Edge Artificial Intelligence (AI) for real-time automatic quantification of filariasis in mobile microscopy

Filariasis, a neglected tropical disease caused by roundworms, is a significant public health concern in many tropical countries. Microscopic examination of blood samples can detect and differentiate parasite species, but it is time consuming and requires expert microscopists, a resource that is not always available. In this context, artificial intelligence (AI) can assist in the diagnosis of this disease by automatically detecting and differentiating microfilariae. In line with the target product profile for lymphatic filariasis as defined by the World Health Organization, we developed an edge AI system running on a smartphone whose camera is aligned with the ocular of an optical microscope that detects and differentiates filarias species in real time without the internet connection. Our object detection algorithm that uses the Single-Shot Detection (SSD) MobileNet V2 detection model was developed with 115 cases, 85 cases with 1903 fields of view and 3342 labels for model training, and 30 cases with 484 fields of view and 873 labels for model validation before clinical validation, is able to detect microfilariae at 10x magnification and distinguishes four species of them at 40x magnification: Loa loa, Mansonella perstans, Wuchereria bancrofti, and Brugia malayi. We validated our augmented microscopy system in the clinical environment by replicating the diagnostic workflow encompassed examinations at 10x and 40x with the assistance of the AI models analyzing 18 samples with the AI running on a middle range smartphone. It achieved an overall precision of 94.14%, recall of 91.90% and F1 score of 93.01% for the screening algorithm and 95.46%, 97.81% and 96.62% for the species differentiation algorithm respectively. This innovative solution has the potential to support filariasis diagnosis and monitoring, particularly in resource-limited settings where access to expert technicians and laboratory equipment is scarce.

Digital Microscopy Augmented by Artificial Intelligence to Interpret Bone Marrow Samples for Hematological Diseases

Analysis of bone marrow aspirates (BMAs) is an essential step in the diagnosis of hematological disorders. This analysis is usually performed based on a visual examination of samples under a conventional optical microscope, which involves a labor-intensive process, limited by clinical experience and subject to high observer variability. In this work, we present a comprehensive digital microscopy system that enables BMA analysis for cell type counting and differentiation in an efficient and objective manner. This system not only provides an accessible and simple method to digitize, store, and analyze BMA samples remotely but is also supported by an Artificial Intelligence (AI) pipeline that accelerates the differential cell counting process and reduces interobserver variability. It has been designed to integrate AI algorithms with the daily clinical routine and can be used in any regular hospital workflow.

Marine microdebris pollution in sediments from three environmental coastal areas in the southwestern Argentine Atlantic

Microplastics (MPs) and antifouling paint particles (APPs) are important components of marine microdebris (MDs), which constitute a potential environmental risk. This study analyzed baseline contamination levels of MDs and mesodebris (MesDs) in intertidal sediments at different depths, exploring the geomorphological influence in three Argentine coastal environments: Bahía Blanca Estuary (BBE), Los Pocitos (LP) and Puerto Madryn (PM). The MDs and MesDs samples were characterized by μ-FTIR, SEM/EDX and XRD. The abundance of MPs and APPs in sediments, range between 19.78 and 1087.19 and between 0 and 172.93 items/kg d.w., respectively. Despite variations in population and industrial developments in these areas, MPs abundance shows no significant differences in low and high intertidal zones. However, mean MPs concentrations were higher in the surface layer (0-5 cm) compared to the deeper sediments (5-10 cm), indicating recent MPs deposition. Chemical characterization evidenced the presence of cellulose (CE) and denser polymers as acrylonitrile butadiene styrene (ABS) and polyacrylics (PAN), APPs, metallic and black MDs. Surface degradation and heavy metals (Zn, Cr, and Ba) were also detected in APPs and other MDs, either as additives or adhered to their surfaces. Changes in crystallinity were also observed on the MesDs due to weathering. The calculated polymer hazard index (PHI) and the presence of hazardous polymers such as ABS and PAN indicated an increased risk of MPs pollution on the BBE and PM coasts. The pollution load index (PLI) values (from 4.63 to 5.34) suggested unpolluted to moderately polluted levels. These findings offer insights into potential risks associated with MDs in Argentine intertidal sediments, underscoring the critical need to comprehend the geomorphology and the influence of coastal dynamics. This is crucial for effectively addressing challenges linked to MDs pollution guiding the development of robust management and mitigation strategies.

Evaluation of the Performance of a 3D-Printed Smartphone-Based Retinal Imaging Device as a Screening Tool for Retinal Pathology in Mozambique

Low-income countries carry approximately 90% of the global burden of visual impairment, and up to 80% of this could be prevented or cured. However, there are only a few studies on the prevalence of retinal disease in these countries. Easier access to retinal information would allow differential diagnosis and promote strategies to improve eye health, which are currently scarce. This pilot study aims to evaluate the functionality and usability of a tele-retinography system for the detection of retinal pathology, based on a low-cost portable retinal scanner, manufactured with 3D printing and controlled by a mobile phone with an application designed ad hoc. The study was conducted at the Manhiça Rural Hospital in Mozambique. General practitioners, with no specific knowledge of ophthalmology or previous use of retinography, performed digital retinographies on 104 hospitalized patients. The retinographies were acquired in video format, uploaded to a web platform, and reviewed centrally by two ophthalmologists, analyzing the image quality and the presence of retinal lesions. In our sample there was a high proportion of exudates and hemorrhages-8% and 4%, respectively. In addition, the presence of lesions was studied in patients with known underlying risk factors for retinal disease, such as HIV, diabetes, and/or hypertension. Our tele-retinography system based on a smartphone coupled with a simple and low-cost 3D printed device is easy to use by healthcare personnel without specialized ophthalmological knowledge and could be applied for the screening and initial diagnosis of retinal pathology.

A Smartphone-Based Platform Assisted by Artificial Intelligence for Reading and Reporting Rapid Diagnostic Tests: Evaluation Study in SARS-CoV-2 Lateral Flow Immunoassays

BACKGROUND

Rapid diagnostic tests (RDTs) are being widely used to manage COVID-19 pandemic. However, many results remain unreported or unconfirmed, altering a correct epidemiological surveillance.

OBJECTIVE

Our aim was to evaluate an artificial intelligence-based smartphone app, connected to a cloud web platform, to automatically and objectively read RDT results and assess its impact on COVID-19 pandemic management.

METHODS

Overall, 252 human sera were used to inoculate a total of 1165 RDTs for training and validation purposes. We then conducted two field studies to assess the performance on real-world scenarios by testing 172 antibody RDTs at two nursing homes and 96 antigen RDTs at one hospital emergency department.

RESULTS

Field studies demonstrated high levels of sensitivity (100%) and specificity (94.4%, CI 92.8%-96.1%) for reading IgG band of COVID-19 antibody RDTs compared to visual readings from health workers. Sensitivity of detecting IgM test bands was 100%, and specificity was 95.8% (CI 94.3%-97.3%). All COVID-19 antigen RDTs were correctly read by the app.

CONCLUSIONS

The proposed reading system is automatic, reducing variability and uncertainty associated with RDTs interpretation and can be used to read different RDT brands. The web platform serves as a real-time epidemiological tracking tool and facilitates reporting of positive RDTs to relevant health authorities.

Remote analysis of sputum smears for mycobacterium tuberculosis quantification using digital crowdsourcing

Worldwide, TB is one of the top 10 causes of death and the leading cause from a single infectious agent. Although the development and roll out of Xpert MTB/RIF has recently become a major breakthrough in the field of TB diagnosis, smear microscopy remains the most widely used method for TB diagnosis, especially in low- and middle-income countries. This research tests the feasibility of a crowdsourced approach to tuberculosis image analysis. In particular, we investigated whether anonymous volunteers with no prior experience would be able to count acid-fast bacilli in digitized images of sputum smears by playing an online game. Following this approach 1790 people identified the acid-fast bacilli present in 60 digitized images, the best overall performance was obtained with a specific number of combined analysis from different players and the performance was evaluated with the F1 score, sensitivity and positive predictive value, reaching values of 0.933, 0.968 and 0.91, respectively.

Combining collective and artificial intelligence for global health diseases diagnosis using crowdsourced annotated medical images

Visual inspection of microscopic samples is still the gold standard diagnostic methodology for many global health diseases. Soil-transmitted helminth infection affects 1.5 billion people worldwide, and is the most prevalent disease among the Neglected Tropical Diseases. It is diagnosed by manual examination of stool samples by microscopy, which is a time-consuming task and requires trained personnel and high specialization. Artificial intelligence could automate this task making the diagnosis more accessible. Still, it needs a large amount of annotated training data coming from experts.In this work, we proposed the use of crowdsourced annotated medical images to train AI models (neural networks) for the detection of soil-transmitted helminthiasis in microscopy images from stool samples leveraging non-expert knowledge collected through playing a video game. We collected annotations made by both school-age children and adults, and we showed that, although the quality of crowdsourced annotations made by school-age children are sightly inferior than the ones made by adults, AI models trained on these crowdsourced annotations perform similarly (AUC of 0.928 and 0.939 respectively), and reach similar performance to the AI model trained on expert annotations (AUC of 0.932). We also showed the impact of the training sample size and continuous training on the performance of the AI models.In conclusion, the workflow proposed in this work combined collective and artificial intelligence for detecting soil-transmitted helminthiasis. Embedded within a digital health platform can be applied to any other medical image analysis task and contribute to reduce the burden of disease.

Mobile microscopy and telemedicine platform assisted by deep learning for the quantification of Trichuris trichiura infection

Soil-transmitted helminths (STH) are the most prevalent pathogens among the group of neglected tropical diseases (NTDs). The Kato-Katz technique is the diagnosis method recommended by the World Health Organization (WHO) although it often presents a decreased sensitivity in low transmission settings and it is labour intensive. Visual reading of Kato-Katz preparations requires the samples to be analyzed in a short period of time since its preparation. Digitizing the samples could provide a solution which allows to store the samples in a digital database and perform remote analysis. Artificial intelligence (AI) methods based on digitized samples can support diagnosis by performing an objective and automatic quantification of disease infection. In this work, we propose an end-to-end pipeline for microscopy image digitization and automatic analysis of digitized images of STH. Our solution includes (a) a digitization system based on a mobile app that digitizes microscope samples using a 3D printed microscope adapter, (b) a telemedicine platform for remote analysis and labelling, and (c) novel deep learning algorithms for automatic assessment and quantification of parasitological infections by STH. The deep learning algorithm has been trained and tested on 51 slides of stool samples containing 949 Trichuris spp. eggs from 6 different subjects. The algorithm evaluation was performed using a cross-validation strategy, obtaining a mean precision of 98.44% and a mean recall of 80.94%. The results also proved the potential of generalization capability of the method at identifying different types of helminth eggs. Additionally, the AI-assisted quantification of STH based on digitized samples has been compared to the one performed using conventional microscopy, showing a good agreement between measurements. In conclusion, this work has presented a comprehensive pipeline using smartphone-assisted microscopy. It is integrated with a telemedicine platform for automatic image analysis and quantification of STH infection using AI models.

First study of the Polycladida (Rhabditophora, Platyhelminthes) from the Pacific Coast of Costa Rica

In the present work was carried out in the intertidal zone of Las Baulas de Guanacaste National Marine Park (PNMB) located on the Pacific coast of Costa Rica.                The main objective was to contribute to knowledge about the invertebrate diversity of the park, one of the richest bioregions on the planet, about which little is known. This study assesses the Order Polycladida Lang, 1884, a cornerstone of this ecosystem and one of the most cosmopolitan and plastic invertebrate taxa in the animal kingdom.                In total, 57 individuals were collected in the rocky intertidal zone of Carbón and Langosta beaches. Nine different species were identified, of which four are new for Costa Rica: Semonia bauliensis n. sp.; Cryptostylochus sesei n. sp.; Paraplanocera angeli n. sp., Prostheceraeus fitae n. sp.; and five new records: Paraplanocera oligoglena (Schmarda, 1859); Marcusia ernesti Hyman, 1953; Enchiridium magec Cuadrado, Moro Noreña, 2017; Pseudobiceros bajae (Hyman, 1953); and the genus Boninia spp.

Polyclad phylogeny persists to be problematic

Two conflicting morphological approaches to polyclad systematics highlight the relevance of molecular data for resolving the interrelationships of Polycladida. In the present study, phylogenetic trees were reconstructed based on a short alignment of the 28S rDNA marker gene with 118 polyclad terminals (24 new) including 100 different polyclad species from 44 genera and 22 families, as well as on a combined dataset using 18S and 28S rDNA genes with 27 polyclad terminals (19 new) covering 26 different polyclad species. In both approaches, Theamatidae and Cestoplanidae were included, two families that have previously been shown to switch from Acotylea to Cotylea. Three different alignment methods were used, both with and without alignment curation by Gblocks, and all alignments were subjected to Bayesian inference and maximum likelihood tree calculations. Over all trees of the combined dataset, an extended majority-rule consensus tree had weak support for Theamatidae and Cestoplanidae as acotyleans, and also the cotylean genera Boninia, Chromyella and Pericelis appeared as acotyleans. With the most inclusive short 28S dataset, on the other hand, there is good support for the aforementioned taxa as cotyleans. Especially with the short 28S matrix, taxon sampling, outgroup selection, alignment method and curation, as well as model choice were all decisive for tree topology. Well-supported parts of the phylogeny over all trees include Pseudocerotoidea, Prosthiostomoidea, Stylochoidea, Leptoplanoidea and Cryptoceloidea, the latter three with new definitions. Unstable positions in the tree were found not only for Theamatidae, Cestoplanidae, Boninia, Chromyella and Pericelis, but also for Anonymus, Chromoplana and Cycloporus.

Collaborative intelligence and gamification for on-line malaria species differentiation

Background

Current World Health Organization recommendations for the management of malaria include the need for a parasitological confirmation prior to triggering appropriate treatment. The use of rapid diagnostic tests (RDTs) for malaria has contributed to a better infection recognition and a more targeted treatment. Nevertheless, low-density infections and parasites that fail to produce HRP2 can cause false-negative RDT results. Microscopy has traditionally been the methodology most commonly used to quantify malaria and characterize the infecting species, but the wider use of this technique remains challenging, as it requires trained personnel and processing capacity.

Objective

In this study, the feasibility of an on-line system for remote malaria species identification and differentiation has been investigated by crowdsourcing the analysis of digitalized infected thin blood smears by non-expert observers using a mobile app.

Methods

An on-line videogame in which players learned how to differentiate the young trophozoite stage of the five Plasmodium species has been designed. Images were digitalized with a smartphone camera adapted to the ocular of a conventional light microscope. Images from infected red blood cells were cropped and puzzled into an on-line game. During the game, players had to decide the malaria species (Plasmodium falciparum, Plasmodium malariae, Plasmodium vivax, Plasmodium ovale, Plasmodium knowlesi) of the infected cells that were shown in the screen. After 2 months, each player’s decisions were analysed individually and collectively.

Results

On-line volunteers playing the game made more than 500,000 assessments for species differentiation. Statistically, when the choice of several players was combined (n > 25), they were able to significantly discriminate Plasmodium species, reaching a level of accuracy of 99% for all species combinations, except for P. knowlesi (80%). Non-expert decisions on which Plasmodium species was shown in the screen were made in less than 3 s.

Conclusion

These findings show that it is possible to train malaria-naïve non-experts to identify and differentiate malaria species in digitalized thin blood samples. Although the accuracy of a single player is not perfect, the combination of the responses of multiple casual gamers can achieve an accuracy that is within the range of the diagnostic accuracy made by a trained microscopist.

Electronic supplementary material

The online version of this article (10.1186/s12936-019-2662-9) contains supplementary material, which is available to authorized users.

Plasmodium species differentiation by non-expert on-line volunteers for remote malaria field diagnosis

Background

Routine field diagnosis of malaria is a considerable challenge in rural and low resources endemic areas mainly due to lack of personnel, training and sample processing capacity. In addition, differential diagnosis of Plasmodium species has a high level of misdiagnosis. Real time remote microscopical diagnosis through on-line crowdsourcing platforms could be converted into an agile network to support diagnosis-based treatment and malaria control in low resources areas. This study explores whether accurate Plasmodium species identification—a critical step during the diagnosis protocol in order to choose the appropriate medication—is possible through the information provided by non-trained on-line volunteers.

Methods

88 volunteers have performed a series of questionnaires over 110 images to differentiate species (Plasmodium falciparum, Plasmodium ovale, Plasmodium vivax, Plasmodium malariae, Plasmodium knowlesi) and parasite staging from thin blood smear images digitalized with a smartphone camera adapted to the ocular of a conventional light microscope. Visual cues evaluated in the surveys include texture and colour, parasite shape and red blood size.

Results

On-line volunteers are able to discriminate Plasmodium species (P. falciparum, P. malariae, P. vivax, P. ovale, P. knowlesi) and stages in thin-blood smears according to visual cues observed on digitalized images of parasitized red blood cells. Friendly textual descriptions of the visual cues and specialized malaria terminology is key for volunteers learning and efficiency.

Conclusions

On-line volunteers with short-training are able to differentiate malaria parasite species and parasite stages from digitalized thin smears based on simple visual cues (shape, size, texture and colour). While the accuracy of a single on-line expert is far from perfect, a single parasite classification obtained by combining the opinions of multiple on-line volunteers over the same smear, could improve accuracy and reliability of Plasmodium species identification in remote malaria diagnosis.

Electronic supplementary material

The online version of this article (10.1186/s12936-018-2194-8) contains supplementary material, which is available to authorized users.

Primary blast lung injury at a NATO Role 3 hospital

BACKGROUND

Primary blast lung injury (PBLI) is defined as lung contusion from barotrauma following an explosive mechanism of injury (MOI). Military data have focused on PBLI characteristics following evacuation from the combat theatre; less is known about its immediate management and epidemiology in the deployed setting. We conducted a quality improvement project to describe the prevalence, clinical characteristics, management strategies and evacuation techniques for PBLI patients prior to evacuation.

METHODS

Patients admitted to a Role 3 hospital in southwest, Afghanistan, from January 2008 to March 2013 with a blast MOI were identified through the Department of Defense Trauma Registry; International Classification of Diseases 9 codes and patient record review were used to identify the PBLI cohort from radiology reports. Descriptive statistics and Fishers exact test were used to report findings.

RESULTS

Prevalence of PBLI among blast injured patients with radiology reports was 11.2% (73/648). The population exhibited high Injury Severity Scores median 25 (IQR 14-34) and most received a massive blood transfusion (mean 33.4±38.3 total blood products/24 h). The mean positive end expiratory pressure (PEEP) requirement was 6.2±3.7 (range 5-15) cm H2O and PaO2 to FiO2 ratio was 297±175.2 (66-796) mm Hg. However, 16.6% of patients had a PaO2 to FiO2 ratio <200, 13.3% required PEEP ≥10 cm H2O and one patient required specialised evacuation for respiratory failure. A dismounted MOI (72.8%) and evacuation from point of injury by the Medical Emergency Response Team (62.3%) appeared to be associated with worse lung injury. Only eight of the 73 PBLI patients died and of the five with retrievable records, none died from respiratory failure.

CONCLUSIONS

PBLI has a low prevalence and conventional lung protective ventilator management is generally appropriate immediately after injury; application of advanced modes of ventilation and specialised evacuation assistance may be required. PBLI may be a marker of underlying injury severity since all deaths were not due to respiratory failure. Further work is needed to determine exact MOI in mounted and dismounted casualties.

Post-bariatric panniculectomy: pre-panniculectomy body mass index impacts the complication profile

BACKGROUND

Morbid obesity continues to increase in the United States, which accounts for the increase in bariatric procedures performed. After these patients experience massive weight loss, many are left with a redundant pannus that poses physical limitations and psychosocial disturbances. An increasing proportion of bariatric patients are returning for body-contouring procedures.

METHODS

This is a retrospective cohort study set in a tertiary care center. We evaluated 126 post-bariatric panniculectomies performed over a 3-year period. Perioperative and postoperative data were collected through chart review. Descriptive and inferential analyses were performed using SPSS 11.0.

RESULTS

Ninety-six percent of patients were female. Mean age of the population was 42 (+/-12). The average post-bariatric weight loss and pre-panniculectomy weight were 53 (+/-16) kg and 78 (+/-14) kg, respectively. Complication rates were as follows: seroma 17%, hematoma 13%, surgical site infection (SSI) 17%, transfusion 6%, skin breakdown/necrosis 11%, and re-exploration 11%. Forty percent of patients experienced a complication. Using multivariate logistic regression, we evaluated age, pre-panniculectomy body mass index (BMI), American Society of Anesthesiologists (ASA) class, specimen weight, and operative duration; only pre-panniculectomy BMI was an independent predictor for developing a postoperative complication (odds ratio 3.3, confidence interval 1.2 to 8.4, P < .01).

CONCLUSIONS

Post-bariatric patients who have sustained significant weight loss report subjective improvement after panniculectomy. Even though this population has experienced significant weight loss, they are still at an increased risk for postoperative complications. Maximal reduction in BMI should be stressed to these patients in order to reduce their risk of complications following panniculectomy.

The impact of hypothermia on trauma care at the 31st combat support hospital

BACKGROUND

The primary objective of this study was to review the incidence of hypothermia, and its effect on surgical management, resource utilization, and survival at the 31st Combat Support Hospital (CSH).

METHODS

This study was a retrospective analysis of all combat trauma injuries treated at the 31st CSH over a 12-month period. All trauma admissions were included. Descriptive and inferential analysis were performed using SPSS 11.0 software package (SPSS Inc., Chicago, IL).

RESULTS

A cohort of 2848 patients was identified; 18% were hypothermic (temperature < 36 degrees C). Hypothermia was significantly (P < .05) correlated with admission Glasgow Coma Scale (GCS), tachycardia, hypotension, lower hematocrit, and acidosis. Hypothermic patients had a significantly higher blood product and factor VIIa requirement. Hypothermia was an independent predictor of operative management of injuries, damage control laparotomy, factor VIIa use, and overall mortality (P < .05).

CONCLUSION

Combat trauma patients have a high percentage of penetrating injuries with variable evacuation times. Hypothermia was a pre-hospital physiologic marker, and independent contributor to overall mortality. Prevention of hypothermia could reduce resource utilization and improve survival in the combat setting.

Bradykinin receptor antagonists containing N-substituted amino acids: in vitro and in vivo B(2) and B(1) receptor antagonist activity

We report a systematic probing of the structural requirements of the bradykinin (BK) type 2 (B(2)) receptor for antagonist activity by incorporating N-alkyl-amino acid residues at positions 7 and 8 of a potent antagonist sequence. Compound 1 (D-Arg(0)-Arg(1)-Pro(2)-Hyp(3)-Gly(4)-Thi(5)-Ser(6)-D-Tic(7)-N-Chg (8)-Arg(9), CP-0597)(1,2) is a potent (pA(2) = 9.3, rat uterus; pK(i) = 9.62, binding, human receptor clone) B(2) receptor antagonist devoid of in vitro B(1) antagonist activity (rabbit aorta). Compound 1 exhibits high potency (ED(50) = 29.2 pmol/kg/min, iv, rabbit) and duration of action when tested in models for in vivo B(2) antagonist activity. Although devoid of activity in a classic B(1) isolated tissue assay, B(1) antagonist activity for 1 was demonstrated in vivo, in a LPS-treated, inducible BK(1) receptor rabbit blood pressure model (ED(50) = 1.7 nmol/kg/min). D-Arg(0) of 1 can be formally replaced by an achiral arginine surrogate, without significant loss in antagonist potency on rat uterus (compound 11, B(2) pA(2) = 9.1). Antagonist 13 (Hyp(2), Nchg(8)), pK(i) = 10.2, and agonist 4 (N-methylcyclohexyl-Gly(8)), pK(i) = 10.1, also exhibited substantial binding to guinea pig ileum membrane receptors as well as a human B(2) receptor clone. Very minor structural changes in the N-alkyl amino acid residues in positions 7 and 8 can modify the activity of this class of compounds from being extremely potent antagonists to tight binding partial or full agonists. These studies have resulted in a series of compounds containing inexpensive amino acid residues but which produce broad spectrum BK receptor blocking potency and exceptional in vivo duration of action.