Quantitative combination of volumetric MR imaging and MR spectroscopy data for the discrimination of meningiomas from metastatic brain tumors by means of pattern recognition.

The analysis of information derived from magnetic resonance imaging (MRI) and spectroscopy (MRS) has been identified as an important indicator for discriminating among different brain pathologies. The purpose of this study was to investigate the efficiency of the combination of textural MRI features and MRS metabolite ratios by means of a pattern recognition system in the task of discriminating between meningiomas and metastatic brain tumors. The data set consisted of 40 brain MR image series and their corresponding spectral data obtained from patients with verified tumors. The pattern recognition system was designed employing the support vector machines classifier with radial basis function kernel; the system was evaluated using an external cross validation process to render results indicative of the generalization performance to "unknown" cases. The combination of MR textural and spectroscopic features resulted in 92.15% overall accuracy in discriminating meningiomas from metastatic brain tumors. The fusion of the information derived from MRI and MRS data might be helpful in providing clinicians a useful second opinion tool for accurate characterization of brain tumors.

Development and evaluation of a PDA-based teleradiology terminal in thyroid nodule diagnosis.

We developed a wireless personal digital assistant (PDA)-based teleradiology terminal which allowed a secure connection to the hospital's Picture Archiving and Communication System (PACS) through the DICOM protocol. Ten members of the hospital's medical staff completed a questionnaire about its mobility, usability, stability, performance and diagnostic efficiency in a real health-care environment. There was a high degree of satisfaction with the system's mobility (mean score 4.1, SD 1.0, on a five-point scale), usability (mean score 4.2, SD 1.1), stability (mean score 3.9, SD 0.4) and performance (mean score 4.2, SD 0.6). The system was evaluated as a tool for providing assistance in diagnosing thyroid nodules from ultrasound images. A total of 144 ultrasound images with thyroid nodules were assessed by an expert. Six image quality attributes were evaluated. The physician concluded that the ultrasound thyroid images on the PDA screen were of similar quality to those displayed on a diagnostic visual display unit screen. However, the expert found difficulties in diagnosing microcalcification, internal echo texture and vascularity. The PDA terminal provided rapid, secure and convenient portable access to PACS images and the image quality was sufficient for diagnostic interpretation of ultrasound images of the thyroid.

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.

Segmentation of complementary DNA microarray images by wavelet-based Markov random field model.

A wavelet-based modification of the Markov random field (WMRF) model is proposed for segmenting complementary DNA (cDNA) microarray images. For evaluation purposes, five simulated and a set of five real microarray images were used. The one-level stationary wavelet transform (SWT) of each microarray image was used to form two images, a denoised image, using hard thresholding filter, and a magnitude image, from the amplitudes of the horizontal and vertical components of SWT. Elements from these two images were suitably combined to form the WMRF model for segmenting spots from their background. The WMRF was compared against the conventional MRF and the Fuzzy C means (FCM) algorithms on simulated and real microarray images and their performances were evaluated by means of the segmentation matching factor (SMF) and the coefficient of determination (r2). Additionally, the WMRF was compared against the SPOT and SCANALYZE, and performances were evaluated by the mean absolute error (MAE) and the coefficient of variation (CV). The WMRF performed more accurately than the MRF and FCM (SMF: 92.66, 92.15, and 89.22, r2 : 0.92, 0.90, and 0.84, respectively) and achieved higher reproducibility than the MRF, SPOT, and SCANALYZE (MAE: 497, 1215, 1180, and 503, CV: 0.88, 1.15, 0.93, and 0.90, respectively).

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.

Pattern recognition system for the discrimination of multiple sclerosis from cerebral microangiopathy lesions based on texture analysis of magnetic resonance images.

In this study, a pattern recognition system has been developed for the discrimination of multiple sclerosis (MS) from cerebral microangiopathy (CM) lesions based on computer-assisted texture analysis of magnetic resonance images. Twenty-three textural features were calculated from MS and CM regions of interest, delineated by experienced radiologists on fluid attenuated inversion recovery images and obtained from 11 patients diagnosed with clinically definite MS and from 18 patients diagnosed with clinically definite CM. The probabilistic neural network classifier was used to construct the proposed pattern recognition system and the generalization of the system to unseen data was evaluated using an external cross validation process. According to the findings of the present study, statistically significant differences exist in the values of the textural features between CM and MS: MS regions were darker, of higher contrast, less homogeneous and rougher as compared to CM.

Enhancing the discrimination accuracy between metastases, gliomas and meningiomas on brain MRI by volumetric textural features and ensemble pattern recognition methods.

Three-dimensional (3D) texture analysis of volumetric brain magnetic resonance (MR) images has been identified as an important indicator for discriminating among different brain pathologies. The purpose of this study was to evaluate the efficiency of 3D textural features using a pattern recognition system in the task of discriminating benign, malignant and metastatic brain tissues on T1 postcontrast MR imaging (MRI) series. The dataset consisted of 67 brain MRI series obtained from patients with verified and untreated intracranial tumors. The pattern recognition system was designed as an ensemble classification scheme employing a support vector machine classifier, specially modified in order to integrate the least squares features transformation logic in its kernel function. The latter, in conjunction with using 3D textural features, enabled boosting up the performance of the system in discriminating metastatic, malignant and benign brain tumors with 77.14%, 89.19% and 93.33% accuracy, respectively. The method was evaluated using an external cross-validation process; thus, results might be considered indicative of the generalization performance of the system to "unseen" cases. The proposed system might be used as an assisting tool for brain tumor characterization on volumetric MRI series.

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 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.

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.

Genes expression level quantification using a spot-based algorithmic pipeline.

An efficient spot-based (SB) algorithmic pipeline of clustering, enhancement, and segmentation techniques was developed to quantify gene expression levels in microarray images. The SB-pipeline employed i/a griding procedure to locate spot-regions, ii/a clustering algorithm (enhanced fuzzy c-means or EnFCM) to roughly segment spots from background and estimate background noise and spot's center, iii/an adaptive histogram modification technique to accentuate spot's boundaries, and iv/a segmentation algorithm (Seeded Region Growing or SRG), to extract microarray spots' intensities. Extracted intensities were comparatively evaluated in term of Mean Absolute Error (MAE) against the MAGIC TOOL's SRG employing a dataset of 7 replicated microarray images (6400 spots each). MAE box-plots mean values were 0.254 and 0.630 for the SB-pipeline and the MAGIC TOOL respectively. Total processing times for the dataset evaluated (7 images) were 2100 seconds and 3410 seconds for the SB-pipeline and MAGIC TOOL respectively.

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.

Mobile consultant: evaluation of additional services.

As the need for mobility in the medical world increases, newer systems and applications came to light; many of them based on wireless and mobile networks. PDA based systems were presented in the past, capable of videoconferencing and transmitting high quality images between a roaming consultant and a fixed point in the hospital. These systems not only had desirable characteristics but also incorporated additional services that were found of value: paging, Voice over IP calling, Internet, email, intranet, patient record update, etc This paper presents an engineering and clinical evaluation of those additional services based on both objective and subjective criteria. It concludes that such complementary services can be desirable as they increase personnel mobility, utilize the hospital resources more efficiently while at the same time increase productivity and decrease the cost of hardware and communications.

Mobile consultant: combining total mobility with constant access.

Minimizing the time required for a medical consultant to offer his/her expert opinion, can be viewed as a life-saving procedure. We have designed and tested an integrated system that will allow a medical consultant to freely move either within, or outside the hospital, while still maintaining constant contact with the patients via videoconferencing and high-resolution imaging. The above system is explained in this paper, along with its advantages and its potential limitations. Conclusively, we demonstrate that such a system further increases the mobility of the medical consultant, while improving the healthcare service.