An intensity-region driven multi-classifier scheme for improving the classification accuracy of proteomic MS-spectra.

In this study, a pattern recognition system is presented for improving the classification accuracy of MS-spectra by means of gathering information from different MS-spectra intensity regions using a majority vote ensemble combination. The method starts by automatically breaking down all MS-spectra into common intensity regions. Subsequently, the most informative features (m/z values), which might constitute potential significant biomarkers, are extracted from each common intensity region over all the MS-spectra and, finally, normal from ovarian cancer MS-spectra are discriminated using a multi-classifier scheme, with members the Support Vector Machine, the Probabilistic Neural Network and the k-Nearest Neighbour classifiers. Clinical material was obtained from the publicly available ovarian proteomic dataset (8-7-02). To ensure robust and reliable estimates, the proposed pattern recognition system was evaluated using an external cross-validation process. The average overall performance of the system in discriminating normal from cancer ovarian MS-spectra was 97.18% with 98.52% mean sensitivity and 94.84% mean specificity values.

A multi-classifier system for the characterization of normal, infectious, and cancerous prostate tissues employing transrectal ultrasound images.

A computer-aided diagnostic system has been developed for the discrimination of normal, infectious and cancer prostate tissues based on texture analysis of transrectal ultrasound images. The proposed system has been designed using a panel of three classifiers, which have been evaluated individually or as a mutli-classifier scheme, using the external cross-validation procedure. Clinical data consisted of 165 transrectal ultrasound images, characterized by an experienced physician as normal (55/165), cancerous (55/165), and infectious (55/165) prostate cases. From each image, the physician delineated the most representative regions of interest, from which, 23 textural features were extracted. Classification was seen as a two level hierarchical decision tree. Normal from infectious and infectious from cancer cases were discriminated at the 1st and 2nd level of the decision tree, respectively. The best classification results for the 1st level were 89.5%, whereas for the 2nd level 90.1%. The utilization of multi-classifier system improved the discrimination of prostate pathologies as compared to individual classifiers; for infectious prostate cases improvement was from 87.3% to 88.7% and for cancer prostate cases improvement was from 84.1% to 91.4%. In terms of overall system performance (the decision tree's node propagating error taken into account), best classification accuracies were 89.5%, 79.6% and 82.7% for the recognition of normal, infectious and cancer cases, respectively. The proposed system might be used as a second opinion tool for assisting diagnosis of different prostate pathologies.

Computer-based association of the texture of expressed estrogen receptor nuclei with histologic grade using immunohistochemically-stained breast carcinomas.

OBJECTIVE: To investigate the potential correlation between estrogen receptor (ER) texture and histologic grade in breast carcinomas. STUDY DESIGN: Clinical material comprised 96 biopsies of infiltrative ductal carcinomas that were hematoxylin-eosin (H-E) and immunohistochemically (IHC) stained. H-E-stained specimens were used for tumor grading, and IHC-stained specimens were analyzed for ER-status estimation. Spearman's correlation test was used to estimate the relation between histologic grade and both the physician's ER-status assessment and a computer system's ER-status evaluation. Moreover, a pattern recognition system was developed that takes as input textural features extracted from ER-expressed nuclei and outputs the grade of the tumor. The system was evaluated using an external cross-validation procedure in order to assess its generalization to new cases. RESULTS: Spearman's correlation revealed that the histologic grading was inversely related to both the physician's ER-status assessment and to the computer system's ER-status evaluation. The pattern recognition system was able to predict histologic grade with 95.2% accuracy. Important textural nuclear features were proven--the skewness, the angular second moment and the sum of entropy. CONCLUSION: ER-expressed nuclei texture was found to contain important information related to histologic grade.

A pilot study investigating the minimum requirements necessary for grading astrocytomas remotely.

OBJECTIVE: To investigate the minimum requirements necessary for remote grading astrocytomas in terms of selected static images and descriptive histologic characteristics. STUDY DESIGN: A histopathologist examined 106 formalin-fixed, paraffin-embedded tissue samples of low- and high-grade astrocytomas. Interobserver-checked cases were reviewed under a microscope to estimate the accuracy of the conventional glass slide diagnoses. Then cases based on 5 static-digitized images from each patient were diagnosed. Next, the grade of each tumor was assessed based on the set of 5 images and the World Health Organization (WHO) description of 8 histologic characteristics defined as crucial in grading astrocytomas. Finally, an evaluation was made using a custom-designed decision support system. RESULTS: Conventional glass slide diagnosis was 93.9%. Diagnosis based only on the set of 5 images dropped to 81.6%. Diagnosis based on the set of 5 images and the WHO characteristics boosted accuracy to 88.8%. Accuracy improved to 91.8% with the addition of the decision support system. CONCLUSION: Our findings suggest that a telepathology system might be valuable for accurate grade diagnosis of astrocytomas-providing a means for avoiding diagnostic errors-without blocks or slides having to leave the department. This could significantly reduce the overall time and cost of diagnosis.

Cascade pattern recognition structure for improving quantitative assessment of estrogen receptor status in breast tissue carcinomas.

OBJECTIVE: To develop and validate a computer-based approach for the quantitative assessment of estrogen receptor (ER) status in breast tissue specimens for breast cancer management. STUDY DESIGN: Microscopy images of 32 immunohistochemically (IHC) stained specimens of breast cancer biopsies were digitized and were primarily assessed for ER status (percentage of positively stained nuclei) by a histopathologist. A pattern recognition system was designed for automatically assessing the ER status of the IHC-stained specimens. Nuclei were automatically segmented from background by a pixel-based unsupervised clustering algorithm and were characterized as positively stained or unstained by a supervised classification algorithm. This cascade structure boosted the system's classification accuracy. RESULTS: System performance in correctly characterizing the nuclei was 95.48%. When specifying each case's ER status, system performance was statistically not significantly different to the physician's assessment (p = 0.13); when ranking each case to a particular 5-scale ER-scoring system (giving the chance of response to endocrine treatment), the system's score and the physician's score were in agreement in 29 of 32 cases. CONCLUSION: The need for reliable and operator independent ER-status estimation procedures may be served by the design of efficient pattern recognition systems to be employed as support opinion tools in clinical practice.

Improving accuracy in astrocytomas grading by integrating a robust least squares mapping driven support vector machine classifier into a two level grade classification scheme.

Grading of astrocytomas is an important task for treatment planning; however, it suffers from significantly great inter-observer variability. Computer-assisted diagnosis systems have been propose to assist towards minimizing subjectivity, however, these systems present either moderate accuracy or utilize specialized staining protocols and grading systems that are difficult to apply in daily clinical practice. The present study proposes a robust mathematical formulation by integrating state-of-art technologies (support vector machines and least squares mapping) in a cascade classification scheme for separating low from high and grade III from grade IV astrocytic tumours. Results have indicated that low from high-grade tumours can be correctly separated with a certainty as high as 97.3%, whereas grade III from grade IV tumours with 97.8%. The overall performance was 95.2%. These high rates have been a result of applying the least squares mapping technique to features prior to classification. A significant byproduct of least squares mapping is that the number of support vectors of the SVM classifiers dropped dramatically from about 80% when no mapping was used to less than 5% when mapping was used. The latter is a clear indication that the SVM classifier has a greater potential to generalize well to new data. In this way, digital image analysis systems for automated grading of astrocytomas are brought closer to clinical practice.

Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features.

The aim of the present study was to design, implement and evaluate a software system for discriminating between metastatic and primary brain tumors (gliomas and meningiomas) on MRI, employing textural features from routinely taken T1 post-contrast images. The proposed classifier is a modified probabilistic neural network (PNN), incorporating a non-linear least squares features transformation (LSFT) into the PNN classifier. Thirty-six textural features were extracted from each one of 67 T1-weighted post-contrast MR images (21 metastases, 19 meningiomas and 27 gliomas). LSFT enhanced the performance of the PNN, achieving classification accuracies of 95.24% for discriminating between metastatic and primary tumors and 93.48% for distinguishing gliomas from meningiomas. To improve the generalization of the proposed classification system, the external cross-validation method was also used, resulting in 71.43% and 81.25% accuracies in distinguishing metastatic from primary tumors and gliomas from meningiomas, respectively. LSFT improved PNN performance, increased class separability and resulted in dimensionality reduction.

Design of a multi-classifier system for discriminating benign from malignant thyroid nodules using routinely H&E-stained cytological images.

A multi-classifier diagnostic system was designed for distinguishing between benign and malignant thyroid nodules from routinely taken (FNA, H&E-stained) cytological images. To construct the multi-classifier system, several combination rules and different mixtures of ensemble classifier members, employing morphological and textural nuclear features, were comparatively evaluated. Experimental results illustrated that the classifier combination k-NN/PNN/Bayesian and the majority vote rule enhanced significantly classification accuracy (95.7%) as compared to best single classifier (PNN: 89.6%). The proposed system was designed with purpose to be utilized in daily clinical practice as a second opinion tool to support cytopathologists' decisions, when a definite diagnosis is difficult to be obtained.

PDA-based system with teleradiology and image analysis capabilities.

The aim of the present study was to design and implement a Personal Digital Assistant (PDA)-based teleradiology system incorporating image processing and analysis facilities for use in emergency situations within a hospital environment. The system comprised a DICOM-server, connected to an MRI unit, 3 wireless access points, and 3 PDAs (HP iPaq rx3715). PDA application software was developed in MS Embedded Visual C++ 4.0. Each PDA can receive, load, process and analyze hi-quality static MR images. Image processing includes gray-scale manipulation and spatial filtering techniques while image analysis incorporates a probabilistic neural network (PNN) classifier, which was optimally designed employing a suitable combination of textural features and was evaluated using the leave-one-out method. The PNN is capable of discriminating between three major types of human brain tumors with accuracy of 86.66%. The developed application may be useful as a mobile medical teleconsultation tool.

Colour-texture based image analysis method for assessing the hormone receptors status in breast tissue sections.

Hormone receptors have been used in prognosis of breast carcinomas and their positive status is of clinical value in hormonal therapy. Determination of this status is based on the subjective visual inspection of the stained nuclei in the specimens. The aim of this study was the assessment of the estrogen receptor's (ER) positive status of breast carcinomas, by means of colour-texture based image analysis methodology. Twenty two cases of immunohistochemically (IHC) stained breast biopsies were initially assessed by a histopathologist for ER positive status, following a clinical scoring protocol. Custom-designed image analysis software was developed for automatically assessing the ER positive status, employing colour textural features and the k-Nearest Neighbor weighted votes classification algorithm. Computer-based image analysis system resulted in 86.4% overall accuracy and in 0.875 Kendall's coefficient of concordance (p<0.001), ranking correctly 19/22 cases. Colour-texture analysis of IHC stained specimens might have an impact in the quantitative assessment of ER status.