A comparative assessment of deep object detection models for blood smear analysis.

A blood smear is a common type of blood test where blood sample is taken from a patient, smear is made from the sample followed by observation of red blood cells, white blood cells and platelets. A pathologist carefully observes the sample and manually counts the number of RBC, WBC and platelets. This entire process from creating a smear to manually counting each element is tedious and susceptible to human errors. That is why, with the advancement of deep learning, various object detection techniques have become useful for automating the process and mitigating human errors in blood smear analysis. This work presents a comparative assessment of three different object detection models namely Faster R-CNN, EfficientDet D3 and CenterNet Hourglass, and presents their respective inference results. The three models have been compared using the COCO evaluation metrics to identify the best model performance for the given task. It is observed that out of the three models, the Faster R-CNN model performs the best in detecting WBCs and platelets in microscopic blood smear images with an average precision of 99.4%. Critical tasks like medical image processing require accurate predictions to prevent unintended ramifications. Therefore, while slower in terms of inference time, Faster R-CNN is the go-to model where accuracy is the priority. The work is also compared with the existing work in this domain to prove its efficiency.

Epidemiology, Genotyping, Mutational and Phylogenetic Analysis of Hepatitis B Virus Infection in North-east India.

BACKGROUND/OBJECTIVE: Hepatitis B virus (HBV) infection is a major public health problem globally. Northeast India is home to indigenous tribes with different ethnicity and high rates of drug abuse and HIV infection. The study was designed to estimate the burden of HBV infection across various spectrums of liver diseases from this region. HBV genotypes and subgenotypes play a role in the chronicity of disease, response to treatment and its progression. As very limited data are available from this region, we tried to elucidate the role of HBV genotypes, HBV mutants and their phylogenetic analysis. METHOD: We designed a prospective multicentric study, and included 7464 liver disease cases, 7432 blood donors and 650 health care workers, who were screened for HBV infection. HBV DNA positive patients were genotyped and subjected to surface protein, precore and core mutation and phylogenetic analysis. RESULTS: The prevalence of HBV infection with respect to different types of liver diseases, blood donors and health care workers was 9.9% (1550/15,546). 49.5% (768/1550) cases were found to be HBV DNA positive. The most common genotype was found to be genotype D 74.2% (570/768), followed by genotype C 6.5% (50/768), A 4.4% (34/768) and I 0.9% (7/768). CONCLUSION: This study highlights the high hepatitis B burden in Northeast India, reflecting lacunae in health care needs of the region. Also, the different genotype distribution and presence of mutations may translate into different rates of liver disease progression, prognosis and ultimately, clinical significance. However, further prospective cohort study from Northeast India is warranted, to elucidate the clinical significance of multiple genotypes and mutation in this unique population.

Study of morphological and textural features for classification of oral squamous cell carcinoma by traditional machine learning techniques.

BACKGROUND: Oral squamous cell carcinoma (OSCC) is the most prevalent form of oral cancer. Very few researches have been carried out for the automatic diagnosis of OSCC using artificial intelligence techniques. Though biopsy is the ultimate test for cancer diagnosis, analyzing a biopsy report is a very much challenging task. To develop computer-assisted software that will diagnose cancerous cells automatically is very important and also a major need of the hour. AIM: To identify OSCC based on morphological and textural features of hand-cropped cell nuclei by traditional machine learning methods. METHODS: In this study, a structure for semi-automated detection and classification of oral cancer from microscopic biopsy images of OSCC, using clinically significant and biologically interpretable morphological and textural features, are examined and proposed. Forty biopsy slides were used for the study from which a total of 452 hand-cropped cell nuclei has been considered for morphological and textural feature extraction and further analysis. After making a comparative analysis of commonly used methods in the segmentation technique, a combined technique is proposed. Our proposed methodology achieves the best segmentation of the nuclei. Henceforth the features extracted were fed into five classifiers, support vector machine, logistic regression, linear discriminant, k-nearest neighbors and decision tree classifier. Classifiers were also analyzed by training time. Another contribution of the study is a large indigenous cell level dataset of OSCC biopsy images. RESULTS: We achieved 99.78% accuracy applying decision tree classifier in classifying OSCC using morphological and textural features. CONCLUSION: It is found that both morphological and textural features play a very important role in OSCC diagnosis. It is hoped that this type of framework will help the clinicians/pathologists in OSCC diagnosis.

Automated oral squamous cell carcinoma identification using shape, texture and color features of whole image strips.

Despite profound knowledge of the incidence of oral cancers and a large body of research beyond it, it continues to beat diagnosis and treatment management. Post physical observation by clinicians, a biopsy is a gold standard for accurate detection of any abnormalities. Towards the application of artificial intelligence as an aid to diagnosis, automated cell nuclei segmentation is the most essential step for the recognition of the cancer cells. In this study, we have extracted the shape, texture and color features from the histopathological images collected indigenously from regional hospitals. A dataset of 42 whole slide slices was used to automatically segment and generate a cell level dataset of 720 nuclei. Next, different classifiers were applied for classification purposes. 99.4 % accuracy using Decision Tree Classifier, 100 % accuracy using both SVM and Logistic regression and 100 % accuracy using SVM, Logistic regression and Linear Discriminant were acquired for shape, textural and color features respectively. The in-depth analysis showed SVM and Linear Discriminant classifier gave the best result for texture and color features respectively. The achieved result can be effectively converted to software as an assistant diagnostic tool.

Histopathological imaging database for oral cancer analysis.

The repository is composed of 1224 images divided into two sets of images with two different resolutions. First set consists of 89 histopathological images with the normal epithelium of the oral cavity and 439 images of Oral Squamous Cell Carcinoma (OSCC) in 100x magnification. The second set consists of 201 images with the normal epithelium of the oral cavity and 495 histopathological images of OSCC in 400x magnification. The images were captured using a Leica ICC50 HD microscope from Hematoxyline and Eosin (H&E) stained tissue slides collected, prepared and catalogued by medical experts from 230 patients. A subset of 269 images from the second data set was used to detect OSCC based on textural features [1]. Histopathology plays a very important role in diagnosing a disease. It is the investigation of biological tissues to detect the presence of diseased cells in microscopic detail. It usually involves a biopsy. Till date biopsy is the gold-standard test to diagnose cancer. The biopsy slides are examined based on various cytological criteria under a microscope. Therefore, there is a high possibility of not retaining uniformity and ensuring reproducibility in outcomes [2, 3]. Computational diagnostic tools, on the other hand, facilitate objective judgments by making the use of the quantitative measure. This dataset can be utilized in establishing automated diagnostic tool using Artificial Intelligence approaches.

Analysis of Morphological Features of Benign and Malignant Breast Cell Extracted From FNAC Microscopic Image Using the Pearsonian System of Curves.

CONTEXT: Cytological changes in terms of shape and size of nuclei are some of the common morphometric features to study breast cancer, which can be observed by careful screening of fine needle aspiration cytology (FNAC) images. AIMS: This study attempts to categorize a collection of FNAC microscopic images into benign and malignant classes based on family of probability distribution using some morphometric features of cell nuclei. MATERIALS AND METHODS: For this study, features namely area, perimeter, eccentricity, compactness, and circularity of cell nuclei were extracted from FNAC images of both benign and malignant samples using an image processing technique. All experiments were performed on a generated FNAC image database containing 564 malignant (cancerous) and 693 benign (noncancerous) cell level images. The five-set extracted features were reduced to three-set (area, perimeter, and circularity) based on the mean statistic. Finally, the data were fitted to the generalized Pearsonian system of frequency curve, so that the resulting distribution can be used as a statistical model. Pearsonian system is a family of distributions where kappa (κ) is the selection criteria computed as functions of the first four central moments. RESULTS AND CONCLUSIONS: For the benign group, kappa (κ) corresponding to area, perimeter, and circularity was -0.00004, 0.0000, and 0.04155 and for malignant group it was 1016942, 0.01464, and -0.3213, respectively. Thus, the family of distribution related to these features for the benign and malignant group were different, and therefore, characterization of their probability curve will also be different.

Profile of Acute Liver Failure from North-east India and Its Differences from other Parts of the Country.

BACKGROUND: Acute liver failure (ALF) is a critical illness with a large number of viral and nonviral causes. Clinical course and etiologies in the Asian countries are different from those reported from the Western world and mortality is high. There may even be intracountry variations in large countries like India, which have differing culture, ethnicity, and environment. Data from North-east part of India is lacking. MATERIALS AND METHODS: Acute liver failure cases (>14 years of age) seen over a period of 8 years (n = 255) were studied at a Government Medical College in Assam for their etiological and other demographic profile. Viral serology was carried out and revalidated at a laboratory in New Delhi. RESULTS: Majority of cases were <30 years of age. Commonest etiology was nonviral (non-ABCE). Amongst viral causes, hepatitis A and E were common, while hepatitis B virus (HBV) was rare. Unknown herbal medication use was very frequent in our cases with a significantly higher mortality. Mortality was highest in cases in 3rd decade of life. Statistically, international normalized ratio (INR) was the strongest predictor of death. CONCLUSION: Unlike the rest of India, hepatitis virus is not the major cause of ALF in our part; hepatitis A being commoner than hepatitis E, and B is rare. Unknown herbal medications are major cause of mortality and is important medicosocial issue. Our study highlights the differences in the profile of ALF from other Indian and western studies, possibly due to sociocultural factors prevalent in this part. HOW TO CITE THIS ARTICLE: Das AK, Begum T, Kar P, Dutta A. Profile of Acute Liver Failure from North-east India and Its Differences from other Parts of the Country. Euroasian J Hepato-Gastroenterol 2016;6(2):111-115.

Drug-induced acute pancreatitis: a rare manifestation of an incomplete "dapsone syndrome".

Drug-induced acute pancreatitis (AP) is under-reported, and a large number of drugs are listed as offenders, but are often overlooked. Knowledge about the possible association of medications in causing AP is important, and needs a high index of suspicion, especially with drugs that have been reported to be the etiology only rarely. Dapsone, a commonly used drug, can cause various hypersensitivity reactions including AP collectively called "dapsone syndrome." Here, we report dapsone-induced AP in a young man. Our case shows certain dissimilarities like associated acute renal failure and acute hemolysis not previously described.

Hepatic and biliary ascariasis.

Ascariasis mainly contributes to the global helminthic burden by infesting a large number of children in the tropical countries. Hepato-biliary ascariasis (HBA) is becoming a common entity now than in the past owing to the frequent usage of ultrasonograms and endoscopic diagnostic procedures in the clinical practice. There are a variety of manifestations in HBA and diagnosis depends on a high index of suspicion in endemic areas coupled with subsequent confirmation by sonographic or endoscopic demonstration of the worm. Most of them present with acute abdomen and jaundice. Oriental or recurrent pyogenic cholangiopathy is possibly the result of HBA, commonly encountered in South-East Asian countries. Conservative treatment with anthelminthic agents is used in the majority. Failure to respond to medical therapy usually indicates the need for endoscopic or surgical interventions. Overall, mortality is low and prognosis is good, but many epidemiological and immunological aspects of Ascaris infection are unclear, meaning our understanding the disease and infection still remains incomplete. Therefore, it is difficult to definitely put down a fixed modality of treatment for HBA. This underscores the need for further studies as ascariasis has the potential to adversely affect the national socio-economy by compromising the health of children and adults alike with its sheer number.

New insights into hepatitis C virus infection in the tribal-dominant part of Northeast India.

Northeast India is known for the demographic heterogeneity of its tribal population, but there is no information about hepatitis C virus infection and associated risk factors. Anti-HCV was measured, HCV-RNA was detected based on the 5' UTR-core region, and genotyping was done by direct sequencing of the NS5b region. Antibodies to HCV were found in 13.7 % of the samples tested (96 out of 700), while HCV-RNA was positive in 73 % of the samples (70 out of 96) and in 5 out of 385 cases of occult HCV infection. Genotypes 1 to 4 were found respectively in 14.6, 7.3, 20, 30.8 %, and genotype 6 in 13.6 %, of the 75 HCV isolates. In acute viral hepatitis (AVH), the most prevalent genotype was 2a (28.6 %), while it was 4a (28 %) in chronic hepatitis C (CHC) and 29.4 % in cirrhosis. Males were more prone than females to HCV infection, and the highest numbers of cases of HCV infection were recorded in the age group of 40-49 years. The major risk factors were intravenous drug abuse (IVDU) (34.6 %), multiple sexual partners (20 %) and contact with professional barbers (38.6 %). The seroprevalence of HCV in Northeast India is higher than in the rest of India. This study highlights the fact that geographical variations occur with respect to HCV genotypes, which could influence the course and progress of different type of liver diseases seen in India.

Dereplication coupled with in vitro antioxidant assay of two flavonoid glycosides from Diospyros peregrina fruit.

Diospyros peregrina is an edible seasonal fruit found in coastal West Bengal, India. The fruits have been reported to possess a significant antioxidant activity. In this study, the aim was to isolate the lead compound responsible for the above-mentioned activity. The aqueous extract of D. peregrina fruit was subjected to dereplication coupled with an in vitro 1,1-diphenyl-2-picryl-hydrazyl (DPPH) radical scavenging assay. The n-butanol fraction of the aqueous extract of D. peregrina fruit exhibited significant antioxidant activity (IC(50), 131.10 µg mL(-1)) as compared with the parent extract (IC(50), 285.15 µg mL(-1)). The n-butanol fraction was subjected to silica gel column chromatographic separation coupled with a chemo-autographic study of column eluents, employing ethanolic DPPH as a spraying reagent. Two bioactive flavonoid glycosides, namely luteoline-4'-methyl-ether-7-O-glucoside and quercetin-3-O-(glucosyl)-glucoside, were identified to exhibit IC(50) values of 74.04 and 65.78 µg mL(-1), respectively in the DPPH assay.

Multimodal approaches of the hydroalcoholic extract of Diospyros peregrina fruits in diabetic therapy.

The matured fruits of Diospyros peregrina possess significant antidiabetic activity. The present investigation was undertaken to evaluate the target of action of the hydroalcoholic extract of D. peregrina fruit in diabetic pathophysiology. The extract was tested in vitro for inhibition of glucose absorption by α-amylase inhibition assay, glucose uptake study by isolated rat hemidiaphragm method and free radical scavenging activity by DPPH method. The extract exhibited significant α-amylase inhibition (IC50 136.5 µg mL⁻¹), peripheral glucose utilisation and radical scavenging (IC50 167.5 µg mL⁻¹) activity. From the results, it may be concluded that the hydroalcoholic extract of D. peregrina fruit can counteract diabetes by multiple mechanisms, namely inhibition of carbohydrate absorption, improving peripheral glucose utilisation and antioxidant defence.

Arsenic-induced myocardial injury: protective role of Corchorus olitorius leaves.

Groundwater arsenic contamination in Bangladesh and its adjoining part of West Bengal (India) is reported to be the biggest arsenic calamity in the world in terms of the affected population. Tossa jute, Corchorus olitorius is a popular crop of this arsenic prone population. The present study was undertaken to evaluate the protective effect of aqueous extract of C. olitorius leaves (AECO) against sodium arsenite (NaAsO(2)) induced cardiotoxicity in experimental rats. The animals exposed to NaAsO(2) (10mg/kg, p.o.) for 10days exhibited a significant inhibition (p<0.01) of superoxide dismutase, catalase, glutathione-S-transferase, glutathione peroxidase, glutathione reductase and reduced glutathione level in myocardial tissues of rats. In addition, it significantly increased (p<0.01) oxidized glutathione, malondialdehyde and protein carbonyl content in myocardial tissue. Treatment with AECO (50 and 100mg/kg, p.o.) for 15days prior to NaAsO(2)-intoxication significantly protected cardiac tissue against arsenic-induced oxidative impairment. In addition, AECO pretreatment significantly prevented NaAsO(2) induced hyperlipidemia, cardiac arsenic content and DNA fragmentation in experimental rats. Histological studies of myocardial tissue supported the protective activity of the AECO. The results concluded that the treatment with AECO prior to arsenic intoxication has significant protecting effect against arsenic-induced myocardial injury.

Protective effect of Corchorus olitorius leaves against arsenic-induced oxidative stress in rat brain.

The present study was undertaken to evaluate the protective effect of an aqueous extract of Corchorus olitorius leaves (AECO) against NaAsO(2) induced brain toxicity in experimental rats. The animals exposed to NaAsO(2) (10mg/kg, p.o.) for 10 days exhibited a significant inhibition (p<0.01) of superoxide dismutase, catalase, glutathione-S-transferase, glutathione peroxidase, glutathione reductase and reduced glutathione levels in rat brain. In addition, the toxin increased (p<0.01) the levels of oxidized glutathione and thiobarbituric acid reactive substances in the brain tissue of experimental rats. Treatment with AECO (50 and 100mg/kg, p.o.) for 15 days prior to arsenic intoxication significantly improved antioxidant markers in a dose dependant manner. Histological studies on the ultrastructural changes of brain tissue supported the protective activity of the AECO. The results suggest that treatment with AECO prior to arsenic intoxication has a significant role in protecting animals from arsenic-induced toxicity.

Protective effect of Corchorus olitorius leaves on sodium arsenite-induced toxicity in experimental rats.

The present study was undertaken to evaluate the protective effect of aqueous extract of Corchorus olitorius leaves (AECO) against sodium arsenite-induced toxicity in experimental rats. The animals exposed to sodium arsenite at a dose of 10mg/kg body weight p.o. for 10days exhibited a significant inhibition (p<0.01) of hepatic and renal antioxidant enzymes namely superoxide dismutase, catalase, glutathione-S-transferase, glutathione peroxidase and glutathione reductase. In addition, arsenic intoxication significantly decreased (p<0.01) the level of reduced glutathione and increased (p<0.01) the levels of oxidized glutathione and thiobarbituric acid reactive substances in selected tissues. Treatment with AECO at doses of 50 and 100mg/kg body weight p.o. for 15days prior to arsenic intoxication significantly improved hepatic and renal antioxidant markers in a dose dependant manner. AECO treatment also significantly reduced the arsenic-induced DNA fragmentation of hepatic and renal tissues. Histological studies on the ultrastructural changes of liver and kidney supported the protective activity of the AECO. The results concluded that the treatment with AECO prior to arsenic intoxication has significant role in protecting animals from arsenic-induced hepatic and renal toxicity.

Antidiabetic activity of Diospyros peregrina fruit: effect on hyperglycemia, hyperlipidemia and augmented oxidative stress in experimental type 2 diabetes.

Diospyros peregrina is an edible fruit of costal West-Bengal. The present investigation was undertaken to evaluate the role of aqueous extract of D. peregrina fruit in streptozotocin-nicotinamide induced type 2 diabetic rats. Oral administration of extract at the doses of 50 and 100mg/kg body weight per day for 28 days to diabetic rats was found to possess significant dose dependant hypoglycemic and hypolipidemic activity. An increased reactive oxygen species and insufficient antioxidant activity is associated with diabetes mellitus, which is mainly responsible for diabetic pathogenesis. The role of extract on antioxidant markers of liver and kidney were estimated. The diabetic rats exhibited lower activities of superoxide dismutase (SOD), catalase (CAT), and reduced glutathione (GSH) content in hepatic and renal tissues as compared with normal rats. The activities of SOD, CAT, and GSH were found to be increased in extract treated diabetic rats in selected tissues. The increased level of lipid peroxidation (thiobarbituric acid reactive substances and hydroperoxide) in diabetic rats was also found to be reverted back to near normal status in extract treated groups.

Swietenine: a potential oral hypoglycemic from Swietenia macrophylla seed.

Swietenine, a tetranortriterpenoid, was isolated from the Swietenia macrophylla seeds. The in vivo hypoglycemic activity was evaluated against neonatal-streptozotocin induced type 2 diabetic rats. Oral administration of swietenine at 25 and 50 mg/kg body weight per day to diabetic rats was found to possess significant dose dependant hypoglycemic and hypolipidemic activity in type 2 diabetic rats.

Mesenteric gastrointestinal stromal tumour presenting as intracranial space occupying lesion.

BACKGROUND: Gastrointestinal stromal tumours (GIST) usually present with non-specific gastrointestinal symptoms such as abdominal mass, pain, anorexia and bowel obstruction. METHODS: We report a case of a 42 year old male who presented with a solitary intracranial space occupying lesion which was established as a metastasis from a mesenteric tumour. RESULTS: The patient was initially treated as a metastatic sarcoma, but a lack of response to chemotherapy prompted testing for CD117 which returned positive. A diagnosis of mesenteric GIST presenting as solitary brain metastasis was made, and the patient was treated with imatinib. CONCLUSION: We recommend that all sarcomas with either an intraabdominal or unknown origin be routinely tested for CD117 to rule out GIST.