Lymphocyte detection for cancer analysis using a novel fusion block based channel boosted CNN

Tumor-infiltrating lymphocytes, specialized immune cells, are considered an important biomarker in cancer analysis. Automated lymphocyte detection is challenging due to its heterogeneous morphology, variable distribution, and presence of artifacts. In this work, we propose a novel Boosted Channels Fusion-based CNN "BCF-Lym-Detector" for lymphocyte detection in multiple cancer histology images. The proposed network initially selects candidate lymphocytic regions at the tissue level and then detects lymphocytes at the cellular level. The proposed "BCF-Lym-Detector" generates diverse boosted channels by utilizing the feature learning capability of different CNN architectures. In this connection, a new adaptive fusion block is developed to combine and select the most relevant lymphocyte-specific features from the generated enriched feature space. Multi-level feature learning is used to retain lymphocytic spatial information and detect lymphocytes with variable appearances. The assessment of the proposed "BCF-Lym-Detector" show substantial improvement in terms of F-score (0.93 and 0.84 on LYSTO and NuClick, respectively), which suggests that the diverse feature extraction and dynamic feature selection enhanced the feature learning capacity of the proposed network. Moreover, the proposed technique's generalization on unseen test sets with a good recall (0.75) and F-score (0.73) shows its potential use for pathologists' assistance.

Revolutionizing the effect of Azadirachta indica extracts on edema induced changes in C-reactive protein and interleukin-6 in albino rats: in silico and in vivo approach

OBJECTIVE

The aim of the present study is to determine the in vivo and in silico anti-inflammatory effect of Azadirachta indica (A. indica) in carrageenan-induced rats and its blood biomarkers. A. indica (Neem) is a widely used medicinal plant across the world, especially in Pakistan. Neem leaves have been traditionally used for the synthesis of drugs and treatment of a wide variety of diseases.

MATERIALS AND METHODS

In this study, sixty albino rats (160-200 g) were divided into 4 groups: control (group I), standard (group II), ethanolic and aqueous (group III and IV) at doses of 50, 100, 200 and 400 mg/kg.

RESULTS

Ethanolic and aqueous extracts showed maximum inhibition in paw size at the 5th hour (400 mg/kg). Similarly, biomarkers measured, including Interleukin-6 and C-reactive protein, exhibited significant anti-inflammatory activity at the highest dose of 400 mg/kg in both experimental groups but were more distinct in the group treated with ethanolic extracts. Correlation between C-reactive protein (CRP) and inter-leukin-6 (IL-6) showed positive correlation in group III, while negative in group IV. Similarly, positive and negative correlations were observed between CRP biomarkers and paw size in group III and IV, and the same results were also shown in the case of IL-6 and paw size. In molecular docking, the binding energy value of protein CRP and IL-1β with the identified ligands quercetin and nimbosterol showed (-8.2 kcal/mol and -7.7 kcal/mol) the best binding affinity as compared to standard drug diclofenac with -7.0 kcal/mol binding energy respectively.

CONCLUSIONS

In conclusion, in silico and in vivo analysis revealed that the extracts of A. indica leaves can be used as an effective drug to manage inflammation.

Attention-guided multi-scale deep object detection framework for lymphocyte analysis in IHC histological images

Tumor-infiltrating lymphocytes are specialized lymphocytes that can detect and kill cancerous cells. Their detection poses many challenges due to significant morphological variations, overlapping occurrence, artifact regions and high-class resemblance between clustered areas and artifacts. In this regard, a Lymphocyte Analysis Framework based on Deep Convolutional neural network (DC-Lym-AF) is proposed to analyze lymphocytes in immunohistochemistry images. The proposed framework comprises (i) pre-processing, (ii) screening phase, (iii) localization phase and (iv) post-processing. In the screening phase, a custom convolutional neural network architecture (lymphocyte dilated network) is developed to screen lymphocytic regions by performing a patch-level classification. This proposed architecture uses dilated convolutions and shortcut connections to capture multi-level variations and ensure reference-based learning. In contrast, the localization phase utilizes an attention-guided multi-scale lymphocyte detector to detect lymphocytes. The proposed detector extracts refined and multi-scale features by exploiting dilated convolutions, attention mechanism and feature pyramid network (FPN) using its custom attention-aware backbone. The proposed DC-Lym-AF shows exemplary performance on the NuClick dataset compared with the existing detection models, with an F-score and precision of 0.84 and 0.83, respectively. We verified the generalizability of our proposed framework by participating in a publically open LYON'19 challenge. Results in terms of detection rate (0.76) and F-score (0.73) suggest that the proposed DC-Lym-AF can effectively detect lymphocytes in immunohistochemistry-stained images collected from different laboratories. In addition, its promising generalization on several datasets implies that it can be turned into a medical diagnostic tool to investigate various histopathological problems. Graphical Abstract.

Efficacy of pentamidine-loaded chitosan nanoparticles as a novel drug delivery system for Leishmania tropica

The present study compares the in vitro effects of nanoparticles loaded pentamidine drug and conventional pentamidine on Leishmania tropica. Herein, pentamidine-loaded chitosan nanoparticles (PTN-CNPs) have been synthesized through an ionic gelation method with sodium tripolyphosphate (TPP). Next, the physical characteristics of PTN-CNPs were determined through the surface texture, zeta potential, in vitro drug release, drug loading content (DLC), and encapsulation efficacy (EE) and compared its efficacy with free pentamidine (PTN) drug against promastigotes and axenic amastigotes forms of L. tropica in vitro. The PTN-CNPs displayed a spherical shape having a size of 88 nm, an almost negative surface charge (-3.09 mV), EE for PTN entrapment of 86%, and in vitro drug release of 92% after 36 h. In vitro antileishmanial activity of PTN-CNPs and free PTN was performed against Leishmania tropica KWH23 promastigote and axenic amastigote using 3-(4, 5- dimethylthiazol-2-yl)-2, 5-diphenyletetrazolium bromide (MTT) assay. It was observed that the effect of PTN-CNPs and free PTN on both forms of the parasite was dose and time dependent. Free PTN presented low efficacy even at higher dose (40 µg/ml) with 25.6 ± 1.3 and 26.5 ±1.4 mean viability rate of the promastigotes and axenic amastigotes, respectively after 72 hrs incubation. While PTN-CNPs showed strong antileishmanial effects on both forms of parasite with 16 ± 0.4 and 19 ± 0.7 mean viability rate at the same higher concentration (40 µg/ml) after 72 hrs incubation. Half maximal inhibitory concentration (IC50) values of PTN-CNPs toward promastigotes and amastigotes were obtained as 0.1375 µg/ml and 0.1910 µg/ml, respectively. In conclusion, PTN-CNPs effectively inhibited both forms of the L. tropica; however, its effect was more salient on promastigotes. This data indicates that the PTN-CNPs act as a target drug delivery system. However, further research is needed to support its efficacy in animal and human CL.

Detection of tumour infiltrating lymphocytes in CD3 and CD8 stained histopathological images using a two-phase deep CNN

BACKGROUND

Immuno-score, a prognostic measure for cancer, employed in determining tumor grade and type, is generated by counting the number of Tumour-Infiltrating Lymphocytes (TILs) in CD3 and CD8 stained histopathological tissue samples. Significant stain variations and heterogeneity in lymphocytes' spatial distribution and density make automated counting of TILs' a challenging task.

METHODS

This work addresses the aforementioned challenges by developing a pipeline "Two-Phase Deep Convolutional Neural Network based Lymphocyte Counter (TDC-LC)" to detect lymphocytes in CD3 and CD8 stained histology images. The proposed pipeline sequentially works by removing hard negative examples (artifacts) in the first phase using a custom CNN "LSATM-Net" that exploits the idea of a split, asymmetric transform, and merge. Whereas, in the second phase, instance segmentation is performed to detect and generate a lymphocyte count against the remaining samples. Furthermore, the effectiveness of the proposed pipeline is measured by comparing it with the state-of-the-art single- and two-stage detectors. The inference code is available at GitHub Repository https://github.com/m-mohsin-zafar/tdc-lc.

RESULTS

The empirical evaluation on samples from LYSTO dataset shows that the proposed LSTAM-Net can learn variations in the images and precisely remove the hard negative stain artifacts with an F-score of 0.74. The detection analysis shows that the proposed TDC-LC outperforms the existing models in identifying and counting lymphocytes with high Recall (0.87) and F-score (0.89). Moreover, the commendable performance of the proposed TDC-LC in different organs suggests a good generalization.

CONCLUSION

The promising performance of the proposed pipeline suggests that it can serve as an automated system for detecting and counting lymphocytes from patches of tissue samples thereby reducing the burden on pathologists.

COVID-19 detection in chest X-ray images using deep boosted hybrid learning

The new emerging COVID-19, declared a pandemic disease, has affected millions of human lives and caused a massive burden on healthcare centers. Therefore, a quick, accurate, and low-cost computer-based tool is required to timely detect and treat COVID-19 patients. In this work, two new deep learning frameworks: Deep Hybrid Learning (DHL) and Deep Boosted Hybrid Learning (DBHL), is proposed for effective COVID-19 detection in X-ray dataset. In the proposed DHL framework, the representation learning ability of the two developed COVID-RENet-1 & 2 models is exploited individually through a machine learning (ML) classifier. In COVID-RENet models, Region and Edge-based operations are carefully applied to learn region homogeneity and extract boundaries features. While in the case of the proposed DBHL framework, COVID-RENet-1 & 2 are fine-tuned using transfer learning on the chest X-rays. Furthermore, deep feature spaces are generated from the penultimate layers of the two models and then concatenated to get a single enriched boosted feature space. A conventional ML classifier exploits the enriched feature space to achieve better COVID-19 detection performance. The proposed COVID-19 detection frameworks are evaluated on radiologist's authenticated chest X-ray data, and their performance is compared with the well-established CNNs. It is observed through experiments that the proposed DBHL framework, which merges the two-deep CNN feature spaces, yields good performance (accuracy: 98.53%, sensitivity: 0.99, F-score: 0.98, and precision: 0.98). Furthermore, a web-based interface is developed, which takes only 5-10s to detect COVID-19 in each unseen chest X-ray image. This web-predictor is expected to help early diagnosis, save precious lives, and thus positively impact society.

Coronavirus disease analysis using chest X-ray images and a novel deep convolutional neural network

Background

The recent emergence of a highly infectious and contagious respiratory viral disease known as COVID-19 has vastly impacted human lives and overloaded the health care system. Therefore, it is crucial to develop a fast and accurate diagnostic system for the timely identification of COVID-19 infected patients and thus to help control its spread.

Methods

This work proposes a new deep CNN based technique for COVID-19 classification in X-ray images. In this regard, two novel custom CNN architectures, namely COVID-RENet-1 and COVID-RENet-2, are developed for COVID-19 specific pneumonia analysis. The proposed technique systematically employs Region and Edge-based operations along with convolution operations. The advantage of the proposed idea is validated by performing series of experimentation and comparing results with two baseline CNNs that exploited either a single type of pooling operation or strided convolution down the architecture. Additionally, the discrimination capacity of the proposed technique is assessed by benchmarking it against the state-of-the-art CNNs on radiologist's authenticated chest X-ray dataset. Implementation is available at https://github.com/PRLAB21/Coronavirus-Disease-Analysis-using-Chest-X-Ray-Images.

Results

The proposed classification technique shows good generalization as compared to existing CNNs by achieving promising MCC (0.96), F-score (0.98) and Accuracy (98%). This suggests that the idea of synergistically using Region and Edge-based operations aid in better exploiting the region homogeneity, textural variations, and region boundary-related information in an image, which helps to capture the pneumonia specific pattern.

Conclusions

The encouraging results of the proposed classification technique on the test set with high sensitivity (0.98) and precision (0.98) suggest the effectiveness of the proposed technique. Thus, it suggests the potential use of the proposed technique in other X-ray imagery-based infectious disease analysis.

Resistant Cytomegalovirus Infection in Solid-organ Transplantation: Single-center Experience, Literature Review of Risk Factors, and Proposed Preventive Strategies

BACKGROUND

Cytomegalovirus (CMV) infection causes morbidity and mortality in solid-organ transplant recipients. Drug-resistant CMV is an emerging problem with poor survival outcomes and limited therapeutic options. In this study we comprehensively address the issue of drug resistance in CMV when compared with standard therapies, such as ganciclovir (GCV) and foscarnet.

METHODS

We conducted a retrospective review of adult patients diagnosed with CMV after solid-organ transplant at our center between 2013 and 2017, and identified 7 resistant CMV cases. To study risk factors in the published literature, we performed an extensive database search.

RESULTS

All patients had documented UL97 mutations, and 3 patients harbored both UL97 and UL54 mutations. For cases with increasing viral load or failure to achieve clinical improvement despite optimal therapy, genetic resistance testing was carried out. Patients received GCV and foscarnet combination therapy. As an adjunct, CMV immunoglobulin, cidofovir, and leflunomide were added. Risk factors, including donor⁺/recipient^- serostatus, persistent high viral replication, prolonged therapeutic GCV exposure (>2.5 months), and allograft rejection, were assessed.

CONCLUSION

Patients at risk, especially those with D⁺/R^- serostatus, should be judiciously monitored for resistance. Prolonged intravenous GCV exposure increases the risk for development of drug resistance. Therefore, precise guidelines are required for prevention of long-term GCV/VGCV exposure. Investigation regarding interferon-gamma release assay and adoptive transfer of T cells in diagnosed CMV patients is warranted to improve future prophylactic and management strategies against CMV, with a potential to reduce the requirement for available toxic antiviral drugs.

Analysis of hepatitis C infection using Raman spectroscopy and proximity based classification in the transformed domain

This work presents a diagnostic system for the hepatitis C infection using Raman spectroscopy and proximity based classification. The proposed method exploits transformed Raman spectra using the proximity based machine learning technique and is denoted as RS-PCA-Prox. First, Raman spectral data is baseline corrected by subtracting noise and low intensity background. After this, a feature transformation of Raman spectra is adopted, not only to reduce the feature's dimensionality but also to learn different deviations in Raman shifts. The proposed RS-PCA-Prox shows significant diagnostic power in terms of accuracy, sensitivity, and specificity as 95%, 0.97 and 0.94 in PCA based transformed domain. The comparison of the RS-PCA-Prox with linear and ensemble based classifiers shows that proximity based classification performs better for the discrimination of HCV infected individuals and is able to differentiate the infected individuals from normal ones on the basis of molecular spectral information. Furthermore, it is observed that characteristic spectral changes are due to variation in the intensity of lectin, chitin, lipids, ammonia and viral protein as a consequence of the HCV infection.

Random Forest-Based Evaluation of Raman Spectroscopy for Dengue Fever Analysis

This work presents the evaluation of Raman spectroscopy using random forest (RF) for the analysis of dengue fever in the infected human sera. A total of 100 dengue suspected blood samples, collected from Holy Family Hospital, Rawalpindi, Pakistan, have been used in this study. Out of these samples, 45 were dengue-positive based on immunoglobulin M (IgM) capture enzyme-linked immunosorbent assay (ELISA) tests. For highlighting the spectral differences between normal and infected samples, an effective machine learning system is developed that automatically learns the pattern of the shift in spectrum for the dengue compared to normal cases and thus is able to predict the unknown class based on the known example. In this connection, dimensionality reduction has been performed with the principal component analysis (PCA), while RF is used for automatic classification of dengue samples. For the determination of diagnostic capabilities of Raman spectroscopy based on RF, sensitivity, specificity, and accuracy have been calculated in comparison to normally performed IgM capture ELISA. According to the experiment, accuracy of 91%, sensitivity of 91%, and specificity of 91% were achieved for the proposed RF-based model.

Renal artery stenosis: clinical picture, frequency, and management

Our review has demonstrated a high prevalence of RAS in the elderly population, particularly the group affected by atherosclerosis, as well as disclosing the potential benefits of early diagnosis, treatments, and the associated morbidity/mortality of each corrective intervention.

The regulatory C proteins from different restriction-modification systems can cross-complement

The BamHI restriction-modification system contains a third gene, bamHIC, which positively regulates bamHIR. Similar small genes from other systems were tested in vivo for their ability to cross-complement. C.BamHI protein was identified, purified, and used to raise polyclonal antibodies. Attempts to detect other C proteins in cell extracts by cross-reactivity with C.BamHI antibodies proved unsuccessful.

Purification and characterization of C.BamHI, a regulator of the BamHI restriction-modification system

The bamHIC gene, controlling the BamHI restriction-modification (R-M) system can functionally be replaced by providing pvuIIC or smaIC in trans. C.BamHI, the protein product encoded by bamHIC, has been purified and shown to bind a 345-bp DNA fragment within the BamHI R-M system.

BseRI a novel restriction endonuclease from a Bacillus species which recognizes the sequence 5'...GAGGAG...3'

Images

A gene required for very short patch repair in Escherichia coli is adjacent to the DNA cytosine methylase gene

Deamination of 5-methylcytosine in DNA results in T/G mismatches. If unrepaired, these mismatches can lead to C-to-T transition mutations. The very short patch (VSP) repair process in Escherichia coli counteracts the mutagenic process by repairing the mismatches in favor of the G-containing strand. Previously we have shown that a plasmid containing an 11-kilobase fragment from the E. coli chromosome can complement a chromosomal mutation defective in both cytosine methylation and VSP repair. We have now mapped the regions essential for the two phenotypes. In the process, we have constructed plasmids that complement the chromosomal mutation for methylation, but not for repair, and vice versa. The genes responsible for these phenotypes have been identified by DNA sequence analysis. The gene essential for cytosine methylation, dcm, is predicted to code for a 473-amino-acid protein and is not required for VSP repair. It is similar to other DNA cytosine methylases and shares extensive sequence similarity with its isoschizomer, EcoRII methylase. The segment of DNA essential for VSP repair contains a gene that should code for a 156-amino-acid protein. This gene, named vsr, is not essential for DNA methylation. Remarkably, the 5' end of this gene appears to overlap the 3' end of dcm. The two genes appear to be transcribed from a common promoter but are in different translational registers. This gene arrangement may assure that Vsr is produced along with Dcm and may minimize the mutagenic effects of cytosine methylation.

Methyl transferases induced during chemical adaptation of M. luteus

Three peaks of methyltransferase activity specific for MNNG alkylated DNA have been identified from extracts of chemically adapted M. luteus. They are designated as TI to TIII in order to their elution from a Sephadex G-75 column. The first one of these peaks has been purified to homogeneity. TI, is an inducible, unusually salt resistant, heat labile protein which corrects O6-methylguanine in alkylated DNA by the transfer of the O6-alkyl group to a cysteine amino acid in the TI protein. There is a stoichiometric relationship between the loss of O6-methylguanine from the DNA and the production of S-methylcysteine. Partially purified TII & TIII proteins show specificity for O4-alkylthymine and methyl phosphotriesters respectively. The mode of repair by the isolated methyltransferases is similar yet there is no competition for substrate specificity. The apparent molecular weights of TI, TII & TIII proteins are 31Kd, 22Kd, and 13Kd respectively.

DNA glycosylase enzymes induced during chemical adaptation of M. luteus

Five peaks of DNA glycosylase activity showing a preference for MNNG alkylated DNA have been identified from extracts of adapted M. luteus. They are numerically designated as GI to GV in order of their decreasing molecular weights. The first two of these peaks have been highly purified. GI, is a constitutive heat labile protein, 35% stimulated by the presence of 50 mM NaCl, acts exclusively on 3 MeA residues in alkylated DNA, 60-70% inhibited by the presence of 2 mM free 3MeA and has been designated as 3MeA DNA glycosylase enzyme. GII, which is an inducible protein, is heat stable, 28% inhibited by the presence of 50 mM NaCl, removes 3MeA, 3MeG, 7MeA & 7MeG with different efficiency, and has been designated as 3,7 methylpurine DNA glycosylase enzyme. The rate of release of 3 methylpurines is 30 times that of 7MeG. There is no activity of either enzyme on O2-MeC, O2-MeT, O4-MeT or O6-MeG. The apparent molecular weights of GI and GII proteins are 28 Kd and 22 Kd respectively.

Cloning and characterization of the dcm locus of Escherichia coli K-12

The dcm locus of Escherichia coli K-12 has been shown to code for a methylase that methylates the second cytosine within the sequence 5'-CC(A/T)GG-3'. This sequence is also recognized by the EcoRII restriction-modification system coded by the E. coli plasmid N3. The methylase within the EcoRII system methylates the same cytosine as the dcm protein. We have isolated, from a library of E. coli K-12 DNA, two overlapping clones that carry the dcm locus. We show that the two clones carry overlapping sequences that are present in a dcm+ strain, but are absent in a delta dcm strain. We also show that the cloned gene codes for a methylase, that it complements mutations in the EcoRII methylase, and that it protects EcoRII recognition sites from cleavage by the EcoRII endonuclease. We found no phage restriction activity associated with the dcm clones.