Prediction of Non-small Cell Lung Cancer Histology by a Deep Ensemble of Convolutional and Bidirectional Recurrent Neural Network.

Histology subtype prediction is a major task for grading non-small cell lung cancer (NSCLC) tumors. Invasive methods such as biopsy often lack in tumor sample, and as a result radiologists or oncologists find it difficult to detect proper histology of NSCLC tumors. The non-invasive methods such as machine learning may play a useful role to predict NSCLC histology by using medical image biomarkers. Few attempts have so far been made to predict NSCLC histology by considering all the major subtypes. The present study aimed to develop a more accurate deep learning model by clubbing convolutional and bidirectional recurrent neural networks. The NSCLC Radiogenomics dataset having 211 subjects was used in the study. Ten best models found during experimentation were averaged to form an ensemble. The model ensemble was executed with 10-fold repeated stratified cross-validation, and the results got were tested with metrics like accuracy, recall, precision, F1-score, Cohen's kappa, and ROC-AUC score. The accuracy of the ensemble model showed considerable improvement over the best model found with the single model. The proposed model may help significantly in the automated prognosis of NSCLC and other types of cancers.

Clinical Profile and Outcome of Patients with Acute Poisoning Admitted in Intensive Care Unit of Tertiary Care Center in Eastern Nepal.

BACKGROUND: Acute poisoning is a common health-care problem requiring admission in the intensive care unit (ICU) in the developing countries. The study was conducted to assess the epidemiological parameters of acute poisoning and factors affecting clinical course and outcome of the patients in ICU in the eastern part of Nepal. METHODOLOGY: This was a prospective observational study conducted at ICU of tertiary care hospital in the eastern part of Nepal for the duration of 2 years. All the acute poisoning cases admitted in the ICU were studied for epidemiological profiles, poisoning characteristics, and various clinical factors affecting the outcome of the patients. RESULTS: Eighty-five patients with acute poisoning were included in the study. Suicidal attempt leading to acute poisoning was seen in majority of the young population. Majority of the poisoning was due to the organophosphorous compounds (43.5%). Patients with organophosphorous poisoning had a significantly longer duration of ICU stay (P = 0.020). The survival of the patients was significantly affected by age, duration of presentation to the hospital, Glasgow Coma Scale, Sequential Organ Failure Assessment score, need for mechanical ventilation, duration of ICU stay, hepatic failure, coagulopathy, and need for vasoactive drugs (P < 0.05). The independent predictors of mortality observed in the study were age, delayed presentation to the hospital, hepatic failure, and need for mechanical ventilation. CONCLUSION: Organophosphorous poisoning was the most common acute poisoning in young population leading to the ICU admission. Older age, delayed initiation of the resuscitative measures, need for mechanical ventilation, and hepatic failure significantly affected the mortality.

Quantitative magnetic resonance imaging of hepatic steatosis: Validation in ex vivo human livers.

UNLABELLED: Emerging magnetic resonance imaging (MRI) biomarkers of hepatic steatosis have demonstrated tremendous promise for accurate quantification of hepatic triglyceride concentration. These methods quantify the proton density fat-fraction (PDFF), which reflects the concentration of triglycerides in tissue. Previous in vivo studies have compared MRI-PDFF with histologic steatosis grading for assessment of hepatic steatosis. However, the correlation of MRI-PDFF with the underlying hepatic triglyceride content remained unknown. The aim of this ex vivo study was to validate the accuracy of MRI-PDFF as an imaging biomarker of hepatic steatosis. Using ex vivo human livers, we compared MRI-PDFF with magnetic resonance spectroscopy-PDFF (MRS-PDFF), biochemical triglyceride extraction, and histology as three independent reference standards. A secondary aim was to compare the precision of MRI-PDFF relative to biopsy for the quantification of hepatic steatosis. MRI-PDFF was prospectively performed at 1.5 Tesla in 13 explanted human livers. We performed colocalized paired evaluation of liver fat content in all nine Couinaud segments using single-voxel MRS-PDFF (n=117) and tissue wedges for biochemical triglyceride extraction (n=117), and five core biopsies performed in each segment for histologic grading (n=585). Accuracy of MRI-PDFF was assessed through linear regression with MRS-PDFF, triglyceride extraction, and histology. Intraobserver agreement, interobserver agreement, and repeatability of MRI-PDFF and histologic grading were assessed through Bland-Altman analyses. MRI-PDFF showed an excellent correlation with MRS-PDFF (r=0.984, confidence interval 0.978-0.989) and strong correlation with histology (r=0.850, confidence interval 0.791-0.894) and triglyceride extraction (r=0.871, confidence interval 0.818-0.909). Intraobserver agreement, interobserver agreement, and repeatability showed a significantly smaller variance for MRI-PDFF than for histologic steatosis grading (all P<0.001). CONCLUSION: MRI-PDFF is an accurate, precise, and reader-independent noninvasive imaging biomarker of liver triglyceride content, capable of steatosis quantification over the entire liver.

Insecticide susceptibility of Phlebotomus argentipes & assessment of vector control in two districts of West Bengal, India.

BACKGROUND & OBJECTIVES: Kala-azar or visceral leishmanisis (VL) is known to be endemic in several States of India including West Bengal (WB). Only meager information is available on the vector dynamics of its vector species, Phlebotomus argentipes particularly in relation to control measure from this State. Hence, a pilot study was undertaken to assess the control strategy and its impact on vector in two endemic districts of WB, India. METHODS: Two villages each from the two districts, Maldah and Burdwan, were selected for the study. Seasonal variation of sandflies was observed during pre-monsoon, post-monsoon and winter seasons. Susceptibility test of P. argentipes against DDT and bioassay on DDT sprayed wall and on long lasting insecticide nets (LN) Perma Net [®] 2.0 were conducted as per the WHO standard methods. RESULTS: P. argentipes density was high during March to October. Susceptibility status of P. argentipes ranged from 40 to 61.54 per cent. Bioassay test showed 57.89 per cent mortality against LN PermaNet [®] -2.0. and 50 per cent against DDT on wall within 30 min of exposure. INTERPRETATION & CONCLUSIONS: Despite the integrated vector management approach, the sandfly population was high in the study area. The reason could be development of resistance in P. argentipes against DDT and low effectiveness of LN PermaNet [®] -2.0. The more pragmatic step will be to conduct large studies to monitor the susceptibility level in P. argentipes against DDT.

Increased heterogeneity in expression of genes associated with cancer progression and drug resistance.

Fluctuations in the number of regulatory molecules and differences in timings of molecular events can generate variation in gene expression among genetically identical cells in the same environmental condition. This variation, termed as expression noise, can create differences in metabolic state and cellular functions, leading to phenotypic heterogeneity. Expression noise and phenotypic heterogeneity have been recognized as important contributors to intra-tumor heterogeneity, and have been associated with cancer growth, progression, and therapy resistance. However, how expression noise changes with cancer progression in actual cancer patients has remained poorly explored. Such an analysis, through identification of genes with increasing expression noise, can provide valuable insights into generation of intra-tumor heterogeneity, and could have important implications for understanding immune-suppression, drug tolerance and therapy resistance. In this work, we performed a genome-wide identification of changes in gene expression noise with cancer progression using single-cell RNA-seq data of lung adenocarcinoma patients at different stages of cancer. We identified 37 genes in epithelial cells that showed an increasing noise trend with cancer progression, many of which were also associated with cancer growth, EMT and therapy resistance. We found that expression of several of these genes was positively associated with expression of mitochondrial genes, suggesting an important role of mitochondria in generation of heterogeneity. In addition, we uncovered substantial differences in sample-specific noise profiles which could have implications for personalized prognosis and treatment.

Disparities in chronic myeloid leukemia survival by age, gender, and ethnicity in pre- and post-imatinib eras in the US.

BACKGROUND: Since May 2001, imatinib mesylate has become the first-line therapy for chronic myeloid leukemia (CML) but the survival pattern by age, sex, and ethnicity is not clear. MATERIAL AND METHODS: We analyzed the Surveillance, Epidemiology, and End Results (SEER*Stat) database to compare survival rates in CML among Caucasians, African-Americans (AA), and other races, and also within each race to see survival differences from the pre-imatinib (1973-2000) to post-imatinib eras (2002-2008). We used Z-tests in SEER*Stat to compare relative survival rates categorized by race, gender, and age groups (all ages, < 50, 50+ years). RESULTS: The three-year relative survival rates among Caucasians, AA, and other races in the pre-imatinib era were 44.9 ± 0.6%, 46.8 ± 1.8%, and 48.0 ± 2.2%, respectively, and in the post-imatinib era 64.4 ± 0.8%, 67.3 ± 2.4%, and 69.6 ± 1.6%, respectively. The relative survival increased from the pre-to post-imatinib era for all ethnic groups. In the post-imatinib era, three-year relative survival rates among young AA women were significantly lower (Z-value = -2.54, p = 0.011) than young Caucasian women, 80.5 ± 4.5% (n = 105) vs. 90.3 ± 1.4% (n = 589). CONCLUSIONS: The relative survival rates of CML patients have improved in the post-imatinib era. However, the improvement in survival rates has been modest in this population-based data compared to those reported from randomized trials. Improvement in survival among older patients is lower than in younger patients. Young (<50 years) AA women with CML had lower relative survival rates compared to young Caucasian women in the post-imatinib era.

Appraisal of Phlebotomus argentipes habitat suitability using a remotely sensed index in the kala-azar endemic focus of Bihar, India.

Visceral leishmaniasis, or kala-azar, is recognised as a serious emerging public health problem in India. In this study, environmental parameters, such as land surface temperature (LST) and renormalised difference vegetation indices (RDVI), were used to delineate the association between environmental variables and Phlebotomus argentipes abundance in a representative endemic region of Bihar, India. The adult P. argentipes were collected between September 2009-February 2010 using the hand-held aspirator technique. The distribution of P. argentipes was analysed with the LST and RDVI of the peak and lean seasons. The association between environmental covariates and P. argentipes density was analysed a multivariate linear regression model. The sandfly density at its maximum in September, whereas the minimum density was recorded in January. The regression model indicated that the season, minimum LST, mean LST and mean RDVI were the best environmental covariates for the P. argentipes distribution. The final model indicated that nearly 74% of the variance of sandfly density could be explained by these environmental covariates. This approach might be useful for mapping and predicting the distribution of P. argentipes, which may help the health agencies that are involved in the kala-azar control programme focus on high-risk areas.

Bilateral acute necrosis of the globi pallidi and rhabdomyolysis due to combined methadone and benzodiazepine toxicity.

Methadone continues to be a widely used maintenance therapy for opiate dependence. However, methadone-related deaths have been reported frequently for over 4 decades now. Anoxic brain injury with pulmonary edema secondary to respiratory depression is the recognized mechanism of methadone death, although pathological intracranial findings are rarely described in methadone deaths. A selective area of brain injury has never been reported with methadone use. We present a case of a 23-year-old man who had acute necrosis of the bilateral globi pallidi in the brain and systemic rhabdomyolysis after ingesting methadone and nasally insufflating alprazolam. We also present a review of the literature on deaths following opioid use and associated brain injury.

Retrospective analysis of clinico-laboratory parameters, outcome and predictors of scrub typhus co- infection in covid-19 affected children.

The objective of this study was to describe clinico-laboratory parameters, outcome and predictors of scrub typhus co- infection in COVID-19 affected children. Ours was a retrospective analysis done in a tertiary care pediatric COVID facility. COVID-19 positive children in the age group of 1 month to 12 years who were tested for scrub typhus co-infection between May to August 2020 were included in the study. In all positive cases, clinical, laboratory, treatment and outcome data were analyzed. Relevant data were compared between scrub typhus confirmed, and suspected but negative patients. All six patients with co-infection had fever for >5 days and four had features of cerebral involvement. These had lymphocytic pleocytosis in cerebrospinal fluid (CSF) analysis and two had eschar. Screening for scrub typhus in persistently febrile children residing in highly endemic areas is highly recommended.

Delimitation of kala-azar risk areas in the district of Vaishali in Bihar (India) using a geo-environmental approach.

Remote sensing and geographical information technologies were used to discriminate areas of high and low risk for contracting kala-azar or visceral leishmaniasis. Satellite data were digitally processed to generate maps of land cover and spectral indices, such as the normalised difference vegetation index and wetness index. To map estimated vector abundance and indoor climate data, local polynomial interpolations were used based on the weightage values. Attribute layers were prepared based on illiteracy and the unemployed proportion of the population and associated with village boundaries. Pearson's correlation coefficient was used to estimate the relationship between environmental variables and disease incidence across the study area. The cell values for each input raster in the analysis were assigned values from the evaluation scale. Simple weighting/ratings based on the degree of favourable conditions for kala-azar transmission were used for all the variables, leading to geo-environmental risk model. Variables such as, land use/land cover, vegetation conditions, surface dampness, the indoor climate, illiteracy rates and the size of the unemployed population were considered for inclusion in the geo-environmental kala-azar risk model. The risk model was stratified into areas of "risk"and "non-risk"for the disease, based on calculation of risk indices. The described approach constitutes a promising tool for microlevel kala-azar surveillance and aids in directing control efforts.

Organ weight changes associated with body mass index determined from a medical autopsy population.

CONTEXT: Existing organ weight charts used by pathologists for patients undergoing medical autopsy do not illustrate the effect of obesity and age on organ weights among a general population of older individuals with multiple comorbidities. METHODS: We retrospectively reviewed 300 medical autopsy reports to extract data to analyze the effect of obesity and age on organ weights. RESULTS: In both men and women, there were statistically significant increases in organ weights with body mass index (BMI) but decreases with age for liver, spleen, and kidneys. In men, increased age was associated with increased left ventricular wall thickness, whereas increased BMI was associated with increased heart weight. In women, only BMI was associated with changes in all 3 anatomic cardiac parameters (heart weight and thickness of the right and left ventricular walls). Age effects were not observed for heart parameters in women. Thyroid weight increased with BMI in men but not in women. CONCLUSIONS: The findings demonstrate changes in organ weights/sizes with obesity and age in a population of patients with multiple comorbidities. The differential effects of age and BMI on the heart between men and women raise the possibility that increased BMI in women may have a greater impact on cardiovascular causes of death than that in men.

Classification of malignant tumors by a non-sequential recurrent ensemble of deep neural network model.

Many significant efforts have so far been made to classify malignant tumors by using various machine learning methods. Most of the studies have considered a particular tumor genre categorized according to its originating organ. This has enriched the domain-specific knowledge of malignant tumor prediction, we are devoid of an efficient model that may predict the stages of tumors irrespective of their origin. Thus, there is ample opportunity to study if a heterogeneous collection of tumor images can be classified according to their respective stages. The present research work has prepared a heterogeneous tumor dataset comprising eight different datasets from The Cancer Imaging Archives and classified them according to their respective stages, as suggested by the American Joint Committee on Cancer. The proposed model has been used for classifying 717 subjects comprising different imaging modalities and varied Tumor-Node-Metastasis stages. A new non-sequential deep hybrid model ensemble has been developed by exploiting branched and re-injected layers, followed by bidirectional recurrent layers to classify tumor images. Results have been compared with standard sequential deep learning models and notable recent studies. The training and validation accuracy along with the ROC-AUC scores have been found satisfactory over the existing models. No model or method in the literature could ever classify such a diversified mix of tumor images with such high accuracy. The proposed model may help radiologists by acting as an auxiliary decision support system and speed up the tumor diagnosis process.

Impact of intensified control on visceral leishmaniasis in a highly-endemic district of Bihar, India: an interrupted time series analysis.

Visceral leishmaniasis (VL) is declining in India and the World Health Organization's (WHO) 2020 'elimination as a public health problem' target has nearly been achieved. Intensified combined interventions might help reach elimination, but their impact has not been assessed. WHO's Neglected Tropical Diseases 2021-2030 roadmap provides an opportunity to revisit VL control strategies. We estimated the combined effect of a district-wide pilot of intensified interventions in the highly-endemic Vaishali district, where cases fell from 3,598 in 2012-2014 to 762 in 2015-2017. The intensified control approach comprised indoor residual spraying with improved supervision; VL-specific training for accredited social health activists to reduce onset-to-diagnosis time; and increased Information Education & Communication activities in the community. We compared the rate of incidence decrease in Vaishali to other districts in Bihar state via an interrupted time series analysis with a spatiotemporal model informed by previous VL epidemiological estimates. Changes in Vaishali's rank among Bihar's endemic districts in terms of monthly incidence showed a change pre-pilot (3rd highest out of 33 reporting districts) vs. during the pilot (9th) (p<1e-10). The rate of decline in Vaishali's incidence saw no change in rank at 11th highest, both pre-pilot & during the pilot. Counterfactual model simulations suggest an estimated median of 352 cases (IQR 234-477) were averted by the Vaishali pilot between January 2015 and December 2017, which was robust to modest changes in the onset-to-diagnosis distribution. Strengthening control strategies may have precipitated a substantial change in VL incidence in Vaishali and suggests this approach should be piloted in other highly-endemic districts.

Estrogen receptor positive breast cancers and their association with environmental factors.

BACKGROUND: Epidemiological studies to assess risk factors for breast cancer often do not differentiate between different types of breast cancers. We applied a general linear model to determine whether data from the Surveillance, Epidemiology, and End Results Program on annual county level age-adjusted incidence rates of breast cancer with and without estrogen receptors (ER+ and ER-) were associated with environmental pollutants. RESULTS: Our final model explained approximately 38% of the variation in the rate of ER+ breast cancer. In contrast, we were only able to explain 14% of the variation in the rate of ER- breast cancer with the same set of environmental variables. Only ER+ breast cancers were positively associated with the EPA's estimated risk of cancer based on toxic air emissions and the proportion of agricultural land in a county. Meteorological variables, including short wave radiation, temperature, precipitation, and water vapor pressure, were also significantly associated with the rate of ER+ breast cancer, after controlling for age, race, premature mortality from heart disease, and unemployment rate. CONCLUSIONS: Our findings were consistent with what we expected, given the fact that many of the commonly used pesticides and air pollutants included in the EPA cancer risk score are classified as endocrine disruptors and ER+ breast cancers respond more strongly to estrogen than ER- breast cancers. The findings of this study suggest that ER+ and ER- breast cancers have different risk factors, which should be taken into consideration in future studies that seek to understand environmental risk factors for breast cancer.

Correlations between meteorological parameters and prostate cancer.

BACKGROUND: There exists a north-south pattern to the distribution of prostate cancer in the U.S., with the north having higher rates than the south. The current hypothesis for the spatial pattern of this disease is low vitamin D levels in individuals living at northerly latitudes; however, this explanation only partially explains the spatial distribution in the incidence of this cancer. Using a U.S. county-level ecological study design, we provide evidence that other meteorological parameters further explain the variation in prostate cancer across the U.S. RESULTS: In general, the colder the temperature and the drier the climate in a county, the higher the incidence of prostate cancer, even after controlling for shortwave radiation, age, race, snowfall, premature mortality from heart disease, unemployment rate, and pesticide use. Further, in counties with high average annual snowfall (>75 cm/yr) the amount of land used to grow crops (a proxy for pesticide use) was positively correlated with the incidence of prostate cancer. CONCLUSION: The trends found in this USA study suggest prostate cancer may be partially correlated with meteorological factors. The patterns observed were consistent with what we would expect given the effects of climate on the deposition, absorption, and degradation of persistent organic pollutants including pesticides. Some of these pollutants are known endocrine disruptors and have been associated with prostate cancer.

Long Non-coding RNAs in Pulmonary Neuroendocrine Neoplasms.

Pulmonary neuroendocrine neoplasms (NENs) are classified into low-grade neuroendocrine tumors and high-grade neuroendocrine carcinomas (NECs). There are significant differences in therapeutic strategies of the different NEN subtypes, and therefore, precise classification of pulmonary NENs is critical. However, challenges in pulmonary NEN classification include overlap of diagnostic histological features among the subtypes and reduced or negative expression of neuroendocrine markers in poorly differentiated pulmonary NECs. Recently, transcription factor insulinoma-associated protein 1 (INSM1) was identified as a sensitive marker of neuroendocrine and neuroepithelial differentiation. In this study, INSM1 expression was detected by immunohistochemistry in greater than 94% of pulmonary NENs, indicating that it is a highly sensitive marker of pulmonary NENs and is useful to detect poorly differentiated pulmonary NECs. Although there are well-established morphological and immunohistologic criteria to diagnose pulmonary NENs, there is no universal consensus regarding prognostic markers of pulmonary NENs. Studies have shown that non-small cell lung cancers express long non-coding RNAs (lncRNAs), which regulate gene expression, epithelial-to-mesenchymal transition, and carcinogenesis. We characterized expression and function of lncRNAs, including HOX transcript antisense RNA (HOTAIR), maternally expressed 3 (MEG3), and prostate cancer antigen 3 (PCA3) in pulmonary NENs, including typical carcinoid tumors, atypical carcinoid tumors, small cell lung carcinoma (SCLC/NEC), and large cell neuroendocrine carcinoma (LCNEC/NEC). In situ hybridization and real-time polymerase chain reaction studies showed higher expression (p < 0.01) of all lncRNAs in SCLC/NEC. Small interfering RNA studies indicated a role for MEG3 and PCA3 in tumor proliferation. Therefore, these lncRNAs may serve as prognostic indicators of pulmonary NEN aggressiveness and as possible therapeutic targets.

Kala-azar elimination in a highly-endemic district of Bihar, India: A success story.

BACKGROUND: Visceral leishmaniasis (VL) or Kala-azar has been a major public health problem in Bihar, India, for several decades. A few VL infected districts including Vaishali have reported >600 cases annually. Hence, in 2015, the Government of India entrusted ICMR-Rajendra Memorial Research Institute of Medical Sciences, Patna, to implement an integrated control strategy for achieving the VL elimination target (<1 case per 10,000 people at the block level) in the Vaishali District of Bihar. METHODOLOGY: This study was conducted between January 2015 and December 2016. An integrated control strategy including the spatio-temporal mapping of VL-case distribution, active case detection, chemical-based vector control using indoor residual spraying (IRS), community awareness campaigns, the training of IRS members, the training of medical doctors for effective treatment, daily monitoring and the supervision of IRS activities, logistic management, post-IRS quality assurance, epidemiological surveillance, and entomological monitoring was performed. An insecticide quantification test was performed for evaluating the IRS quality on sprayed walls. A modern compression pump was used to maintain spray quality on different wall surfaces. The impact of IRS was assessed through sand fly collection in human dwellings and cattle sheds in pre- and post-IRS. The insecticide susceptibility of local P. argentipes was performed before each IRS round (in February and June) during 2015-2016. Statistical analysis such as the mean, percentage, and 95% CI were used to summarize the results. FINDINGS: All 16 blocks of the Vaishali District achieved the VL elimination target in 2016. The integrated VL control strategy helped reduce the number of VL cases from 664 in 2014 to 163 in 2016 and the number of endemic villages from 282 in 2014 to 142 in 2016. The case reduction rate was increased from 22.6% in 2014 to 58.8% in 2016. On average, 74 VL infected villages became Kala-azar free each year from 2015 to 2016. CONCLUSIONS: The results of this study suggest that the elimination of VL is possible from all endemic blocks of Bihar if the integrated Vaishali VL control strategy is applied under strong monitoring and supervision.

Spatial trends of breast and prostate cancers in the United States between 2000 and 2005.

BACKGROUND: Breast cancer in females and prostate cancer in males are two of the most common cancers in the United States, and the literature suggests that they share similar features. However, it is unknown whether the occurrence of these two cancers at the county level in the United States is correlated. We analyzed Caucasian age-adjusted county level average annual incidence rates for breast and prostate cancers from the National Cancer Institute and State Cancer Registries to determine whether there was a spatial correlation between the two conditions and whether the two cancers had similar spatial patterns. RESULTS: There was a significant correlation between breast and prostate cancers by county (r = 0.332, p < 0.001). This relationship was more pronounced when we performed a geographically-weighted regression (GWR) analysis (r = 0.552) adjusting for county unemployment rates. There was variation in the parameter estimates derived with the GWR; however, the majority of the estimates indicted a positive association. The strongest relationship between breast and prostate cancer was in the eastern parts of the Midwest and South, and the Southeastern U.S. We also observed a north-south pattern for both cancers with our cluster analyses. Clusters of counties with high cancer incidence rates were more frequently found in the North and clusters of counties with low incidence rates were predominantly in the South. CONCLUSION: Our analyses suggest breast and prostate cancers cluster spatially. This finding corroborates other studies that have found these two cancers share similar risk factors. The north-south distribution observed for both cancers warrants further research to determine what is driving this spatial pattern.

Automated AJCC (7th edition) staging of non-small cell lung cancer (NSCLC) using deep convolutional neural network (CNN) and recurrent neural network (RNN).

PURPOSE: A large chunk of lung cancers are of the type non-small cell lung cancer (NSCLC). Both the treatment planning and patients' prognosis depend greatly on factors like AJCC staging which is an abstraction over TNM staging. Many significant efforts have so far been made towards automated staging of NSCLC, but the groundbreaking application of a deep neural networks (DNNs) is yet to be observed in this domain of study. DNN is capable of achieving higher level of accuracy than the traditional artificial neural networks (ANNs) as it uses deeper layers of convolutional neural network (CNN). The objective of the present study is to propose a simple yet fast CNN model combined with recurrent neural network (RNN) for automated AJCC staging of NSCLC and to compare the outcome with a few standard machine learning algorithms along with a few similar studies. METHODS: The NSCLC radiogenomics collection from the cancer imaging archive (TCIA) dataset was considered for the study. The tumor images were refined and filtered by resizing, enhancing, de-noising, etc. The initial image processing phase was followed by texture based image segmentation. The segmented images were fed into a hybrid feature detection and extraction model which was comprised of two sequential phases: maximally stable extremal regions (MSER) and the speeded up robust features (SURF). After a prolonged experiment, the desired CNN-RNN model was derived and the extracted features were fed into the model. RESULTS: The proposed CNN-RNN model almost outperformed the other machine learning algorithms under consideration. The accuracy remained steadily higher than the other contemporary studies. CONCLUSION: The proposed CNN-RNN model performed commendably during the study. Further studies may be carried out to refine the model and develop an improved auxiliary decision support system for oncologists and radiologists.

Assessing the combined effects of household type and insecticide effectiveness for kala-azar vector control using indoor residual spraying: a case study from North Bihar, India.

BACKGROUND: Indoor residual spraying (IRS) is the mainstay for vector control intervention of visceral leishmaniasis (VL) in India. Little is known on the control effects of IRS on different household types. Here, we assessed if IRS with insecticides has an equal residual and interventional effect on all household types in a village. We also developed a combined spatial-risk map and a sand fly, Phlebotomus argentipes density analytical model based on household characteristics, insecticide susceptibility and IRS-status to explore the spatio-temporal distributions of the vector at a micro-scale level. METHODS: This study was carried out in two villages of Mahnar block in Vaishali district, Bihar. IRS using two insecticides [dichlorodiphenyltrichloroethane (DDT 50%) and synthetic pyrethroid (SP 5%)] was evaluated for VL-vector (P. argentipes) control. Temporal residual efficacy of the insecticides on different wall-surface types was evaluated using the cone-bioassay technique according to WHO guidelines. Insecticide susceptibility of local P. argentipes was explored using the tube-bioassay method. Pre- and post-IRS sand fly densities were monitored in human dwellings and animal shelters using Centers for Disease Control light-traps installed between 18:00-6:00 h. A best-fit model for sand fly density analysis was developed using multiple logistic regression analysis. Geographical information system based spatial analysis techniques were employed to map the household type distribution of insecticide susceptibility of the vector, and IRS-status of the households to interpret the spatio-temporal distributions of P. argentipes. RESULTS: Phlebotomus argentipes was highly susceptible to SP (100%) but showed high resistance to DDT with a 49.1% mortality rate. SP-IRS has been reported as having better community acceptance than DDT-IRS in all household types. Residual efficacies were varied between wall-surfaces; both insecticides failed to achieve the duration of IRS effectiveness recommended by the WHO. Reduction in P. argentipes counts due to SP-IRS was higher than DDT-IRS between household groups (i.e. sprayed and sentinel), in all intervals post-IRS. Combined spatial risk-maps revealed a better control effect of SP-IRS on sand flies than DDT-IRS in all household types risk-zones. The multilevel logistic regression analysis explored five risk-factors that were strongly associated with the density of P. argentipes. CONCLUSIONS: The results contribute to furthering current understanding of IRS-practices for control of visceral leishmaniasis in endemic Bihar, which may help in future actions for improvements.