Guiding ultrasound image capture with artificial intelligence

Construction of machine learning diagnostic models for cardiovascular pan-disease based on blood routine and biochemical detection data

BACKGROUND

Cardiovascular disease, also known as circulation system disease, remains the leading cause of morbidity and mortality worldwide. Traditional methods for diagnosing cardiovascular disease are often expensive and time-consuming. So the purpose of this study is to construct machine learning models for the diagnosis of cardiovascular diseases using easily accessible blood routine and biochemical detection data and explore the unique hematologic features of cardiovascular diseases, including some metabolic indicators.

METHODS

After the data preprocessing, 25,794 healthy people and 32,822 circulation system disease patients with the blood routine and biochemical detection data were utilized for our study. We selected logistic regression, random forest, support vector machine, eXtreme Gradient Boosting (XGBoost), and deep neural network to construct models. Finally, the SHAP algorithm was used to interpret models.

RESULTS

The circulation system disease prediction model constructed by XGBoost possessed the best performance (AUC: 0.9921 (0.9911-0.9930); Acc: 0.9618 (0.9588-0.9645); Sn: 0.9690 (0.9655-0.9723); Sp: 0.9526 (0.9477-0.9572); PPV: 0.9631 (0.9592-0.9668); NPV: 0.9600 (0.9556-0.9644); MCC: 0.9224 (0.9165-0.9279); F1 score: 0.9661 (0.9634-0.9686)). Most models of distinguishing various circulation system diseases also had good performance, the model performance of distinguishing dilated cardiomyopathy from other circulation system diseases was the best (AUC: 0.9267 (0.8663-0.9752)). The model interpretation by the SHAP algorithm indicated features from biochemical detection made major contributions to predicting circulation system disease, such as potassium (K), total protein (TP), albumin (ALB), and indirect bilirubin (NBIL). But for models of distinguishing various circulation system diseases, we found that red blood cell count (RBC), K, direct bilirubin (DBIL), and glucose (GLU) were the top 4 features subdividing various circulation system diseases.

CONCLUSIONS

The present study constructed multiple models using 50 features from the blood routine and biochemical detection data for the diagnosis of various circulation system diseases. At the same time, the unique hematologic features of various circulation system diseases, including some metabolic-related indicators, were also explored. This cost-effective work will benefit more people and help diagnose and prevent circulation system diseases.

Augmented reality-based software (Echo-QR) for guiding the echographic probe toward the acoustic window: a pilot study

Introduction

With current technology, ultrasound imaging in remote conditions, such as the International Space Station, is performed with vocal guidance or using a teleoperated echograph controlled by an expert. Both methods require real-time communications between the novice operator and expert to locate the probe over the appropriate acoustic windows (AW). The current study presents the development and testing of a new augmented reality software (Echo-QR) that would allow novice operators (with no medical imaging background) to correctly locate the ultrasound probe over the AW of interest without expert assistance.

Methods

On the first day of the study, the positions of the probe over the AWs were identified for each organ by an expert sonographer and saved in the Echo-QR software. On the second day, the novices independently performed the ultrasound investigation using the Echo-QR software to correctly position the probe over each organ's AW.

Results

Using the Echo-QR software, novice operators found the AW in 73 (92%) of the 79 organs. The 2D images acquired by the novices "2D direct image" were acceptable for medical evaluation in 41% of the cases. However, when the "2D direct image" did not show the entire organ, a 3D capture of the volume below the probe was also performed, which allowed for the extraction of the appropriate 2D image "2D/3D image" for medical evaluation in 85% of the cases.

Discussion

Therefore, in the absence of real-time communication between an isolated participant and an expert sonographer, novel software (Echo-QR) and automated 3D volume capture can be used to obtain images usable for ultrasound diagnostics.

Artificial intelligence in liver imaging: methods and applications

Liver disease is regarded as one of the major health threats to humans. Radiographic assessments hold promise in terms of addressing the current demands for precisely diagnosing and treating liver diseases, and artificial intelligence (AI), which excels at automatically making quantitative assessments of complex medical image characteristics, has made great strides regarding the qualitative interpretation of medical imaging by clinicians. Here, we review the current state of medical-imaging-based AI methodologies and their applications concerning the management of liver diseases. We summarize the representative AI methodologies in liver imaging with focusing on deep learning, and illustrate their promising clinical applications across the spectrum of precise liver disease detection, diagnosis and treatment. We also address the current challenges and future perspectives of AI in liver imaging, with an emphasis on feature interpretability, multimodal data integration and multicenter study. Taken together, it is revealed that AI methodologies, together with the large volume of available medical image data, might impact the future of liver disease care.

Lung Imaging and Artificial Intelligence in ARDS

Artificial intelligence (AI) can make intelligent decisions in a manner akin to that of the human mind. AI has the potential to improve clinical workflow, diagnosis, and prognosis, especially in radiology. Acute respiratory distress syndrome (ARDS) is a very diverse illness that is characterized by interstitial opacities, mostly in the dependent areas, decreased lung aeration with alveolar collapse, and inflammatory lung edema resulting in elevated lung weight. As a result, lung imaging is a crucial tool for evaluating the mechanical and morphological traits of ARDS patients. Compared to traditional chest radiography, sensitivity and specificity of lung computed tomography (CT) and ultrasound are higher. The state of the art in the application of AI is summarized in this narrative review which focuses on CT and ultrasound techniques in patients with ARDS. A total of eighteen items were retrieved. The primary goals of using AI for lung imaging were to evaluate the risk of developing ARDS, the measurement of alveolar recruitment, potential alternative diagnoses, and outcome. While the physician must still be present to guarantee a high standard of examination, AI could help the clinical team provide the best care possible.

The Left Outflow Tract in Fetal Cardiac Screening Examination: Introduction of Quality Criteria Is Not Always Associated With an Improvement of Practice When Supervised by Humans

OBJECTIVES

Since 2016, the French CNEOF included the left ventricular outflow tract (LVOT) in the second and third trimester of pregnancy in addition to the four-chamber view and the parasagittal view of the right outflow tract. The objective of this study was to define quality criteria for fetal LVOT assessment and to perform a human audit of past and current practices, before and after the implementation of those quality criteria at a large scale.

METHODS

Seven quality criteria were investigated and rated from 0 to 1 during three periods of interest. Files were randomly selected from three centers, and average total and specific scores were calculated.

RESULTS

LVOT pictures were present in more than 94.3% of reports. The average quality score was 5.49/7 (95% confidence interval [CI]: 5.36-5.62), 5.91/7 (95% CI: 5.80-6.03), and 5.70/7 (95% CI: 5.58-5.82) for the three centers in the three periods of interest. There was no significant difference following the introduction of the quality criteria, 2017 versus 2020, P = .054.

CONCLUSION

Fetal LVOT images were present in most of ultrasound reports but the introduction of the proposed quality criteria under human supervision seems not associated with a significant change in practice.

Feasibility of using AI to auto-catch responsible frames in ultrasound screening for breast cancer diagnosis

The research of AI-assisted breast diagnosis has primarily been based on static images. It is unclear whether it represents the best diagnosis image.To explore the method of capturing complementary responsible frames from breast ultrasound screening by using artificial intelligence. We used feature entropy breast network (FEBrNet) to select responsible frames from breast ultrasound screenings and compared the diagnostic performance of AI models based on FEBrNet-recommended frames, physician-selected frames, 5-frame interval-selected frames, all frames of video, as well as that of ultrasound and mammography specialists. The AUROC of AI model based on FEBrNet-recommended frames outperformed other frame set based AI models, as well as ultrasound and mammography physicians, indicating that FEBrNet can reach level of medical specialists in frame selection.FEBrNet model can extract video responsible frames for breast nodule diagnosis, whose performance is equivalent to the doctors selected responsible frames.

How does the artificial intelligence-based image-assisted technique help physicians in diagnosis of pulmonary adenocarcinoma? A randomized controlled experiment of multicenter physicians in China

OBJECTIVE

Although artificial intelligence (AI) has achieved high levels of accuracy in the diagnosis of various diseases, its impact on physicians' decision-making performance in clinical practice is uncertain. This study aims to assess the impact of AI on the diagnostic performance of physicians with differing levels of self-efficacy under working conditions involving different time pressures.

MATERIALS AND METHODS

A 2 (independent diagnosis vs AI-assisted diagnosis) × 2 (no time pressure vs 2-minute time limit) randomized controlled experiment of multicenter physicians was conducted. Participants diagnosed 10 pulmonary adenocarcinoma cases and their diagnostic accuracy, sensitivity, and specificity were evaluated. Data analysis was performed using multilevel logistic regression.

RESULTS

One hundred and four radiologists from 102 hospitals completed the experiment. The results reveal (1) AI greatly increases physicians' diagnostic accuracy, either with or without time pressure; (2) when no time pressure, AI significantly improves physicians' diagnostic sensitivity but no significant change in specificity, while under time pressure, physicians' diagnostic sensitivity and specificity are both improved with the aid of AI; (3) when no time pressure, physicians with low self-efficacy benefit from AI assistance thus improving diagnostic accuracy but those with high self-efficacy do not, whereas physicians with low and high levels of self-efficacy both benefit from AI under time pressure.

DISCUSSION

This study is one of the first to provide real-world evidence regarding the impact of AI on physicians' decision-making performance, taking into account 2 boundary factors: clinical time pressure and physicians' self-efficacy.

CONCLUSION

AI-assisted diagnosis should be prioritized for physicians working under time pressure or with low self-efficacy.

Use of artificial intelligence as a didactic tool to improve ejection fraction assessment in the emergency department: A randomized controlled pilot study

OBJECTIVES

Incorporating artificial intelligence (AI) into echocardiography operated by clinicians working in the emergency department to accurately assess left-ventricular ejection fraction (LVEF) may lead to better diagnostic decisions. This randomized controlled pilot study aimed to evaluate AI use as a didactic tool to improve noncardiologist clinicians' assessment of LVEF from the apical 4-chamber (A4ch) view.

METHODS

This prospective randomized controlled pilot study tested the feasibility and acceptability of the incorporation of AI as a didactic tool by comparing the ability of 16 clinicians who work in the emergency department to assess LVEF before and after the introduction of an AI-based ultrasound application. Following a brief didactic course, participants were randomly equally divided into an intervention and a control group. In each of the first and second sessions, both groups were shown 10 echocardiography A4ch clips and asked to assess LVEF. Following each clip assessment, only the intervention group was shown the results of the AI-based tool. For the final session, both groups were presented with a new set of 40 clips and asked to evaluate the LVEF.

RESULTS

In the "normal-abnormal" category evaluation, as related to own baseline accuracy assessment, the intervention group had an improvement in accuracy on 50 consecutive clip assessments compared with a decline in the control group (0.10 vs. -0.12, respectively, p = 0.038). In the "significantly reduced LVEF" category, the intervention group showed significantly less decline in clip assessment as compared to the control group (-0.03 vs. -0.12, respectively, p = 0.050).

CONCLUSIONS

A study involving AI incorporation as a didactic tool for clinicians working in the emergency department appears feasible and acceptable. The introduction of an AI-based tool to clinicians working in the emergency department improved the assessment accuracy of LVEF as compared to the control group.

Deep learning in image-based breast and cervical cancer detection: a systematic review and meta-analysis

Accurate early detection of breast and cervical cancer is vital for treatment success. Here, we conduct a meta-analysis to assess the diagnostic performance of deep learning (DL) algorithms for early breast and cervical cancer identification. Four subgroups are also investigated: cancer type (breast or cervical), validation type (internal or external), imaging modalities (mammography, ultrasound, cytology, or colposcopy), and DL algorithms versus clinicians. Thirty-five studies are deemed eligible for systematic review, 20 of which are meta-analyzed, with a pooled sensitivity of 88% (95% CI 85–90%), specificity of 84% (79–87%), and AUC of 0.92 (0.90–0.94). Acceptable diagnostic performance with analogous DL algorithms was highlighted across all subgroups. Therefore, DL algorithms could be useful for detecting breast and cervical cancer using medical imaging, having equivalent performance to human clinicians. However, this tentative assertion is based on studies with relatively poor designs and reporting, which likely caused bias and overestimated algorithm performance. Evidence-based, standardized guidelines around study methods and reporting are required to improve the quality of DL research.

Classification of Lung Disease in Children by Using Lung Ultrasound Images and Deep Convolutional Neural Network

Bronchiolitis is the most common cause of hospitalization of children in the first year of life and pneumonia is the leading cause of infant mortality worldwide. Lung ultrasound technology (LUS) is a novel imaging diagnostic tool for the early detection of respiratory distress and offers several advantages due to its low-cost, relative safety, portability, and easy repeatability. More precise and efficient diagnostic and therapeutic strategies are needed. Deep-learning-based computer-aided diagnosis (CADx) systems, using chest X-ray images, have recently demonstrated their potential as a screening tool for pulmonary disease (such as COVID-19 pneumonia). We present the first computer-aided diagnostic scheme for LUS images of pulmonary diseases in children. In this study, we trained from scratch four state-of-the-art deep-learning models (VGG19, Xception, Inception-v3 and Inception-ResNet-v2) for detecting children with bronchiolitis and pneumonia. In our experiments we used a data set consisting of 5,907 images from 33 healthy infants, 3,286 images from 22 infants with bronchiolitis, and 4,769 images from 7 children suffering from bacterial pneumonia. Using four-fold cross-validation, we implemented one binary classification (healthy vs. bronchiolitis) and one three-class classification (healthy vs. bronchiolitis vs. bacterial pneumonia) out of three classes. Affine transformations were applied for data augmentation. Hyperparameters were optimized for the learning rate, dropout regularization, batch size, and epoch iteration. The Inception-ResNet-v2 model provides the highest classification performance, when compared with the other models used on test sets: for healthy vs. bronchiolitis, it provides 97.75% accuracy, 97.75% sensitivity, and 97% specificity whereas for healthy vs. bronchiolitis vs. bacterial pneumonia, the Inception-v3 model provides the best results with 91.5% accuracy, 91.5% sensitivity, and 95.86% specificity. We performed a gradient-weighted class activation mapping (Grad-CAM) visualization and the results were qualitatively evaluated by a pediatrician expert in LUS imaging: heatmaps highlight areas containing diagnostic-relevant LUS imaging-artifacts, e.g., A-, B-, pleural-lines, and consolidations. These complex patterns are automatically learnt from the data, thus avoiding hand-crafted features usage. By using LUS imaging, the proposed framework might aid in the development of an accessible and rapid decision support-method for diagnosing pulmonary diseases in children using LUS imaging.

Articles That Use Artificial Intelligence for Ultrasound: A Reader's Guide

Artificial intelligence (AI) transforms medical images into high-throughput mineable data. Machine learning algorithms, which can be designed for modeling for lesion detection, target segmentation, disease diagnosis, and prognosis prediction, have markedly promoted precision medicine for clinical decision support. There has been a dramatic increase in the number of articles, including articles on ultrasound with AI, published in only a few years. Given the unique properties of ultrasound that differentiate it from other imaging modalities, including real-time scanning, operator-dependence, and multi-modality, readers should pay additional attention to assessing studies that rely on ultrasound AI. This review offers the readers a targeted guide covering critical points that can be used to identify strong and underpowered ultrasound AI studies.

Performance of Ultrasound Techniques and the Potential of Artificial Intelligence in the Evaluation of Hepatocellular Carcinoma and Non-Alcoholic Fatty Liver Disease

Global statistics show an increasing percentage of patients that develop non-alcoholic fatty liver disease (NAFLD) and NAFLD-related hepatocellular carcinoma (HCC), even in the absence of cirrhosis. In the present review, we analyzed the diagnostic performance of ultrasonography (US) in the non-invasive evaluation of NAFLD and NAFLD-related HCC, as well as possibilities of optimizing US diagnosis with the help of artificial intelligence (AI) assistance. To date, US is the first-line examination recommended in the screening of patients with clinical suspicion of NAFLD, as it is readily available and leads to a better disease-specific surveillance. However, the conventional US presents limitations that significantly hamper its applicability in quantifying NAFLD and accurately characterizing a given focal liver lesion (FLL). Ultrasound contrast agents (UCAs) are an essential add-on to the conventional B-mode US and to the Doppler US that further empower this method, allowing the evaluation of the enhancement properties and the vascular architecture of FLLs, in comparison to the background parenchyma. The current paper also explores the new universe of AI and the various implications of deep learning algorithms in the evaluation of NAFLD and NAFLD-related HCC through US methods, concluding that it could potentially be a game changer for patient care.

Accelerating Detection of Lung Pathologies with Explainable Ultrasound Image Analysis

Care during the COVID-19 pandemic hinges upon the existence of fast, safe, and highly sensitive diagnostic tools. Considering significant practical advantages of lung ultrasound (LUS) over other imaging techniques, but difficulties for doctors in pattern recognition, we aim to leverage machine learning toward guiding diagnosis from LUS. We release the largest publicly available LUS dataset for COVID-19 consisting of 202 videos from four classes (COVID-19, bacterial pneumonia, non-COVID-19 viral pneumonia and healthy controls). On this dataset, we perform an in-depth study of the value of deep learning methods for the differential diagnosis of lung pathologies. We propose a frame-based model that correctly distinguishes COVID-19 LUS videos from healthy and bacterial pneumonia data with a sensitivity of 0.90±0.08 and a specificity of 0.96±0.04. To investigate the utility of the proposed method, we employ interpretability methods for the spatio-temporal localization of pulmonary biomarkers, which are deemed useful for human-in-the-loop scenarios in a blinded study with medical experts. Aiming for robustness, we perform uncertainty estimation and demonstrate the model to recognize low-confidence situations which also improves performance. Lastly, we validated our model on an independent test dataset and report promising performance (sensitivity 0.806, specificity 0.962). The provided dataset facilitates the validation of related methodology in the community and the proposed framework might aid the development of a fast, accessible screening method for pulmonary diseases. Dataset and all code are publicly available at: https://github.com/BorgwardtLab/covid19_ultrasound.

Applications of Artificial Intelligence (AI) for cardiology during COVID-19 pandemic

Background and aims

Artificial Intelligence (AI) shows extensive capabilities to impact different healthcare areas during the COVID-19 pandemic positively. This paper tries to assess the capabilities of AI in the field of cardiology during the COVID-19 pandemic. This technology is useful to provide advanced technology-based treatment in cardiology as it can help analyse and measure the functioning of the human heart.

Methods

We have studied a good number of research papers on Artificial Intelligence on cardiology during the COVID-19 pandemic to identify its significant benefits, applications, and future scope. AI uses artificial neuronal networks (ANN) to predict. In cardiology, it is used to predict the survival of a COVID-19 patient from heart failure.

Results

AI involves complex algorithms for predicting somewhat successful diagnosis and treatments. This technology uses different techniques, such as cognitive computing, deep learning, and machine learning. It is incorporated to make a decision and resolve complex challenges. It can focus on a large number of diseases, their causes, interactions, and prevention during the COVID-19 pandemic. This paper introduces AI-based care and studies its need in the field of cardiology. Finally, eleven major applications of AI in cardiology during the COVID-19 pandemic are identified and discussed.

Conclusions

Cardiovascular diseases are one of the major causes of death in human beings, and it is increasing for the last few years. Cardiology patients' treatment is expensive, so this technology is introduced to provide a new pathway and visualise cardiac anomalies. AI is used to identify novel drug therapies and improve the efficiency of a physician. It is precise to predict the outcome of the COVID-19 patient from cardiac-based algorithms. Artificial Intelligence is becoming a popular feature of various engineering and healthcare sectors, is thought for providing a sustainable treatment platform. During the COVID-19 pandemic, this technology digitally controls some processes of treatments.

Lung ultrasound: The future ahead and the lessons learned from COVID-19

Lung ultrasound (LUS) is a rapidly evolving field of application for ultrasound technologies. Especially during the current pandemic, many clinicians around the world have employed LUS to assess the condition of the lung for patients suspected and/or affected by COVID-19. However, LUS is currently performed with standard ultrasound imaging, which is not designed to cope with the high air content present in lung tissues. Nowadays LUS lacks standardization and suffers from the absence of quantitative approaches. To elevate LUS to the level of other ultrasound imaging applications, several aspects deserve attention from the technical and clinical world. This overview piece tries to provide the reader with a forward-looking view on the future for LUS.

Artificial Intelligence and Health in Nepal

The growth in information technology and computer capacity has opened up opportunities to deal with much and much larger data sets than even a decade ago. There has been a technological revolution of big data and Artificial Intelligence (AI). Perhaps many readers would immediately think about robotic surgery or self-driving cars, but there is much more to AI. This Short Communication starts with an overview of the key terms, including AI, machine learning, deep learning and Big Data. This Short Communication highlights so developments of AI in health that could benefit a low-income country like Nepal and stresses the need for Nepal's health and education systems to track such developments and apply them locally. Moreover, Nepal needs to start growing its own AI expertise to help develop national or South Asian solutions. This would require investing in local resources such as access to computer power/capacity as well as training young Nepali to work in AI.