Time filter

Source Type

Bhowmick S.,Tezpur University | Das D.K.,Indian Institute of Technology Kharagpur | Maiti A.K.,Midnapur Medical College and Hospital | Chakraborty C.,Indian Institute of Technology Kharagpur
Micron | Year: 2013

The objective of this study is to address quantitative microscopic approach for automated screening of erythrocytes in anaemic cases using scanning electron microscopic (SEM) images of unstained blood cells. Erythrocytes were separated from blood samples and processed for SEM imaging. Thereafter, erythrocytes were segmented using marker controlled watershed transformation technique. Total 47 structural and textural features of erythrocytes were extracted using various mathematical measures for six types of anaemic cases as compared to the control group. These features were statistically evaluated at 1% level of significance and subsequently ranked using Fisher's F-statistic describing the group discriminating potentiality. Amongst all extracted features, twenty nine features were found to be statistically significant (p< 0.001). Finally, Bayesian classifier was applied to classify six types of anaemia based on top seventeen ranked features those of which are of course statistically significant. The present study yielded a predictive accuracy of 88.99%. © 2012 Elsevier Ltd.

Das D.K.,Indian Institute of Technology Kharagpur | Ghosh M.,Indian Institute of Technology Kharagpur | Pal M.,Midnapur Medical College and Hospital | Maiti A.K.,Midnapur Medical College and Hospital | Chakraborty C.,Indian Institute of Technology Kharagpur
Micron | Year: 2013

The aim of this paper is to address the development of computer assisted malaria parasite characterization and classification using machine learning approach based on light microscopic images of peripheral blood smears. In doing this, microscopic image acquisition from stained slides, illumination correction and noise reduction, erythrocyte segmentation, feature extraction, feature selection and finally classification of different stages of malaria (Plasmodium vivax and Plasmodium falciparum) have been investigated. The erythrocytes are segmented using marker controlled watershed transformation and subsequently total ninety six features describing shape-size and texture of erythrocytes are extracted in respect to the parasitemia infected versus non-infected cells. Ninety four features are found to be statistically significant in discriminating six classes. Here a feature selection-cum-classification scheme has been devised by combining F-statistic, statistical learning techniques i.e., Bayesian learning and support vector machine (SVM) in order to provide the higher classification accuracy using best set of discriminating features. Results show that Bayesian approach provides the highest accuracy i.e., 84% for malaria classification by selecting 19 most significant features while SVM provides highest accuracy i.e., 83.5% with 9 most significant features. Finally, the performance of these two classifiers under feature selection framework has been compared toward malaria parasite classification. © 2012 Elsevier Ltd.

Das D.,Indian Institute of Technology Kharagpur | Ghosh M.,Indian Institute of Technology Kharagpur | Chakraborty C.,Indian Institute of Technology Kharagpur | Pal M.,Midnapur Medical College and Hospital | Maity A.K.,Midnapur Medical College and Hospital
International Conference on Systems in Medicine and Biology, ICSMB 2010 - Proceedings | Year: 2010

Erythrocyte shape recognition is very important in the detection of thalassemia and anemia using microscopic images. This study aims to develop a computer aided shape recognizer for the recognition of abnormal shapes viz., tear drop, echinocyte, eliptocyte. Here such recognition is done using Hu's moments and other geometric features followed by gray level thresholding and marker controlled watershed segmentation. These features are statistically evaluated to show their significant in discriminating the mentioned abnormal and normal shapes. In the result, it is found that six moment based features are significant. © 2010 IEEE.

Pal D.,Chittaranjan National Cancer Institute | Banerjee S.,Chittaranjan National Cancer Institute | Mukherjee S.,Chittaranjan National Cancer Institute | Roy A.,Midnapur Medical College and Hospital | And 2 more authors.
Journal of Dermatological Science | Year: 2010

Background: Eugenol is the active component of essential oil isolated from clove (Syzigium aromaticum). Eugenol has antimutagenic, antigenotoxic, anti-inflammatory properties. The anticarcinogenic effect of eugenol was evident in different types of cell lines. However, its anticarcinogenic effect in in vivo has not yet been fully explored. Objective: The aim of this study is to evaluate the chemopreventive potential of eugenol in an experimental skin carcinogenesis mice model system. Method: Skin tumor was induced by topical application of DMBA croton oil in Swiss mice. To assess the chemopreventive potential of eugenol, it was orally administered 15 days prior carcinogen treatment. The development of skin carcinogenesis was confirmed by histopathological analysis. Cellular proliferation and apoptosis in the skin tumor were analyzed by in situ cellular proliferation and in situ cell death assay. Expression of some proliferation and apoptosis associated genes was analyzed by RT-PCR and protein expression was analyzed by Western blot. Results: Reduction in incidence and sizes of skin tumors along with overall increase in survival of mice were seen due to eugenol treatment. Restriction of skin carcinogenesis at the dysplastic stage along with reduced rate of cellular proliferation and increase in apoptosis were evident in eugenol treated skin tumors. Eugenol treatment led to the downregulation of c-Myc, H-ras and Bcl2 expression along with upregulation of P53, Bax and active Caspase-3 expression in the skin lesions. Conclusion: Restriction of skin carcinogenesis at dysplastic stage by eugenol was due to attenuation of c-Myc, H-ras and modification of some p53 associated gene expression. © 2010 Japanese Society for Investigative Dermatology.

Bhowmick S.,Tezpur University | Das D.K.,Indian Institute of Technology Kharagpur | Maiti A.K.,Midnapur Medical College and Hospital | Chakraborty C.,Indian Institute of Technology Kharagpur
Journal of Medical Imaging and Health Informatics | Year: 2012

This paper aims to develop a computer vision approach for thalassemia screening using geometric features characterizing morphology of erythrocytes based on scanning electron microscopic (SEM) images. Erythrocytes were separated from blood samples and chemically processed for SEM imaging at 2000× resolution. Thereafter, marker controlled watershed transform was used to segregate erythrocytes from SEM images. Seventeen geometric features were extracted using various mathematical measures. Independent sample t-test revealed that nine features were statistically significant (p < 0.001). Finally, a multilayer perception (MLP) neural network was trained for thalassemia and healthy erythrocytes using these features and tested. It was observed that MLP provided a high overall accuracy of 94.59% with 90.38% sensitivity, 98.81% specificity and 98.93% positive predictive value. Copyright © 2012 American Scientific Publishers.

Das D.K.,Indian Institute of Technology Kharagpur | Maiti A.K.,Midnapur Medical College and Hospital | Chakraborty C.,Indian Institute of Technology Kharagpur
Journal of Microscopy | Year: 2015

In this paper, we propose a comprehensive image characterization cum classification framework for malaria-infected stage detection using microscopic images of thin blood smears. The methodology mainly includes microscopic imaging of Leishman stained blood slides, noise reduction and illumination correction, erythrocyte segmentation, feature selection followed by machine classification. Amongst three-image segmentation algorithms (namely, rule-based, Chan-Vese-based and marker-controlled watershed methods), marker-controlled watershed technique provides better boundary detection of erythrocytes specially in overlapping situations. Microscopic features at intensity, texture and morphology levels are extracted to discriminate infected and noninfected erythrocytes. In order to achieve subgroup of potential features, feature selection techniques, namely, F-statistic and information gain criteria are considered here for ranking. Finally, five different classifiers, namely, Naive Bayes, multilayer perceptron neural network, logistic regression, classification and regression tree (CART), RBF neural network have been trained and tested by 888 erythrocytes (infected and noninfected) for each features' subset. Performance evaluation of the proposed methodology shows that multilayer perceptron network provides higher accuracy for malaria-infected erythrocytes recognition and infected stage classification. Results show that top 90 features ranked by F-statistic (specificity: 98.64%, sensitivity: 100%, PPV: 99.73% and overall accuracy: 96.84%) and top 60 features ranked by information gain provides better results (specificity: 97.29%, sensitivity: 100%, PPV: 99.46% and overall accuracy: 96.73%) for malaria-infected stage classification. © 2014 Royal Microscopical Society.

Thakur A.K.,Indian Institute of Technology Kharagpur | Purkait B.,Midnapur Medical College and Hospital
Medicinal Chemistry Research | Year: 2010

A systematic study of the effect of the commercially available, ultradiluted drug, Digitalis purpurea (extract of Foxglove leaves) with aqueous ethanol was conducted to monitor changes in its chemical structure/functional group arrangements using vibrational (Fourier Transform Infrared and Raman) spectroscopy. These changes suggest a significant effect of ultradilution (\micro volumes) in the spectrum profile of Digitalis bands in the fingerprint region. The study shows that the process of serial dilution assists in changing the chemical environment in the backbone matrix of the medicinally active ingredient of Digitalis purpurea. In particular, increase in dilution of Digitalis purpurea causes a change in its vibrational mode profile that matches well with the vibrational bands of digoxin. The technique seems to be useful in the detection and identification of compounds/ chemical groups present at levels lower than microvolume in drugs used in alternative/ complementary medicine. © Birkhäuser Boston 2009.

Sharma A.,Indian Institute of Technology Kharagpur | Purkait B.,Midnapur Medical College and Hospital
Journal of Analytical Methods in Chemistry | Year: 2012

Serially diluted and agitated (SAD) drugs available commercially are in use with great faith because of the astonishing results they produce. The scientific viewpoint attached to the centuries-old therapy with SAD drugs, as in homeopathy, remained doubtful for want of appropriate research and insufficient evidence base. The conflicting points related to SAD drug mostly related to the level of concentrations/dilutions, use of drug in contradictory clinical conditions compared to the modern system of medicine, identification of medicinally active ingredient in concentrations and dilutions used in commercially available SAD drugs, and lack of laboratory-based pharmacological data vis - vis modern medicine. Modus operandi of SAD drug is also unknown. To address some of these issues an analytical study was carried out wherein commercially available SAD drug Digitalis purpurea, commonly used in different systems of medicine, was put to test. Various concentrations of commercially available Digitalis purpurea were analyzed using analytical methods: cyclic voltammetry, emission spectroscopy, and UV-VIS spectroscopy. These analytical methods apparently identified the medicinal ingredients and effect of serial dilution in commercial preparation of the drugs. © 2012 Anup Sharma and Bulbul Purkait.

Das D.K.,Indian Institute of Technology Kharagpur | Chakraborty C.,Indian Institute of Technology Kharagpur | Mitra B.,Midnapur Medical College and Hospital | Maiti A.K.,Midnapur Medical College and Hospital | Ray A.K.,Bengal Engineering and Science University
Journal of Microscopy | Year: 2013

Anaemia is one of the most common diseases in the world population. Primarily anaemia is identified based on haemoglobin level; and then microscopically examination of peripheral blood smear is required for characterizing and confirmation of anaemic stages. In conventional approach, experts visually characterize abnormality present in the erythrocytes under light microscope, and this evaluation process is subjective in nature and error prone. In this study, we have proposed a methodology using machine learning techniques for characterizing erythrocytes in anaemia associated with anaemia using microscopic images of peripheral blood smears. First, peripheral blood smear images are preprocessed based on grey world assumption technique and geometric mean filter for reducing unevenness of background illumination and noise reduction. Then erythrocyte cells are segmented using marker-controlled watershed segmentation technique. The erythrocytes in anaemia, such as, tear drop, echinocyte, acanthocyte, elliptocyte, sickle cells and normal erythrocytes cells have been characterized and classified based on their morphological changes. Optimal subset of features, ranked by information gain measure provides highest classification performance using logistic regression classifier in comparison with other standard classifiers. © 2012 The Authors Journal of Microscopy © 2012 Royal Microscopical Society.

PubMed | CSIR - Central Electrochemical Research Institute, West Bengal University of Animal and Fishery Sciences, Midnapur Medical College and Hospital and Indian Institute of Technology Kharagpur
Type: | Journal: Hernia : the journal of hernias and abdominal wall surgery | Year: 2016

Adhesion formation remains a major complication following hernia repair surgery. Physical barriers though effective for adhesion prevention in clinical settings are associated with major disadvantages, therefore, needs further investigation. This study evaluates silk fibroin hydrogel as a physical barrier on polypropylene mesh for the prevention of adhesion following ventral hernia repair.Peritoneal explants were cultured on silk fibroin scaffold to evaluate its support for mesothelial cell growth. Full thickness uniform sized defects were created on the ventral abdominal wall of rabbits, and the defects were covered either with silk hydrogel coated polypropylene mesh or with plain polypropylene mesh as a control. The animals were killed after 1month, and the adhesion formation was graded; healing response of peritoneum was evaluated by immunohistochemistry with calretinin, collagen staining of peritoneal sections, and expression of PCNA, collagen-I, TNF, IL6 by real time PCR; and its adverse effect if any was determined.Silk fibroin scaffold showed excellent support for peritoneal cell growth in vitro and the cells expressed calretinin. A remarkable prevention of adhesion formation was observed in the animals implanted with silk hydrogel coated mesh compared to the control group; in these animals peritoneal healing was complete and predominantly by mesothelial cells with minimum fibrotic changes. Expression of inflammatory cytokines decreased compared to control animals, histology of abdominal organs, haematological and blood biochemical parameters remained normal.Therefore, silk hydrogel coating of polypropylene mesh can improve peritoneal healing, minimize adhesion formation, is safe and can augment the outcome of hernia surgery.

Loading Midnapur Medical College and Hospital collaborators
Loading Midnapur Medical College and Hospital collaborators