Automated interpretation of ventilation-perfusion lung scintigrams for the diagnosis of pulmonary embolism using artificial neural networks

Charting Tomorrow's Healthcare: A Traditional Literature Review for an Artificial Intelligence-Driven Future

Electronic health record (EHR) systems have developed over time in parallel with general advancements in mainstream technology. As artificially intelligent (AI) systems rapidly impact multiple societal sectors, it has become apparent that medicine is not immune from the influences of this powerful technology. Particularly appealing is how AI may aid in improving healthcare efficiency with note-writing automation. This literature review explores the current state of EHR technologies in healthcare, specifically focusing on possibilities for addressing EHR challenges through the automation of dictation and note-writing processes with AI integration. This review offers a broad understanding of existing capabilities and potential advancements, emphasizing innovations such as voice-to-text dictation, wearable devices, and AI-assisted procedure note dictation. The primary objective is to provide researchers with valuable insights, enabling them to generate new technologies and advancements within the healthcare landscape. By exploring the benefits, challenges, and future of AI integration, this review encourages the development of innovative solutions, with the goal of enhancing patient care and healthcare delivery efficiency.

The Past, Present, and Future Role of Artificial Intelligence in Ventilation/Perfusion Scintigraphy: A Systematic Review

Ventilation-perfusion (V/Q) lung scans constitute one of the oldest nuclear medicine procedures, remain one of the few studies performed in the acute setting, and are amongst the few performed in the emergency setting. V/Q studies have witnessed a long fluctuation in adoption rates in parallel to continuous advances in image processing and computer vision techniques. This review provides an overview on the status of artificial intelligence (AI) in V/Q scintigraphy. To clearly assess the past, current, and future role of AI in V/Q scans, we conducted a systematic Ovid MEDLINE(R) literature search from 1946 to August 5, 2022 in addition to a manual search. The literature was reviewed and summarized in terms of methodologies and results for the various applications of AI to V/Q scans. The PRISMA guidelines were followed. Thirty-one publications fulfilled our search criteria and were grouped into two distinct categories: (1) disease diagnosis/detection (N = 22, 71.0%) and (2) cross-modality image translation into V/Q images (N = 9, 29.0%). Studies on disease diagnosis and detection relied heavily on shallow artificial neural networks for acute pulmonary embolism (PE) diagnosis and were primarily published between the mid-1990s and early 2000s. Recent applications almost exclusively regard image translation tasks from CT to ventilation or perfusion images with modern algorithms, such as convolutional neural networks, and were published between 2019 and 2022. AI research in V/Q scintigraphy for acute PE diagnosis in the mid-90s to early 2000s yielded promising results but has since been largely neglected and thus have yet to benefit from today's state-of-the art machine-learning techniques, such as deep neural networks. Recently, the main application of AI for V/Q has shifted towards generating synthetic ventilation and perfusion images from CT. There is therefore considerable potential to expand and modernize the use of real V/Q studies with state-of-the-art deep learning approaches, especially for workflow optimization and PE detection at both acute and chronic stages. We discuss future challenges and potential directions to compensate for the lag in this domain and enhance the value of this traditional nuclear medicine scan.

Clinical decision support system RHINA in the diagnosis and treatment of acute or chronic rhinosinusitis

Background

Rhinosinusitis is an inflammation of the sinonasal cavity which affects roughly one in seven people per year. Acute rhinosinusitis (ARS) is mostly, apart from allergic etiology, caused by a viral infection and, in some cases (30–50%), by a bacterial superinfection. Antibiotics, indicated only in rare cases according to EPOS guidelines, are nevertheless prescribed in more than 80% of ARS cases, which increases the resistant bacterial strains in the population.

Methods

We have designed a clinical decision support system (CDSS), RHINA, based on a web application created in HTML 5, using JavaScript, jQuery, CCS3 and PHP scripting language. The presented CDSS RHINA helps general physicians to decide whether or not to prescribe antibiotics in patients with rhinosinusitis.

Results

In a retrospective study of a total of 1465 patients with rhinosinusitis, the CDSS RHINA presented a 90.2% consistency with the diagnosis and treatment made by the ENT specialist.

Conclusion

Patients assessed with the assistance of our CDSS RHINA would decrease the over-prescription of antibiotics, which in turn would help to reduce the bacterial resistance to the most commonly prescribed antibiotics.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-021-01599-3.

Machine Learning and Deep Neural Network Applications in the Thorax: Pulmonary Embolism, Chronic Thromboembolic Pulmonary Hypertension, Aorta, and Chronic Obstructive Pulmonary Disease

The radiologic community is rapidly integrating a revolution that has not fully entered daily practice. It necessitates a close collaboration between computer scientists and radiologists to move from concepts to practical applications. This article reviews the current littérature on machine learning and deep neural network applications in the field of pulmonary embolism, chronic thromboembolic pulmonary hypertension, aorta, and chronic obstructive pulmonary disease.

From Early Morphometrics to Machine Learning-What Future for Cardiovascular Imaging of the Pulmonary Circulation?

Imaging plays a cardinal role in the diagnosis and management of diseases of the pulmonary circulation. Behind the picture itself, every digital image contains a wealth of quantitative data, which are hardly analysed in current routine clinical practice and this is now being transformed by radiomics. Mathematical analyses of these data using novel techniques, such as vascular morphometry (including vascular tortuosity and vascular volumes), blood flow imaging (including quantitative lung perfusion and computational flow dynamics), and artificial intelligence, are opening a window on the complex pathophysiology and structure-function relationships of pulmonary vascular diseases. They have the potential to make dramatic alterations to how clinicians investigate the pulmonary circulation, with the consequences of more rapid diagnosis and a reduction in the need for invasive procedures in the future. Applied to multimodality imaging, they can provide new information to improve disease characterization and increase diagnostic accuracy. These new technologies may be used as sophisticated biomarkers for risk prediction modelling of prognosis and for optimising the long-term management of pulmonary circulatory diseases. These innovative techniques will require evaluation in clinical trials and may in themselves serve as successful surrogate end points in trials in the years to come.

Neural hypernetwork approach for pulmonary embolism diagnosis

BACKGROUND

Hypernetworks are based on topological simplicial complexes and generalize the concept of two-body relation to many-body relation. Furthermore, Hypernetworks provide a significant generalization of network theory, enabling the integration of relational structure, logic and analytic dynamics. A pulmonary embolism is a blockage of the main artery of the lung or one of its branches, frequently fatal.

RESULTS

Our study uses data on 28 diagnostic features of 1427 people considered to be at risk of pulmonary embolism enrolled in the Department of Internal and Subintensive Medicine of an Italian National Hospital "Ospedali Riuniti di Ancona". Patients arrived in the department after a first screening executed by the emergency room. The resulting neural hypernetwork correctly recognized 94% of those developing pulmonary embolism. This is better than previous results obtained with other methods (statistical selection of features, partial least squares regression, topological data analysis in a metric space).

CONCLUSION

In this work we successfully derived a new integrative approach for the analysis of partial and incomplete datasets that is based on Q-analysis with machine learning. The new approach, called Neural Hypernetwork, has been applied to a case study of pulmonary embolism diagnosis. The novelty of this method is that it does not use clinical parameters extracted by imaging analysis.

A knowledge-based artificial neural network classifier for pulmonary embolism diagnosis

This paper aims to demonstrate that knowledge-based hybrid learning algorithms are positioned to offer better performance in comparison with purely empirical machine learning algorithms for the automatic classification task associated with the diagnosis of a medical condition described as pulmonary embolism (PE). The main premise is that there exists substantial and significant specialized knowledge in the domain of PE, which can readily be leveraged for bootstrapping a knowledge-based hybrid classifier that employs both the explanation-based and the empirical learning. The modified prospective investigation of pulmonary embolism diagnosis (PIOPED) criteria, which represent the pre-eminent collective experiential knowledge base among nuclear radiologists as a diagnosis procedure for PE, are conveniently defined in terms of a set of if-then rules. As such, it lends itself to being captured into a knowledge base through instantiating a knowledge-based hybrid learning algorithm. This study shows the instantiation of a knowledge-based artificial neural network (KBANN) classifier through the modified PIOPED criteria for the diagnosis of PE. The development effort for the KBANN that captures the rule base associated with the PIOPED criteria as well as further refinement of the same rule base through highly specialized domain expertise is presented. Through a testing dataset generated with the help of nuclear radiologists, performance of the instantiated KBANN is profiled. Performances of a set of empirical machine learning algorithms, which are configured as classifiers and include the nai ve Bayes, the Bayesian Belief network, the multilayer perceptron neural network, the C4.5 decision tree algorithm, and two meta learners with boosting and bagging, are also profiled on the same dataset for the purpose of comparison with that of the KBANN. Simulation results indicate that the KBANN can effectively model and leverage the PIOPED knowledge base and its further refinements through the domain expertise, and exhibited enhanced performance compared to those of purely empirical learning based classifiers.

Objective Analysis of Tomographic Ventilation–Perfusion Scintigraphy in Pulmonary Embolism

RATIONALE

Ventilation-perfusion scintigraphy is highly sensitive for pulmonary embolism (PE), but its clinical usefulness is limited by its nondiagnostic rate. Objective analysis of single photon emission computed tomography (SPECT) three-dimensional scintigraphy may improve its diagnostic performance compared with subjective interpretation.

OBJECTIVES

To determine the diagnostic accuracy of objective SPECT analysis in PE.

METHODS

We determined the ventilation/perfusion (V(.)/Q(.)) relationship using SPECT scintigraphy in a retrospective cohort of 73 patients. Measures of V(.)/Q(.) heterogeneity (logSD(Q(.)), logSD(V(.)), logSD(VQR)), including a novel parameter, the weighted median V(.)/Q(.) value, were calculated. Using receiver operating characteristic (ROC) analysis, each parameter's diagnostic accuracy was determined. The weighted median V(.)/Q(.) value was then assessed prospectively in a second cohort of 50 patients.

MEASUREMENTS AND MAIN RESULTS

In cohort 1, all parameters of V(.)/Q(.) heterogeneity were higher in patients with PE (p < 0.002). The weighted median V(.)/Q(.) had the highest area under the ROC curve (0.93; 95% confidence interval, 0.87-0.98). When applied to the prospective cohort, the area under the ROC curve was 0.87 (95% confidence interval, 0.75-0.99), with diagnostic cutoff values having negative and positive predictive values of 96 and 83%, respectively. In the retrospective and prospective cohorts, 82 and 73% of initially reported intermediate or low probability scans had diagnostic weighted median V(.)/Q(.) values, with 90 and 100% accuracy, respectively.

CONCLUSIONS

Objective analysis of SPECT scintigraphy has a high diagnostic accuracy in patients with suspected PE. Objective analysis has the potential to reduce the number of nondiagnostic scan results, and may be useful for quantifying V(.)/Q(.) mismatch in other pulmonary disorders.

The lung scan and the abnormal chest X-ray: difficult diagnoses

PURPOSE

The ventilation-perfusion lung scan is evolving into an alternative diagnostic test for patients who cannot tolerate contrast computed tomography studies. It is likely that this shift in patient population will result in a larger proportion of patients with abnormal chest radiographs. The purpose of this study was to determine whether a computer based scan analysis could assist clinical interpretation in this diagnostically difficult population.

METHODS

Radionuclide ventilation-perfusion (V-P) images were obtained from 118 patients with normal chest radiographs and 144 patients with abnormal radiographs who underwent pulmonary angiography within 3 days of the radionuclide study. Artificial neural networks (ANNs) were created using only objective image-derived inputs to diagnose the presence of pulmonary embolism. The ANN predictions were compared with clinical scan interpretations and with the results of angiography.

RESULTS

In both patients with normal and with abnormal chest radiographs, the ANN based method performed comparably to the clinical interpretation of record. An average of the clinical and ANN estimates of the likelihood of embolism was more accurate than was either method alone.

CONCLUSIONS

Computer-based V-P scan analysis performs comparably to clinical interpretation for patients with abnormal chest radiographs. The different analytical perspective of the digital method improves test performance when used in conjunction with standard clinical interpretation. This can improve the chances of reaching a diagnosis for patients who lack diagnostic alternatives to the V-P scan.

An automated method for the detection of pulmonary embolism in V/Q-scans

In this paper, a fully automatic method for the diagnosis of pulmonary embolism (PE) from V/Q-scans is presented. Image analysis is applied to the ventilation and the perfusion images obtained in the V/Q-scan. The difference of the ventilation and the perfusion is calculated after transformation and hot-spot reduction of the images. From this difference image the integral of the underperfused areas are used as features. With the aid of these features a simple test for PE is devised. The method is evaluated on two sets of patients. One set comprises 102 patients who have undergone both V/Q-scanning and angiography. The performance given as the area under the Receiver Operating Characteristic (ROC) curve is 0.85. Another set is made up by the 507 consecutive patients examined with V/Q-scanning at Lund University Hospital in Sweden. In this case, the reference was the consensus opinion of two radiologists, the ROC-area is 0.67. A fully automatic and reasonably robust expert system is developed to aid the radiologist in the interpretation of V/Q-scans for PE.

Predicting the presence of acute pulmonary embolism: a comparative analysis of the artificial neural network, logistic regression, and threshold models

OBJECTIVE

The objective of this study was to determine whether an artificial neural network, a new data analysis method, offers increased performance over conventional logistic regression in predicting the presence of a pulmonary embolism for patients in a well-known data set.

MATERIALS AND METHODS

Data from the 1064 patients who received an angiographically based diagnosis of pulmonary embolism in the Prospective Investigation of Pulmonary Embolism Diagnosis study were encoded using a previously described method. The 21 input variables represented abnormalities identified on each patient's ventilation-perfusion scan and chest radiograph. Two methods-an artificial neural network with one hidden layer and a multivariate logistic regression-were compared for accuracy in predicting the presence or absence of pulmonary embolism on subsequent pulmonary arteriography.

RESULTS

No significant difference was observed between the two methods. Areas under the receiver operating characteristic curves +/- standard deviation were 0.78 +/- 0.02 for the artificial neural network model and 0.79 +/- 0.02 for the logistic regression model. Furthermore, use of these two methods resulted in no more diagnostic accuracy than did the use of a simple threshold model based only on the number of subsegmental perfusion defects, which was the dominant input variable.

CONCLUSION

In the study population, the usefulness of data from ventilation-perfusion scans as predictors of the presence of a pulmonary embolism was similar for the three analytic methods, a finding that reinforces the importance of making comparisons to simpler or more established methods when performing studies involving complex analytic models, such as artificial neural networks.