that each element is processed only once, the amount of allocated memory is constant and the models incorporate changes of investigated streams. A vast majority of available methods have been developed for data stream classification and only a few of them attempted to solve regression problems, using various heuristic approaches. In this paper, we develop mathematically justified regression models working in a time-varying environment. More specifically, we study incremental versions of generalized regression neural networks, called IGRNNs, and we prove their tracking properties - weak (in probability) and strong (with probability one) convergence assuming various concept drift scenarios. First, we present the IGRNNs, based on the Parzen kernels, for modeling stationary systems under nonstationary noise. Next, we extend our approach to modeling time-varying systems under nonstationary noise. We present several types of concept drifts to be handled by our approach in such a way that weak and strong convergence holds under certain conditions. Finally, in the series of simulations, we compare our method with commonly used heuristic approaches, based on forgetting mechanism or sliding windows, to deal with concept drift. Finally, we apply our concept in a real life scenario solving the problem of currency exchange rates prediction.

A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery

Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases.

Resting State Effective Connectivity Allows Auditory Hallucination Discrimination

Hallucinations are elusive phenomena that have been associated with psychotic behavior, but that have a high prevalence in healthy population. Some generative mechanisms of Auditory Hallucinations (AH) have been proposed in the literature, but so far empirical evidence is scarce. The most widely accepted generative mechanism hypothesis nowadays consists in the faulty workings of a network of brain areas including the emotional control, the audio and language processing, and the inhibition and self-attribution of the signals in the auditive cortex. In this paper, we consider two methods to analyze resting state fMRI (rs-fMRI) data, in order to measure effective connections between the brain regions involved in the AH generation process. These measures are the Dynamic Causal Modeling (DCM) cross-covariance function (CCF) coefficients, and the partially directed coherence (PDC) coefficients derived from Granger Causality (GC) analysis. Effective connectivity measures are treated as input classifier features to assess their significance by means of cross-validation classification accuracy results in a wrapper feature selection approach. Experimental results using Support Vector Machine (SVM) classifiers on an rs-fMRI dataset of schizophrenia patients with and without a history of AH confirm that the main regions identified in the AH generative mechanism hypothesis have significant effective connection values, under both DCM and PDC evaluation.

Discrimination of schizophrenia auditory hallucinators by machine learning of resting-state functional MRI

Auditory hallucinations (AH) are a symptom that is most often associated with schizophrenia, but patients with other neuropsychiatric conditions, and even a small percentage of healthy individuals, may also experience AH. Elucidating the neural mechanisms underlying AH in schizophrenia may offer insight into the pathophysiology associated with AH more broadly across multiple neuropsychiatric disease conditions. In this paper, we address the problem of classifying schizophrenia patients with and without a history of AH, and healthy control (HC) subjects. To this end, we performed feature extraction from resting state functional magnetic resonance imaging (rsfMRI) data and applied machine learning classifiers, testing two kinds of neuroimaging features: (a) functional connectivity (FC) measures computed by lattice auto-associative memories (LAAM), and (b) local activity (LA) measures, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF). We show that it is possible to perform classification within each pair of subject groups with high accuracy. Discrimination between patients with and without lifetime AH was highest, while discrimination between schizophrenia patients and HC participants was worst, suggesting that classification according to the symptom dimension of AH may be more valid than discrimination on the basis of traditional diagnostic categories. FC measures seeded in right Heschl's gyrus (RHG) consistently showed stronger discriminative power than those seeded in left Heschl's gyrus (LHG), a finding that appears to support AH models focusing on right hemisphere abnormalities. The cortical brain localizations derived from the features with strong classification performance are consistent with proposed AH models, and include left inferior frontal gyrus (IFG), parahippocampal gyri, the cingulate cortex, as well as several temporal and prefrontal cortical brain regions. Overall, the observed findings suggest that computational intelligence approaches can provide robust tools for uncovering subtleties in complex neuroimaging data, and have the potential to advance the search for more neuroscience-based criteria for classifying mental illness in psychiatry research.

Brain tumor classification using AFM in combination with data mining techniques

Although classification of astrocytic tumors is standardized by the WHO grading system, which is mainly based on microscopy-derived, histomorphological features, there is great interobserver variability. The main causes are thought to be the complexity of morphological details varying from tumor to tumor and from patient to patient, variations in the technical histopathological procedures like staining protocols, and finally the individual experience of the diagnosing pathologist. Thus, to raise astrocytoma grading to a more objective standard, this paper proposes a methodology based on atomic force microscopy (AFM) derived images made from histopathological samples in combination with data mining techniques. By comparing AFM images with corresponding light microscopy images of the same area, the progressive formation of cavities due to cell necrosis was identified as a typical morphological marker for a computer-assisted analysis. Using genetic programming as a tool for feature analysis, a best model was created that achieved 94.74% classification accuracy in distinguishing grade II tumors from grade IV ones. While utilizing modern image analysis techniques, AFM may become an important tool in astrocytic tumor diagnosis. By this way patients suffering from grade II tumors are identified unambiguously, having a less risk for malignant transformation. They would benefit from early adjuvant therapies.

The identification of gut neuroendocrine tumor disease by multiple synchronous transcript analysis in blood

Gastroenteropancreatic (GEP) neuroendocrine neoplasms (NENs) are increasing in both incidence and prevalence. A delay in correct diagnosis is common for these lesions. This reflects the absence of specific blood biomarkers to detect NENs. Measurement of the neuroendocrine secretory peptide Chromogranin A (CgA) is used, but is a single value, is non-specific and assay data are highly variable. To facilitate tumor detection, we developed a multi-transcript molecular signature for PCR-based blood analysis. NEN transcripts were identified by computational analysis of 3 microarray datasets: NEN tissue (n = 15), NEN peripheral blood (n = 7), and adenocarcinoma (n = 363 tumors). The candidate gene signature was examined in 130 blood samples (NENs: n = 63) and validated in two independent sets (Set 1 [n = 115, NENs: n = 72]; Set 2 [n = 120, NENs: n = 58]). Comparison with CgA (ELISA) was undertaken in 176 samples (NENs: n = 81). 51 significantly elevated transcript markers were identified. Gene-based classifiers detected NENs in independent sets with high sensitivity (85–98%), specificity (93–97%), PPV (95–96%) and NPV (87–98%). The AUC for the NEN gene-based classifiers was 0.95–0.98 compared to 0.64 for CgA (Z-statistic 6.97–11.42, p<0.0001). Overall, the gene-based classifier was significantly (χ² = 12.3, p<0.0005) more accurate than CgA. In a sub-analysis, pancreatic NENs and gastrointestinal NENs could be identified with similar efficacy (79–88% sensitivity, 94% specificity), as could metastases (85%). In patients with low CgA, 91% exhibited elevated transcript markers. A panel of 51 marker genes differentiates NENs from controls with a high PPV and NPV (>90%), identifies pancreatic and gastrointestinal NENs with similar efficacy, and confirms GEP-NENs when CgA levels are low. The panel is significantly more accurate than the CgA assay. This reflects its utility to identify multiple diverse biological components of NENs. Application of this sensitive and specific PCR-based blood test to NENs will allow accurate detection of disease, and potentially define disease progress enabling monitoring of treatment efficacy.

Ranking-based kernels in applied biomedical diagnostics using a support vector machine

This paper presents some essential findings and results on using ranking-based kernels for the analysis and utilization of high dimensional and noisy biomedical data in applied clinical diagnostics. We claim that presented kernels combined with a state-of-the-art classification technique - a Support Vector Machine (SVM) - could significantly improve the classification rate and predictive power of the wrapper method, e.g. SVM. Moreover, the advantage of such kernels could be potentially exploited for other kernel methods and essential computer-aided tasks such as novelty detection and clustering. Our experimental results and theoretical generalization bounds imply that ranking-based kernels outperform other traditionally employed SVM kernels on high dimensional biomedical and microarray data.

Clinical decision support systems and computer-aided diagnosis in otology

OBJECTIVES

We reviewed the progress of the implementation of expert diagnostic systems in the field of otology.

STUDY DESIGN AND SETTING

We conducted a review of the literature at a research institute.

RESULTS

The utilization of expert diagnostic systems in otology is very limited. Previous applications focused primarily upon the diagnosis of vertiginous disorders with the use of deterministic algorithms and, more recently, with adaptive algorithms such as neural networks.

CONCLUSION

Expert systems provide greater diagnostic accuracy to physicians across a wide range of medical specialties. The success of such a system depends upon the strength of its reasoning algorithm, the validity of its knowledge base, and its ease of use.

SIGNIFICANCE

There have been no attempts to develop an adaptive expert system for the full range of otological conditions. Such a tool may be of great use to physicians as a diagnostic aid and educational resource, particularly for those located in isolated sites.

Quantitative automated image analysis system with automated debris filtering for the detection of breast carcinoma cells

OBJECTIVE

To develop an intraoperative method for margin status evaluation during breast conservation therapy (BCT) using an automated analysis of imprint cytology specimens.

STUDY DESIGN

Imprint cytology samples were prospectively taken from 47 patients undergoing either BCT or breast reduction surgery. Touch preparations from BCT patients were taken on cut sections through the tumor to generate positive margin controls. For breast reduction patients, slide imprints were taken at cuts through the center of excised tissue. Analysis results from the presented technique were compared against standard pathologic diagnosis. Slides were stained with cytokeratin and Hoechst, imaged with an automated fluorescent microscope, and analyzed with a fast algorithm to automate discrimination between epithelial cells and noncellular debris.

RESULTS

The accuracy of the automated analysis was 95% for identifying invasive cancers compared against final pathologic diagnosis. The overall sensitivity was 87% while specificity was 100% (no false positives). This is comparable to the best reported results from manual examination of intraoperative imprint cytology slides while reducing the need for direct input from a cytopathologist.

CONCLUSION

This work demonstrates a proof of concept for developing a highly accurate and automated system for the intraoperative evaluation of margin status to guide surgical decisions and lower positive margin rates.

Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme

The objective of this study is to investigate the use of pattern classification methods for distinguishing different types of brain tumors, such as primary gliomas from metastases, and also for grading of gliomas. The availability of an automated computer analysis tool that is more objective than human readers can potentially lead to more reliable and reproducible brain tumor diagnostic procedures. A computer-assisted classification method combining conventional MRI and perfusion MRI is developed and used for differential diagnosis. The proposed scheme consists of several steps including region-of-interest definition, feature extraction, feature selection, and classification. The extracted features include tumor shape and intensity characteristics, as well as rotation invariant texture features. Feature subset selection is performed using support vector machines with recursive feature elimination. The method was applied on a population of 102 brain tumors histologically diagnosed as metastasis (24), meningiomas (4), gliomas World Health Organization grade II (22), gliomas World Health Organization grade III (18), and glioblastomas (34). The binary support vector machine classification accuracy, sensitivity, and specificity, assessed by leave-one-out cross-validation, were, respectively, 85%, 87%, and 79% for discrimination of metastases from gliomas and 88%, 85%, and 96% for discrimination of high-grade (grades III and IV) from low-grade (grade II) neoplasms. Multiclass classification was also performed via a one-vs-all voting scheme.

Predicting neuroendocrine tumor (carcinoid) neoplasia using gene expression profiling and supervised machine learning

BACKGROUND

A more accurate taxonomy of small intestinal (SI) neuroendocrine tumors (NETs) is necessary to accurately predict tumor behavior and prognosis and to define therapeutic strategy. In this study, the authors identified a panel of such markers that have been implicated in tumorigenicity, metastasis, and hormone production and hypothesized that transcript levels of the genes melanoma antigen family D2 (MAGE-D2), metastasis-associated 1 (MTA1), nucleosome assembly protein 1-like (NAP1L1), Ki-67 (a marker of proliferation), survivin, frizzled homolog 7 (FZD7), the Kiss1 metastasis suppressor (Kiss1), neuropilin 2 (NRP2), and chromogranin A (CgA) could be used to define primary SI NETs and to predict the development of metastases.

METHODS

Seventy-three clinically and World Health Organization pathologically classified NET samples (primary tumor, n = 44 samples; liver metastases, n = 29 samples) and 30 normal human enterochromaffin (EC) cell preparations were analyzed using real-time polymerase chain reaction. Transcript levels were normalized to 3 NET housekeeping genes (asparagine-linked glycosylation 9 or ALG9, transcription factor CP2 or TFCP2, and zinc finger protein 410 or ZNF410) using geNorm analysis. A predictive gene-based model was constructed using supervised learning algorithms from the transcript expression levels.

RESULTS

Primary SI NETs could be differentiated from normal human EC cell preparations with 100% specificity and 92% sensitivity. Well differentiated NETs (WDNETs), well differentiated neuroendocrine carcinomas, and poorly differentiated NETs (PDNETs) were classified with a specificity of 78%, 78%, and 71%, respectively; whereas poorly differentiated neuroendocrine carcinomas were misclassified as either WDNETs or PDNETs. Metastases were predicted in all cases with 100% sensitivity and specificity.

CONCLUSIONS

The current results indicated that gene expression profiling and supervised machine learning can be used to classify SI NET subtypes and accurately predict metastasis. The authors believe that the application of this technique will facilitate accurate molecular pathologic delineation of NET disease, better define its extent, facilitate the assessment of prognosis, and provide a guide for the identification of appropriate strategies for individualized patient treatment.

Digital pathology: a tool for 21st century neuropathology

Digital pathology represents an electronic environment for performing pathologic analysis and managing the information associated with this activity. The technology to create and support digital pathology has largely developed over the last decade. The use of digital pathology tools is essential to adapt and lead in the rapidly changing environment of 21st century neuropathology. The utility of digital pathology has already been demonstrated by pathologists in several areas including consensus reviews, quality assurance (Q/A), tissue microarrays (TMAs), education and proficiency testing. These utilities notwithstanding, interface issues, storage and image formatting all present challenges to the integration of digital pathology into the neuropathology work environment. With continued technologic improvements, as well as the introduction of fluorescent side scanning and multispectral detection, future developments in digital pathology offer the promise of adding powerful analytic tools to the pathology work environment. The integration of digital pathology with biorepositories offers particular promise for neuropathologists engaged in tissue banking. The utilization of these tools will be essential for neuropathologists to continue as leaders in diagnostics, translational research and basic science in the 21st century.

Molecular classification of brain tumor biopsies using solid-state magic angle spinning proton magnetic resonance spectroscopy and robust classifiers

Brain tumors are one of the leading causes of death in adults with cancer; however, molecular classification of these tumors with in vivo magnetic resonance spectroscopy (MRS) is limited because of the small number of metabolites detected. In vitro MRS provides highly informative biomarker profiles at higher fields, but also consumes the sample so that it is unavailable for subsequent analysis. In contrast, ex vivo high-resolution magic angle spinning (HRMAS) MRS conserves the sample but requires large samples and can pose technical challenges for producing accurate data, depending on the sample testing temperature. We developed a novel approach that combines a two-dimensional (2D), solid-state, HRMAS proton (1H) NMR method, TOBSY (total through-bond spectroscopy), which maximizes the advantages of HRMAS and a robust classification strategy. We used approximately 2 mg of tissue at -8 degrees C from each of 55 brain biopsies, and reliably detected 16 different biologically relevant molecular species. We compared two classification strategies, the support vector machine (SVM) classifier and a feed-forward neural network using the Levenberg-Marquardt back-propagation algorithm. We used the minimum redundancy/maximum relevance (MRMR) method as a powerful feature-selection scheme along with the SVM classifier. We suggest that molecular characterization of brain tumors based on highly informative 2D MRS should enable us to type and prognose even inoperable patients with high accuracy in vivo.

A novel approach for prediction of tacrolimus blood concentration in liver transplantation patients in the intensive care unit through support vector regression

Introduction

Tacrolimus is an important immunosuppressive drug for organ transplantation patients. It has a narrow therapeutic range, toxic side effects, and a blood concentration with wide intra- and interindividual variability. Hence, it is of the utmost importance to monitor tacrolimus blood concentration, thereby ensuring clinical effect and avoiding toxic side effects. Prediction models for tacrolimus blood concentration can improve clinical care by optimizing monitoring of these concentrations, especially in the initial phase after transplantation during intensive care unit (ICU) stay. This is the first study in the ICU in which support vector machines, as a new data modeling technique, are investigated and tested in their prediction capabilities of tacrolimus blood concentration. Linear support vector regression (SVR) and nonlinear radial basis function (RBF) SVR are compared with multiple linear regression (MLR).

Methods

Tacrolimus blood concentrations, together with 35 other relevant variables from 50 liver transplantation patients, were extracted from our ICU database. This resulted in a dataset of 457 blood samples, on average between 9 and 10 samples per patient, finally resulting in a database of more than 16,000 data values. Nonlinear RBF SVR, linear SVR, and MLR were performed after selection of clinically relevant input variables and model parameters. Differences between observed and predicted tacrolimus blood concentrations were calculated. Prediction accuracy of the three methods was compared after fivefold cross-validation (Friedman test and Wilcoxon signed rank analysis).

Results

Linear SVR and nonlinear RBF SVR had mean absolute differences between observed and predicted tacrolimus blood concentrations of 2.31 ng/ml (standard deviation [SD] 2.47) and 2.38 ng/ml (SD 2.49), respectively. MLR had a mean absolute difference of 2.73 ng/ml (SD 3.79). The difference between linear SVR and MLR was statistically significant (p < 0.001). RBF SVR had the advantage of requiring only 2 input variables to perform this prediction in comparison to 15 and 16 variables needed by linear SVR and MLR, respectively. This is an indication of the superior prediction capability of nonlinear SVR.

Conclusion

Prediction of tacrolimus blood concentration with linear and nonlinear SVR was excellent, and accuracy was superior in comparison with an MLR model.

Exploiting sample variability to enhance multivariate analysis of microarray data

MOTIVATION

Biological and technical variability is intrinsic in any microarray experiment. While most approaches aim to account for this variability, they do not actively exploit it. Here, we consider a novel approach that uses the variability between arrays to provide an extra source of information that can enhance gene expression analyses.

RESULTS

We develop a method that uses sample similarity to incorporate sample variability into the analysis of gene expression profiles. This allows each pairwise correlation calculation to borrow information from all the data in the experiment. Results on synthetic and human cancer microarray datasets show that the inclusion of this information leads to a significant increase in the ability to identify previously characterized relationships and a reduction in false discovery rate, when compared to a standard analysis using Pearson correlation. The information carried by the variability between arrays can be exploited to significantly improve the analysis of gene expression data.

AVAILABILITY

Matlab script files are available from the author.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A fully automated method for lung nodule detection from postero-anterior chest radiographs

In the past decades, a great deal of research work has been devoted to the development of systems that could improve radiologists' accuracy in detecting lung nodules. Despite the great efforts, the problem is still open. In this paper, we present a fully automated system processing digital postero-anterior (PA) chest radiographs, that starts by producing an accurate segmentation of the lung field area. The segmented lung area includes even those parts of the lungs hidden behind the heart, the spine, and the diaphragm, which are usually excluded from the methods presented in the literature. This decision is motivated by the fact that lung nodules may be found also in these areas. The segmented area is processed with a simple multiscale method that enhances the visibility of the nodules, and an extraction scheme is then applied to select potential nodules. To reduce the high number of false positives extracted, cost-sensitive support vector machines (SVMs) are trained to recognize the true nodules. Different learning experiments were performed on two different data sets, created by means of feature selection, and employing Gaussian and polynomial SVMs trained with different parameters; the results are reported and compared. With the best SVM models, we obtain about 1.5 false positives per image (fp/image) when sensitivity is approximately equal to 0.71; this number increases to about 2.5 and 4 fp/image when sensitivity is = 0.78 and = 0.85, respectively. For the highest sensitivity (= 0.92 and 1.0), we get 7 or 8 fp/image.

Robust estimation of bioaffinity assay fluorescence signals

In this paper, the challenging problem of robust mean-signal estimation of a single-step microparticle bioaffinity assay is investigated. For this purpose, a density estimation-based robust algorithm (DER) was developed. The DER algorithm was comparatively evaluated with four other parameter estimation methods (mean value, median filtering, least square estimation, Welsch robust m-estimator). Two important questions were raised and investigated: 1) Which of the five methods can robustly estimate the mean bioaffinity signal? and 2) How many microparticles need to be measured in order to obtain an accurate estimate of the mean signal value? To answer the questions, bootstrap and coefficient of variation (CV) analyses were performed. In the CV analysis, the DER algorithm gave the best results: The CV ranged from 0.8% to 4.9% when the number of microparticles used for the mean signal estimation varied from 800 to 30. In the bootstrap analysis of the standard error, the DER algorithm had the smallest variance. As a conclusion, it can be underlined that: 1) of all methods tested, the DER algorithm gave the most consistent and reproducible results according to the bootstrap and CV analysis; 2) using the DER algorithm accurate estimates could be calculated based on 80-100 particles, corresponding to a typical assay measurement time of 1 min; and 3) the investigated bioaffinity signals contained a large number of outliers (observations that severely deviate from the majority of data) and therefore robust techniques were necessary for the mean signal estimation tasks.