Jyotirmoy Chatterjee

Brightness preserving dynamic fuzzy histogram equalization

This paper proposes a novel modification of the brightness preserving dynamic histogram equalization technique to improve its brightness preserving and contrast enhancement abilities while reducing its computational complexity. The modified technique, called Brightness Preserving Dynamic Fuzzy Histogram Equalization (BPDFHE), uses fuzzy statistics of digital images for their representation and processing. Representation and processing of images in the fuzzy domain enables the technique to handle the inexactness of gray level values in a better way, resulting in improved performance. Execution time is dependent on image size and nature of the histogram, however experimental results show it to be faster as compared to the techniques compared here. The performance analysis of the BPDFHE along with that for BPDHE has been given for comparative evaluation.

A novel wavelet neural network based pathological stage detection technique for an oral precancerous condition

Aim: To describe a novel neural network based oral precancer (oral submucous fibrosis; OSF) stage detection method. Method: The wavelet coefficients of transmission electron microscopy images of collagen fibres from normal oral submucosa and OSF tissues were used to choose the feature vector which, in turn, was used to train the artificial neural network. Results: The trained network was able to classify normal and oral precancer stages (less advanced and advanced) after obtaining the image as an input. Conclusions: The results obtained from this proposed technique were promising and suggest that with further optimisation this method could be used to detect and stage OSF, and could be adapted for other conditions.

Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration

We present an algorithm for identifying retinal pathologies given retinal optical coherence tomography (OCT) images. Our approach fine-tunes a pre-trained convolutional neural network (CNN), GoogLeNet, to improve its prediction capability (compared to random initialization training) and identifies salient responses during prediction to understand learned filter characteristics. We considered a data set containing subjects with diabetic macular edema, or dry age-related macular degeneration, or no pathology. The fine-tuned CNN could effectively identify pathologies in comparison to classical learning. Our algorithm aims to demonstrate that models trained on non-medical images can be fine-tuned for classifying OCT images with limited training data.

Quantitative Analysis of Histopathological Features of Precancerous Lesion and Condition Using Image Processing Technique

This paper aims at quantitative analysis of histopathological features of precancerous lesion and condition using image processing technique. The algorithm involves median and low pass filtering, segmentation by adaptive region growing, optimal and local thresholding, morphological operations such as opening and closing of gray scale and binary images and some numerical methods. Differentiation on the basis of type and level of precancerous type or condition is carried out based on image marker, defined as a vector of cancer related features viz. length and curvature of radius of rete-ridges and papillae, population density of cells within epithelium, etc. Implementation of presented algorithms is done in MATLAB. The results support quantitative analysis of pathological condition in respect with progression towards malignancy. This analysis may help in developing automated analysis tool

Assessment of malignant potential of oral submucous fibrosis through evaluation of p63, E-cadherin and CD105 expression

Background The assessment of malignant potential of oral submucous fibrosis grades vis-à-vis their progression towards malignancy is associated with expression of possible multiple molecular markers. Aims To analyse p63, E-cadherin and CD105 expression in this premalignant pathosis with a view to unravel and understand the expression of these molecules as markers. Methods The oral mucosal biopsies (normal, oral submucous fibrosis with and without dysplasia) were studied with routine H&E, and by immunohistochemistry for p63, E-cadherin and CD105 expression. p63 was assessed as percentage of positive nuclei. E-cadherin expression was estimated through (i) distance between basement membrane and E-cadherin expression initiation point, (ii) ratio between epithelial thickness and epithelial thickness displaying E-cadherin, and (iii) E-cadherin intensity variation along the expression path. CD105 expression was assessed qualitatively. Results The p63+ cells were highest in severely dysplastic tissues followed by other dysplastic grades, normal oral mucosa and non-dysplastic conditions. However, the p63+ cells displayed the feature of progressive maturation only in normal mucosa. There was a loss of membranous E-cadherin in basal layers of all diseased conditions; it was highest in severe dysplasia. There was significant variation (p<0.0001) in E-cadherin intensity within and between the tissues (normal and diseased). CD105 expression increased abruptly in dysplasia. Conclusions The malignant potential of this pre-cancerous condition is likely to be correlated with an increase in p63 and CD105 expression and a concomitant loss of membranous E-cadherin. This may lead to marker identification through greater validation.

Automated classification of cells in sub-epithelial connective tissue of oral sub-mucous fibrosis-An SVM based approach

Quantitative evaluation of histopathological features is not only vital for precise characterization of any precancerous condition but also crucial in developing automated computer aided diagnostic system. In this study segmentation and classification of sub-epithelial connective tissue (SECT) cells except endothelial cells in oral mucosa of normal and OSF conditions has been reported. Segmentation has been carried out using multi-level thresholding and subsequently the cell population has been classified using support vector machine (SVM) based classifier. Moreover, the geometric features used here have been observed to be statistically significant, which enhance the statistical learning potential and classification accuracy of the classifier. Automated classification of SECT cells characterizes this precancerous condition very precisely in a quantitative manner and unveils the opportunity to understand OSF related changes in cell population having definite geometric properties. The paper presents an automated classification method for understanding the deviation of normal structural profile of oral mucosa during precancerous changes.

Electrospun nanofibers of a phosphorylated polymer--a bioinspired approach for bone graft applications.

Biomaterials based on bioinspired mineralization are expected to offer osteoconductive and osteoinductive scaffolds for bone regeneration. An important role in the mediation of in vivo biomineralization process is played by highly anionic non-collagenous phosphoproteins (NCP) bound to the collagen matrix. Inspired by this fact, synthetic analogues of the NCPs like polyvinyl phosphonic acid which provide surface nucleation sites have been employed successfully for mineralization of hard tissues. In this study, electrospun nanofibrous scaffolds of partially phosphorylated polyvinyl alcohol (PPVA) are prepared and studied for matrix mineralization and maturation of human pre-osteoblasts like MG63 cells. Partial phosphorylation was found to affect many solution properties of PVA like increase in surface tension, conductivity and semi-crystalline intermolecular hydrogen bond formations narrowing down the electrospinning window for PPVA. In vitro mineralization under SBF treatment was uniform along the length of fibers on PPVA nanofibers. Further, MG63 cells showed increased adherence and proliferation on PPVA nanofibers and the expression of alkaline phosphatase activity and cell-matrix calcium levels were about two times higher than PVA nanofibers. The study established fabrication of electrospun nanofibers of a partially phosphorylated polymer, PVA resulting in improved osteoconduction and expression of early markers of osteoinduction in MG63 cells.

Segmentation of blood smear images using normalized cuts for detection of malarial parasites

This paper presents an optimized normalized cut method for segmentation of RBCs infected with malarial parasites using peripheral blood smears. The algorithm is applied over various color spaces to find its optimal performance for microscopic blood smear images. We tested the efficacy of results in RGB, YCbCr, HSV and NTSC using the Rands Index. The work is useful in telepathology applications and can automate the screening of malaria in rural areas where healthcare manpower is limited.

Epithelio-mesenchymal transitional attributes in oral sub-mucous fibrosis.

Evaluating molecular attributes in association with its epithelial and sub-epithelial changes of oral sub-mucous fibrosis is meaningful in exploring the plausibility of an epithelio-mesenchymal transition (EMT) and malignant potentiality of this pathosis. In this study histopathological and histochemical attributes for basement membrane and connective tissue in biopsies of oral sub-mucous fibrosis (n = 55) and normal oral mucosa (n = 16) were assessed and expressions of p63, E-cadherin, β-catenin, N-cadherin and TWIST were analyzed immunohistochemically. The p63 and its isoforms (TA and ∆N), PARD3, E-cadherin and β-catenin were also assessed transcriptomically by q-PCR and EMT players like TWIST1, ZEB1, MMP9 and micro-RNA 205 were searched in gene expression microarrays. Oral epithelium demonstrating impairment in progressive maturation in oral sub-mucous fibrosis concomitantly experienced an increase in basement membrane thickness and collagen deposition along with alteration in target molecular expressions. In comparison to non-dysplastic conditions dysplastic stages exhibited significant increase in p63 and p63∆N expressions whereas, E-cadherin and β-catenin exhibited loss from the membrane with concurrent increase in cytoplasm. Further the N-cadherin and TWIST were gained remarkably along with the appearance of nuclear accumulation features of β-catenin. The microarray search had noticed the up-regulation of TWIST1, ZEB1 and MMP9 along with down regulation of micro-RNA 205. The simultaneous increase in basement membrane thickness and sub-epithelial collagen deposition were the plausible indicators for increased matrix stiffness with expected impact on oral epithelial functional homoeostasis. This was corroborated with the increase in expressions of epithelial master regulator p63 and its oncogenic isoform (∆N) along with membranous loss of E-cadherin (EMT hallmark) and its associate β-catein and gain of mesenchymal markers like N-cadherin and TWIST. These also became indicative for the induction of epithelial to mesenchymal transitional mechanism in oral sub-mucous fibrosis when connoted here with the relevant modulation in expressions of EMT regulators.

Structural markers for normal oral mucosa and oral sub-mucous fibrosis

This article presents a quantitative approach for the characterization of normal oral mucosa (NOM) in respect to thickness and textural properties of its entire epithelial layer. Histological images of oral mucosa depict that both thickness and tissue architecture at cellular and tissue level undergo change, as mucosa converts from normal to precancerous or cancerous state. In this study the thickness and fractal dimension of the mucosal epithelium of NOM and oral sub-mucous fibrosis (OSF) condition have been computed using 83 normal and 29 OSF images of oral mucosa. The result shows significant delineation between NOM and OSF in respect of both the epithelial thickness (in microm) and fractal dimensions. This quantitative characterization of oral epithelium will be of immense help for oral onco-pathologists and researchers to assess the biological nature of normal and diseased (OSF) mucosa with higher accuracy. Moreover, further differential applications may enable them to find out newer accurate quantitative diagnostic procedures to that of the usual histopathological gold standard for the assessment of malignant potentiality.