The Morphology of Brain Neurons: The Box-Counting Method in the Quantitative Analysis of 2D Images.

This chapter begins by showing the difference between fractal geometry and fractal analysis. The text shows the difference between mathematical and natural fractals and how they are best defined by explaining the concept of fractal analysis. Furthermore, the text presents the most famous technique of fractal analysis: the box-counting method. Defining this method and showing the methodology that leads to the precise value of the fractal (i.e., the box) dimension is done by demonstrating the images of human dentate neurons. A more detailed explanation of the methodology was presented in the previous version of this chapter.This version promotes the notion of monofractal analysis and shows how three types of the same neuronal images can quantify four image properties. The results showed that monofractal parameters successfully quantified four image properties in three nuclei of the cerebellum. Finally, the author discusses the results of this chapter and previously published conclusions. The results show how the monofractal parameters discriminate images of neurons from the three nuclei of the human cerebrum. These outcomes are discussed along with the results of previous studies.

Using the photoplethysmography method to monitor age-related changes in the cardiovascular system.

Introduction: Aging is a physiological process characterized by progressive changes in all organ systems. In the last few decades, the elderly population has been growing, so the scientific community is focusing on the investigation of the aging process, all in order to improve the quality of life in elderly. One of the biggest challenges in studying the impact of the aging on the human body represents the monitoring of the changes that inevitably occur in arterial blood vessels. Therefore, the medical community has invested a great deal of effort in studying and discovering new methods and tools that could be used to monitor the changes in arterial blood vessels caused by the aging process. The goal of our research was to develop a new diagnostic method using a photoplethysmographic sensor and to examine the impact of the aging process on the cardiovascular system in adults. Long-term recorded arterial blood flow waveforms were analyzed using detrended fluctuation analysis. Materials and Methods: The study included 117 respondents, aged 20-70 years. The waveform of the arterial blood flow was recorded for 5 min, with an optical sensor placed above the left common carotid artery, simultaneously with a single-channel ECG. For each cardiac cycle, the blood flow amplitude was determined, and a new time series was formed, which was analyzed non-linearly (DFA method). The values of the scalar coefficients α 1 and α 2, particularly their ratio (α 1/α 2) were obtained, which were then monitored in relation to the age of the subjects. Result: The values of the scalar ratio (α 1/α 2) were significantly different between the subjects older and younger than 50 years. The value of the α 1/α 2 decreased exponentially with the aging. In the population of middle-aged adults, this ratio had a value around 1, in young adults the value was exclusively higher than 1 and in older adults the value was exclusively lower than 1. Conclusion: The results of this study indicated that the aging led to a decrease in the α 1/α 2 in the population of healthy subjects. With this non-invasive method, changes in the cardiovascular system due to aging can be detected and monitored.

Quantitative analysis of the Golgi impregnated human (neo)striatal neurons: Observation of the morphological characteristics followed by an emphasis on the functional diversity of cells.

BACKGROUND: The (neo)striatum is the major input structure of the basal nuclei, which is involved in the execution of voluntary movements, but also in controlling the processes that lead to the movement, such as motivation and cognition. The striatum provides its function through an interaction between projection neurons and interneurons. The aim of this study was to quantify the morphological properties of neurons in the precommissural putamen and precommissural caudate nucleus head and to evaluate whether there is a difference in cell morphology between different cell groups within one part and between the same cell groups within different parts of the striatum. METHODS: A total of 652 neuronal images of human striatum were observed. The features of the neuronal morphology (soma size, dendritic field size, shape of neuronal image, dendritic curviness, dendritic branching complexity) were observed by determining appropriate parameters of digital images of neurons. RESULTS: According to the presence of spines on the soma and/or dendrites, neurons were qualitatively classified into 446 spiny and 206 aspiny cells. The analysis of the distribution of the dendritic field area shows that spiny and aspiny neurons from both parts of the neostriatum can be decomposed into two distributions, which means that they can be classified into subgroups. A quantitative analysis of the spiny/aspiny neurons in the human putamen or caudate nucleus head has shown that there is a statistically significant difference between them. By comparing the morphology of neurons of the same group between different parts of the human neostriatum (putamen and caudate nucleus), it was also determined that there is a statistically significant difference. CONCLUSION: Since the morphology and function of neurons are in close correlation, it can be assumed that different groups of neurons in the human striatum might support functional diversity of the studied area.

Computational analysis of MRIs predicts osteosarcoma chemoresponsiveness.

Aim: This study aimed to improve osteosarcoma chemoresponsiveness prediction by optimization of computational analysis of MRIs. Patients & methods: Our retrospective predictive model involved osteosarcoma patients with MRI scans performed before OsteoSa MAP neoadjuvant cytotoxic chemotherapy. Results: We found that several monofractal and multifractal algorithms were able to classify tumors according to their chemoresponsiveness. The predictive clues were defined as morphological complexity, homogeneity and fractality. The monofractal feature CV for Λ'(G) provided the best predictive association (area under the ROC curve = 0.88; p <0.001), followed by   Y-axis intersection of the regression line  for â€Šbox fractal dimension, r²â€Š for  FDM and tumor circularity. Conclusion: This is the first full-scale study to indicate that computational analysis of pretreatment MRIs could provide imaging biomarkers for the classification of osteosarcoma according to their chemoresponsiveness.

Classification by morphology of multipolar neurons of the human principal olivary nucleus.

The principal olivary nucleus is the largest part of the inferior olivary complex and is involved in the spatial and temporal organization of movement and motor learning. Nearly all neurons in this nucleus is multipolar along with having a highly complex dendritic tree and significant asymmetry in shape. In this study, we updated the current classification scheme, examined morphological differences between the proposed groups, and investigated age-related morphological changes. Histological preparations were digitized by a light microscope and a sample of 259 images of neurons was analyzed by 17 computationally generated parameters of morphology. These were reduced to the four variables of principal component analysis and the sample was classified by k-means method of clustering into three clusters. The differences between clusters were documented and for medium-sized neurons the relationship between four morphological parameters and age were investigated. Finally, for two of the age groups the changes in the morphology were explored. This study includes a detailed and robust classification of the PON neurons and the findings improve upon past qualitative work.

Analysis of Spatial Distribution and Prognostic Value of Different Pan Cytokeratin Immunostaining Intensities in Breast Tumor Tissue Sections.

Cancer risk prognosis could improve patient survival through early personalized treatment decisions. This is the first systematic analysis of the spatial and prognostic distribution of different pan cytokeratin immunostaining intensities in breast tumors. The prognostic model included 102 breast carcinoma patients, with distant metastasis occurrence as the endpoint. We segmented the full intensity range (0-255) of pan cytokeratin digitized immunostaining into seven discrete narrow grey level ranges: 0-130, 130-160, 160-180, 180-200, 200-220, 220-240, and 240-255. These images were subsequently examined by 33 major (GLCM), fractal and first-order statistics computational analysis features. Interestingly, while moderate intensities were strongly associated with metastasis outcome, high intensities of pan cytokeratin immunostaining provided no prognostic value even after an exhaustive computational analysis. The intense pan cytokeratin immunostaining was also relatively rare, suggesting the low differentiation state of epithelial cells. The observed variability in immunostaining intensities highlighted the intratumoral heterogeneity of the malignant cells and its association with a poor disease outcome. The prognostic importance of the moderate intensity range established by complex computational morphology analyses was supported by simple measurements of its immunostaining area which was associated with favorable disease outcome. This study reveals intratumoral heterogeneity of the pan cytokeratin immunostaining together with the prognostic evaluation and spatial distribution of its discrete intensities.

Size and Shape Filtering of Malignant Cell Clusters within Breast Tumors Identifies Scattered Individual Epithelial Cells as the Most Valuable Histomorphological Clue in the Prognosis of Distant Metastasis Risk.

Survival and life quality of breast cancer patients could be improved by more aggressive chemotherapy for those at high metastasis risk and less intense treatments for low-risk patients. Such personalized treatment cannot be currently achieved due to the insufficient reliability of metastasis risk prognosis. The purpose of this study was therefore, to identify novel histopathological prognostic markers of metastasis risk through exhaustive computational image analysis of 80 size and shape subsets of epithelial clusters in breast tumors. The group of 102 patients had a follow-up median of 12.3 years, without lymph node spread and systemic treatments. Epithelial cells were stained by the AE1/AE3 pan-cytokeratin antibody cocktail. The size and shape subsets of the stained epithelial cell clusters were defined in each image by use of the circularity and size filters and analyzed for prognostic performance. Epithelial areas with the optimal prognostic performance were uniformly small and round and could be recognized as individual epithelial cells scattered in tumor stroma. Their count achieved an area under the receiver operating characteristic curve (AUC) of 0.82, total area (AUC = 0.77), average size (AUC = 0.63), and circularity (AUC = 0.62). In conclusion, by use of computational image analysis as a hypothesis-free discovery tool, this study reveals the histomorphological marker with a high prognostic value that is simple and therefore easy to quantify by visual microscopy.

Novel application of the gray-level co-occurrence matrix analysis in the parvalbumin stained hippocampal gyrus dentatus in distinct rat models of Parkinson's disease.

To reveal the best choice of algorithm for parvalbumin-immunostained images of the hippocampal gyrus dentatus in two distinct rat models of Parkinson's disease (PD), particularly in terms of extracting the crucial information from the image, we tested whether the impact of experimentally induced dopaminergic (hemiparkinsonism) vs. cholinergic (PD cholinopathy) innervation impairment on the parvalbumin stained GABA interneurons could be detected using two separate algorithms, the fractal box-count and the gray-level co-occurrence matrix analysis (GLCM) algorithms. For the texture and fractal analysis of the hippocampal gyrus dentatus images, we used.tif images from three experimental groups of adult male Wistar rats: control rats, rats with Parkinson disease (PD) cholinergic neuropathology (with a PPT lesion), and hemiparkinsonian rats (with a SNpc lesion). For the suprapyramidal layer of the gyrus dentatus ASM and Entropy differentiated the images of the SNpc lesion versus the images of the control and the PPT lesion subjects, with significantly higher ASM and lower Entropy, indicating the homogenization of the images and their lower gray-level complexity. The infrapyramidal images of the SNpc group were differentiated versus the images from the control and PPT groups in terms of all the GLCM parameters: they showed lower mean Entropy and Contrast and higher ASM, Correlation and IDM. These results strongly suggest a rise in the uniformity, homogeneity and orderliness in the gray-levels of images from the SNpc group. Our results indicate that GLCM analysis is a more sensitive tool than fractal analysis for the detection of increased dendritic arborization in histological images.

Computational quantitative MR image features - a potential useful tool in differentiating glioblastoma from solitary brain metastasis.

PURPOSE: Glioblastomas (GBM) and metastases are the most frequent malignant brain tumors in the adult population. Their presentation on conventional MRI is quite similar, but treatment strategy and prognosis are substantially different. Even with advanced MR techniques, in some cases diagnostic uncertainty remains. The main objective of this study was to determine whether fractal, texture, or both MR image analyses could aid in differentiating glioblastoma from solitary brain metastasis. METHOD: In a retrospective study of 55 patients (30 glioblastomas and 25 solitary metastases) who underwent T2W/SWI/CET1 MRI, quantitative parameters of fractal and texture analysis were estimated, using box-counting and gray level co-occurrence matrix (GLCM) methods. RESULTS: All five GLCM parameters obtained from T2W images showed significant difference between glioblastomas and solitary metastases, as well as on CET1 images except correlation (SCOR), contrary to SWI images which showed different values of two parameters (angular second moment-SASM and contrast-SCON). Only three fractal features (binary box dimension-Dbin, normalized box dimension-Dnorm and lacunarity-λ) measured on T2W and Dnorm measured on CET1 images significantly differed GBMs from solitary metastases. The highest sensitivity and specificity were obtained from inverse difference moment (SIDM) on T2W and SIDM on CET1 images, respectively. Combination of several GLCM parameters yielded better results. The processing of T2W images provided the most significantly different parameters between the groups, followed by CET1 and SWI images. CONCLUSIONS: Computational-aided quantitative image analysis may potentially improve diagnostic accuracy. According to our results texture features are more significant than fractal-based features in differentiation glioblastoma from solitary metastasis.

Aspergillus fumigatus branching complexity in vitro: 2D images and dynamic modeling.

BACKGROUND: Aspergillus fumigatus causes serious infections in humans, and its virulence correlates with hyphal growth, branching and formation of the filamentous mycelium. The filamentous mycelium is a complex structure inconvenient for quantity analysis. In this study, we monitored the branching of A. fumigatus filamentous mycelium in vitro at different points in time in order to assess the complexity degree and develop a dynamic model for the branching complexity. METHOD: We used fractal analysis of microscopic images (FAMI) to measure the fractal dimensions (D) of the branching complexity within 24 h of incubation. RESULTS: By photographing the filamentous mycelium dynamically and processing the images, the D variation curve of A. fumigatus complexity degree was obtained. We acquired the D variation curve which contained initial exponential period and stationary period of A. fumigatus branching. Further, the obtained data of D was modeled via the logistic model (LM) to develop a dynamic model of A. fumigatus branching for the prediction of the specific growth rate of branching value (0.23 h-1). CONCLUSIONS: Developed FAMI and LM models present a simple and non-destructive method of predicting the evolution of branching complexity of A. fumigatus. These models are useful as laboratory measurements for the prediction of hyphal and mycelium development, especially relevant to the pathogenesis study of aspergillosis, as well as pathogenesis of other diseases caused by moulds.

Morphological Properties of the Two Types of Caudate Interneurons: Kohonen Self-Organizing Maps and Correlation-Comparison Analysis.

Our previous study found that caudate and putaminal interneurons are morphologically very different, and that accordingly they could be divided in two separate clusters. In addition, it also demonstrated, as a collateral result, that the caudate cluster itself consists of two clusters of morphologically different interneurons. Hence, the objective of this study is a morphological description and subtle differing of morphologies of these two types of caudate interneurons, i.e., an investigation of those morphological traits which characterize them uniquely, and which would distinguish them. Binary two-dimensional images of caudate interneurons, taken from deceased adult human subjects, were analyzed by using 46 parameters, describing the morphology of interneurons. The parameters can be divided in the following classes: size (surface) of a neuron, neuronal shape, length of neuronal morphological compartments, dendritic branching, morphological organization, and complexity. The morphological determination of caudate interneurons was performed in a step-wise manner. The first step was the assignment of each individual neuron to an adequate cluster where it belonged according to morphological criteria. This was done by using the trained artificial neural network, Kohonen self-organizing map. After the clusters were formed, the analysis is further continued by the precise, feature-wise determination of morphological differences found between clusters of caudate interneurons and then finished by defining correlation-based, mutual, inter-parametric relations for each of the clusters. The first was performed by using single-factor analysis, and the second by correlation-comparison analysis. Single-factor analysis showed significance for 34 parameters (morphological features) that distinguish between the clusters. Correlation-comparison analysis extended the results of single-factor analysis by demonstrating significance for 198 inter-parametric correlation pairs that represent 19.13% of mismatched correlations of the first kind among the total number of correlations. This represents a significant inter-cluster separation zone. In addition, the analysis extracted one correlation of the second kind, namely, the DO-MDCBO, very highly significant (p<0.001), positive (r=0.45) in the cluster I, while negative (r=-0.13), also significant (p<0.05) in the cluster II. The two clusters of caudate interneurons were found to be significantly morphologically different. These differences, albeit not strong as the caudate-putaminal differences, are more numerous with respect to significant morphological properties defining them. They probably underlie, influence, and modulate different neurofunctional behavior of the two types of interneurons, which need to be further investigated by future studies.

The Pan-Cytokeratin Staining Intensity and Fractal Computational Analysis of Breast Tumor Malignant Growth Patterns Prognosticate the Occurrence of Distant Metastasis.

Improved prognosis of breast cancer outcome could prolong patient survival by reliable identification of patients at high risk of metastasis occurrence which could benefit from more aggressive treatments. Based on such clinical need, we prognostically evaluated the malignant cells in breast tumors, as the obvious potential source of unexploited prognostic information. The patient group was homogeneous, without any systemic treatments or lymph node spread, with smaller tumor size (pT1/2) and a long follow-up. Epithelial cells were labeled with AE1/AE3 pan-cytokeratin antibody cocktail and comprehensively analyzed. Monofractal and multifractal analyses were applied for quantification of distribution, shape, complexity and texture of malignant cell clusters, while mean pixel intensity and total area were measures of the pan-cytokeratin immunostaining intensity. The results surprisingly indicate that simple binary images and monofractal analysis provided better prognostic information then grayscale images and multifractal analysis. The key findings were that shapes and distribution of malignant cell clusters (by binary fractal dimension; AUC = 0.29), their contour shapes (by outline fractal dimension; AUC = 0.31) and intensity of the pan-cytokeratin immunostaining (by mean pixel intensity; AUC = 0.30) offered significant performance in metastasis risk prognostication. The results reveal an association between the lower pan-cytokeratin staining intensity and the high metastasis risk. Another interesting result was that multivariate analysis could confirm the prognostic independence only for fractal but not for immunostaining intensity features. The obtained results reveal several novel and unexpected findings highlighting the independent prognostic efficacy of malignant cell cluster distribution and contour shapes in breast tumors.

Investigating the Fractal Dimension of the Foveal Microvasculature in Relation to the Morphology of the Foveal Avascular Zone and to the Macular Circulation in Patients With Type 2 Diabetes Mellitus.

In this study, we examined the relationship between the fractal dimension (FD), the morphology of the foveal avascular zone (FAZ) and the macular circulation in healthy controls and patients with type 2 diabetes mellitus (T2DM) with and with no diabetic retinopathy (DR). Cross-sectional data of 47 subjects were analyzed from a 5-year longitudinal study using a multimodal optical imaging approach. Healthy eyes from nondiabetic volunteers (n = 12) were selected as controls. Eyes from patients with T2DM were selected and divided into two groups: diabetic subjects with mild DR (MDR group, n = 15) and subjects with DM but without DR (DM group, n = 20). Our results demonstrated a higher FD in the healthy group (mean, 1.42 ± 0.03) than in the DM and MDR groups (1.39 ± 0.02 and 1.35 ± 0.03, respectively). Also, a bigger perimeter, area, and roundness of the FAZ were found in MDR eyes. A significant difference in area and perimeter (p ≤ 0.005) was observed for the MDR group supporting the enlargement of the FAZ due to diabetic complications in the eye. A moderate positive correlation (p = 0.014, R2 = 43.8%) between the FD and blood flow rate (BFR) was only found in the healthy control group. The BFR calculations revealed the lowest values in the MDR group (0.98 ± 0.27 µl/s vs. 1.36 ± 0.86 µl/s and 1.36 ± 0.57 µl/sec in the MDR, DM, and healthy groups, respectively, p = 0.2). Our study suggests that the FD of the foveal vessel arborization could provide useful information to identify early morphological changes in the retina of patients with T2DM. Our results also indicate that the enlargement and asymmetry of the FAZ might be related to a lower BFR because of the DR onset and progression. Interestingly, due to the lack of FAZ symmetry observed in the DM and MDR eyes, it appears that the distribution of flow within the retinal vessels loses complexity as the vascular structures distributing the flow are not well described by fractal branching. Further research could determine how our approach may be used to aid the diagnosis of retinal neurodegeneration and vascular impairment at the early stage of DR.

Translaminar neuromorphotopological clustering and classification of dentate nucleus neurons.

Thisstudy aims to determine whether dentate neurons can be translaminarlyneuromorphotopologically classified as ventrolateral or dorsomedial type. Adulthuman dentate interneuron 2D binary images are analyzed. The analysis isperformed on both real and virtual neuron samples and 29 parameters are used.They are divided into the classes: neuron surface, shape, length, branching andcomplexity. Clustering is performed by an algorithm that employs predictor extraction (matrix attractor analysis/non-negative matrix factorization and cluster analysis of predictor factors - separate unifactor analysis/Student's t-test and MANOVA) and multivariate cluster analysis (cluster analysis, principal component analysis, factor analysis with pro/varimax rotation, Fisher's linear discriminant analysis and feed-forward backpropagation artificial neural networks). The separate unifactor analysis extracted as significant the following predictors from the natural cell sample: the Npd (p< 0:05), and from the virtual cell sample: the Adt (p< 0.05),Do (p< 0.001), Ms (p< 0.01), Dwdth (p< 0:001), Npd (p< 0:05), Nsd (p< 0.001), Nt/hod (p< 0.001), Nmax (p< 0.01), Ds (p< 0.001), Cdf (Nt/hod)st (p< 0.05). For the multidimensional analysis, with the exception of the Fisher's linear discriminant analysis which gave a false positive result, all other analyses rejected the translaminar dentate neuron classification. Thus, dentate neurons cannot be classified into ventrolateral/dorsomedial neuromorphotopological subtypes. Although some differences were found to exist, they are not sufficient to carry this classification. The methods of multidimensional statistical analysis are again shown to be the best for such kinds of analysis.

The neuromorphological caudate-putaminal clustering of neostriate interneurons: Kohonen self-organizing maps and supervised artificial neural networks with multivariate analysis.

AIMS: The objective of this study is to investigate the possibility of the neuromorphotopological clustering of neostriate interneurons (NSIN) and their consequent classification into caudate (CIN) and putaminal neuron type (PIN), according to the nuclear localization of the neurons. It tends to discover whether these two topological neuron types are morphologically different. MATERIAL AND METHODS: The binary images of adult human NSIN are used for the purposes of the analysis. The total of the 46 neuromorphological parameters is used. They can be divided into the following classes: neuron surface/size, shape, compartmental length, dendritic branching, neuromorphological organization and complexity. The clustering is performed by an algorithm which consists of the steps of predictor extraction, multivariate cluster analysis set and cluster identification. RESULTS: Unifactor analysis extracted as significant the following parameters: neurosoma/perikaryon size (AS), the size of a dendritic tree (ADT), the size of a dendritic field area (ADF), the size of an entire neuron field area (ANF), the size of a perineuronal space (APNS), the fractal dimension of a neuron (DN), the index of perikaryon asymmetry (MS), total dendritic length (L), standardized total dendritic length (Lst), standardized dendritic width (DWDTHst), dendritic centrifugal branching order (DCBO), branching polarization index (MDCBO), dendritic partial surface (DSP), the fractal dimension of a skeletonized neuron image (DS), the index of maximal complex density of a dendritic tree (NMAX) and standardized dendritic branching pattern complexity (CDF/ADFst). The cluster analysis set together with Kohonen self-organizing maps and backpropagation feed-forward artificial neural networks confirmed the classification on both unsupervised and supervised manner, respectively. As a final step, the cluster identification is performed by an assignment of each neuron to a particular cluster. CONCLUSION: NSIN can be classified neuromorphologically into CIN and PIN type. Differences are expected since the two nuclei have different functional roles in processing the information involved in volitional movement control.

Fractal and Gray Level Cooccurrence Matrix Computational Analysis of Primary Osteosarcoma Magnetic Resonance Images Predicts the Chemotherapy Response.

The prediction of induction chemotherapy response at the time of diagnosis may improve outcomes in osteosarcoma by allowing for personalized tailoring of therapy. The aim of this study was thus to investigate the predictive potential of the so far unexploited computational analysis of osteosarcoma magnetic resonance (MR) images. Fractal and gray level cooccurrence matrix (GLCM) algorithms were employed in retrospective analysis of MR images of primary osteosarcoma localized in distal femur prior to the OsteoSa induction chemotherapy. The predicted and actual chemotherapy response outcomes were then compared by means of receiver operating characteristic (ROC) analysis and accuracy calculation. Dbin, Λ, and SCN were the standard fractal and GLCM features which significantly associated with the chemotherapy outcome, but only in one of the analyzed planes. Our newly developed normalized fractal dimension, called the space-filling ratio (SFR) exerted an independent and much better predictive value with the prediction significance accomplished in two of the three imaging planes, with accuracy of 82% and area under the ROC curve of 0.20 (95% confidence interval 0-0.41). In conclusion, SFR as the newly designed fractal coefficient provided superior predictive performance in comparison to standard image analysis features, presumably by compensating for the tumor size variation in MR images.

Box-Counting Method of 2D Neuronal Image: Method Modification and Quantitative Analysis Demonstrated on Images from the Monkey and Human Brain.

This study calls attention to the difference between traditional box-counting method and its modification. The appropriate scaling factor, influence on image size and resolution, and image rotation, as well as different image presentation, are showed on the sample of asymmetrical neurons from the monkey dentate nucleus. The standard BC method and its modification were evaluated on the sample of 2D neuronal images from the human neostriatum. In addition, three box dimensions (which estimate the space-filling property, the shape, complexity, and the irregularity of dendritic tree) were used to evaluate differences in the morphology of type III aspiny neurons between two parts of the neostriatum.

Prognostic biomarker value of binary and grayscale breast tumor histopathology images.

AIM: Breast cancer prognosis is in the spotlight owing to its potentially major clinical importance in effective therapeutic management. Following our recent prognostic establishment of the fractal features calculated on binary breast tumor histopathology images, this study aimed to accomplish the first optimization of this methodology by direct comparison of monofractal, multifractal and co-occurrence algorithms in analysis of binary versus grayscale image formats. PATIENTS & METHODS: The study included 93 patients with invasive breast cancer, without systemic treatment and a long median follow-up of 150 months. RESULTS: Grayscale images provided a better prognostic source in comparison to binary, while monofractal, multifractal and co-occurrence image analysis algorithms exerted a comparable performance. CONCLUSION: The critical prognostic importance of the grayscale texture is revealed.

Comparison of Monofractal, Multifractal and gray level Co-occurrence matrix algorithms in analysis of Breast tumor microscopic images for prognosis of distant metastasis risk.

Breast cancer prognosis is a subject undergoing intense study due to its high clinical relevance for effective therapeutic management and a great patient interest in disease progression. Prognostic value of fractal and gray level co-occurrence matrix texture analysis algorithms has been previously established on tumour histology images, but without any direct performance comparison. Therefore, this study was designed to compare the prognostic power of the monofractal, multifractal and co-occurrence algorithms on the same set of images. The investigation was retrospective, with 51 patients selected on account of non-metastatic IBC diagnosis, stage IIIB. Image analysis was performed on digital images of primary tumour tissue sections stained with haematoxylin/eosin. Bootstrap-corrected Cox proportional hazards regression P-values indicated a significant association with metastasis outcome of at least one of the features within each group. AUC values were far better for co-occurrence (0.66-0.77) then for fractal features (0.60-0.64). Correction by the split-sample cross-validation likewise indicated the generalizability only for the co-occurrence features, with their classification accuracies ranging between 67 and 72 %, while accuracies of monofractal and multifractal features were reduced to nearly random 52-55 %. These findings indicate for the first time that the prognostic value of texture analysis of tumour histology is less dependent on the morphological complexity of the image as measured by fractal analysis, but predominantly on the spatial distribution of the gray pixel intensities as calculated by the co-occurrence features.

Classification of adult human dentate nucleus border neurons: Artificial neural networks and multidimensional approach.

AIMS: Primary aim in this study is to investigate whether external and internal border neurons of adult human dentate nucleus express the same neuromorphological features or belong to a different morphological types i.e. whether can be classified not only by way of their topology as external and internal, but also based on their morphological features or in addition to their topology also by way of their morphology. Secondary aim is to determine and compare various methodologies in order to perform the first aim in a more accurate and efficient manner. MATERIAL AND METHODS: Blocks of tissue were cut out from the adult human cerebellum and stained according to the Kopsch-Bubenaite method. Border neurons of the dentate nucleus were investigated and digitized under the light microscope and processed thereafter. Seventeen parameters quantifying various aspects of neuron morphology are then measured. They can be categorized as shape, magnitude, complexity, length and branching parameters. Analyzes used are neural networks, separate unifactor, cluster, principal component, discriminant and correlation-comparison analysis. RESULTS: The external and internal border neurons differ significantly in six of the seventeen parameters investigated, mainly concerning dendritic ramification patterns, overall shape of dendritic tree and dendritic length. All six methodological approaches are in accordance showing slight clustering of data. Classification is based on six parameters: neuron (field) area, dendritic (field) area, total dendrite length, and position of maximal dendritic arborization density. Cluster analysis shows two data clusters. Separate unifactor analysis demonstrates inter-cluster differences with statistical significance (p < 0.05) for all six parameters separately. Principal component, discriminant and correlation-comparison analysis further prove the result on a more factor integrate manner and explain it, respectively. Thus, these neurons can be classified, not only according to their location but also according to some morphological features. Also, the group if internal border neurons is more homogeneous in itself than the other group of external border neurons. CONCLUSION: Border neurons from adult human dentate nucleus can be divided to external and internal according to its topology and based on neuromorphological computational parameters. This has potentially significant neurofunctional implications but further studies are needed to elucidate that. Multimethodological approach is shown as the best for finding the solution closest to reality. The possible functional meaning of these morphological differences for cerebellar network structure and function are discussed.