Hybrid Artificial Intelligence Solution Combining Convolutional Neural Network and Analytical Approach Showed Higher Accuracy in A-lines Detection on Lung Ultrasound in Thoracic Surgery Patients Compared with Radiology Resident.

OBJECTIVES: Lung ultrasound reduces the number of chest X-rays after thoracic surgery and thus the radiation. COVID-19 pandemic has accelerated research in lung ultrasound artifacts detection using artificial intelligence. This study evaluates the accuracy of artificial intelligence in A-lines detection in thoracic surgery patients using a novel hybrid solution that combines convolutional neural networks and analytical approach and compares it with a radiology resident and radiology experts' results. DESIGN: Prospective observational study. MATERIAL AND METHODS: Single-center study evaluates the accuracy of artificial intelligence and a radiology resident in A-line detection on lung ultrasound footages compared with the consensual opinion of two expert radiologists as the reference. After resident's first reading, the artificial intelligence results were presented to the resident and he was asked to revise the results based on artificial intelligence. RESULTS: 82 consecutive patients underwent 82 ultrasound examinations. 328 ultrasound recordings were evaluated. Accuracy, sensitivity, specificity, positive and negative predictive values of artificial inelligence in A-line detection were 0.866, 0.928, 0.834, 0.741 and 0.958 respectively. The resident's values were 0.558, 0.973, 0.346, 0.432 and 0.962 respectively. The resident's values after correction based on artificial intelligence results were 0.854, 0.991, 0.783, 0.701 and 0.994 respectively. CONCLUSION: Artificial intelligence showed high accuracy in A-line detection in thoracic surgery patients and was more accurate compared to a resident. Artificial intelligence could play important role in lung ultrasound artifact detection in thoracic surgery patients and in residents' education.

Lung Ultrasound Reduces Chest X-rays in Postoperative Care after Thoracic Surgery: Is There a Role for Artificial Intelligence?-Systematic Review.

BACKGROUND: Chest X-ray (CXR) remains the standard imaging modality in postoperative care after non-cardiac thoracic surgery. Lung ultrasound (LUS) showed promising results in CXR reduction. The aim of this review was to identify areas where the evaluation of LUS videos by artificial intelligence could improve the implementation of LUS in thoracic surgery. METHODS: A literature review of the replacement of the CXR by LUS after thoracic surgery and the evaluation of LUS videos by artificial intelligence after thoracic surgery was conducted in Medline. RESULTS: Here, eight out of 10 reviewed studies evaluating LUS in CXR reduction showed that LUS can reduce CXR without a negative impact on patient outcome after thoracic surgery. No studies on the evaluation of LUS signs by artificial intelligence after thoracic surgery were found. CONCLUSION: LUS can reduce CXR after thoracic surgery. We presume that artificial intelligence could help increase the LUS accuracy, objectify the LUS findings, shorten the learning curve, and decrease the number of inconclusive results. To confirm this assumption, clinical trials are necessary. This research is funded by the Slovak Research and Development Agency, grant number APVV 20-0232.

Explainability of deep learning models in medical video analysis: a survey.

Deep learning methods have proven to be effective for multiple diagnostic tasks in medicine and have been performing significantly better in comparison to other traditional machine learning methods. However, the black-box nature of deep neural networks has restricted their use in real-world applications, especially in healthcare. Therefore, explainability of the machine learning models, which focuses on providing of the comprehensible explanations of model outputs, may affect the possibility of adoption of such models in clinical use. There are various studies reviewing approaches to explainability in multiple domains. This article provides a review of the current approaches and applications of explainable deep learning for a specific area of medical data analysis-medical video processing tasks. The article introduces the field of explainable AI and summarizes the most important requirements for explainability in medical applications. Subsequently, we provide an overview of existing methods, evaluation metrics and focus more on those that can be applied to analytical tasks involving the processing of video data in the medical domain. Finally we identify some of the open research issues in the analysed area.

Classification of the drifting data streams using heterogeneous diversified dynamic class-weighted ensemble.

Data streams can be defined as the continuous stream of data coming from different sources and in different forms. Streams are often very dynamic, and its underlying structure usually changes over time, which may result to a phenomenon called concept drift. When solving predictive problems using the streaming data, traditional machine learning models trained on historical data may become invalid when such changes occur. Adaptive models equipped with mechanisms to reflect the changes in the data proved to be suitable to handle drifting streams. Adaptive ensemble models represent a popular group of these methods used in classification of drifting data streams. In this paper, we present the heterogeneous adaptive ensemble model for the data streams classification, which utilizes the dynamic class weighting scheme and a mechanism to maintain the diversity of the ensemble members. Our main objective was to design a model consisting of a heterogeneous group of base learners (Naive Bayes, k-NN, Decision trees), with adaptive mechanism which besides the performance of the members also takes into an account the diversity of the ensemble. The model was experimentally evaluated on both real-world and synthetic datasets. We compared the presented model with other existing adaptive ensemble methods, both from the perspective of predictive performance and computational resource requirements.