An interpretable decision-support model for breast cancer diagnosis using histopathology images.

Microscopic examination of biopsy tissue slides is perceived as the gold-standard methodology for the confirmation of presence of cancer cells. Manual analysis of an overwhelming inflow of tissue slides is highly susceptible to misreading of tissue slides by pathologists. A computerized framework for histopathology image analysis is conceived as a diagnostic tool that greatly benefits pathologists, augmenting definitive diagnosis of cancer. Convolutional Neural Network (CNN) turned out to be the most adaptable and effective technique in the detection of abnormal pathologic histology. Despite their high sensitivity and predictive power, clinical translation is constrained by a lack of intelligible insights into the prediction. A computer-aided system that can offer a definitive diagnosis and interpretability is therefore highly desirable. Conventional visual explanatory techniques, Class Activation Mapping (CAM), combined with CNN models offers interpretable decision making. The major challenge in CAM is, it cannot be optimized to create the best visualization map. CAM also decreases the performance of the CNN models. To address this challenge, we introduce a novel interpretable decision-support model using CNN with a trainable attention mechanism using response-based feed-forward visual explanation. We introduce a variant of DarkNet19 CNN model for the classification of histopathology images. In order to achieve visual interpretation as well as boost the performance of the DarkNet19 model, an attention branch is integrated with DarkNet19 network forming Attention Branch Network (ABN). The attention branch uses a convolution layer of DarkNet19 and Global Average Pooling (GAP) to model the context of the visual features and generate a heatmap to identify the region of interest. Finally, the perception branch is constituted using a fully connected layer to classify images. We trained and validated our model using more than 7000 breast cancer biopsy slide images from an openly available dataset and achieved 98.7% accuracy in the binary classification of histopathology images. The observations substantiated the enhanced clinical interpretability of the DarkNet19 CNN model, supervened by the attention branch, besides delivering a 3%-4% performance boost of the baseline model. The cancer regions highlighted by the proposed model correlate well with the findings of an expert pathologist. The coalesced approach of unifying attention branch with the CNN model capacitates pathologists with augmented diagnostic interpretability of histological images with no detriment to state-of-art performance. The model's proficiency in pinpointing the region of interest is an added bonus that can lead to accurate clinical translation of deep learning models that underscore clinical decision support.

Construction of novel g-C3N4 coupled efficient Bi2O3 nanoparticles for improved Z-scheme photocatalytic removal of environmental wastewater contaminant: Insight mechanism.

Recently, the major environmental pollution produced by the release of wastewater in liquid type is one of the most extensive forms of foremost pollution in water ecosystems. In this article, the Bi2O3/g-C3N4 nanocomposite with a direct Z-scheme was effectively obtained by a facile hydrothermal system. The crystal structures, surface morphology, chemical composition, and the optical belongings of the as-obtained composite catalysts were examined by Power XRD, FT-IR spectra, High-resolution XPS spectra, FE-SEM images with EDX spectra, High-resolution TEM images, UV-Vis DRS, and PL spectra respectively. Furthermore, the photocatalytic performance was assessed by the degradation of aqueous Rhodamine B (Rh B) dye under visible-light exposure. The Bi2O3/g-C3N4 composite photocatalysts (PCs) showed the maximum photo-degradation efficiency through a rate constant value of 0.0149 min-1, which is 4.9 and 5.3 folds superior to Bi2O3, and GCN, respectively. The better GBO2 nanocomposite PCs showed a superior photocatalytic degradation performance (>82%) of aqueous Rh B dye after five successive recycles. Moreover, based on these outcomes of the radical scavenging test, a direct and effective Z-scheme photocatalytic charger transfer mechanism was also projected. Finally, the reusability of the as-obtained Bi2O3/g-C3N4 nanocomposite has better stability and reusability, which was a favourable applicant for wastewater handling.

Facile construction of cost-effective zinc-aluminium polymeric framework for efficient removal of selective both drug and dye from an aqueous medium.

A novel aluminium (Al) and its active alloys are extensively been used in nearly all areas owing to their cost-effectiveness. But when it is subjected to an aqueous medium, gets corroded through a chemical response. In this paper, a novel framework was fabricated by copolymer coating over on Al and loaded with zinc via electro polymerization and electrodeposition method ([EDA- OPDA]Al@Zn). The as-fabricated composite has emerged for the sorption of Methylene Blue (MB) aqueous dye and Paracetomal drug (PAR). The as-fabricated composite framework has been categorized via IR spectra, FE-SEM images, and EDX spectra. The sorption progression was optimized for numerous prompting features like pH, contact time and impact of dosage. Based on kinetics data, the growth in QE value by an enhancement in temperature for adsorption and the higher r values shows the adsorption progression is a pseudo-second-order model. The thermodynamic constraints specify that the field of adsorbate is impulsive and typical endothermic process. Instead, the corrosion resistance of a composite in the 3.5% of NaCl. Solution was explored via EIS spectra and potentio-dynamic polarization. Depending on the observed features, it indicates that the [EDA-OPDA]Al@Zn framework provided fantastic corrosion resistance. So it is obvious that the as-synthesized framework is of multitasking, that it could be successfully performed for the exclusion of MB aqueous dye and PAR drug from the aqueous medium and it also withstands effectively in this corrosive medium.

Poisoning and its pattern among patients in a tertiary care center in Kancheepuram district, Tamil Nadu.

INTRODUCTION: Poisoning is an important global health problem that leads to increase in mortality and morbidity. Worldwide, a million people die each year because of poisoning. The incidence of poisoning is also highest in India, with an estimated death of 50,000 people every year. There is a paucity of literature on various factors associated with poisoning which hinders effective poisoning prevention. AIMS: The present study aimed to study the pattern of poisoning among patients in a tertiary care center and to assess the factors associated with poisoning. METHODOLOGY: The prospective study was conducted at the intensive care unit of a tertiary care hospital from May 2018 to September 2018. All the patients who had exposure to poisoning were included in the study. A pretested questionnaire was administered, and information regarding sociodemographic factors, type, mode, and outcome of poisoning were obtained. Statistical analysis was done through SPSS version 21. RESULTS: Of 106 poisoning patients admitted, 55.7% were female and majority were from rural area (52.8%). The major type of poisoning was suicidal (86.8%). Among suicidal, tablet poisoning was predominant (35.8%), followed by corrosive poisoning (17.9%) and Organophosphorus poisoning (13.2%). The major reason for suicidal poisoning was family problems (63.4%), and the association was statistically significant (P < 0.001). Suicidal poisoning was more among the age group of 21-30 years and middle socioeconomic status, which was statistically significant (P < 0.001). The prevalence of poisoning was 20.8% and 19.8% among homemakers and college students, respectively, which was statistically significant. CONCLUSION: Young adults, especially homemakers and college students, are more affected from poisoning in the current study. The involvement of family, educational institutes, and community is very important in identifying the risk factors and timely counseling. Emphasis should be made on legislative measures to combat socioeconomic problems.

Enhanced biodegradation of hydrocarbons in petroleum tank bottom oil sludge and characterization of biocatalysts and biosurfactants.

Petroleum hydrocarbon removal from tank bottom oil sludge is a major issue due to its properties. Conventional physicochemical treatment techniques are less effective. Though the bioremediation is considered for the hydrocarbon removal from tank bottom oil sludge, the efficiency is low and time taking due to the low yield of biocatalysts and biosurfactants. The focal theme of the present investigation is to modify the process by introducing the intermittent inoculation for the enhanced biodegradation of hydrocarbons in the tank bottom oil sludge by maintaining a constant level of biocatalysts such as oxidoreductase, catalase, and lipase as well as biosurfactants. In addition, the heavy metal removal was also addressed. The microbial consortia comprising Shewanalla chilikensis, Bacillus firmus, and Halomonas hamiltonii was used for the biodegradation of oil sludge. One variable at a time approach was used for the optimum of culture conditions. The bacterial consortia degraded the oil sludge by producing biocatalysts such as lipase (80 U/ml), catalase (46 U/ml), oxidoreductase (68 U/ml) along with the production of lipoprotein biosurfactant (152 mg/g of oil sludge) constantly and achieved 96% reduction of total petroleum hydrocarbon. The crude enzymes were characterized by FT-IR and the biosurfactant was characterized by surface tension reduction, emulsification index, FT-IR, TLC, and SDS-PAGE. GC-MS and NMR also revealed that the hydrocarbons present in the oil sludge were effectively degraded by the microbial consortia. The ICP-OES result indicated that the microbial consortium is also effective in removing the heavy metals. Hence, bioremediation using the hydrocarbonoclastic microbial consortium can be considered as an environmentally friendly process for disposal of tank bottom oil sludge from petroleum oil refining industry.

IsomiR processing during differentiation of myelogenous leukemic cell line K562 by phorbol ester PMA.

Chronic myelocytic leukemia cell line K562 undergoes differentiation by phorbol esters to megakaryocytes and we have used this system to understand miRNA processing leading to isomiR generation. PMA treatment significantly altered the production of miRNA in K562 cells. Expression of 24.4% of miRNAs were found to be stimulated whereas expression of 10% miRNAs were inhibited by PMA treatment. Our results suggest that miRNA precursors are processed into isomiRs in a deterministic manner. The relative levels of different isomiRs of a miRNA remained mainly unchanged even after PMA treatment irrespective of overall changes in expression (either up-regulation or down-regulation). However, not all miRNAs behave in the same way, about 7% showed a variation of isomiR profiles after PMA treatment. Most of the later class of miRNAs were found to be oncogenic miRNAs. Further, it was also found that number of isomiRs was independent of abundance of a miRNA. Functional importance of different isomiRs was demonstrated using three different isomiRs of miR-22. Our results showed that different isomiRs could inhibit expression of targets genes with different efficiencies. Our study suggests that the heterogeneity of a miRNA population generated during processing is in general regulated and that variation in the generation of an isomiR can be a functionally important regulatory feature.

Flash Glucose Monitoring in Subjects with Diabetes on Hemodialysis: A Pilot Study.

BACKGROUND: In patients with diabetes related end-stage renal disease (ESRD) on hemodialysis, blood glucose management can be challenging due to the kinetics of glucose and insulin in addition to other factors. The glucose monitoring systems which measure glucose levels continuously may be useful to study the glucose profile of patients with diabetes undergoing hemodialysis. Our study is designed to use ambulatory glucose profile to study the glucose pattern - during, before, and after a session of hemodialysis. MATERIALS AND METHODS: Ten patients with type 2 diabetes with ESRD undergoing hemodialysis were recruited. Forty-eight glucose readings were recorded in a 12-h period which included 4 h each prior, during, and after the dialysis session with a flash glucose monitor (FreeStyle Libre-pro). The same 12 h time frame was also monitored on a non-dialysis day. RESULTS: On the day of dialysis, the mean glucose level was significantly lower (P = 0.013) compared to the day without dialysis (95 ± 12.7 mg/dl vs 194 ± 76.8 mg/dl). As compared to the pre-dialysis period, the mean blood glucose levels during dialysis were lower (P = 0.004). As compared to the dialysis period, the mean blood glucose levels in the post-dialysis period were higher but did not reach statistical significance. CONCLUSION: In our study, subjects with type 2 diabetes on hemodialysis had lower glucose levels on the day of dialysis compared to non-dialysis day. Glucose levels showed a fall during hemodialysis and then a rise to higher levels after dialysis.

An approach to analyze the breast tissues in infrared images using nonlinear adaptive level sets and Riesz transform features.

BACKGROUND: Breast thermography is a potential imaging method for the early detection of breast cancer. The pathological conditions can be determined by measuring temperature variations in the abnormal breast regions. Accurate delineation of breast tissues is reported as a challenging task due to inherent limitations of infrared images such as low contrast, low signal to noise ratio and absence of clear edges. OBJECTIVE: Segmentation technique is attempted to delineate the breast tissues by detecting proper lower breast boundaries and inframammary folds. Characteristic features are extracted to analyze the asymmetrical thermal variations in normal and abnormal breast tissues. METHODS: An automated analysis of thermal variations of breast tissues is attempted using nonlinear adaptive level sets and Riesz transform. Breast thermal images are initially subjected to Stein's unbiased risk estimate based orthonormal wavelet denoising. These denoised images are enhanced using contrast-limited adaptive histogram equalization method. The breast tissues are then segmented using non-linear adaptive level set method. The phase map of enhanced image is integrated into the level set framework for final boundary estimation. The segmented results are validated against the corresponding ground truth images using overlap and regional similarity metrics. The segmented images are further processed with Riesz transform and structural texture features are derived from the transformed coefficients to analyze pathological conditions of breast tissues. RESULTS: Results show that the estimated average signal to noise ratio of denoised images and average sharpness of enhanced images are improved by 38% and 6% respectively. The interscale consideration adopted in the denoising algorithm is able to improve signal to noise ratio by preserving edges. The proposed segmentation framework could delineate the breast tissues with high degree of correlation (97%) between the segmented and ground truth areas. Also, the average segmentation accuracy and sensitivity are found to be 98%. Similarly, the maximum regional overlap between segmented and ground truth images obtained using volume similarity measure is observed to be 99%. Directionality as a feature, showed a considerable difference between normal and abnormal tissues which is found to be 11%. CONCLUSION: The proposed framework for breast thermal image analysis that is aided with necessary preprocessing is found to be useful in assisting the early diagnosis of breast abnormalities.

An Approach to Diagnosis of Auto-Immune Diseases using HEP-2 Staining Pattern and Fractal Texture Features.

Observing and classifying the indirect immunofluorescence patterns on HEp-2 cells can help in detecting Anti-Nuclear-Antibodies. A computer algorithm to perform this function can lead to a more standardized, faster and accurate diagnosis of auto-immune diseases such as systemic lupus erythematosus, sjogren’s syndrome, and rheumatoid arthritis. In this paper, HEp-2 staining patterns are classified using segmentation based fractal texture features. The images used for this experimentation are obtained from a publicly available database. The features extracted from a cell image is used to classify it into homogenous, fine speckled, coarse speckled, centromere and nucleolus. The cell images are segmented using the ground truth mask provided in the database. Adaptive histogram equalization is applied to the segmented images for contrast enhancement. Three features namely mean intensity, area and Hausdorff fractal dimension of the border are extracted for 8 different Otsu threshold levels. Finally, the 24 features thus extracted are fed to a support vector machine with Gaussian radial basis function kernel. It is observed that the overall accuracy of classification is 65.17%. The accuracy is greatly dependent on scaling and distribution of the features given to SVM. It appears that the segmentation based fractal texture features and SVM could help to build a robust automated diagnosis tool for auto-immune diseases.

Filtering of high noise breast thermal images using fast non-local means.

Analyses of breast thermograms are still a challenging task primarily due to the limitations such as low contrast, low signal to noise ratio and absence of clear edges. Therefore, always there is a requirement for preprocessing techniques before performing any quantitative analysis. In this work, a noise removal framework using fast non-local means algorithm, method noise and median filter was used to denoise breast thermograms. The images considered were subjected to Anscombe transformation to convert the distribution from Poisson to Gaussian. The pre-denoised image was obtained by subjecting the transformed image to fast non-local means filtering. The method noise which is the difference between the original and pre-denoised image was observed with the noise component merged in few structures and fine detail of the image. The image details presented in the method noise was extracted by smoothing the noise part using the median filter. The retrieved image part was added to the pre-denoised image to obtain the final denoised image. The performance of this technique was compared with that of Wiener and SUSAN filters. The results show that all the filters considered are able to remove the noise component. The performance of the proposed denoising framework is found to be good in preserving detail and removing noise. Further, the method noise is observed with negligible image details. Similarly, denoised image with no noise and smoothed edges are observed using Wiener filter and its method noise is contained with few structures and image details. The performance results of SUSAN filter is found to be blurred denoised image with little noise and also method noise with extensive structure and image details. Hence, it appears that the proposed denoising framework is able to preserve the edge information and generate clear image that could help in enhancing the diagnostic relevance of breast thermograms. In this paper, the introduction, objectives, materials and methods, results and discussion and conclusions are presented in detail.

Analysis of breast thermograms using Gabor wavelet anisotropy index.

In this study, an attempt is made to distinguish the normal and abnormal tissues in breast thermal images using Gabor wavelet transform. Thermograms having normal, benign and malignant tissues are considered in this study and are obtained from public online database. Segmentation of breast tissues is performed by multiplying raw image and ground truth mask. Left and right breast regions are separated after removing the non-breast regions from the segmented image. Based on the pathological conditions, the separated breast regions are grouped as normal and abnormal tissues. Gabor features such as energy and amplitude in different scales and orientations are extracted. Anisotropy and orientation measures are calculated from the extracted features and analyzed. A distinctive variation is observed among different orientations of the extracted features. It is found that the anisotropy measure is capable of differentiating the structural changes due to varied metabolic conditions. Further, the Gabor features also showed relative variations among different pathological conditions. It appears that these features can be used efficiently to identify normal and abnormal tissues and hence, improve the relevance of breast thermography in early detection of breast cancer and content based image retrieval.

miR-22 regulates expression of oncogenic neuro-epithelial transforming gene 1, NET1.

MicroRNAs control cellular processes by regulating expression of their target genes. Here we report that neuro-epithelial transforming gene 1 (NET1) is a target of tumor suppressor microRNA 22 (miR-22). miR-22 is downregulated in peripheral blood mononuclear cells derived from chronic myeloid leukemia (CML) patients and in CML cell line K562. NET1 was identified as one of the targets of miR-22 using both in vitro and in vivo experiments. Either mutations or naturally occurring single-nucleotide polymorphisms in NET1 3'-UTR that map at the miR-22 binding site were found to affect binding of miR-22 to NET1 mRNA. Over expression of NET1 in K562 cells resulted in increased proliferation. However decreased proliferation and alteration in cell cycle were observed on either overexpression of miR-22 or knockdown of NET1 expression respectively. We also found that overexpression of miR-22 or NET1 knockdown inhibits actin fiber formation, probably by downregulation of NET1 as NET1 knockdown also resulted in depletion of actin fiber formation. We suggest that the oncogenic properties of CML cells are probably due to deregulated expression of NET1 as a result of altered expression of miR-22.

Evaluation of human hand thermal images using wavelet transform based local spatial features - biomed 2013.

Transform-based spatial analyses of medical Infrared (IR) images are found to be useful to extract local information, which can be used to identify the abnormalities associated with in region of interest. In this work, human hand infrared images are analyzed by extracting local spatial features using wavelet transform method. The images for this study were acquired using uncooled micro bolometer with focal plane array technology based medical IR camera with dedicated software having high array resolution and spectral response under controlled protocol. The acquired images were decomposed into Intrinsic Mode Functions (IMFs) using bidimensional empirical mode decomposition. Extrema points were detected using eight connected neighbor window method and interpolated using thin plate spline interpolation technique to generate IMFs. The edge information were extracted from local phase of the first IMF. Edges were detected using phase congruency measure by applying Gabor function based wavelet transform. The results showed that it was possible to detect edges from only the first IMF without being influenced by other IMFs. It was further observed that the edge intermittence that arises due to noise component was reduced by treating images with local phase distributions. Hence, it appears that the edge information extraction could enhance the diagnostic relevance of thermal image analysis.