Efficient feature selection based novel clinical decision support system for glaucoma prediction from retinal fundus images.

The process of feature selection (FS) is vital aspect of machine learning (ML) model's performance enhancement where the objective is the selection of the most influential subset of features. This paper suggests the Gravitational search optimization algorithm (GSOA) technique for metaheuristic-based FS. Glaucoma disease is selected as the subject of investigation as this disease is spreading worldwide at a very fast pace; 111 million instances of glaucoma are expected by 2040, up from 64 million in 2015. It causes widespread vision impairment. Optic nerve fibres can be degraded and cannot be replaced later in this disease. As a starting point, the retinal fundus images of glaucoma infected persons and healthy persons are used, and 36 features were retrieved from these images of public benchmark datasets and private dataset. Six ML models are trained for classification on the basis of the GSOA's returned subset of features. The suggested FS technique enhances classification performance with selection of most influential features. The eight statistical performance evaluating parameters along with execution time are calculated. The training and testing have been performed using a split approach (70:30), 5-fold cross validation (CV), as well as 10-fold CV. The suggested approach achieved 95.36 % accuracy. Due to its auspicious performance, doctors might use the suggested method to receive a second opinion, which would also help overburdened skilled medical practitioners and save patients from vision loss.

Best Fit DNA-Based Cryptographic Keys: The Genetic Algorithm Approach.

DNA (Deoxyribonucleic Acid) Cryptography has revolutionized information security by combining rigorous biological and mathematical concepts to encode original information in terms of a DNA sequence. Such schemes are crucially dependent on corresponding DNA-based cryptographic keys. However, owing to the redundancy or observable patterns, some of the keys are rendered weak as they are prone to intrusions. This paper proposes a Genetic Algorithm inspired method to strengthen weak keys obtained from Random DNA-based Key Generators instead of completely discarding them. Fitness functions and the application of genetic operators have been chosen and modified to suit DNA cryptography fundamentals in contrast to fitness functions for traditional cryptographic schemes. The crossover and mutation rates are reducing with each new population as more keys are passing fitness tests and need not be strengthened. Moreover, with the increasing size of the initial key population, the key space is getting highly exhaustive and less prone to Brute Force attacks. The paper demonstrates that out of an initial 25 × 25 population of DNA Keys, 14 keys are rendered weak. Complete results and calculations of how each weak key can be strengthened by generating 4 new populations are illustrated. The analysis of the proposed scheme for different initial populations shows that a maximum of 8 new populations has to be generated to strengthen all 500 weak keys of a 500 × 500 initial population.

Performance evaluation of various deep learning based models for effective glaucoma evaluation using optical coherence tomography images.

Glaucoma is the dominant reason for irreversible blindness worldwide, and its best remedy is early and timely detection. Optical coherence tomography has come to be the most commonly used imaging modality in detecting glaucomatous damage in recent years. Deep Learning using Optical Coherence Tomography Modality helps in predicting glaucoma more accurately and less tediously. This experimental study aims to perform glaucoma prediction using eight different ImageNet models from Optical Coherence Tomography of Glaucoma. A thorough investigation is performed to evaluate these models' performances on various efficiency metrics, which will help discover the best performing model. Every net is tested on three different optimizers, namely Adam, Root Mean Squared Propagation, and Stochastic Gradient Descent, to find the best relevant results. An attempt has been made to improvise the performance of models using transfer learning and fine-tuning. The work presented in this study was initially trained and tested on a private database that consists of 4220 images (2110 normal optical coherence tomography and 2110 glaucoma optical coherence tomography). Based on the results, the four best-performing models are shortlisted. Later, these models are tested on the well-recognized standard public Mendeley dataset. Experimental results illustrate that VGG16 using the Root Mean Squared Propagation Optimizer attains auspicious performance with 95.68% accuracy. The proposed work concludes that different ImageNet models are a good alternative as a computer-based automatic glaucoma screening system. This fully automated system has a lot of potential to tell the difference between normal Optical Coherence Tomography and glaucomatous Optical Coherence Tomography automatically. The proposed system helps in efficiently detecting this retinal infection in suspected patients for better diagnosis to avoid vision loss and also decreases senior ophthalmologists' (experts) precious time and involvement.

Type Va Duplication of the Common Bile Duct With Type IIIa Intrahepatic Bile Duct Anatomy: A Rare Combination of Dual Biliary Ductal Anomaly With Difficulty to Extract Common Bile Duct Stone.

Extrahepatic duplication of the common bile duct (CBD) is an extremely rare anatomic variation seen in the biliary tract. It represents failure of regression of the primitive duplicated biliary ductal system, resulting in five different subtypes of the duplicated CBD as described by Choi et al. To date, only few such cases have been reported in the literature. Associated variation in branching of intrahepatic bile ducts presenting as combined dual ductal anomaly is even rarer phenomena to be seen. We report a case of a 67-year-old man with chronic kidney disease and obstructive jaundice resulting from choledocholithiasis. Evaluation revealed type IIIa branching of intrahepatic bile ducts with type Va duplication of the CBD.

HPi: A Novel Parameter to Predict Graft-related Outcome in Adult Living Donor Liver Transplant.

BACKGROUND: Portal hyperperfusion is frequently associated with early allograft dysfunction (EAD). It is imperative to identify patients who would require portal inflow modulation. We aimed to identify factors associated with hyperperfusion-related graft injury and develop a predictive index for the same. METHODS: Prospectively maintained database was queried to identify 135 adult living donor liver transplant recipients between September 2016 and July 2020. According to the calculated sample size, 96 patients were randomly selected for "test cohort". The remaining 39 patients made the "validation cohort." EAD was defined according to the A2ALL study. "Hyperperfusion index (HPi)," defined as posttransplant portal pressure gradient (ΔPpost)/graft-to-recipient splenic volume ratio (GRSVR), was devised on the basis of laws of flow dynamics and regression analysis. RESULTS: Overall, 40 patients (29.6%) had EAD, six 90-d mortalities (4.4%) were attributable to EAD. In the test cohort, EAD patients (n = 29, 30.2%) had lower GRSVR (1.00 versus 2.22, P < 0.001), higher ΔPpost (14.8 versus 11.9, P = 0.004), and HPi (20.89 versus 8.67, P < 0.001). Multivariate analysis revealed GRSVR, ΔPpost, and HPi as significant factors to predict EAD. Receiver operating characteristic determined cutoff of HPi ≥9.97 could predict EAD with sensitivity of 90% and specificity of 73% (F-score = 0.712). HPi ≥16.25 predicted 90-d mortality with sensitivity of 100% and specificity of 78.9%. Patients with higher HPi had delayed graft-related recovery. Non-EAD patients had a higher 1-y (96% versus 79%) and 2-y (88% versus 79%) survival. The cutoff of HPi was validated well in the validation cohort (F-score = 0.645) (Hosmer-Lemeshow test, P = 0.89). CONCLUSIONS: While predicted GRSVR may help identify at-risk patients preoperatively, intraoperatively calculated HPi is more accurate in identifying patients who would require portal inflow modulation. Achieving an HPi below target cutoff significantly decreases the risk of EAD even in low-GRSVR patients.

Bone Cancer Detection Using Feature Extraction Based Machine Learning Model.

Bone cancer is considered a serious health problem, and, in many cases, it causes patient death. The X-ray, MRI, or CT-scan image is used by doctors to identify bone cancer. The manual process is time-consuming and required expertise in that field. Therefore, it is necessary to develop an automated system to classify and identify the cancerous bone and the healthy bone. The texture of a cancer bone is different compared to a healthy bone in the affected region. But in the dataset, several images of cancer and healthy bone are having similar morphological characteristics. This makes it difficult to categorize them. To tackle this problem, we first find the best suitable edge detection algorithm after that two feature sets one with hog and another without hog are prepared. To test the efficiency of these feature sets, two machine learning models, support vector machine (SVM) and the Random forest, are utilized. The features set with hog perform considerably better on these models. Also, the SVM model trained with hog feature set provides an F1-score of 0.92 better than Random forest F1-score 0.77.

Recurrent Hepatic Artery Thrombosis Following Living Donor Liver Transplant as Sequelae of SARS-CoV-2 Infection-a Case Report.

As the second wave of COVID-19 disease is gripping the globe, liver transplant centers are increasingly receiving patients recovered from SARS-CoV-2 infection in recent few weeks. Unexpected complications in these patients are increasingly being recognized. We performed liver transplantation on a 51-year-old gentleman with decompensated liver disease 23 days after recovering from a mild SARS-CoV-2 infection. Surprisingly, despite massive blood loss and a prolonged anhepatic phase, his thromboelastographic (TEG) parameters persistently revealed hypercoagulability. After a brief uneventful early post-operative period, he developed hepatic arterial thrombosis on the 14th post-operative day, and again after 4 days, both of which required surgical intervention. Following discharge, the artery was thrombosed again which was only picked up when he developed a cholangiolar abscess, leading to graft loss necessitating re-transplantation. There is a lot of evidence suggesting that patients with SARS-CoV-2 infection tend to be hypercoagulable. We believe that this hypercoagulability might have played a significant role in the development of hepatic arterial thrombosis and eventual graft loss in this patient. This highlights the importance of revisiting anticoagulation protocols in liver transplant recipients recovered from COVID-19 and base them on TEG rather than routine parameters such as INR and APTT, which are routinely deranged in such patients.

An enhanced deep image model for glaucoma diagnosis using feature-based detection in retinal fundus.

This paper proposes a deep image analysis-based model for glaucoma diagnosis that uses several features to detect the formation of glaucoma in retinal fundus. These features are combined with most extracted parameters like inferior, superior, nasal, and temporal region area, and cup-to-disc ratio that overall forms a deep image analysis. This proposed model is exercised to investigate the various aspects related to the prediction of glaucoma in retinal fundus images that help the ophthalmologist in making better decisions for the human eye. The proposed model is presented with the combination of four machine learning algorithms that provide the classification accuracy of 98.60% while other existing models like support vector machine (SVM), K-nearest neighbors (KNN), and Naïve Bayes provide individually with accuracies of 97.61%, 90.47%, and 95.23% respectively. These results clearly demonstrate that this proposed model offers the best methodology to an early diagnosis of glaucoma in retinal fundus.

Pre-existing liver disease is associated with poor outcome in patients with SARS CoV2 infection; The APCOLIS Study (APASL COVID-19 Liver Injury Spectrum Study).

BACKGROUND AND AIMS: COVID-19 is a dominant pulmonary disease, with multisystem involvement, depending upon comorbidities. Its profile in patients with pre-existing chronic liver disease (CLD) is largely unknown. We studied the liver injury patterns of SARS-Cov-2 in CLD patients, with or without cirrhosis. METHODS: Data was collected from 13 Asian countries on patients with CLD, known or newly diagnosed, with confirmed COVID-19. RESULTS: Altogether, 228 patients [185 CLD without cirrhosis and 43 with cirrhosis] were enrolled, with comorbidities in nearly 80%. Metabolism associated fatty liver disease (113, 61%) and viral etiology (26, 60%) were common. In CLD without cirrhosis, diabetes [57.7% vs 39.7%, OR = 2.1 (1.1-3.7), p = 0.01] and in cirrhotics, obesity, [64.3% vs. 17.2%, OR = 8.1 (1.9-38.8), p = 0.002] predisposed more to liver injury than those without these. Forty three percent of CLD without cirrhosis presented as acute liver injury and 20% cirrhotics presented with either acute-on-chronic liver failure [5 (11.6%)] or acute decompensation [4 (9%)]. Liver related complications increased (p < 0.05) with stage of liver disease; a Child-Turcotte Pugh score of 9 or more at presentation predicted high mortality [AUROC 0.94, HR = 19.2 (95 CI 2.3-163.3), p < 0.001, sensitivity 85.7% and specificity 94.4%). In decompensated cirrhotics, the liver injury was progressive in 57% patients, with 43% mortality. Rising bilirubin and AST/ALT ratio predicted mortality among cirrhosis patients. CONCLUSIONS: SARS-Cov-2 infection causes significant liver injury in CLD patients, decompensating one fifth of cirrhosis, and worsening the clinical status of the already decompensated. The CLD patients with diabetes and obesity are more vulnerable and should be closely monitored.

Sofosbuvir and Ribavirin for 24 Weeks Is An Effective Treatment Option for Recurrent Hepatitis C Infection After Living Donor Liver Transplantation.

BACKGROUND: Recurrent hepatitis C virus (HCV) has been a serious problem after liver transplantation (LT). We report our experience of 24-week therapy with sofosbuvir (SOF) and ribavirin (RBV) in post-LT recurrent HCV in living donor liver transplantation (LDLT) setting in South Asia. METHODS: Data from all patients treated for post-transplantation HCV recurrence in a single center were analyzed. Treatment regimen was 24 weeks of SOF 400 mg daily and RBV (starting at 800 mg daily, increased as tolerated). Sustained virological response (SVR) was assessed 12 weeks and 24 weeks after completion of treatment. RESULTS: 63 patients (median age 52 [range 30-69] years; 80% males) were treated. Most (76.2%) were treatment experienced and predominant HCV genotype was 3 (77.7%) followed by 1 (20.6%). Median transient elastography (Fibroscan) score was 7 (range 3-11) kPa and none of the patients had cirrhosis. SVR12 was achieved in 60 of 63 patients (95.2%) while SVR24 was noted in 59 (93.7%). SVR12 rates were as good in genotype-3 as in genotype-1. Older age, longer period after transplantation, higher Fibroscan value and higher need for erythropoietin were likely to be associated with relapse. Adverse effects were noted in 34 patients and weakness and fatigue were the commonest side effects. Significant drop in hemoglobin (<8 g/dL) was seen in 6 patients. CONCLUSIONS: SOF + RBV combination therapy for 24 weeks was safe and effective in treatment of for post-LT recurrent HCV in a single LT center and remains relevant due to its low cost and lack of drug interactions.

Influence of variceal bleeding on natural history of ACLF and management options.

Patients with diagnosed and undiagnosed chronic liver diseases experience one or more acute assaults of a hepatic nature and develop a downhill course of liver diseases, a condition regarded as acute-on-chronic liver failure (ACLF). It is a medical emergency, the prognosis of ACLF is extremely bad and considerable numbers of patients with ACLF die even after diagnosis and receiving conservative treatment. ACLF is characterized by jaundice, coagulopathy, ascites and encephalopathy. ACLF patients are very sick and associated with different hemodynamic profiles and have very high 3-month mortality. As these groups of patients have high baseline hepatic venous pressure gradients, the chances of variceal bleed are also high, and the impact is also greater in comparison to stable cirrhosis; however, evidence is lacking to substantiate such effects. The aim of this review is to discuss the natural course of variceal bleeding in ACLF patients and to develop insights into the management of variceal bleeding in ACLF.

Portal hypertensive gastropathy and gastric antral vascular ectasia.

Portal hypertensive gastropathy (PHG) and gastric antral vascular ectasia (GAVE) are gastric mucosal lesions that mostly present as chronic anemia and rarely cause the acute gastrointestinal hemorrhage. Despite similar clinical manifestations, their pathophysiology and management are entirely different. PHG is seen exclusively in patients with portal hypertension, but GAVE can also be observed in patients with other conditions. Their diagnosis is endoscopic, and although generally each of them has a characteristic endoscopic appearance and distribution, there are cases in which the differential is difficult and must rely on histology. This review focuses on the management of both entities. The mainstay of management of PHG is based on portal-hypotensive pharmacological treatment while GAVE benefits from hormonal therapy, endoscopic Nd:YAG laser, and argon plasma coagulation. More invasive options should be reserved for refractory cases.

Approach to clinical syndrome of jaundice and encephalopathy in tropics.

A large number of patients present with jaundice and encephalopathy in tropical country like India and acute liver failure is the usual cause. Clinical presentation like ALF is also a complication of many tropical infections, and these conditions may mimic ALF but may have subtle differences from ALF. Moreover, what hepatologists see as acute liver failure in tropics is different from what is commonly described in Western Textbooks. Paracetamol overdose, which is possibly the commonest cause of ALF in UK and USA, is hardly ever seen in India. Most common etiology here is viral hepatitis (hepatitis E > hepatitis B> hepatitis A). Apart from ALF, one may also come across subacute hepatic failure (SAHF) as well as acute-on-chronic liver failure (ACLF) due to viral hepatitis. Interestingly, a host of other conditions can mimic ALF because clinical presentation in these conditions can be dominated by jaundice and encephalopathy. Malarial hepatopathy is possibly the best-known condition out of these and is not an uncommon manifestation of severe malaria. A similar presentation can also be seen in other common infections in tropics such as dengue fever, typhoid fever, leptospirosis, scrub typhus, amoebic liver abscesses, tuberculosis and other bacterial and fungal infections with or without human immunodeficiency virus (HIV) related disease. In many of these conditions, liver failure may not be underlying pathophysiology. Some pregnancy related liver diseases could also present with jaundice and encephalopathy. This review summarizes the commonly seen presentations in tropical country like India, where jaundice and encephalopathy dominate the clinical picture.

Combination of granulocyte colony-stimulating factor and erythropoietin improves outcomes of patients with decompensated cirrhosis.

BACKGROUND & AIMS: Patients with decompensated cirrhosis have significantly reduced survival without liver transplantation. Granulocyte colony-stimulating factor (G-CSF) has been shown to increase survival in patients with acute-on-chronic liver failure, and erythropoietin promoted hepatic regeneration in animal studies. We performed a double-blind, randomized, placebo-controlled trial to determine whether co-administration of these growth factors improved outcomes for patients with advanced cirrhosis. METHODS: In a prospective study, consecutive patients with decompensated cirrhosis seen at the Institute of Liver and Biliary Sciences, New Delhi (from May 2011 through June 2012) were randomly assigned to groups given subcutaneous G-CSF (5 µg/kg/d) for 5 days and then every third day (12 total doses), along with subcutaneous darbopoietin α(40 mcg/wk) for 4 weeks (GDP group, n = 29), or only placebos (control group, n = 26). All patients also received standard medical therapy and were followed for 12 months. Histology was performed on liver biopsies. The primary end point was survival at 12 months. RESULTS: Baseline characteristics of patients were comparable; alcohol intake was the most common etiology of cirrhosis. A higher proportion of patients in the GDP group than controls survived until 12 months (68.6% vs 26.9%; P = .003). At 12 months, Child-Turcotte Pugh scores were reduced by 48.6% in the GDP group and 39.1% in the control group, from baseline (P = .001); Model for End Stage Liver Disease scores were reduced by 40.4% and 33%, respectively (P = .03). The need for large-volume paracentesis was significantly reduced in GDP group, compared with controls (P < .05). A lower proportion of patients in the GDP group developed septic shock (6.9%) during follow-up compared with controls (38.5%; P = .005). No major adverse events were observed in either group. CONCLUSIONS: In a single-center randomized trial, a significantly larger proportion of patients with decompensated cirrhosis given a combination of G-CSF and darbopoietin α survived for 12 months more than patients given only placebo. The combination therapy also reduced liver severity scores and sepsis to a greater extent than placebo. Clinicaltrials.gov ID: NCT01384565.

Altered frequencies of dendritic cells and IFN-gamma-secreting T cells with granulocyte colony-stimulating factor (G-CSF) therapy in acute-on- chronic liver failure.

BACKGROUND & AIMS: Acute-on-chronic liver failure (ACLF) is a serious hepatic ailment with impaired immunity and poor treatment options resulting high mortality. Treatment with granulocyte colony-stimulating factor(G-CSF) mobilizes CD34(+) cells in ACLF patients; however its effect on impaired immune responses remains to be elucidated. To analyse the effect of G-CSF in immune modulation in ACLF. METHODS: We have analysed the frequencies of circulating and intrahepatic myeloid (mDCs) and plasmacytoid(pDCs) dendritic cells (DCs) and T cells in ACLF patients treated with G-CSF (Group A; n = 23) and placebo (Group B; n = 24) using flow cytometry. IFN-c production was compared in both groups following stimulation of PBMCs with phorbol myristate acetate (PMA). RESULTS: In Group A, circulating and intrahepatic mDCs, pDCs (P < 0.04, P < 0.02) and T cells(CD3, CD4 and CD8) increased significantly post-G-CSF treatment in comparison to placebo group. Importantly in Group A, IFN-c-producing CD8 T cells were significantly decreased (P > 0.05) along with decreased serum bilirubin and international normalized ratio (INR). Intrahepatic DCs and IFN-clevel were compared in survivor and non-survivor. Non-survivors from both groups, showed decreased DCs, high IFN-c level and no improvement in clinical parameters including s-bilirubin and INR. CONCLUSIONS: G-CSF therapy increased the frequencies of dendritic cells and reduced IFN-c secreting CD8 T cells with improved clinical severity indices. Decreased IFN- c production may contribute to reduced hepatocellular damage in ACLF patients.Our observations support the basis for further use of G-CSF therapy as immune modulator in these patients.

Acute-on-chronic liver failure: consensus recommendations of the Asian Pacific Association for the Study of the Liver (APASL) 2014.

The first consensus report of the working party of the Asian Pacific Association for the Study of the Liver (APASL) set up in 2004 on acute-on-chronic liver failure (ACLF) was published in 2009. Due to the rapid advancements in the knowledge and available information, a consortium of members from countries across Asia Pacific, "APASL ACLF Research Consortium (AARC)," was formed in 2012. A large cohort of retrospective and prospective data of ACLF patients was collated and followed up in this data base. The current ACLF definition was reassessed based on the new AARC data base. These initiatives were concluded on a 2-day meeting in February 2014 at New Delhi and led to the development of the final AARC consensus. Only those statements which were based on the evidence and were unanimously recommended were accepted. These statements were circulated again to all the experts and subsequently presented at the annual conference of the APASL at Brisbane, on March 14, 2014. The suggestions from the delegates were analyzed by the expert panel, and the modifications in the consensus were made. The final consensus and guidelines document was prepared. After detailed deliberations and data analysis, the original proposed definition was found to withstand the test of time and identify a homogenous group of patients presenting with liver failure. Based on the AARC data, liver failure grading, and its impact on the "Golden therapeutic Window," extra-hepatic organ failure and development of sepsis were analyzed. New management options including the algorithms for the management of coagulation disorders, renal replacement therapy, sepsis, variceal bleed, antivirals, and criteria for liver transplantation for ACLF patients were proposed. The final consensus statements along with the relevant background information are presented here.