Automated Interpretation of Blood Culture Gram Stains by Use of a Deep Convolutional Neural Network

Application of image recognition technology in pathological diagnosis of blood smears

Traditional manual blood smear diagnosis methods are time-consuming and prone to errors, often relying heavily on the experience of clinical laboratory analysts for accuracy. As breakthroughs in key technologies such as neural networks and deep learning continue to drive digital transformation in the medical field, image recognition technology is increasingly being leveraged to enhance existing medical processes. In recent years, advancements in computer technology have led to improved efficiency in the identification of blood cells in blood smears through the use of image recognition technology. This paper provides a comprehensive summary of the methods and steps involved in utilizing image recognition algorithms for diagnosing diseases in blood smears, with a focus on malaria and leukemia. Furthermore, it offers a forward-looking research direction for the development of a comprehensive blood cell pathological detection system.

Capabilities of GPT-4o and Gemini 1.5 Pro in Gram stain and bacterial shape identification

Aim: Assessing the visual accuracy of two large language models (LLMs) in microbial classification.Materials & methods: GPT-4o and Gemini 1.5 Pro were evaluated in distinguishing Gram-positive from Gram-negative bacteria and classifying them as cocci or bacilli using 80 Gram stain images from a labeled database.Results: GPT-4o achieved 100% accuracy in identifying simultaneously Gram stain and shape for Clostridium perfringens, Pseudomonas aeruginosa and Staphylococcus aureus. Gemini 1.5 Pro showed more variability for similar bacteria (45, 100 and 95%, respectively). Both LLMs failed to identify both Gram stain and bacterial shape for Neisseria gonorrhoeae. Cumulative accuracy plots indicated that GPT-4o consistently performed equally or better in every identification, except for Neisseria gonorrhoeae's shape.Conclusion: These results suggest that these LLMs in their unprimed state are not ready to be implemented in clinical practice and highlight the need for more research with larger datasets to improve LLMs' effectiveness in clinical microbiology.

A Clinical Bacterial Dataset for Deep Learning in Microbiological Rapid On-Site Evaluation

Microbiological Rapid On-Site Evaluation (M-ROSE) is based on smear staining and microscopic observation, providing critical references for the diagnosis and treatment of pulmonary infectious disease. Automatic identification of pathogens is the key to improving the quality and speed of M-ROSE. Recent advancements in deep learning have yielded numerous identification algorithms and datasets. However, most studies focus on artificially cultured bacteria and lack clinical data and algorithms. Therefore, we collected Gram-stained bacteria images from lower respiratory tract specimens of patients with lung infections in Chinese PLA General Hospital obtained by M-ROSE from 2018 to 2022 and desensitized images to produce 1705 images (4,912 × 3,684 pixels). A total of 4,833 cocci and 6,991 bacilli were manually labelled and differentiated into negative and positive. In addition, we applied the detection and segmentation networks for benchmark testing. Data and benchmark algorithms we provided that may benefit the study of automated bacterial identification in clinical specimens.

The Impact of Artificial Intelligence on Microbial Diagnosis

Traditional microbial diagnostic methods face many obstacles such as sample handling, culture difficulties, misidentification, and delays in determining susceptibility. The advent of artificial intelligence (AI) has markedly transformed microbial diagnostics with rapid and precise analyses. Nonetheless, ethical considerations accompany AI adoption, necessitating measures to uphold patient privacy, mitigate biases, and ensure data integrity. This review examines conventional diagnostic hurdles, stressing the significance of standardized procedures in sample processing. It underscores AI's significant impact, particularly through machine learning (ML), in microbial diagnostics. Recent progressions in AI, particularly ML methodologies, are explored, showcasing their influence on microbial categorization, comprehension of microorganism interactions, and augmentation of microscopy capabilities. This review furnishes a comprehensive evaluation of AI's utility in microbial diagnostics, addressing both advantages and challenges. A few case studies including SARS-CoV-2, malaria, and mycobacteria serve to illustrate AI's potential for swift and precise diagnosis. Utilization of convolutional neural networks (CNNs) in digital pathology, automated bacterial classification, and colony counting further underscores AI's versatility. Additionally, AI improves antimicrobial susceptibility assessment and contributes to disease surveillance, outbreak forecasting, and real-time monitoring. Despite a few limitations, integration of AI in diagnostic microbiology presents robust solutions, user-friendly algorithms, and comprehensive training, promising paradigm-shifting advancements in healthcare.

Performance evaluation of machine-assisted interpretation of Gram stains from positive blood cultures

Manual microscopy of Gram stains from positive blood cultures (PBCs) is crucial for diagnosing bloodstream infections but remains labor intensive, time consuming, and subjective. This study aimed to evaluate a scan and analysis system that combines fully automated digital microscopy with deep convolutional neural networks (CNNs) to assist the interpretation of Gram stains from PBCs for routine laboratory use. The CNN was trained to classify images of Gram stains based on staining and morphology into seven different classes: background/false-positive, Gram-positive cocci in clusters (GPCCL), Gram-positive cocci in pairs (GPCP), Gram-positive cocci in chains (GPCC), rod-shaped bacilli (RSB), yeasts, and polymicrobial specimens. A total of 1,555 Gram-stained slides of PBCs were scanned, pre-classified, and reviewed by medical professionals. The results of assisted Gram stain interpretation were compared to those of manual microscopy and cultural species identification by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS). The comparison of assisted Gram stain interpretation and manual microscopy yielded positive/negative percent agreement values of 95.8%/98.0% (GPCCL), 87.6%/99.3% (GPCP/GPCC), 97.4%/97.8% (RSB), 83.3%/99.3% (yeasts), and 87.0%/98.5% (negative/false positive). The assisted Gram stain interpretation, when compared to MALDI-TOF MS species identification, also yielded similar results. During the analytical performance study, assisted interpretation showed excellent reproducibility and repeatability. Any microorganism in PBCs should be detectable at the determined limit of detection of 105 CFU/mL. Although the CNN-based interpretation of Gram stains from PBCs is not yet ready for clinical implementation, it has potential for future integration and advancement.

Retrospective validation of MetaSystems' deep-learning-based digital microscopy platform with assistance compared to manual fluorescence microscopy for detection of mycobacteria

This study aimed to validate Metasystems' automated acid-fast bacilli (AFB) smear microscopy scanning and deep-learning-based image analysis module (Neon Metafer) with assistance on respiratory and pleural samples, compared to conventional manual fluorescence microscopy (MM). Analytical parameters were assessed first, followed by a retrospective validation study. In all, 320 archived auramine-O-stained slides selected non-consecutively [85 originally reported as AFB-smear-positive, 235 AFB-smear-negative slides; with an overall mycobacterial culture positivity rate of 24.1% (77/320)] underwent whole-slide imaging and were analyzed by the Metafer Neon AFB Module (version 4.3.130) using a predetermined probability threshold (PT) for AFB detection of 96%. Digital slides were then examined by a trained reviewer blinded to previous AFB smear and culture results, for the final interpretation of assisted digital microscopy (a-DM). Paired results from both microscopic methods were compared to mycobacterial culture. A scanning failure rate of 10.6% (34/320) was observed, leaving 286 slides for analysis. After discrepant analysis, concordance, positive and negative agreements were 95.5% (95%CI, 92.4%-97.6%), 96.2% (95%CI, 89.2%-99.2%), and 95.2% (95%CI, 91.3%-97.7%), respectively. Using mycobacterial culture as reference standard, a-DM and MM had comparable sensitivities: 90.7% (95%CI, 81.7%-96.2%) versus 92.0% (95%CI, 83.4%-97.0%) (P-value = 1.00); while their specificities differed 91.9% (95%CI, 87.4%-95.2%) versus 95.7% (95%CI, 92.1%-98.0%), respectively (P-value = 0.03). Using a PT of 96%, MetaSystems' platform shows acceptable performance. With a national laboratory staff shortage and a local low mycobacterial infection rate, this instrument when combined with culture, can reliably triage-negative AFB-smear respiratory slides and identify positive slides requiring manual confirmation and semi-quantification.

IMPORTANCE

This manuscript presents a full validation of MetaSystems' automated acid-fast bacilli (AFB) smear microscopy scanning and deep-learning-based image analysis module using a probability threshold of 96% including accuracy, precision studies, and evaluation of limit of AFB detection on respiratory samples when the technology is used with assistance. This study is complementary to the conversation started by Tomasello et al. on the use of image analysis artificial intelligence software in routine mycobacterial diagnostic activities within the context of high-throughput laboratories with low incidence of tuberculosis.

A high-speed microscopy system based on deep learning to detect yeast-like fungi cells in blood

Background: Blood-invasive fungal infections can cause the death of patients, while diagnosis of fungal infections is challenging. Methods: A high-speed microscopy detection system was constructed that included a microfluidic system, a microscope connected to a high-speed camera and a deep learning analysis section. Results: For training data, the sensitivity and specificity of the convolutional neural network model were 93.5% (92.7-94.2%) and 99.5% (99.1-99.5%), respectively. For validating data, the sensitivity and specificity were 81.3% (80.0-82.5%) and 99.4% (99.2-99.6%), respectively. Cryptococcal cells were found in 22.07% of blood samples. Conclusion: This high-speed microscopy system can analyze fungal pathogens in blood samples rapidly with high sensitivity and specificity and can help dramatically accelerate the diagnosis of fungal infectious diseases.

Clinical applications of artificial intelligence in identification and management of bacterial infection: Systematic review and meta-analysis

Pneumonia is declared a global emergency public health crisis in children less than five age and the geriatric population. Recent advancements in deep learning models could be utilized effectively for the timely and early diagnosis of pneumonia in immune-compromised patients to avoid complications. This systematic review and meta-analysis utilized PRISMA guidelines for the selection of ten articles included in this study. The literature search was done through electronic databases including PubMed, Scopus, and Google Scholar from 1st January 2016 till 1 July 2023. Overall studies included a total of 126,610 images and 1706 patients in this meta-analysis. At a 95% confidence interval, for pooled sensitivity was 0.90 (0.85-0.94) and I2 statistics 90.20 (88.56 - 91.92). The pooled specificity for deep learning models' diagnostic accuracy was 0.89 (0.86---0.92) and I2 statistics 92.72 (91.50 - 94.83). I2 statistics showed low heterogeneity across studies highlighting consistent and reliable estimates, and instilling confidence in these findings for researchers and healthcare practitioners. The study highlighted the recent deep learning models single or in combination with high accuracy, sensitivity, and specificity to ensure reliable use for bacterial pneumonia identification and differentiate from other viral, fungal pneumonia in children and adults through chest x-rays and radiographs.

Artificial Intelligence: Exploring utility in detection and typing of fungus with futuristic application in fungal cytology

Artificial Intelligence (AI) is an emerging, transforming and revolutionary technology that has captured attention worldwide. It is translating research into precision oncology treatments. AI can analyse large or big data sets requiring high-speed specialized computing solutions. The data are big in terms of volume and multimodal with the amalgamation of images, text and structure. Machine learning has identified antifungal drug targets, and taxonomic and phylogenetic classification of fungi based on sequence analysis is now available. Real-time identification tools and user-friendly mobile applications for identifying fungi have been discovered. Akin to histopathology, AI can be applied to fungal cytology. AI has been fruitful in cytopathology of the thyroid gland, breast, urine and uterine cervical lesions. AI has a huge scope in fungal cytology and would certainly bear fruit with its accuracy, reproducibility and capacity for handling big data. The purpose of this systematic review was to highlight the AI's utility in detecting fungus and its typing with a special focus on future application in fungal cytology. We also touch upon the basics of AI in brief.

Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review

Healthcare-associated infections (HAIs) are the most common adverse events in healthcare and constitute a major global public health concern. Surveillance represents the foundation for the effective prevention and control of HAIs, yet conventional surveillance is costly and labor intensive. Artificial intelligence (AI) and machine learning (ML) have the potential to support the development of HAI surveillance algorithms for the understanding of HAI risk factors, the improvement of patient risk stratification as well as the prediction and timely detection and prevention of infections. AI-supported systems have so far been explored for clinical laboratory testing and imaging diagnosis, antimicrobial resistance profiling, antibiotic discovery and prediction-based clinical decision support tools in terms of HAIs. This review aims to provide a comprehensive summary of the current literature on AI applications in the field of HAIs and discuss the future potentials of this emerging technology in infection practice. Following the PRISMA guidelines, this study examined the articles in databases including PubMed and Scopus until November 2023, which were screened based on the inclusion and exclusion criteria, resulting in 162 included articles. By elucidating the advancements in the field, we aim to highlight the potential applications of AI in the field, report related issues and shortcomings and discuss the future directions.

A prospective observational multicentric clinical trial to evaluate microscopic examination of acid-fast bacilli in sputum by artificial intelligence-based microscopy system

Microscopy-based tuberculosis (TB) diagnosis i.e., Ziehl-Neelsen (ZN) stained smear screening still remains the primary diagnostic method in resource poor and high TB burden countries, however itrequires considerable experience and is bound to human errors. In remote areas, wherever expert microscopist is not available, timely diagnosis at initial level is not possible. Artificial intelligence (AI)-based microscopy may be a solution to this problem. A prospective observational multi-centric clinical trial to evaluate microscopic examination of acid-fast bacilli (AFB) in sputum by the AI based system was done in three hospitals in Northern India. Sputum samples from 400 clinically suspected cases of pulmonary tuberculosis were collected from three centres. Ziehl-Neelsen staining of smears was done. All the smears were observed by 3 microscopist and the AI based microscopy system. AI based microscopy was found to have a sensitivity, specificity, positive predictive value, negative predictive value and diagnostic accuracy of 89.25%, 92.15%, 75.45%, 96.94%, 91.53% respectively. AI based sputum microscopy has an acceptable degree of accuracy, PPV, NPV, specificity and sensitivity and thus may be used as a screening tool for the diagnosis of pulmonary tuberculosis.

Revolutionizing healthcare: the role of artificial intelligence in clinical practice

INTRODUCTION

Healthcare systems are complex and challenging for all stakeholders, but artificial intelligence (AI) has transformed various fields, including healthcare, with the potential to improve patient care and quality of life. Rapid AI advancements can revolutionize healthcare by integrating it into clinical practice. Reporting AI's role in clinical practice is crucial for successful implementation by equipping healthcare providers with essential knowledge and tools.

RESEARCH SIGNIFICANCE

This review article provides a comprehensive and up-to-date overview of the current state of AI in clinical practice, including its potential applications in disease diagnosis, treatment recommendations, and patient engagement. It also discusses the associated challenges, covering ethical and legal considerations and the need for human expertise. By doing so, it enhances understanding of AI's significance in healthcare and supports healthcare organizations in effectively adopting AI technologies.

MATERIALS AND METHODS

The current investigation analyzed the use of AI in the healthcare system with a comprehensive review of relevant indexed literature, such as PubMed/Medline, Scopus, and EMBASE, with no time constraints but limited to articles published in English. The focused question explores the impact of applying AI in healthcare settings and the potential outcomes of this application.

RESULTS

Integrating AI into healthcare holds excellent potential for improving disease diagnosis, treatment selection, and clinical laboratory testing. AI tools can leverage large datasets and identify patterns to surpass human performance in several healthcare aspects. AI offers increased accuracy, reduced costs, and time savings while minimizing human errors. It can revolutionize personalized medicine, optimize medication dosages, enhance population health management, establish guidelines, provide virtual health assistants, support mental health care, improve patient education, and influence patient-physician trust.

CONCLUSION

AI can be used to diagnose diseases, develop personalized treatment plans, and assist clinicians with decision-making. Rather than simply automating tasks, AI is about developing technologies that can enhance patient care across healthcare settings. However, challenges related to data privacy, bias, and the need for human expertise must be addressed for the responsible and effective implementation of AI in healthcare.

Attention-Guided Transfer Learning for Identification of Filamentous Fungi Encountered in the Clinical Laboratory

This study addresses the challenge of accurately identifying filamentous fungi in medical laboratories using transfer learning with convolutional neural networks (CNNs). The study uses microscopic images from touch-tape slides with lactophenol cotton blue staining, the most common method in clinical settings, to classify fungal genera and identify Aspergillus species. The training and test data sets included 4,108 images with representative microscopic morphology for each genus, and a soft attention mechanism was incorporated to enhance classification accuracy. As a result, the study achieved an overall classification accuracy of 94.9% for four frequently encountered genera and 84.5% for Aspergillus species. One of the distinct features is the involvement of medical technologists in developing a model that seamlessly integrates into routine workflows. In addition, the study highlights the potential of merging advanced technology with medical laboratory practices to diagnose filamentous fungi accurately and efficiently. IMPORTANCE This study utilizes transfer learning with CNNs to classify fungal genera and identify Aspergillus species using microscopic images from touch-tape preparation and lactophenol cotton blue staining. The training and test data sets included 4,108 images with representative microscopic morphology for each genus, and a soft attention mechanism was incorporated to enhance classification accuracy. As a result, the study achieved an overall classification accuracy of 94.9% for four frequently encountered genera and 84.5% for Aspergillus species. One of the distinct features is the involvement of medical technologists in developing a model that seamlessly integrates into routine workflows. In addition, the study highlights the potential of merging advanced technology with medical laboratory practices to diagnose filamentous fungi accurately and efficiently.

An improved Yolov5s based on transformer backbone network for detection and classification of bronchoalveolar lavage cells

Biological tissue information of the lung, such as cells and proteins, can be obtained from bronchoalveolar lavage fluid (BALF), through which it can be used as a complement to lung biopsy pathology. BALF cells can be confused with each other due to the similarity of their characteristics and differences in the way sections are handled or viewed. This poses a great challenge for cell detection. In this paper, An Improved Yolov5s Based on Transformer Backbone Network for Detection and Classification of BALF Cells is proposed, focusing on the detection of four types of cells in BALF: macrophages, lymphocytes, neutrophils and eosinophils. The network is mainly based on the Yolov5s network and uses Swin Transformer V2 technology in the backbone network to improve cell detection accuracy by obtaining global information; the C3Ghost module (a variant of the Convolutional Neural Network architecture) is used in the neck network to reduce the number of parameters during feature channel fusion and to improve feature expression performance. In addition, embedding intersection over union Loss (EIoU_Loss) was used as a bounding box regression loss function to speed up the bounding box regression rate, resulting in higher accuracy of the algorithm. The experiments showed that our model could achieve mAP of 81.29% and Recall of 80.47%. Compared to the original Yolov5s, the mAP has improved by 3.3% and Recall by 3.67%. We also compared it with Yolov7 and the newly launched Yolov8s. mAP improved by 0.02% and 2.36% over Yolov7 and Yolov8s respectively, while the FPS of our model was higher than both of them, achieving a balance of efficiency and accuracy, further demonstrating the superiority of our model.

Lightweight Visual Transformers Outperform Convolutional Neural Networks for Gram-Stained Image Classification: An Empirical Study

We aimed to automate Gram-stain analysis to speed up the detection of bacterial strains in patients suffering from infections. We performed comparative analyses of visual transformers (VT) using various configurations including model size (small vs. large), training epochs (1 vs. 100), and quantization schemes (tensor- or channel-wise) using float32 or int8 on publicly available (DIBaS, n = 660) and locally compiled (n = 8500) datasets. Six VT models (BEiT, DeiT, MobileViT, PoolFormer, Swin and ViT) were evaluated and compared to two convolutional neural networks (CNN), ResNet and ConvNeXT. The overall overview of performances including accuracy, inference time and model size was also visualized. Frames per second (FPS) of small models consistently surpassed their large counterparts by a factor of 1-2×. DeiT small was the fastest VT in int8 configuration (6.0 FPS). In conclusion, VTs consistently outperformed CNNs for Gram-stain classification in most settings even on smaller datasets.

Improving the Detection of Epidemic Clones in Candida parapsilosis Outbreaks by Combining MALDI-TOF Mass Spectrometry and Deep Learning Approaches

Identifying fungal clones propagated during outbreaks in hospital settings is a problem that increasingly confronts biologists. Current tools based on DNA sequencing or microsatellite analysis require specific manipulations that are difficult to implement in the context of routine diagnosis. Using deep learning to classify the mass spectra obtained during the routine identification of fungi by MALDI-TOF mass spectrometry could be of interest to differentiate isolates belonging to epidemic clones from others. As part of the management of a nosocomial outbreak due to Candida parapsilosis in two Parisian hospitals, we studied the impact of the preparation of the spectra on the performance of a deep neural network. Our purpose was to differentiate 39 otherwise fluconazole-resistant isolates belonging to a clonal subset from 56 other isolates, most of which were fluconazole-susceptible, collected during the same period and not belonging to the clonal subset. Our study carried out on spectra obtained on four different machines from isolates cultured for 24 or 48 h on three different culture media showed that each of these parameters had a significant impact on the performance of the classifier. In particular, using different culture times between learning and testing steps could lead to a collapse in the accuracy of the predictions. On the other hand, including spectra obtained after 24 and 48 h of growth during the learning step restored the good results. Finally, we showed that the deleterious effect of the device variability used for learning and testing could be largely improved by including a spectra alignment step during preprocessing before submitting them to the neural network. Taken together, these experiments show the great potential of deep learning models to identify spectra of specific clones, providing that crucial parameters are controlled during both culture and preparation steps before submitting spectra to a classifier.

Artificial intelligence in microbial natural product drug discovery: current and emerging role

Covering: up to the end of 2022Microorganisms are exceptional sources of a wide array of unique natural products and play a significant role in drug discovery. During the golden era, several life-saving antibiotics and anticancer agents were isolated from microbes; moreover, they are still widely used. However, difficulties in the isolation methods and repeated discoveries of the same molecules have caused a setback in the past. Artificial intelligence (AI) has had a profound impact on various research fields, and its application allows the effective performance of data analyses and predictions. With the advances in omics, it is possible to obtain a wealth of information for the identification, isolation, and target prediction of secondary metabolites. In this review, we discuss drug discovery based on natural products from microorganisms with the help of AI and machine learning.

Rapid and Simple Approaches for Diagnosis of Staphylococcus aureus in Bloodstream Infections

Staphylococcus aureus is an important causative pathogen of bloodstream infections. An amplification assay such as real-time PCR is a sensitive, specific technique to detect S. aureus. However, it needs well-trained personnel, and costs are high. A literature review focusing on rapid and simple methods for diagnosing S. aureus was performed. The following methods were included: (a) Hybrisep in situ hybridization test, (b) T2Dx system, (c) BinaxNow Staphylococcus aureus and PBP2a, (d) Gram staining, (e) PNA FISH and QuickFISH, (f) Accelerate Pheno^TM system, (g) MALDI-TOF MS, (h) BioFire FilmArray, (i) Xpert MRSA/SA. These rapid and simple methods can rapidly identify S. aureus in positive blood cultures or direct blood samples. Furthermore, BioFire FilmArray and Xpert MRSA/SA identify methicillin-resistant S. aureus (MRSA), and the Accelerate Pheno^TM system can also provide antimicrobial susceptibility testing (AST) results. The rapidity and simplicity of results generated by these methods have the potential to improve patient outcomes and aid in the prevention of the emergence and transmission of MRSA.

Rapid Convolutional Neural Networks for Gram-Stained Image Classification at Inference Time on Mobile Devices: Empirical Study from Transfer Learning to Optimization

Despite the emergence of mobile health and the success of deep learning (DL), deploying production-ready DL models to resource-limited devices remains challenging. Especially, during inference time, the speed of DL models becomes relevant. We aimed to accelerate inference time for Gram-stained analysis, which is a tedious and manual task involving microorganism detection on whole slide images. Three DL models were optimized in three steps: transfer learning, pruning and quantization and then evaluated on two Android smartphones. Most convolutional layers (≥80%) had to be retrained for adaptation to the Gram-stained classification task. The combination of pruning and quantization demonstrated its utility to reduce the model size and inference time without compromising model quality. Pruning mainly contributed to model size reduction by 15×, while quantization reduced inference time by 3× and decreased model size by 4×. The combination of two reduced the baseline model by an overall factor of 46×. Optimized models were smaller than 6 MB and were able to process one image in <0.6 s on a Galaxy S10. Our findings demonstrate that methods for model compression are highly relevant for the successful deployment of DL solutions to resource-limited devices.

SARS-CoV-2 Morphometry Analysis and Prediction of Real Virus Levels Based on Full Recurrent Neural Network Using TEM Images

The SARS-CoV-2 virus is responsible for the rapid global spread of the COVID-19 disease. As a result, it is critical to understand and collect primary data on the virus, infection epidemiology, and treatment. Despite the speed with which the virus was detected, studies of its cell biology and architecture at the ultrastructural level are still in their infancy. Therefore, we investigated and analyzed the viral morphometry of SARS-CoV-2 to extract important key points of the virus's characteristics. Then, we proposed a prediction model to identify the real virus levels based on the optimization of a full recurrent neural network (RNN) using transmission electron microscopy (TEM) images. Consequently, identification of virus levels depends on the size of the morphometry of the area (width, height, circularity, roundness, aspect ratio, and solidity). The results of our model were an error score of training network performance 3.216 × 10^-11 at 639 epoch, regression of -1.6 × 10^-9, momentum gain (Mu) 1 × 10^-9, and gradient value of 9.6852 × 10^-8, which represent a network with a high ability to predict virus levels. The fully automated system enables virologists to take a high-accuracy approach to virus diagnosis, prevention of mutations, and life cycle and improvement of diagnostic reagents and drugs, adding a point of view to the advancement of medical virology.

Computer aided detection of tuberculosis using two classifiers

OBJECTIVES

Tuberculosis caused by Mycobacterium tuberculosis have been a major challenge for medical and healthcare sectors in many underdeveloped countries with limited diagnosis tools. Tuberculosis can be detected from microscopic slides and chest X-ray but as a result of the high cases of tuberculosis, this method can be tedious for both microbiologist and Radiologist and can lead to miss-diagnosis. The main objective of this study is to addressed these challenges by employing Computer Aided Detection (CAD) using Artificial Intelligence-driven models which learn features based on convolution and result in an output with high accuracy.

METHOD

In this paper, we described automated discrimination of X-ray and microscopic slide images of tuberculosis into positive and negative cases using pretrained AlexNet Models. The study employed Chest X-ray dataset made available on Kaggle repository and microscopic slide images from both Near East university hospital and Kaggle repository.

RESULTS

For classification of tuberculosis and healthy microscopic slide using AlexNet+Softmax, the model achieved accuracy of 98.14%. For classification of tuberculosis and healthy microscopic slide using AlexNet+SVM, the model achieved 98.73% accuracy. For classification of tuberculosis and healthy chest X-ray images using AlexNet+Softmax, the model achieved accuracy of 98.19%. For classification of tuberculosis and healthy chest X-ray images using AlexNet+SVM, the model achieved 98.38% accuracy.

CONCLUSION

The result obtained has shown to outperformed several studies in the current literature. Future studies will attempt to integrate Internet of Medical Things (IoMT) for the design of IoMT/AI-enabled platform for detection of Tuberculosis from both X-ray and Microscopic slide images.

Integrating Artificial Intelligence for Clinical and Laboratory Diagnosis - a Review

Introduction: The development of medical artificial intelligence (AI) is related to programs intended to help clinicians formulate diagnoses, make therapeutic decisions and predict outcomes. It is bringing a paradigm shift to healthcare, powered by the increasing availability of healthcare data and rapid progress in analytical techniques (1). Artificial intelligence techniques include machine learning methods for structured data, such as classical support vector machines and neural networks, modern deep learning (DL), and natural language processing for unstructured data. Methodology:More than 50 articles were reviewed and 41 of them were shortlisted. The review was based on a literature search in PubMed, Embase, Google Scholar, and Scopus databases. Review:Laboratory medicine incorporates new technologies to aid in clinical decision-making, disease monitoring, and patient safety. Clinical microbiology informatics is progressively using AI. Genomic information from isolated bacteria, metagenomic microbial results from original specimens, mass spectra recorded from grown bacterial isolates and large digital photographs are examples of enormous datasets in clinical microbiology that may be used to build AI diagnoses. Conclusion:Technological innovation in healthcare is accelerating and has become increasingly interwoven with our daily lives and medical practices such as smart health trackers and diagnostic algorithms.

[Feasibility of using artificial intelligence for screening COVID-19 patients in ParaguayViabilidade do uso de inteligência artificial na triagem de pacientes com COVID-19 no Paraguai]

Objetivo.

Estudiar la factibilidad de utilización de la inteligencia artificial como método sensible y específico para el cribado de COVID-19 en pacientes con afecciones respiratorias empleando imágenes de tórax obtenidas con tomógrafo y una plataforma de telemedicina.

Métodos.

Entre marzo del 2020 y junio del 2021 se realizó un estudio observacional descriptivo multicéntrico de factibilidad basada en inteligencia artificial (IA) para el cribado de COVID-19 en imágenes de tórax de pacientes con afecciones respiratorias que acudieron a hospitales públicos. El diagnóstico de las imágenes tomográficas de tórax se realizó a través de la plataforma de IA; luego, se comparó con el diagnóstico molecular (RT-PCR) para determinar la concordancia entre ambos y analizar su factibilidad para el cribado de pacientes con sospecha de COVID-19. Las imágenes y los resultados diagnóstico se enviaron a través de una plataforma de telemedicina.

Resultados.

Se realizó el cribado de 3 514 pacientes con sospecha diagnóstica de COVID-19, en 14 hospitales a nivel nacional. La mayoría de los pacientes tenían entre 27 y 59 años, seguidos por los mayores de 60 años. La edad promedio fue de 48,6 años; el 52,8% eran de sexo masculino. Los hallazgos más frecuentes fueron neumonía grave, neumonía bilateral con derrame pleural, enfisema pulmonar bilateral y opacidad difusa en vidrio esmerilado, entre otros. Se determinó un promedio de 93% de concordancia y 7% de discordancia entre las imágenes analizadas mediante IA y la RT-PCR. La sensibilidad y especificidad del sistema de IA, obtenidas comparando el resultado del cribado obtenido por IA con la RT-PCR, fueron de 93% y 80% respectivamente.

Conclusiones.

Es viable la utilización de IA sensible y específica para la detección rápida estratificada de COVID-19 en pacientes con afecciones respiratorias utilizando imágenes obtenidas mediante tomografía de tórax y una plataforma de telemedicina en los hospitales públicos de Paraguay.

Bacterial keratitis: identifying the areas of clinical uncertainty

Bacterial keratitis is a common corneal infection that is treated with topical antimicrobials. By the time of presentation there may already be severe visual loss from corneal ulceration and opacity, which may persist despite treatment. There are significant differences in the associated risk factors and the bacterial isolates between high income and low- or middle-income countries, so that general management guidelines may not be appropriate. Although the diagnosis of bacterial keratitis may seem intuitive there are multiple uncertainties about the criteria that are used, which impacts the interpretation of investigations and recruitment to clinical studies. Importantly, the concept that bacterial keratitis can only be confirmed by culture ignores the approximately 50% of cases clinically consistent with bacterial keratitis in which investigations are negative. The aetiology of these culture-negative cases is unknown. Currently, the estimation of bacterial susceptibility to antimicrobials is based on data from systemic administration and achievable serum or tissue concentrations, rather than relevant corneal concentrations and biological activity in the cornea. The provision to the clinician of minimum inhibitory concentrations of the antimicrobials for the isolated bacteria would be an important step forward. An increase in the prevalence of antimicrobial resistance is a concern, but the effect this has on disease outcomes is yet unclear. Virulence factors are not routinely assessed although they may affect the pathogenicity of bacteria within species and affect outcomes. New technologies have been developed to detect and kill bacteria, and their application to bacterial keratitis is discussed. In this review we present the multiple areas of clinical uncertainty that hamper research and the clinical management of bacterial keratitis, and we address some of the assumptions and dogma that have become established in the literature.

Automated interpretation and analysis of bronchoalveolar lavage fluid

BACKGROUND

The cytological analysis of bronchoalveolar lavage fluid (BALF) plays an essential role in the differential diagnosis of respiratory diseases. In recent years, deep learning has demonstrated excellent performance in image processing and object recognition.

OBJECTIVES

We aim to apply deep learning to the automated interpretation and analysis of BALF.

METHOD

Visual images were acquired using an automated biological microscopy platform. We propose a three-step algorithm to automatically interpret BALF cytology based on a convolutional neural network (CNN). The clinical value was evaluated at the patient level.

RESULTS

Our model successfully detected most cells in BALF specimens and achieved a sensitivity, precision, and F1 score of over 0.9 for most cell types. In two tests in the clinical context, the algorithm outperformed experienced practitioners.

CONCLUSION

The program can automatically provide the cytological background of BALF and augment clinical decision-making for clinicians.

Artificial Intelligence and Mapping a New Direction in Laboratory Medicine: A Review

BACKGROUND

Modern artificial intelligence (AI) and machine learning (ML) methods are now capable of completing tasks with performance characteristics that are comparable to those of expert human operators. As a result, many areas throughout healthcare are incorporating these technologies, including in vitro diagnostics and, more broadly, laboratory medicine. However, there are limited literature reviews of the landscape, likely future, and challenges of the application of AI/ML in laboratory medicine.

CONTENT

In this review, we begin with a brief introduction to AI and its subfield of ML. The ensuing sections describe ML systems that are currently in clinical laboratory practice or are being proposed for such use in recent literature, ML systems that use laboratory data outside the clinical laboratory, challenges to the adoption of ML, and future opportunities for ML in laboratory medicine.

SUMMARY

AI and ML have and will continue to influence the practice and scope of laboratory medicine dramatically. This has been made possible by advancements in modern computing and the widespread digitization of health information. These technologies are being rapidly developed and described, but in comparison, their implementation thus far has been modest. To spur the implementation of reliable and sophisticated ML-based technologies, we need to establish best practices further and improve our information system and communication infrastructure. The participation of the clinical laboratory community is essential to ensure that laboratory data are sufficiently available and incorporated conscientiously into robust, safe, and clinically effective ML-supported clinical diagnostics.

State-of-the-Art Techniques for Diagnosis of Medical Parasites and Arthropods

Conventional methods such as microscopy have been used to diagnose parasitic diseases and medical conditions related to arthropods for many years. Some techniques are considered gold standard methods. However, their limited sensitivity, specificity, and accuracy, and the need for costly reagents and high-skilled technicians are critical problems. New tools are therefore continually being developed to reduce pitfalls. Recently, three state-of-the-art techniques have emerged: DNA barcoding, geometric morphometrics, and artificial intelligence. Here, data related to the three approaches are reviewed. DNA barcoding involves an analysis of a barcode sequence. It was used to diagnose medical parasites and arthropods with 95.0% accuracy. However, this technique still requires costly reagents and equipment. Geometric morphometric analysis is the statistical analysis of the patterns of shape change of an anatomical structure. Its accuracy is approximately 94.0-100.0%, and unlike DNA barcoding, costly reagents and equipment are not required. Artificial intelligence technology involves the analysis of pictures using well-trained algorithms. It showed 98.8-99.0% precision. All three approaches use computer programs instead of human interpretation. They also have the potential to be high-throughput technologies since many samples can be analyzed at once. However, the limitation of using these techniques in real settings is species coverage.

Clinical Laboratory Employees' Attitudes Toward Artificial Intelligence

OBJECTIVE

The objective of this study was to determine the attitudes of laboratory personnel toward the application of artificial intelligence (AI) in the laboratory.

METHODS

We surveyed laboratory employees who covered a range of work roles, work environments, and educational levels.

RESULTS

The survey response rate was 42%. Most respondents (79%) indicated that they were at least somewhat familiar with AI. Very few (4%) classified themselves as experts. Contact with AI varied by educational level (P = .005). Respondents believed that AI could help them perform their work by reducing errors (24%) and saving time (16%). The most common concern (27%) was job security (being replaced by AI). The majority (64%) of the respondents expressed support for the development of AI projects in the organization.

CONCLUSIONS

Laboratory employees see the potential for AI and generally support the adoption of AI tools but have concerns regarding job security and quality of AI performance.

New Microbiological Techniques for the Diagnosis of Bacterial Infections and Sepsis in ICU Including Point of Care

Purpose of Review

The aim of this article is to review current and emerging microbiological techniques that support the rapid diagnosis of bacterial infections in critically ill patients, including their performance, strengths and pitfalls, as well as available data evaluating their clinical impact.

Recent Findings

Bacterial infections and sepsis are responsible for significant morbidity and mortality in patients admitted to the intensive care unit and their management is further complicated by the increase in the global burden of antimicrobial resistance. In this setting, new diagnostic methods able to overcome the limits of traditional microbiology in terms of turn-around time and accuracy are highly warranted. We discuss the following broad themes: optimisation of existing culture-based methodologies, rapid antigen detection, nucleic acid detection (including multiplex PCR assays and microarrays), sepsis biomarkers, novel methods of pathogen detection (e.g. T2 magnetic resonance) and susceptibility testing (e.g. morphokinetic cellular analysis) and the application of direct metagenomics on clinical samples. The assessment of the host response through new “omics” technologies might also aid in early diagnosis of infections, as well as define non-infectious inflammatory states.

Summary

Despite being a promising field, there is still scarce evidence about the real-life impact of these assays on patient management. A common finding of available studies is that the performance of rapid diagnostic strategies highly depends on whether they are integrated within active antimicrobial stewardship programs. Assessing the impact of these emerging diagnostic methods through patient-centred clinical outcomes is a complex challenge for which large and well-designed studies are awaited.

Deep convolutional neural network: a novel approach for the detection of Aspergillus fungi via stereomicroscopy

Fungi of the genus Aspergillus are ubiquitously distributed in nature, and some cause invasive aspergillosis (IA) infections in immunosuppressed individuals and contamination in agricultural products. Because microscopic observation and molecular detection of Aspergillus species represent the most operator-dependent and time-intensive activities, automated and cost-effective approaches are needed. To address this challenge, a deep convolutional neural network (CNN) was used to investigate the ability to classify various Aspergillus species. Using a dissecting microscopy (DM)/stereomicroscopy platform, colonies on plates were scanned with a 35× objective, generating images of sufficient resolution for classification. A total of 8,995 original colony images from seven Aspergillus species cultured in enrichment medium were gathered and autocut to generate 17,142 image crops as training and test datasets containing the typical representative morphology of conidiophores or colonies of each strain. Encouragingly, the Xception model exhibited a classification accuracy of 99.8% on the training image set. After training, our CNN model achieved a classification accuracy of 99.7% on the test image set. Based on the Xception performance during training and testing, this classification algorithm was further applied to recognize and validate a new set of raw images of these strains, showing a detection accuracy of 98.2%. Thus, our study demonstrated a novel concept for an artificial-intelligence-based and cost-effective detection methodology for Aspergillus organisms, which also has the potential to improve the public's understanding of the fungal kingdom.

Rapid identification of pathogens by using surface-enhanced Raman spectroscopy and multi-scale convolutional neural network

Salmonella is a prevalent pathogen causing serious morbidity and mortality worldwide. There are over 2600 serovars of Salmonella. Among them, Salmonella Enteritidis, Salmonella Typhimurium, and Salmonella Paratyphi were reported to be the most common foodborne pathogenic serovars in the EU and China. In order to provide a more efficient approach to detect and distinguish these serovars, a new analytical method was developed by combining surface-enhanced Raman spectroscopy (SERS) with multi-scale convolutional neural network (CNN). We prepared 34-nm gold nanoparticles (AuNPs) as the label-free Raman substrate, measured 1854 SERS spectra of these three Salmonella serovars, and then proposed a multi-scale CNN model with three parallel CNNs to achieve multi-dimensional extraction of SERS spectral features. We observed the impact of the number of iterations and training samples on the recognition accuracy by changing the ratio of the number of the training and testing sets. By comparing the calculated data with experimental one, it was shown that our model could reach recognition accuracy more than 97%. These results indicate that it was not only feasible to combine SERS spectroscopy with multi-scale CNN for Salmonella serotype identification, but also for other pathogen species and serovar identifications.

Deep Learning for Imaging and Detection of Microorganisms

Despite tremendous recent interest, the application of deep learning in microbiology has still not reached its full potential. To tackle the challenges faced by human-operated microscopy, deep-learning-based methods have been proposed for microscopic image analysis of a wide range of microorganisms, including viruses, bacteria, fungi, and parasites. We believe that deep-learning technology-based systems will be on the front line of monitoring and investigation of microorganisms.

Deep Neural Networks Offer Morphologic Classification and Diagnosis of Bacterial Vaginosis

Bacterial vaginosis (BV) is caused by the excessive and imbalanced growth of bacteria in vagina, affecting 30 to 50% of women. Gram staining followed by Nugent scoring based on bacterial morphotypes under the microscope is considered the gold standard for BV diagnosis; this method is often labor-intensive and time-consuming, and results vary from person to person. We developed and optimized a convolutional neural network (CNN) model and evaluated its ability to automatically identify and classify three categories of Nugent scores from microscope images. The CNN model was first established with a panel of microscopic images with Nugent scores determined by experts. The model was trained by minimizing the cross-entropy loss function and optimized by using a momentum optimizer. The separate test sets of images collected from three hospitals were evaluated by the CNN model. The CNN model consisted of 25 convolutional layers, 2 pooling layers, and a fully connected layer. The model obtained 82.4% sensitivity and 96.6% specificity with the 5,815 validation images when altered vaginal flora and BV were considered the positive samples, which was better than the rates achieved by top-level technologists and obstetricians in China. The capability of our model for generalization was so strong that it exhibited 75.1% accuracy in three categories of Nugent scores on the independent test set of 1,082 images, which was 6.6% higher than the average of three technologists, who are hold bachelor's degrees in medicine and are qualified to make diagnostic decisions. When three technologists ran one specimen in triplicate, the precision of three categories of Nugent scores was 54.0%. One hundred three samples diagnosed by two technologists on different days showed a repeatability of 90.3%. The CNN model outperformed human health care practitioners in terms of accuracy and stability for three categories of Nugent score diagnosis. The deep learning model may offer translational applications in automating diagnosis of bacterial vaginosis with proper supporting hardware.

Mini Review: Clinical Routine Microbiology in the Era of Automation and Digital Health

Clinical microbiology laboratories are the first line to combat and handle infectious diseases and antibiotic resistance, including newly emerging ones. Although most clinical laboratories still rely on conventional methods, a cascade of technological changes, driven by digital imaging and high-throughput sequencing, will revolutionize the management of clinical diagnostics for direct detection of bacteria and swift antimicrobial susceptibility testing. Importantly, such technological advancements occur in the golden age of machine learning where computers are no longer acting passively in data mining, but once trained, can also help physicians in making decisions for diagnostics and optimal treatment administration. The further potential of physically integrating new technologies in an automation chain, combined to machine-learning-based software for data analyses, is seducing and would indeed lead to a faster management in infectious diseases. However, if, from one side, technological advancement would achieve a better performance than conventional methods, on the other side, this evolution challenges clinicians in terms of data interpretation and impacts the entire hospital personnel organization and management. In this mini review, we discuss such technological achievements offering practical examples of their operability but also their limitations and potential issues that their implementation could rise in clinical microbiology laboratories.

Recent evolutions of machine learning applications in clinical laboratory medicine

Machine learning (ML) is gaining increased interest in clinical laboratory medicine, mainly triggered by the decreased cost of generating and storing data using laboratory automation and computational power, and the widespread accessibility of open source tools. Nevertheless, only a handful of ML-based products are currently commercially available for routine clinical laboratory practice. In this review, we start with an introduction to ML by providing an overview of the ML landscape, its general workflow, and the most commonly used algorithms for clinical laboratory applications. Furthermore, we aim to illustrate recent evolutions (2018 to mid-2020) of the techniques used in the clinical laboratory setting and discuss the associated challenges and opportunities. In the field of clinical chemistry, the reviewed applications of ML algorithms include quality review of lab results, automated urine sediment analysis, disease or outcome prediction from routine laboratory parameters, and interpretation of complex biochemical data. In the hematology subdiscipline, we discuss the concepts of automated blood film reporting and malaria diagnosis. At last, we handle a broad range of clinical microbiology applications, such as the reduction of diagnostic workload by laboratory automation, the detection and identification of clinically relevant microorganisms, and the detection of antimicrobial resistance.

A CNN-based active learning framework to identify mycobacteria in digitized Ziehl-Neelsen stained human tissues

Tuberculosis is the most common mycobacterial disease that affects humans worldwide. Rapid and reliable diagnosis of mycobacteria is crucial to identify infected individuals, to initiate and monitor treatment and to minimize or prevent transmission. Microscopic identification of acid-fast mycobacteria (AFB) in tissue sections is usually accomplished by examining Ziehl-Neelsen (ZN) stained slides in which AFB appear bright red against the blue background. Because the ZN-stained slides require time consuming and meticulous screening by an experienced pathologist, our team developed a machine learning pipeline to classify digitized ZN-stained slides as AFB-positive or AFB-negative. The pipeline includes two convolutional neural network (CNN) models to recognize tiles containing AFB, and a logistic regression (LR) model to classify slides based on features from AFB-probability maps assembled from the CNN tile-based classification results. The first CNN was trained using tiles from 6 AFB-positive and 8 AFB-negative slides, and the second CNN was trained using the initial tile set expanded by additional tiles from 19 AFB-negative slides selected within an active learning framework. When evaluated on a separate set of tiles, the two CNNs yielded F1 scores of 99.03% and 98.75%, respectively, and were used to classify tiles in a separate set of 134 slides (46 AFB-positive and 88 AFB-negative). The classification yielded two AFB-probability maps, one for each CNN. The LR model was then 10-fold cross-validated using the average of feature vectors extracted from the AFB-probability maps generated by each CNN. The feature vector consisted of seven features of the AFB-probability map histogram and the positive tile rate (PTR). The sensitivity (87.13%), specificity (87.62%) and F1 (80.18%) achieved by this model were superior to the baseline performance of PTR-based separation of slides that yielded F1 scores of 73.13% and 66.67% in the AFB-probability maps outputted by the CNN trained within the active learning framework and the CNN trained only on the initial set of slides, respectively. Our CNNs outperformed several recently published models for AFB detection. Active learning induced robust learning of features by the CNN and led to improved LR classification performance of slides. In the 52 AFB-positive slides used in the pipeline development, the AFB were infrequent, predominantly single and only rarely found in small clusters. Our pipeline can classify slides and visualize suspected AFB-positive areas in each slide, and thus potentially facilitate evaluation of ZN-stained tissue sections for AFB.

Deep Learning Frameworks for Rapid Gram Stain Image Data Interpretation: Protocol for a Retrospective Data Analysis

Background

In recent years, remarkable progress has been made in deep learning technology and successful use cases have been introduced in the medical domain. However, not many studies have considered high-performance computing to fully appreciate the capability of deep learning technology.

Objective

This paper aims to design a solution to accelerate an automated Gram stain image interpretation by means of a deep learning framework without additional hardware resources.

Methods

We will apply and evaluate 3 methodologies, namely fine-tuning, an integer arithmetic–only framework, and hyperparameter tuning.

Results

The choice of pretrained models and the ideal setting for layer tuning and hyperparameter tuning will be determined. These results will provide an empirical yet reproducible guideline for those who consider a rapid deep learning solution for Gram stain image interpretation. The results are planned to be announced in the first quarter of 2021.

Conclusions

Making a balanced decision between modeling performance and computational performance is the key for a successful deep learning solution. Otherwise, highly accurate but slow deep learning solutions can add value to routine care.

International Registered Report Identifier (IRRID)

DERR1-10.2196/16843

Digital microbiology

BACKGROUND

Digitalization and artificial intelligence have an important impact on the way microbiology laboratories will work in the near future. Opportunities and challenges lie ahead to digitalize the microbiological workflows. Making efficient use of big data, machine learning, and artificial intelligence in clinical microbiology requires a profound understanding of data handling aspects.

OBJECTIVE

This review article summarizes the most important concepts of digital microbiology. The article gives microbiologists, clinicians and data scientists a viewpoint and practical examples along the diagnostic process.

SOURCES

We used peer-reviewed literature identified by a PubMed search for digitalization, machine learning, artificial intelligence and microbiology.

CONTENT

We describe the opportunities and challenges of digitalization in microbiological diagnostic processes with various examples. We also provide in this context key aspects of data structure and interoperability, as well as legal aspects. Finally, we outline the way for applications in a modern microbiology laboratory.

IMPLICATIONS

We predict that digitalization and the usage of machine learning will have a profound impact on the daily routine of laboratory staff. Along the analytical process, the most important steps should be identified, where digital technologies can be applied and provide a benefit. The education of all staff involved should be adapted to prepare for the advances in digital microbiology.

Detection of Intestinal Protozoa in Trichrome-Stained Stool Specimens by Use of a Deep Convolutional Neural Network

Intestinal protozoa are responsible for relatively few infections in the developed world, but the testing volume is disproportionately high. Manual light microscopy of stool remains the gold standard but can be insensitive, time-consuming, and difficult to maintain competency. Artificial intelligence and digital slide scanning show promise for revolutionizing the clinical parasitology laboratory by augmenting the detection of parasites and slide interpretation using a convolutional neural network (CNN) model. The goal of this study was to develop a sensitive model that could screen out negative trichrome slides, while flagging potential parasites for manual confirmation. Conventional protozoa were trained as "classes" in a deep CNN. Between 1,394 and 23,566 exemplars per class were used for training, based on specimen availability, from a minimum of 10 unique slides per class. Scanning was performed using a 40× dry lens objective automated slide scanner. Data labeling was performed using a proprietary Web interface. Clinical validation of the model was performed using 10 unique positive slides per class and 125 negative slides. Accuracy was calculated as slide-level agreement (e.g., parasite present or absent) with microscopy. Positive agreement was 98.88% (95% confidence interval [CI], 93.76% to 99.98%), and negative agreement was 98.11% (95% CI, 93.35% to 99.77%). The model showed excellent reproducibility using slides containing multiple classes, a single class, or no parasites. The limit of detection of the model and scanner using serially diluted stool was 5-fold more sensitive than manual examinations by multiple parasitologists using 4 unique slide sets. Digital slide scanning and a CNN model are robust tools for augmenting the conventional detection of intestinal protozoa.

Improving Augmented Human Intelligence to Distinguish Burkitt Lymphoma From Diffuse Large B-Cell Lymphoma Cases

OBJECTIVES

To assess and improve the assistive role of a deep, densely connected convolutional neural network (CNN) to hematopathologists in differentiating histologic images of Burkitt lymphoma (BL) from diffuse large B-cell lymphoma (DLBCL).

METHODS

A total of 10,818 images from BL (n = 34) and DLBCL (n = 36) cases were used to either train or apply different CNNs. Networks differed by number of training images and pixels of images, absence of color, pixel and staining augmentation, and depth of the network, among other parameters.

RESULTS

Cases classified correctly were 17 of 18 (94%), nine with 100% of images correct by the best performing network showing a receiver operating characteristic curve analysis area under the curve 0.92 for both DLBCL and BL. The best performing CNN used all available training images, two random subcrops per image of 448 × 448 pixels, random H&E staining image augmentation, random horizontal flipping of images, random alteration of contrast, reduction on validation error plateau of 15 epochs, block size of six, batch size of 32, and depth of 22. Other networks and decreasing training images had poorer performance.

CONCLUSIONS

CNNs are promising augmented human intelligence tools for differentiating a subset of BL and DLBCL cases.

Image analysis and artificial intelligence in infectious disease diagnostics

BACKGROUND

Microbiologists are valued for their time-honed skills in image analysis, including identification of pathogens and inflammatory context in Gram stains, ova and parasite preparations, blood smears and histopathologic slides. They also must classify colony growth on a variety of agar plates for triage and assessment. Recent advances in image analysis, in particular application of artificial intelligence (AI), have the potential to automate these processes and support more timely and accurate diagnoses.

OBJECTIVES

To review current AI-based image analysis as applied to clinical microbiology; and to discuss future trends in the field.

SOURCES

Material sourced for this review included peer-reviewed literature annotated in the PubMed or Google Scholar databases and preprint articles from bioRxiv. Articles describing use of AI for analysis of images used in infectious disease diagnostics were reviewed.

CONTENT

We describe application of machine learning towards analysis of different types of microbiologic image data. Specifically, we outline progress in smear and plate interpretation as well as the potential for AI diagnostic applications in the clinical microbiology laboratory.

IMPLICATIONS

Combined with automation, we predict that AI algorithms will be used in the future to prescreen and preclassify image data, thereby increasing productivity and enabling more accurate diagnoses through collaboration between the AI and the microbiologist. Once developed, image-based AI analysis is inexpensive and amenable to local and remote diagnostic use.