Search

Abstract CRISPR tools can generate knockout and knock-in animal models easily, but the models can contain off-target genomic lesions or random insertions of donor DNAs. Simpler methods to identify off-target lesions and random insertions, using tail or earpiece DNA, are unavailable. We develop CRISPR-KRISPR (CRISPR-Knock-ins and Random Inserts Searching P Rotocol), a method to identify both off-target lesions and random insertions. CRISPR-KRISPR uses as little as 3.4 μg of genomic DNA; thus, it can be easily incorporated as an additional step to genotype founder animals for further breeding.

Abstract Background Alzheimer’s disease (AD) is a progressive neurodegenerative disorder characterized by pathological deposition of misfolded self-protein amyloid beta (Aβ) which in kind facilitates tau aggregation and neurodegeneration. Neuroinflammation is accepted as a key disease driver caused by innate microglia activation. Recently, adaptive immune alterations have been uncovered that begin early and persist throughout the disease. How these occur and whether they can be harnessed to halt disease progress is unclear. We propose that self-antigens would induct autoreactive effector T cells (Teffs) that drive pro-inflammatory and neurodestructive immunity leading to cognitive impairments. Here, we investigated the role of effector immunity and how it could affect cellular-level disease pathobiology in an AD animal model. Methods In this report, we developed and characterized cloned lines of amyloid beta (Aβ) reactive type 1 T helper (Th1) and type 17 Th (Th17) cells to study their role in AD pathogenesis. The cellular phenotype and antigen-specificity of Aβ-specific Th1 and Th17 clones were confirmed using flow cytometry, immunoblot staining and Aβ T cell epitope loaded haplotype-matched major histocompatibility complex II IAb (MHCII-IAb–KLVFFAEDVGSNKGA) tetramer binding. Aβ-Th1 and Aβ-Th17 clones were adoptively transferred into APP/PS1 double-transgenic mice expressing chimeric mouse/human amyloid precursor protein and mutant human presenilin 1, and the mice were assessed for memory impairments. Finally, blood, spleen, lymph nodes and brain were harvested for immunological, biochemical, and histological analyses. Results The propagated Aβ-Th1 and Aβ-Th17 clones were confirmed stable and long-lived. Treatment of APP/PS1 mice with Aβ reactive Teffs accelerated memory impairment and systemic inflammation, increased amyloid burden, elevated microglia activation, and exacerbated neuroinflammation. Both Th1 and Th17 Aβ-reactive Teffs progressed AD pathology by downregulating anti-inflammatory and immunosuppressive regulatory T cells (Tregs) as recorded in the periphery and within the central nervous system. Conclusions These results underscore an important pathological role for CD4+ Teffs in AD progression. We posit that aberrant disease-associated effector T cell immune responses can be controlled. One solution is by Aβ reactive Tregs. Graphical Abstract

The clustered regularly interspersed palindromic repeats (CRISPR) system is a powerful genome-editing tool to modify genomes, virtually in any species. The CRISPR tool has now been utilized in many areas of medical research, including gene therapy. Although several proof-of-concept studies show the feasibility of in vivo gene therapy applications for correcting disease-causing mutations, and new and improved tools are constantly being developed, there are not many choices of suitable reporter models to evaluate genome editor tools and their delivery methods. Here, we developed and validated reporter mouse models containing a single copy of disrupted EGFP (ΔEGFP) via frameshift mutations. We tested several delivery methods for validation of the reporters, and we demonstrated their utility to assess both non-homologous end-joining (NHEJ) and via homology-directed repair (HDR) processes in embryos and in somatic tissues. With the use of the reporters, we also show that hydrodynamic delivery of ribonucleoprotein (RNP) with Streptococcus pyogenes (Sp)Cas9 protein mixed with synthetic guide RNA (gRNA) elicits better genome-editing efficiencies than the plasmid vector-based system in mouse liver. The reporters can also be used for assessing HDR efficiencies of the Acidaminococcus sp. (As)Cas12a nuclease. The results suggest that the ΔEGFP mouse models serve as valuable tools for evaluation of in vivo genome editing.

Molecular diversity of proprioceptive neuron types (Ia, Ib and II PNs) is unclear. Here, the authors characterized the functional organization and development of eight subtypes of PNs in mice. Importantly, Ia subtypes are plastic, suggesting a role in adaptive proprioception during motor behavior.

Mucopolysaccharidosis type I (MPSI) is a lysosomal storage disease caused by insufficient iduronidase (IDUA) activity. Here, the authors use an ex vivo genome editing approach to overexpress IDUA in human hematopoietic stem and progenitor cells and show it can phenotypically correct MSPI in mouse model.

Abstract Background CRISPR-Cas9 gene-editing technology has facilitated the generation of knockout mice, providing an alternative to cumbersome and time-consuming traditional embryonic stem cell-based methods. An earlier study reported up to 16% efficiency in generating conditional knockout (cKO or floxed) alleles by microinjection of 2 single guide RNAs (sgRNA) and 2 single-stranded oligonucleotides as donors (referred herein as “two-donor floxing” method). Results We re-evaluate the two-donor method from a consortium of 20 laboratories across the world. The dataset constitutes 56 genetic loci, 17,887 zygotes, and 1718 live-born mice, of which only 15 (0.87%) mice contain cKO alleles. We subject the dataset to statistical analyses and a machine learning algorithm, which reveals that none of the factors analyzed was predictive for the success of this method. We test some of the newer methods that use one-donor DNA on 18 loci for which the two-donor approach failed to produce cKO alleles. We find that the one-donor methods are 10- to 20-fold more efficient than the two-donor approach. Conclusion We propose that the two-donor method lacks efficiency because it relies on two simultaneous recombination events in cis, an outcome that is dwarfed by pervasive accompanying undesired editing events. The methods that use one-donor DNA are fairly efficient as they rely on only one recombination event, and the probability of correct insertion of the donor cassette without unanticipated mutational events is much higher. Therefore, one-donor methods offer higher efficiencies for the routine generation of cKO animal models.

Abstract Background The use of immunodeficient mice transplanted with human hematopoietic stem cells is an accepted approach to study human-specific infectious diseases such as HIV-1 and to investigate multiple aspects of human immune system development. However, mouse and human are different in sialylation patterns of proteins due to evolutionary mutations of the CMP-N-acetylneuraminic acid hydroxylase (CMAH) gene that prevent formation of N-glycolylneuraminic acid from N-acetylneuraminic acid. How changes in the mouse glycoproteins’ chemistry affect phenotype and function of transplanted human hematopoietic stem cells and mature human immune cells in the course of HIV-1 infection are not known. Results We mutated mouse CMAH in the NOD/scid-IL2Rγc −/− (NSG) mouse strain, which is widely used for the transplantation of human cells, using the CRISPR/Cas9 system. The new strain provides a better environment for human immune cells. Transplantation of human hematopoietic stem cells leads to broad B cells repertoire, higher sensitivity to HIV-1 infection, and enhanced proliferation of transplanted peripheral blood lymphocytes. The mice showed no effect on the clearance of human immunoglobulins and enhanced transduction efficiency of recombinant adeno-associated viral vector rAAV2/DJ8. Conclusion NSG-cmah −/− mice expand the mouse models suitable for human cells transplantation, and this new model has advantages in generating a human B cell repertoire. This strain is suitable to study different aspects of the human immune system development, provide advantages in patient-derived tissue and cell transplantation, and could allow studies of viral vectors and infectious agents that are sensitive to human-like sialylation of mouse glycoproteins.

Background: We reviewed our experience with ruptured sinus of Valsalva aneurysms (RSOV) to determine a correlation with preexisting heart failure (HF) and coexisting cardiac lesions (aortic regurgitation [AR] and ventricular septal defect [VSD]) to postoperative left ventricular (LV) dysfunction and postoperative outcomes. Materials and Methods: Retrospective review of RSOV cases over 15 years showed that RSOV repair was done in 87 patients. We looked for patients who presented with HF and patients having AR and/or VSDs. Statistical analysis was done to see if the coexisting lesions and preoperative HF were associated with postoperative LV dysfunction. Chi-square test was used on contingency table for statistical analysis. Complications in the postoperative period and prolonged Intensive Care Unit stay were noted. Results: 17% (15/87) presented with HF. Fifty-two patients had moderate to severe AR and 50 patients had VSD. Seventeen patients had postoperative LV dysfunction. The correlation of preoperative HF and coexisting lesions with postoperative LV dysfunction was not statistically significant. Two patients underwent redo surgery for residual RSOV and AR. Two patients had arrhythmias. One patient had cerebrovascular accident. No mortality was seen in the study. Conclusion: Preoperative HF and the presence of VSD and/or AR have no statistical significant correlation with postoperative LV dysfunction. As the outcome of RSOV repair is good, all patients need to undergo early repair to avoid complications.

Lymphangiomas are relatively uncommon lesions of the lymphatic channels which can arise in virtually any part of the body. Although the most common site is the head/neck region, they could be found in the mediastinum. If mediastinal lymphangiomas are said to be rare, the thymic subentity is even scanty. We describe one case of mediastinal lymphangioma with a true intrathymic localization, which to our knowledge has been reported just once in the literature. This case report elucidates the surgical management of the first lymphangioma reported in an infant.

Abstract We present a robust method called improved-Genome editing via Oviductal Nucleic Acids Delivery (i-GONAD) that delivers CRISPR ribonucleoproteins to E0.7 embryos via in situ electroporation. The method generates mouse models containing single-base changes, kilobase-sized deletions, and knock-ins. The efficiency of i-GONAD is comparable to that of traditional microinjection methods, which rely on ex vivo handling of zygotes and require recipient animals for embryo transfer. In contrast, i-GONAD avoids these technically difficult steps, and it can be performed at any laboratory with simple equipment and technical expertise. Further, i-GONAD-treated females retain reproductive function, suggesting future use of the method for germline gene therapy.

Abstract Background Conditional knockout mice and transgenic mice expressing recombinases, reporters, and inducible transcriptional activators are key for many genetic studies and comprise over 90% of mouse models created. Conditional knockout mice are generated using labor-intensive methods of homologous recombination in embryonic stem cells and are available for only ~25% of all mouse genes. Transgenic mice generated by random genomic insertion approaches pose problems of unreliable expression, and thus there is a need for targeted-insertion models. Although CRISPR-based strategies were reported to create conditional and targeted-insertion alleles via one-step delivery of targeting components directly to zygotes, these strategies are quite inefficient. Results Here we describe Easi-CRISPR (Efficient additions with ssDNA inserts-CRISPR), a targeting strategy in which long single-stranded DNA donors are injected with pre-assembled crRNA + tracrRNA + Cas9 ribonucleoprotein (ctRNP) complexes into mouse zygotes. We show for over a dozen loci that Easi-CRISPR generates correctly targeted conditional and insertion alleles in 8.5–100% of the resulting live offspring. Conclusions Easi-CRISPR solves the major problem of animal genome engineering, namely the inefficiency of targeted DNA cassette insertion. The approach is robust, succeeding for all tested loci. It is versatile, generating both conditional and targeted insertion alleles. Finally, it is highly efficient, as treating an average of only 50 zygotes is sufficient to produce a correctly targeted allele in up to 100% of live offspring. Thus, Easi-CRISPR offers a comprehensive means of building large-scale Cre-LoxP animal resources.

To encode light-dependent changes in membrane potential, rod and cone photoreceptors utilize synaptic ribbons to sustain continuous exocytosis while making rapid, fine adjustments to release rate. Release kinetics are shaped by vesicle delivery down ribbons and by properties of exocytotic Ca2+ sensors. We tested the role for synaptotagmin-1 (Syt1) in photoreceptor exocytosis by using novel mouse lines in which Syt1 was conditionally removed from rods or cones. Photoreceptors lacking Syt1 exhibited marked reductions in exocytosis as measured by electroretinography and single-cell recordings. Syt1 mediated all evoked release in cones, whereas rods appeared capable of some slow Syt1-independent release. Spontaneous release frequency was unchanged in cones but increased in rods lacking Syt1. Loss of Syt1 did not alter synaptic anatomy or reduce Ca2+ currents. These results suggest that Syt1 mediates both phasic and tonic release at photoreceptor synapses, revealing unexpected flexibility in the ability of Syt1 to regulate Ca2+-dependent synaptic transmission.

Over the past decade, new methods and procedures have been developed to generate genetically engineered mouse models of human disease. This At a Glance article highlights several recent technical advances in mouse genome manipulation that have transformed our ability to manipulate and study gene expression in the mouse. We discuss how conventional gene targeting by homologous recombination in embryonic stem cells has given way to more refined methods that enable allele-specific manipulation in zygotes. We also highlight advances in the use of programmable endonucleases that have greatly increased the feasibility and ease of editing the mouse genome. Together, these and other technologies provide researchers with the molecular tools to functionally annotate the mouse genome with greater fidelity and specificity, as well as to generate new mouse models using faster, simpler and less costly techniques.

Aorto-left ventricular tunnel (ALVT) is a rare congenital anomaly with extracardiac channel connecting ascending aorta to the ventricle. It presents early in life due to congestive cardiac failure. We present a case of ALVT with unusual morphology in an 11-year-old male child with palpitations and dyspnea. We also describe the transesophageal echocardiography evaluation of ALVT.

Targeted transgenic mouse models, where an exogenous gene is inserted into a specified genomic locus to achieve its stable and reliable expression, have been widely used in biomedical research. However, the available methodologies for targeted insertion of sequences require many laborious steps that involve the use of embryonic stem (ES) cells. We recently developed Pronuclear Injection‐based Targeted Transgenesis (PITT), a method that uses a recombinase‐mediated cassette exchange (RMCE) to enable insertion of sequences at a predetermined genomic locus, such asROSA26. The PITT technique uses fertilized eggs (instead of ES cells) collected from ‘seed mice’ that contain the RMCE landing pad. The PITT method can rapidly generate reliable targeted transgenic mice; it requires a seed mouse, which in our previous study was generated using ES cell targeting approaches. Here, we demonstrate that seed mice containing the RMCE landing pad can be developed rapidly by using the CRISPR/Cas9 system. One of the CRISPR targets tested in this study enabled the insertion of sequences precisely at the originalROSA26 provirus integration site. We anticipate that using a similar approach, PITT landing pad sequences can be rapidly and precisely inserted at other genomic loci to develop an array of PITT tools. This two‐step strategy combines the best features of the two newer technologies—rapid creation of PITT landing pads using the CRISPR/Cas9 system and efficient and precise insertion of larger cassettes at the landing pads using PITT. This study also revealed that anomalous and mosaic sequence insertions can occur with the CRISPR/Cas9 system.

Cysteine-rich receptor-like kinases (CRKs) are transmembrane proteins characterized by the presence of two domains of unknown function 26 (DUF26) in their ectodomain. The CRKs form one of the largest groups of receptor-like protein kinases in plants, but their biological functions have so far remained largely uncharacterized. We conducted a large-scale phenotyping approach of a nearly complete crk T-DNA insertion line collection showing that CRKs control important aspects of plant development and stress adaptation in response to biotic and abiotic stimuli in a non-redundant fashion. In particular, the analysis of reactive oxygen species (ROS)-related stress responses, such as regulation of the stomatal aperture, suggests that CRKs participate in ROS/redox signalling and sensing. CRKs play general and fine-tuning roles in the regulation of stomatal closure induced by microbial and abiotic cues. Despite their great number and high similarity, large-scale phenotyping identified specific functions in diverse processes for many CRKs and indicated that CRK2 and CRK5 play predominant roles in growth regulation and stress adaptation, respectively. As a whole, the CRKs contribute to specificity in ROS signalling. Individual CRKs control distinct responses in an antagonistic fashion suggesting future potential for using CRKs in genetic approaches to improve plant performance and stress tolerance.

Cardio circulatory changes associated with pregnancy result in a significant haemodynamic burden and lead to morbidity and even mortality in women with cardiac disease. We report a rare case of severe pulmonary stenosis who underwent elective caesarean section under general anaesthesia with satisfactory maternal and neonatal outcome.

Retinoblastoma 1 (Rb1) is an essential gene regulating cellular proliferation, differentiation, and homeostasis. To exert these functions, Rb1 is recruited and physically interacts with a growing variety of signaling pathways. While Rb1 does not appear to be ubiquitously expressed, its expression has been confirmed in a variety of hematopoietic and neuronal-derived cells, including the inner ear hair cells (HCs). Studies in transgenic mice demonstrate that complete germline or conditional Rb1 deletion leads to abnormal cell proliferation, followed by massive apoptosis; making it difficult to fully address Rb1’s biochemical activities. To overcome these limitations, we developed a tetracycline-inducible TetO-CB-myc6-Rb1 (CBRb) mouse model to achieve transient and inducible dominant negative (DN) inhibition of the endogenous RB1 protein. Our strategy involved fusing the Rb1 gene to the lysosomal protease pre-procathepsin B (CB), thus allowing for further routing of the DN-CBRb fusion protein and its interacting complexes for proteolytic degradation. Moreover, reversibility of the system is achieved upon suppression of doxycycline (Dox) administration. Preliminary characterization of DN-CBRb mice bred to a ubiquitous rtTA mouse line demonstrated a significant inhibition of the endogenous RB1 protein in the inner ear and in a number of other organs where RB1 is expressed. Examination of the postnatal (P) DN-CBRb mice inner ear at P10 and P28 showed the presence of supernumerary inner HCs in the lower turns of the cochleae, which corresponds to the described expression domain of the endogenous Rb1 gene. Selective and reversible suppression of gene expression is both an experimental tool for defining function and a potential means to medical therapy. Given the limitations associated with Rb1-null mice lethality, this model provides a valuable resource for understanding RB1 activity, relative contribution to HC regeneration and its potential therapeutic application.

RNAi-based strategies have been used for hypomorphic analyses. However, there are technical challenges to achieve robust, reproducible knockdown effect. Here we examined the artificial microRNA (amiRNA) architectures that could provide higher knockdown efficiencies. Using transient and stable transfection assays in cells, we found that simple amiRNA-expression cassettes, that did not contain a marker gene (-MG), displayed higher amiRNA expression and more efficient knockdown than those that contained a marker gene (+MG). Further, we tested this phenomenon in vivo, by analyzing amiRNA-expressing mice that were produced by the pronuclear injection-based targeted transgenesis (PITT) method. While we observed significant silencing of the target gene (eGFP) in +MG hemizygous mice, obtaining -MG amiRNA expression mice, even hemizygotes, was difficult and the animals died perinatally. We obtained only mosaic mice having both "-MG amiRNA" cells and "amiRNA low-expression" cells but they exhibited growth retardation and cataracts, and they could not transmit the -MG amiRNA allele to the next generation. Furthermore, +MG amiRNA homozygotes could not be obtained. These results suggested that excessive amiRNAs transcribed by -MG expression cassettes cause deleterious effects in mice, and the amiRNA expression level in hemizygous +MG amiRNA mice is near the upper limit, where mice can develop normally. In conclusion, the PITT-(+MG amiRNA) system demonstrated here can generate knockdown mouse models that reliably express highest and tolerable levels of amiRNAs.

Marker assisted speed congenics technique is commonly used to facilitate backcrossing of mouse strains in nearly half the time it normally takes otherwise. Traditionally, the technique is performed by analyzing PCR amplified regions of simple sequence length polymorphism (SSLP) markers between the recipient and donor strains: offspring with the highest number of markers showing the recipient genome across all chromosomes is chosen for the next generation. Although there are well-defined panels of SSLP makers established between certain pairs of mice strains, they are incomplete for most strains. The availability of well-established marker sets for speed congenic screens would enable the scientific community to transfer mutations across strain backgrounds. In this study, we tested the suitability of over 400 SSLP marker sets among 10 mouse strains commonly used for generating genetically engineered models. The panel of markers presented here can readily identify the specified strains and will be quite useful in marker assisted speed congenic screens. Moreover, unlike newer single nucleotide polymorphism (SNP) array methods which require sophisticated equipment, the SSLP markers panel described here only uses PCR and agarose gel electrophoresis of amplified products; therefore it can be performed in most research laboratories.

Reprogramming somatic cells to a pluripotent state by nucleic acid based (NAB) approaches, involving the ectopic expression of transcription factors, has emerged as a standard method. We recently demonstrated that limbal progenitors that regenerate cornea are reprogrammable to pluripotency by a non-NAB approach through simple manipulation of microenvironment thus extending the possible therapeutic use of these readily accessible cells beyond the proven treatment of corneal diseases and injury. Therefore, to determine the validity and robustness of non-cell autonomous reprogramming of limbal progenitors for a wider clinical use, here, we have compared their reprogramming by non-NAB and NAB approaches. We observed that both approaches led to (1) the emergence of colonies displaying pluripotency markers, accompanied by a temporal reciprocal changes in limbal-specific and pluripotency gene expression, and (2) epigenetic alterations of Oct4 and Nanog, associated with the de-novo activation of their expression. While the efficiency of reprogramming and passaging of re-programmed cells were significantly better with the NAB approach, the non-NAB approach, in contrast, led to a regulated reprogramming of gene expression, and a significant decrease in the expression of Hormad1, a gene associated with immunogenic responses. The reprogramming efficiency by non-NAB approach was influenced by exosomes present in conditioned medium. Cells reprogrammed by both approaches were capable of differentiating along the three germ lineages and generating chimeras. The analysis suggests that both approaches are effective in reprogramming limbal progenitors but the non-NAB approach may be more suitable for potential clinical applications by averting the risk of insertional mutagenesis and immune responses associated with the NAB approach.

Eps15 Homology Domain-containing 3 (EHD3), a member of the EHD protein family that regulates endocytic recycling, is the first protein reported to be specifically expressed in the glomerular endothelium in the kidney; therefore we generated Ehd3(-/-) mice and assessed renal development and pathology. Ehd3(-/-) animals showed no overt defects, and exhibited no proteinuria or glomerular pathology. However, as the expression of EHD4, a related family member, was elevated in the glomerular endothelium of Ehd3(-/-) mice and suggested functional compensation, we generated and analyzed Ehd3(-/-); Ehd4(-/-) mice. These mice were smaller, possessed smaller and paler kidneys, were proteinuric and died between 3-24 weeks of age. Detailed analyses of Ehd3(-/-); Ehd4(-/-) kidneys demonstrated thrombotic microangiopathy (TMA)-like glomerular lesions including thickening and duplication of glomerular basement membrane, endothelial swelling and loss of fenestrations. Other changes included segmental podocyte foot process effacement, mesangial interposition, and abnormal podocytic and mesangial marker expression. The glomerular lesions observed were strikingly similar to those seen in human pre-eclampsia and mouse models of reduced VEGF expression. As altered glomerular endothelial VEGFR2 expression and localization and increased apoptosis was observed in the absence of EHD3 and EHD4, we propose that EHD-mediated endocytic traffic of key surface receptors such as VEGFR2 is essential for physiological control of glomerular function. Furthermore, Ehd3(-/-); Ehd4(-/-) mice provide a unique model to elucidate mechanisms of glomerular endothelial injury which is observed in a wide variety of human renal and extra-renal diseases.

Pure red cell disorder is an uncommon disorder in which maturation arrest occurs in the maturation of erythrocytes. Erythroblats are virtually absent in the bone marrow. Surgery poses a very high-risk for these patients because of the several complications that can occur in the perioperative period. In this case report, we report a pregnant patient with a pure red cell aplasia who was optimized pre-operatively and underwent cesarean section under sub-arachnoid block.

Human Activity Recognition (HAR) has gained significant attention due to its broad range of applications, such as healthcare, industrial work safety, activity assistance, and driver monitoring. Most prior HAR systems are based on recorded sensor data (i.e., past information) recognizing human activities. In fact, HAR works based on future sensor data to predict human activities are rare. Human Activity Prediction (HAP) can benefit in multiple applications, such as fall detection or exercise routines, to prevent injuries. This work presents a novel HAP system based on forecasted activity data of Inertial Measurement Units (IMU). Our HAP system consists of a deep learning forecaster of IMU activity signals and a deep learning classifier to recognize future activities. Our deep learning forecaster model is based on a Sequence-to-Sequence structure with attention and positional encoding layers. Then, a pre-trained deep learning Bi-LSTM classifier is used to classify future activities based on the forecasted IMU data. We have tested our HAP system for five daily activities with two tri-axial IMU sensors. The forecasted signals show an average correlation of 91.6% to the actual measured signals of the five activities. The proposed HAP system achieves an average accuracy of 97.96% in predicting future activities.

A new artificial intelligence-based approach is proposed by developing a deep learning (DL) model for identifying the people who violate the face mask protocol in public places. To achieve this goal, a private dataset was created, including different face images with and without masks. The proposed model was trained to detect face masks from real-time surveillance videos. The proposed face mask detection (FMDNet) model achieved a promising detection of 99.0% in terms of accuracy for identifying violations (no face mask) in public places. The model presented a better detection capability compared to other recent DL models such as FSA-Net, MobileNet V2, and ResNet by 24.03%, 5.0%, and 24.10%, respectively. Meanwhile, the model is lightweight and had a confidence score of 99.0% in a resource-constrained environment. The model can perform the detection task in real-time environments at 41.72 frames per second (FPS). Thus, the developed model can be applicable and useful for governments to maintain the rules of the SOP protocol.

Melanoma, a kind of skin cancer that is very risky, is distinguished by uncontrolled cell multiplication. Melanoma detection is of the utmost significance in clinical practice because of the atypical border structure and the numerous types of tissue it can involve. The identification of melanoma is still a challenging process for color images, despite the fact that numerous approaches have been proposed in the research that has been done. In this research, we present a comprehensive system for the efficient and precise classification of skin lesions. The framework includes preprocessing, segmentation, feature extraction, and classification modules. Preprocessing with DullRazor eliminates skin-imaging hair artifacts. Next, Fully Connected Neural Network (FCNN) semantic segmentation extracts precise and obvious Regions of Interest (ROIs). We then extract relevant skin image features from ROIs using an enhanced Sobel Directional Pattern (SDP). For skin image analysis, Sobel Directional Pattern outperforms ABCD. Finally, a stacked Restricted Boltzmann Machine (RBM) classifies skin ROIs. Stacked RBMs accurately classify skin melanoma. The experiments have been conducted on five datasets: Pedro Hispano Hospital (PH2), International Skin Imaging Collaboration (ISIC 2016), ISIC 2017, Dermnet, and DermIS, and achieved an accuracy of 99.8%, 96.5%, 95.5%, 87.9%, and 97.6%, respectively. The results show that a stack of Restricted Boltzmann Machines is superior for categorizing skin cancer types using the proposed innovative SDP.

Malaria is predominant in many subtropical nations with little health-monitoring infrastructure. To forecast malaria and condense the disease’s impact on the population, time series prediction models are necessary. The conventional technique of detecting malaria disease is for certified technicians to examine blood smears visually for parasite-infected RBC (red blood cells) underneath a microscope. This procedure is ineffective, and the diagnosis depends on the individual performing the test and his/her experience. Automatic image identification systems based on machine learning have previously been used to diagnose malaria blood smears. However, so far, the practical performance has been insufficient. In this paper, we have made a performance analysis of deep learning algorithms in the diagnosis of malaria disease. We have used Neural Network models like CNN, MobileNetV2, and ResNet50 to perform this analysis. The dataset was extracted from the National Institutes of Health (NIH) website and consisted of 27,558 photos, including 13,780 parasitized cell images and 13,778 uninfected cell images. In conclusion, the MobileNetV2 model outperformed by achieving an accuracy rate of 97.06% for better disease detection. Also, other metrics like training and testing loss, precision, recall, fi-score, and ROC curve were calculated to validate the considered models.

Dexterous object manipulation using anthropomorphic robot hands is of great interest for natural object manipulations across the areas of healthcare, smart homes, and smart factories. Deep reinforcement learning (DRL) is a particularly promising approach to solving dexterous manipulation tasks with five-fingered robot hands. Yet, controlling an anthropomorphic robot hand via DRL in order to obtain natural, human-like object manipulation with high dexterity remains a challenging task in the current robotic field. Previous studies have utilized some predefined human hand poses to control the robot hand’s movements for successful object-grasping. However, the hand poses derived from these grasping taxonomies are limited to a partial range of adaptability that could be performed by the robot hand. In this work, we propose a combinatory approach of a deep transformer network which produces a wider range of natural hand poses to configure the robot hand’s movements, and an adaptive DRL to control the movements of an anthropomorphic robot hand according to these natural hand poses. The transformer network learns and infers the natural robot hand poses according to the object affordance. Then, DRL trains a policy using the transformer output to grasp and relocate the object to the designated target location. Our proposed transformer-based DRL (T-DRL) has been tested using various objects, such as an apple, a banana, a light bulb, a camera, a hammer, and a bottle. Additionally, its performance is compared with a baseline DRL model via natural policy gradient (NPG). The results demonstrate that our T-DRL achieved an average manipulation success rate of 90.1% for object manipulation and outperformed NPG by 24.8%.

Blood cells carry important information that can be used to represent a person’s current state of health. The identification of different types of blood cells in a timely and precise manner is essential to cutting the infection risks that people face on a daily basis. The BCNet is an artificial intelligence (AI)-based deep learning (DL) framework that was proposed based on the capability of transfer learning with a convolutional neural network to rapidly and automatically identify the blood cells in an eight-class identification scenario: Basophil, Eosinophil, Erythroblast, Immature Granulocytes, Lymphocyte, Monocyte, Neutrophil, and Platelet. For the purpose of establishing the dependability and viability of BCNet, exhaustive experiments consisting of five-fold cross-validation tests are carried out. Using the transfer learning strategy, we conducted in-depth comprehensive experiments on the proposed BCNet’s architecture and test it with three optimizers of ADAM, RMSprop (RMSP), and stochastic gradient descent (SGD). Meanwhile, the performance of the proposed BCNet is directly compared using the same dataset with the state-of-the-art deep learning models of DensNet, ResNet, Inception, and MobileNet. When employing the different optimizers, the BCNet framework demonstrated better classification performance with ADAM and RMSP optimizers. The best evaluation performance was achieved using the RMSP optimizer in terms of 98.51% accuracy and 96.24% F1-score. Compared with the baseline model, the BCNet clearly improved the prediction accuracy performance 1.94%, 3.33%, and 1.65% using the optimizers of ADAM, RMSP, and SGD, respectively. The proposed BCNet model outperformed the AI models of DenseNet, ResNet, Inception, and MobileNet in terms of the testing time of a single blood cell image by 10.98, 4.26, 2.03, and 0.21 msec. In comparison to the most recent deep learning models, the BCNet model could be able to generate encouraging outcomes. It is essential for the advancement of healthcare facilities to have such a recognition rate improving the detection performance of the blood cells.