Early stage black pepper leaf disease prediction based on transfer learning using ConvNets.

Plants get exposed to diseases, insects and fungus. This causes heavy damages to crop resulting in various leaves diseases. Leaf diseases can be diagnosed at an early stage with the aid of a smart computer vision system and timely disease prevention can be targeted. Black pepper is a medicinal plant that is extensively used in Ayurvedic medicine because of its therapeutic properties. The proposed work represents an intelligent transfer learning technique through state-of-the-art deep learning implementation using convolutional neural network to predict the presence of prominent diseases in black pepper leaves. The ImageNet dataset available online is used for training deep neural network. Later, this trained network is utilized for the prediction of the newly developed black pepper leaf image dataset. The developed data set consist of real time leaf images, which are candidly taken from the fields and annotated under supervision of an expert. The leaf diseases considered are anthracnose, slow wilt, early stage phytophthora, phytophthora and yellowing. The hyperparameters chosen for tuning in to deep learning models are initial learning rates, optimization algorithm, image batches, epochs, validation and training data, etc. The accuracy obtained with 0.001 learning rate ranges from 99.1 to 99.7% for the Inception V3, GoogleNet, SqueezeNet and Resnet18 models. Proposed Resnet18 model outperforms all model with 99.67% accuracy. The resulting validation accuracy obtained using these models is high and the validation loss is low. This work represents improvement in agriculture and a cutting edge deep neural network method for early stage leaf disease identification and prediction. This is an approach using a deep learning network to predict early stage black pepper leaf diseases.

Deep Learning-Based Modeling of Drug-Target Interaction Prediction Incorporating Binding Site Information of Proteins.

Chemogenomics, also known as proteochemometrics, covers various computational methods for predicting interactions between related drugs and targets on large-scale data. Chemogenomics is used in the early stages of drug discovery to predict the off-target effects of proteins against therapeutic candidates. This study aims to predict unknown ligand-target interactions using one-dimensional SMILES as inputs for ligands and binding site residues for proteins in a computationally efficient manner. We first formulate a Deep learning CNN model using one-dimensional SMILES for drugs and motif-rich binding pocket subsequences of proteins as inputs. We evaluate and compare the proposed deep learning model trained on expert-based features against shallow feature-based machine learning methods. The proposed method achieved better or similar performance on the MSE and AUPR metrics than the shallow methods. Additionally, We show that our deep learning model, DeepPS is computationally more efficient than the deep learning model trained on full-length raw sequences of proteins. We conclude that a beneficial research approach would be to integrate structural information of proteins for modeling drug-target interaction prediction of large datasets for more interpretability, high throughput, and broad applicability.

Lipidomic landscape in cancer: Actionable insights for membrane-based therapy and diagnoses.

Cancer cells display altered cellular lipid metabolism, including disruption in endogenous lipid synthesis, storage, and exogenous uptake for membrane biogenesis and functions. Altered lipid metabolism and, consequently, lipid composition impacts cellular function by affecting membrane structure and properties, such as fluidity, rigidity, membrane dynamics, and lateral organization. Herein, we provide an overview of lipid membranes and how their properties affect cellular functions. We also detail how the rewiring of lipid metabolism impacts the lipidomic landscape of cancer cell membranes and influences the characteristics of cancer cells. Furthermore, we discuss how the altered cancer lipidome provides cues for developing lipid-inspired innovative therapeutic and diagnostic strategies while improving our limited understanding of the role of lipids in cancer initiation and progression. We also present the arcade of membrane characterization techniques to cement their relevance in cancer diagnosis and monitoring of treatment response.

Visual Examination Standard for Forklift and Crane Operators: A Report for 66 Operators of a Factory in Mumbai.

CONTEXT: Forklift and crane industry in India is progressing at a rapid pace and the visual integrity of the operators is crucial for occupational safety. Hence, we performed a vision screening at a factory based in Mumbai. AIMS: To evaluate the current visual status of forklift and crane operators working at a factory in Mumbai. SETTINGS AND DESIGN: Prospective observational cross-sectional. METHODS AND MATERIALS: All forklift and crane operators were invited to undertake visual examination that included visual acuity (VA) assessment, refraction, slit-lamp examination, color vision assessment, visual field assessment, and stereopsis. Referrals were made for participants who needed further assessment. STATISTICAL ANALYSIS USED: Mean and standard deviation were calculated and presented. RESULTS: A total of 66 forklift operators with an average age of 48 years that ranged from 26-60 years completed the study. The average distance VA in LogMAR with current spectacles was 0.1 ± 0.14. The near VA with usual spectacles averaged at 0.63 M ± 0.2 M. The best-corrected VA (BCVA) of 0 LogMAR was not achieved by 12% subjects; however, all participants except one met the 0.3 LogMAR visual acuity criteria. The average stereopsis was 55.8 ± 47.8 with 8% operators had lower than acceptable levels of stereopsis while 7% could not meet the set criteria. One operator had 400 s of an arc and 4 had 100 s of arc stereopsis. CONCLUSIONS: The study demonstrates an urgent need to set up standards for vision assessment at the time of employment and frequency of eye examination for forklift and other powered industrial vehicles.

Etiological Spectrum and Histopathological Diagnosis of Rhabdomyolysis Associated Myoglobin Cast Nephropathy in South India.

BACKGROUND AND AIMS: Rhabdomyolysis occurs due to injury to skeletal muscle fibers and the release of muscle constituents into the circulation. Myoglobin cast nephropathy leading to acute kidney injury is one of the most severe complications of rhabdomyolysis. This is a retrospective study which aims to analyse the clinicopathological features of myoglobin cast nephropathy. METHODS: A total of 57 cases of myoglobin cast nephropathy were identified after performing immunohistochemical staining for myoglobin on all renal biopsies with pigment casts. The clinical, laboratory data, histopathological findings and clinical outcome of these cases were evaluated. RESULTS: The mean patient age was 34.47 years (range 17-77) and the male to female ratio was 6.1:1. All patients presented with acute kidney injury with mean serum creatinine of 8.4 mg/dl (range: 1.7 to 20.8 mg/dl). Rhabdomyolysis was clinically suspected only in 31 patients. Along with myoglobin casts, acute tubular injury was present in all the biopsies. The most frequent conditions associated with myoglobin cast nephropathy in our study were snake envenomation and unaccustomed physical activities. A few activities that caused rhabdomyolysis in our patients were unique to India. CONCLUSION: Clinicians should be aware of the wide spectrum of causes for rhabdomyolysis. The classical clinical and laboratory findings of rhabdomyolysis may not be present in many of the patients. The pathologist must have a high index of suspicion, and immunohistochemical stain should be used to confirm the diagnosis.

Contrast-Sensitivity Function and Photo Stress-Recovery Time in Prediabetes.

PURPOSE: The purpose of this study was to assess contrast sensitivity and macular function test in prediabetes. METHODS: Participants aged 25-45 years with or without diabetes were enrolled and classified as normal, prediabetic, and diabetic based on their HbA1C values. They underwent a comprehensive eye examination, and those with diabetic retinopathy, cataract, glaucoma, and high myopia were excluded. Participants with best-corrected visual acuity of 0 logMAR were included. Contrast-sensitivity function (CSF) was measured using a Pelli-Robson chart, and photo stress-recovery time (PSRT) assessed using direct ophthalmoscopy for the 70 eligible participants. Mean values were compared among the three groups. DESIGN: This was a cross-sectional observational study. RESULTS: In the 70 participants, mean CSF was 1.71±0.10, 1.64±0.11, and 1.61±0.08 log units in the normal, prediabetic, and diabetic groups, respectively (p<0.001). Similarly, PSRT was found to be 35.80 seconds, 41.63 seconds, and 47.77 seconds in the normal, prediabetic, and diabetic groups, respectively (p<0.001). CONCLUSION: The data suggested that reduced CSF and delayed PSRT seen in subjects with prediabetes could give valuable clinical insight into early changes before diabetes and microvascular damage is incurred. A future study with a larger sample could help substantiate the results.

Machine learning models for drug-target interactions: current knowledge and future directions.

Predicting the binding affinity between compounds and proteins with reasonable accuracy is crucial in drug discovery. Computational prediction of binding affinity between compounds and targets greatly enhances the probability of finding lead compounds by reducing the number of wet-lab experiments. Machine-learning and deep-learning techniques using ligand-based and target-based approaches have been used to predict binding affinities, thereby saving time and cost in drug discovery efforts. In this review, we discuss about machine-learning and deep-learning models used in virtual screening to improve drug-target interaction (DTI) prediction. We also highlight current knowledge and future directions to guide further development in this field.

Atheroembolic Renal Disease: A Case Series.

Atheroembolic renal disease (AERD), a part of systemic cholesterol embolization syndrome, is caused by the occlusion of small arteries in the kidneys by cholesterol crystal emboli from ulcerated atherosclerotic plaques. Kidney is commonly involved because of its proximity to the abdominal aorta and its enormous blood supply. AERD is an under diagnosed condition. We report eight cases of AERD, highlighting the variability in its clinical presentation and the importance of a renal biopsy to arrive at a definitive diagnosis.

Dense deposit disease: a greatly increased biopsy incidence in India versus the USA.

BACKGROUND: We present the largest clinicopathologic case series to date of dense deposit disease (DDD) in an Indian population and compare the renal biopsy incidence rate to that seen in a large renal laboratory in USA. METHODS: Cases of DDD were identified and evaluated from native kidney biopsies reported at Renopath, India and at Arkana Laboratories, in the USA. Renopath receives biopsies from four states, located in the South and Eastern part of India. Arkana Laboratories' biopsies came from 37 states across the USA. RESULTS: During the study period, there were a total of 25 patients diagnosed with DDD among the 7335 native kidney biopsies at Renopath. Thus, the biopsy incidence rate (cases of DDD/total renal biopsies/year) is 0.0034. By comparison, there were 10 cases of DDD diagnosed among 26 319 native kidney biopsies at Arkana Laboratories during the same time period, with a renal biopsy incidence rate of 0.00038. CONCLUSIONS: DDD in this Indian subpopulation has similar clinical and pathologic characteristics when compared to previously reported studies. However, the biopsy incidence rate is about 890% or 8.9 times more common in this subset of the Indian population when compared with a broad cross-section of the US population. In addition to potential genetic factors, environmental conditions and chronic infections likely contribute to the markedly higher biopsy incidence rate. Given the much greater number of patients with DDD in this population, further retrospective and prospective studies would allow more rapid progress in understanding the pathogenesis of DDD and thus potential treatment of patients with DDD.

Cytomegalovirus Induced Collapsing Glomerulopathy and Necrotizing Glomerulonephritis in a Renal Allograft Recipient.

In renal allograft recipients, cytomegalovirus (CMV) typically causes tubulointerstitial nephritis. Only rarely glomeruli are involved. We present a rare case of CMV with collapsing glomerulopathy, necrotizing glomerulonephritis, and crescent formation in a renal allograft recipient. Immunohistochemistry confirmed CMV infection. The patient was started on valganciclovir and his renal function remained stable. A repeat renal biopsy performed three months later showed morphologically normal glomeruli and CMV immunostaining was also negative. Nephropathologists have to carefully screen for CMV in cases with crescentic or collapsing glomerulopathy as the later lesions resolve after treating the underlying viral infection. This study will add on to the various glomerular changes associated with CMV infection.

A Survey of Telepractice in Speech-Language Pathology and Audiology in India.

Telepractice has emerged as a form of service delivery to assess and treat individuals with communication disorders. The present study surveyed speech-language pathologists and audiologists in India about the use of telepractice. Two hundred and five (N=205) speech-language pathologists and audiologists responded to a questionnaire, with 12.19% reporting their use of telepractice to deliver clinical services. Respondents also indicated an urgent shortage of professionals in India to deliver clinical services in speech-language pathology and audiology, and opined that these needs can be met via the use of telepractice. India is well known throughout the world for the advanced application of Information and Communication Technology (ICT), with 931.95 million telephone subscribers, over 900 million mobile phone users, and the second-largest mobile phone usage in the world. India has also experienced a tremendous rise in the number of internet users. Therefore, India is well poised to fully develop telepractice to overcome the barriers of distance and amplify the availability of speech-language pathology, audiology and other healthcare services. But first, the widespread use of telepractice throughout the nation will require an improved infrastructure (e.g., to uphold privacy and security); training for professionals; and telepractice policies. While very promising, the deployment of telepractice throughout India will require the attention of policy makers and government organizations.

Renal cell carcinoma with t(6,11): A case report and review of literature.

Renal cell carcinomas (RCCs) with t(6,11) are very rare tumours. Only a few cases have been reported so far. t(6,11) results in fusion of alpha gene and transcription factor EB (TFEB) gene resulting in the overexpression of TFEB. The specific light and immunohistochemical features help in the diagnosis of this rare type of tumor. We report a case of t(6,11) RCC in a 38-year-old female who was incidentally found to have a right renal mass. We present this case to emphasize the typical light microscopic picture of this extremely rare tumor. Two population of cells are seen: larger cells with abundant cytoplasm and smaller cells with scant cytoplasm. Smaller cells are arranged around hyaline nodules resulting in the formation of characteristic pseudorosettes. Immunohistochemically, these tumors are diffusely positive for vimentin and focally positive for HMB 45 and CD 117. Knowledge about the typical biphasic light microscopic appearance and the characteristic immunohistochemical features help in the diagnosis of this rare type of translocation associated RCC.

A novel strategy for management of uncorrected refractive errors in urban slums.

BACKGROUND: Blindness and Vision impairment remains a major public health issue not only in rural but also in urban areas. Concept of using peripheral health centers to render primary health care services to the community was a WHO proposed model. However, establishing them in urban slums is a challenge as most of the slums are illegal establishments. So, aim was to establish vision centers for providing primary eye care services in the urban slums of Mumbai, West India. METHODS: Vision centers were established in various slum pockets of Mumbai from the year 2008 till 2009. Refraction and screening for ocular morbidity were carried out for those who attended this center and management for uncorrected refractive errors was done. RESULTS: Data from 6 such vision centers located in various slum pockets of Mumbai city from April 9 to March 2011 were collected and analyzed. Of the 19,550 adults, 2270 (11.61%) had moderate vision impairment with presenting visual acuity of <0.5 LogMAR in both eyes. Severe Visual impairment was seen in (723) 3.70%. Blindness was seen in (357) 1.82%. Of the 2993, which were moderately and severely visually impaired, 1893 subjects that is, 63.24% of them improved to 0.2 LogMAR or better with spectacle correction. CONCLUSIONS: About 63.24% of visual impairment was due to uncorrected refractive errors, these included both moderately and severely vision impaired. Totally, 357 (1.82%) were also identified as blind. This model of vision centers has a role in the identification and management of sight-threatening problems.

Inflectional versus derivational abilities of children with specific language impairment- A panorama from sequential cognition.

BACKGROUND: Specific Language Impairment (SLI) is a neurodevelopmental disorder affecting language acquisition in the absence of frank neurological damage, hearing deficits, severe environmental deprivation, or mental retardation. Children with SLI have significant difficulties in syntax domain of language compared to semantics, while their acquisition of pragmatics is relatively spared. PURPOSE: The purpose of the present study is to examine the judgment and revision of inflectional and derivational morphemes of children with specific language impairment (SLI). METHODS: 31 children with SLI and 33 typically developing (TD) children participated in the study (age range 8-13 years). The stimuli consisted of 18 sentences with inflectional morphemes and 18 sentences with derivational morphemes for grammatical judgment and revision tasks. Inflectional and derivational performance of SLI group was compared with TD group on judgment and revision scores. RESULTS: Children with SLI were significantly poorer compared to TD children on inflectional operations (invariably on judging & revising) but performed like TD children on derivational morphemes. Within SLI, inflectional performance was significantly poorer than derivational performance. In contrast, TD children performed better on inflections than derivations. Findings supported the predictions and discussed using possible sequencing problems in children with SLI. CONCLUSION: The study describes the findings using sequential difficulties reported by procedural deficit hypothesis (PDH) in SLI.