Rashmi Mukherjee

Automated tissue classification framework for reproducible chronic wound assessment.

The aim of this paper was to develop a computer assisted tissue classification (granulation, necrotic, and slough) scheme for chronic wound (CW) evaluation using medical image processing and statistical machine learning techniques. The red-green-blue (RGB) wound images grabbed by normal digital camera were first transformed into HSI (hue, saturation, and intensity) color space and subsequently the “S” component of HSI color channels was selected as it provided higher contrast. Wound areas from 6 different types of CW were segmented from whole images using fuzzy divergence based thresholding by minimizing edge ambiguity. A set of color and textural features describing granulation, necrotic, and slough tissues in the segmented wound area were extracted using various mathematical techniques. Finally, statistical learning algorithms, namely, Bayesian classification and support vector machine (SVM), were trained and tested for wound tissue classification in different CW images. The performance of the wound area segmentation protocol was further validated by ground truth images labeled by clinical experts. It was observed that SVM with 3rd order polynomial kernel provided the highest accuracies, that is, 86.94%, 90.47%, and 75.53%, for classifying granulation, slough, and necrotic tissues, respectively. The proposed automated tissue classification technique achieved the highest overall accuracy, that is, 87.61%, with highest kappa statistic value (0.793).

Comparison of oral dydrogestrone with progesterone gel and micronized progesterone for luteal support in 1,373 women undergoing in vitro fertilization: a randomized clinical study.

OBJECTIVE To compare the efficacy of oral dydrogesterone with that of micronized vaginal P gel and micronized P capsule for luteal supplementation. DESIGN Prospective, randomized clinical study. SETTING Institute of Reproductive Medicine, Kolkata, India. PATIENT(S) A total of 1,373 infertile women undergoing IVF participated. INTERVENTION(S) Micronized P gel, P capsule, and oral dydrogesterone were administered for luteal support and compared. MAIN OUTCOME MEASURE(S) Demographic profile and pregnancy and miscarriage rates. RESULT(S) The overall pregnancy rate and miscarriage rate were comparable among the three groups. CONCLUSION(S) Oral dydrogesterone seems to be a promising drug for luteal support in woman undergoing IVF.

Computational microscopic imaging for malaria parasite detection: a systematic review

Malaria, being an epidemic disease, demands its rapid and accurate diagnosis for proper intervention. Microscopic image‐based characterization of erythrocytes plays an integral role in screening of malaria parasites. In practice, microscopic evaluation of blood smear image is the gold standard for malaria diagnosis; where the pathologist visually examines the stained slide under the light microscope. This visual inspection is subjective, error‐prone and time consuming. In order to address such issues, computational microscopic imaging methods have been given importance in recent times in the field of digital pathology. Recently, such quantitative microscopic techniques have rapidly evolved for abnormal erythrocyte detection, segmentation and semi/fully automated classification by minimizing such diagnostic errors for computerized malaria detection. The aim of this paper is to present a review on enhancement, segmentation, microscopic feature extraction and computer‐aided classification for malaria parasite detection.

Automatic leukocyte nucleus segmentation by intuitionistic fuzzy divergence based thresholding

The paper proposes a robust approach to automatic segmentation of leukocytes nucleus from microscopic blood smear images under normal as well as noisy environment by employing a new exponential intuitionistic fuzzy divergence based thresholding technique. The algorithm minimizes the divergence between the actual image and the ideally thresholded image to search for the final threshold. A new divergence formula based on exponential intuitionistic fuzzy entropy has been proposed. Further, to increase its noise handling capacity, a neighborhood-based membership function for the image pixels has been designed. The proposed scheme has been applied on 110 normal and 54 leukemia (chronic myelogenous leukemia) affected blood samples. The nucleus segmentation results have been validated by three expert hematologists. The algorithm achieves an average segmentation accuracy of 98.52% in noise-free environment. It beats the competitor algorithms in terms of several other metrics. The proposed scheme with neighborhood based membership function outperforms the competitor algorithms in terms of segmentation accuracy under noisy environment. It achieves 93.90% and 94.93% accuracies for Speckle and Gaussian noises, respectively. The average area under the ROC curves comes out to be 0.9514 in noisy conditions, which proves the robustness of the proposed algorithm.

Nanoscale Surface Characterization of Human Erythrocytes by Atomic Force Microscopy: A Critical Review

Erythrocytes (red blood cells, RBCs), the most common type of blood cells in humans are well known for their ability in transporting oxygen to the whole body through hemoglobin. Alterations in their membrane skeletal proteins modify shape and mechanical properties resulting in several diseases. Atomic force microscopy (AFM), a new emerging technique allows non-invasive imaging of cell, its membrane and characterization of surface roughness at micrometer/nanometer resolution with minimal sample preparation. AFM imaging provides direct measurement of single cell morphology, its alteration and quantitative data on surface properties. Hence, AFM studies of human RBCs have picked up pace in the last decade. The aim of this paper is to review the various applications of AFM for characterization of human RBCs topology. AFM has been used for studying surface characteristics like nanostructure of membranes, cytoskeleton, microstructure, fluidity, vascular endothelium, etc., of human RBCs. Various modes of AFM imaging has been used to measure surface properties like stiffness, roughness, and elasticity. Topological alterations of erythrocytes in response to different pathological conditions have also been investigated by AFM. Thus, AFM-based studies and application of image processing techniques can effectively provide detailed insights about the morphology and membrane properties of human erythrocytes at nanoscale.

Posterior capsular opacification and intraocular lens surface micro-roughness characteristics: An atomic force microscopy study

OBJECTIVE Surface roughness parameters of various intraocular lenses (IOLs) biomaterials using atomic force microscopy (AFM) are compared. Variation, if any, in the micro-roughness properties of different IOLs made up of the same biomaterial is also explored. Retrospective analysis of posterior capsular opacification (PCO) incidence has been followed up for a period of four years post IOL implantation to evaluate the correlation of PCO formation with surface roughness of IOLs. DESIGN Experimental materials study. MATERIALS AND PARTICIPANTS: Surface characteristics of 20 different IOL models were assessed using AFM. These IOL models were made up of PMMA or HEMA or acrylic hydrophobic or acrylic hydrophilic or silicone. Retrospective analysis of PCO incidence in 3629 eyes of 2656 patients implanted with the same IOL models was performed. METHODS Topological characteristics of 20 different IOLs made up of 5 different biomaterials including (i) PMMA, (ii) HEMA, (iii) acrylic hydrophobic, (iv) acrylic hydrophilic and (v) silicone were evaluated using AFM in the tapping mode. Images were acquired with a resolution of 256 × 256 data points per scan at a scan rate of 0.5 Hz per line and a scan size of 10 × 10μm. Rate of PCO formation in 3629 eyes of 2656 patients implanted with the five different IOL biomaterials was retrospectively analyzed. RESULTS AFM images of IOL optic surfaces showed a collection of pores, grooves, ridges and surface irregularities. Surface roughness parameters of the IOL optics were significantly different on comparing lenses of different materials. Acrylic hydrophobic IOLs had minimum surface roughness while acrylic hydrophilic IOLs showed the highest surface roughness. Different IOL models of the same biomaterial showed varied topological roughness characteristics. Retrospective analyses of PCO formation rate after IOL implantation was carried out, which revealed that rate of PCO incidence, was directly proportional to the increase in surface micro-roughness of IOLs. CONCLUSIONS AFM is a powerful technique for the topological characterization of IOLs. Acrylic hydrophobic IOLs showed minimum surface roughness properties as well as minimum PCO incidence over a period of four years post implantation. It is, therefore, tempting to consider acrylic hydrophobic IOLs over other IOL biomaterials as the ideal biocompatible material for lowering PCO incidence. These results suggest an urgent need for manufacturers to optimize the various steps involved in the fabrication of IOLs.

Computer-aided diagnosis of breast cancer using cytological images: A systematic review

Cytological evaluation by microscopic image-based characterization [imprint cytology (IC) and fine needle aspiration cytology (FNAC)] plays an integral role in primary screening/detection of breast cancer. The sensitivity of IC and FNAC as a screening tool is dependent on the image quality and the pathologists level of expertise. Computer-aided diagnosis (CAD) is used to assists the pathologists by developing various machine learning and image processing algorithms. This study reviews the various manual and computer-aided techniques used so far in breast cytology. Diagnostic applications were studied to estimate the role of CAD in breast cancer diagnosis. This paper presents an overview of image processing and pattern recognition techniques that have been used to address several issues in breast cytology-based CAD including slide preparation, staining, microscopic imaging, pre-processing, segmentation, feature extraction and diagnostic classification. This review provides better insights to readers regarding the state of the art the knowledge on CAD-based breast cancer diagnosis to date.

Altered metabolic profile in early and late onset preeclampsia: An FTIR spectroscopic study.

OBJECTIVE Metabolic anomalies, if any, between early and late onset preeclampsia [PE] were explored using Fourier transform infrared [FTIR] spectroscopy. SETTING Department of Gynecology and Obstetrics, SSKM Hospital, IPGMER, Kolkata and Midnapur Medical College Hospital, Midnapur, India. SAMPLE 80 pregnant women attending routine antenatal care units; (i) early onset PE [gestational age; GA<34weeks] (ii) late onset PE [GA>34weeks] (iii) early onset control [GA 24-34weeks] and (iv) late onset control [GA>34weeks]. METHODS Serum FTIR spectra were obtained in the wave-number range of 600-4000cm(-1) at 4cm(-1) resolution. (1)H NMR and estimation of atherosclerotic index (AI) were performed to validate the FTIR findings. MAIN OUTCOME MEASURE(S) Clinical characteristics and metabolic profile. RESULTS 13 spectral peaks corresponding to the carbohydrate, protein and lipid region were significantly altered in early onset PE [P<0.001; at 95% confidence interval]. Discriminant analysis identified five highly significant wave-numbers (1078, 1088, 1122, 1169 and 1171cm(-1)) having ⩾80% overall accuracy. Hierarchical cluster analysis of the obtained spectra at these 5 wave-numbers provided excellent segregation of early and late onset PE with respect to their controls. Principal component analysis revealed that these 5 wave-numbers significantly separated the two sub-groups of PE (97.95% of the total variance). (1)H NMR results showed that serum levels of glutamate, choline, alanine and lactate were significantly higher while ariginine and citrate were significantly decreased in early onset PE as compared to late onset cases. CONCLUSION Our study reveals differences in metabolomic profiles of early and late onset preeclamptic cases.

Serum-based diagnostic prediction of oral submucous fibrosis using FTIR spectrometry

Oral submucous fibrosis (OSF) is found to have the highest malignant potentiality among all other pre-cancerous lesions. However, its detection prior to tissue biopsy can be challenging in clinics. Moreover, biopsy examination is invasive and painful. Hence, there is an urgent need of new technology that facilitates accurate diagnostic prediction of OSF prior to biopsy. Here, we used FTIR spectroscopy coupled with chemometric techniques to distinguish the serum metabolic signatures of OSF patients (n=30) and healthy controls (n=30). Serum biochemical analyses have been performed to further support the FTIR findings. Absorbance intensities of 45 infrared wavenumbers differed significantly between OSF and normal serum FTIR spectra representing alterations in carbohydrates, proteins, lipids and nucleic acids. Nineteen prominent significant wavenumbers (P≤0.001) at 1020, 1025, 1035, 1039, 1045, 1078, 1055, 1100, 1117, 1122, 1151, 1169, 1243, 1313, 1398, 1453, 1544, 1650 and 1725cm-1 provided excellent segregation of OSF spectra from normal using multivariate statistical techniques. These findings provided essential information on the metabolic features of blood serum of OSF patients and established that FTIR spectroscopy coupled with chemometric analysis can be potentially useful in the rapid and accurate preoperative screening/diagnosis of OSF.

Morphometric Evaluation of Preeclamptic Placenta Using Light Microscopic Images

Deficient trophoblast invasion and anomalies in placental development generally lead to preeclampsia (PE) but the inter-relationship between placental function and morphology in PE still remains unknown. The aim of this study was to evaluate the morphometric features of placental villi and capillaries in preeclamptic and normal placentae. The study included light microscopic images of placental tissue sections of 40 preeclamptic and 35 normotensive pregnant women. Preprocessing and segmentation of these images were performed to characterize the villi and capillaries. Fishers linear discriminant analysis (FLDA), hierarchical cluster analysis (HCA), and principal component analysis (PCA) were applied to identify the most significant placental (morphometric) features from microscopic images. A total of 10 morphometric features were extracted, of which the villous parameters were significantly altered in PE. FLDA identified 5 highly significant morphometric features (>90% overall discrimination accuracy). Two large subclusters were clearly visible in HCA based dendrogram. PCA returned three most significant principal components cumulatively explaining 98.4% of the total variance based on these 5 significant features. Hence, quantitative microscopic evaluation revealed that placental morphometry plays an important role in characterizing PE, where the villous is the major component that is affected.