Adaptable pattern recognition system for discriminating Melanocytic Nevi from Malignant Melanomas using plain photography images from different image databases.

OBJECTIVE: The aim of this study was to propose features that evaluate pictorial differences between melanocytic nevus (mole) and melanoma lesions by computer-based analysis of plain photography images and to design a cross-platform, tunable, decision support system to discriminate with high accuracy moles from melanomas in different publicly available image databases. MATERIAL AND METHODS: Digital plain photography images of verified mole and melanoma lesions were downloaded from (i) Edinburgh University Hospital, UK, (Dermofit, 330moles/70 melanomas, under signed agreement), from 5 different centers (Multicenter, 63moles/25 melanomas, publicly available), and from the Groningen University, Netherlands (Groningen, 100moles/70 melanomas, publicly available). Images were processed for outlining the lesion-border and isolating the lesion from the surrounding background. Fourteen features were generated from each lesion evaluating texture (4), structure (5), shape (4) and color (1). Features were subjected to statistical analysis for determining differences in pictorial properties between moles and melanomas. The Probabilistic Neural Network (PNN) classifier, the exhaustive search features selection, the leave-one-out (LOO), and the external cross-validation (ECV) methods were used to design the PR-system for discriminating between moles and melanomas. RESULTS: Statistical analysis revealed that melanomas as compared to moles were of lower intensity, of less homogenous surface, had more dark pixels with intensities spanning larger spectra of gray-values, contained more objects of different sizes and gray-levels, had more asymmetrical shapes and irregular outlines, had abrupt intensity transitions from lesion to background tissue, and had more distinct colors. The PR-system designed by the Dermofit images scored on the Dermofit images, using the ECV, 94.1%, 82.9%, 96.5% for overall accuracy, sensitivity, specificity, on the Multicenter Images 92.0%, 88%, 93.7% and on the Groningen Images 76.2%, 73.9%, 77.8% respectively. CONCLUSION: The PR-system as designed by the Dermofit image database could be fine-tuned to classify with good accuracy plain photography moles/melanomas images of other databases employing different image capturing equipment and protocols.

Computer-based automated estimation of breast vascularity and correlation with breast cancer in DCE-MRI images.

Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) with gadolinium constitutes one of the most promising protocols for boosting up the sensitivity in breast cancer detection. The aim of this study was twofold: first to design an image processing methodology to estimate the vascularity of the breast region in DCE-MRI images and second to investigate whether the differences in the composition/texture and vascularity of normal, benign and malignant breasts may serve as potential indicators regarding the presence of the disease. Clinical material comprised thirty nine cases examined on a 3.0-T MRI system (SIGNA HDx; GE Healthcare). Vessel segmentation was performed using a custom made modification of the Seeded Region Growing algorithm that was designed in order to identify pixels belonging to the breast vascular network. Two families of features were extracted: first, morphological and textural features from segmented images in order to quantify the extent and the properties of the vascular network; second, textural features from the whole breast region in order to investigate whether the nature of the disease causes statistically important changes in the texture of affected breasts. Results have indicated that: (a) the texture of vessels presents statistically significant differences (p<0.001) between normal, benign and malignant cases, (b) the texture of the whole breast region for malignant and non-malignant breasts, produced statistically significant differences (p<0.001), (c) the relative ratios of the texture between the two breasts may be used for the discrimination of non-malignant from malignant patients, and (d) an area under the receiver operating characteristic curve of 0.908 (AUC) was found when features were combined in a logistic regression prediction rule according to ROC analysis.

Multimodality GPU-based computer-assisted diagnosis of breast cancer using ultrasound and digital mammography images.

PURPOSE: To improve the computer-aided diagnosis of breast lesions, by designing a pattern recognition system (PR-system) on commercial graphics processing unit (GPU) cards using parallel programming and textural information from multimodality imaging. MATERIAL AND METHODS: Patients with histologically verified breast lesions underwent both ultrasound (US) and digital mammography (DM), lesions were outlined on the images by an experienced radiologist, and textural features were calculated. The PR-system was designed to provide highest possible precision by programming in parallel the multiprocessors of the NVIDIA's GPU cards, GeForce 8800GT or 580GTX, and using the CUDA programming framework and C++. The PR-system was built around the probabilistic neural network classifier, and its performance was evaluated by a re-substitution method, for estimating the system's highest accuracy, and by the external cross-validation method, for assessing the PR-system's unbiased accuracy to new, "unseen" by the system, data. RESULTS: Classification accuracies for discriminating malignant from benign lesions were as follows: 85.5 % using US-features alone, 82.3 % employing DM features alone, and 93.5 % combining US and DM features. Mean accuracy to new "unseen" data for the combined US and DM features was 81 %. Those classification accuracies were about 10 % higher than accuracies achieved on a single CPU, using sequential programming methods, and 150-fold faster. CONCLUSION: The proposed PR-system improves breast-lesion discrimination accuracy, it may be redesigned on site when new verified data are incorporated in its depository, and it may serve as a second opinion tool in a clinical environment.

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).

Complementary DNA microarray image processing based on the fuzzy gaussian mixture model.

The objective of this paper was to investigate the segmentation ability of the fuzzy Gaussian mixture model (FGMM) clustering algorithm, applied on complementary DNA (cDNA) images. Following a standard established procedure, a simulated microarray image of 1600 cells, each containing one spot, was produced. For further evaluation of the algorithm, three real microarray images were also used, each containing 6400 spots. For the task of locating spot borders and surrounding background (BG) in each cell, an automatic gridding process was developed and applied on microarray images. The FGMM and the Gaussian mixture model (GMM) algorithms were applied to each cell with the purpose of discriminating foreground (FG) from BG. The segmentation abilities of both algorithms were evaluated by means of the segmentation matching factor, coefficient of determination, and concordance correlation, in respect to the actual classes (FG-BG pixels) of the simulated spots. Pairwise correlation and mean absolute error of the real images among replicates were also calculated. The FGMM was found to perform better and with equal processing time, as compared to the GMM, rendering the FGMM algorithm an efficient alternative for segmenting cDNA microarray images.

Monte Carlo study on the imaging performance of powder Lu2SiO5:Ce phosphor screens under x-ray excitation: comparison with Gd2O2S:Tb screens.

Lu2SiO5: Ce (LSO) scintillator is a relatively new luminescent material which has been successfully applied in positron emission tomography systems. Since it has been recently commercially available in powder form, it could be of value to investigate its performance for use in x-ray projection imaging as both physical and scintillating properties indicate a promising material for such applications. In the present study, a custom and validated Monte Carlo simulation code was used in order to examine the performance of LSO, under diagnostic radiology (mammography and general radiography) conditions. The Monte Carlo code was based on a model using Mie scattering theory for the description of light attenuation. Imaging characteristics, related to image brightness, spatial resolution and noise of LSO screens were predicted using only physical parameters of the phosphor. The overall performance of LSO powder phosphor screens was investigated in terms of the: (i) quantum detection efficiency (ii) emitted K-characteristic radiation (iii) luminescence efficiency (iv) modulation transfer function (v) Swank factor and (vi) zero-frequency detective quantum efficiency [DQE(0)]. Results were compared to the traditional rare-earth Gd2O2S:Tb (GOS) phosphor material. The relative luminescence efficiency of LSO phosphor was found inferior to that of GOS. This is due to the lower intrinsic conversion efficiency of LSO (0.08 instead of 0.15 of GOS) and the relatively high light extinction coefficient mext of this phosphor (0.239 mircom(-1) instead of 0.218 /microm(-1) for GOS). However, the property of increased light extinction combined with the rather sharp angular distribution of scattered light photons (anisotropy factor g=0.624 for LSO instead of 0.494 for GOS) reduce lateral light spreading and improve spatial resolution. In addition, LSO screens were found to exhibit better x-ray absorption as well as higher signal to noise transfer properties in the energy range from 18 keV up to 50.2 keV (e.g. DQE(0)=0.62 at 18 keV and for 34 mg/cm2, instead of 0.58 for GOS). The results indicate that certain optical properties of LSO (optical extinction coefficient, scattering anisotropy factor) combined with the relatively high x-ray coefficients, make this material a promising phosphor which, under appropriate conditions, could be considered for use in x-ray projection imaging detectors.

Modeling granular phosphor screens by Monte Carlo methods.

The intrinsic phosphor properties are of significant importance for the performance of phosphor screens used in medical imaging systems. In previous analytical-theoretical and Monte Carlo studies on granular phosphor materials, values of optical properties, and light interaction cross sections were found by fitting to experimental data. These values were then employed for the assessment of phosphor screen imaging performance. However, it was found that, depending on the experimental technique and fitting methodology, the optical parameters of a specific phosphor material varied within a wide range of values, i.e., variations of light scattering with respect to light absorption coefficients were often observed for the same phosphor material. In this study, x-ray and light transport within granular phosphor materials was studied by developing a computational model using Monte Carlo methods. The model was based on the intrinsic physical characteristics of the phosphor. Input values required to feed the model can be easily obtained from tabulated data. The complex refractive index was introduced and microscopic probabilities for light interactions were produced, using Mie scattering theory. Model validation was carried out by comparing model results on x-ray and light parameters (x-ray absorption, statistical fluctuations in the x-ray to light conversion process, number of emitted light photons, output light spatial distribution) with previous published experimental data on Gd2O2S: Tb phosphor material (Kodak Min-R screen). Results showed the dependence of the modulation transfer function (MTF) on phosphor grain size and material packing density. It was predicted that granular Gd2O2S: Tb screens of high packing density and small grain size may exhibit considerably better resolution and light emission properties than the conventional Gd2O2S: Tb screens, under similar conditions (x-ray incident energy, screen thickness).