Considerations on Baseline Generation for Imaging AI Studies Illustrated on the CT-Based Prediction of Empyema and Outcome Assessment (original) (raw)
Related papers
The Use Of AI In Advanced Medical Imaging
CERN European Organization for Nuclear Research - Zenodo, 2022
Machine learning and AI have the potential to change almost every facet of human life; medical imaging and data interpretation is no exception to this rule. This article discusses current and potential uses of machine learning and artificial intelligence in cardiology, diagnostic imaging, and much more, as well as guidance for physicians on critical elements of AI and ML. Based on what it can do, AI is currently in the initial development stages and is divided into two categories, weak and strong AI. The research paper explores the capabilities of ANI, otherwise known as weak AI, in the medical field. Predictive modeling fundamentals important in cardiology are first reviewed, including feature selection and modern implementation of machine learning combined with hard-coded programming. Second, it analyzes several performances in cardiology and relevant disciplines and discusses some of the most popular supervised learning & implementation methods. Third, it shows how unsupervised learning, including deep understanding, may allow precision cardiology and enhance patient outcomes. It presents examples from both general care and cardiovascular medicine as background.
Artificial Intelligence in Diagnostic Imaging
2023
In this review article, the current and future impact of artificial intelligence (AI) technologies on diagnostic imaging is discussed, with a focus on cardio-thoracic applications. The processing of imaging data is described at 4 levels of increasing complexity and wider implications. At the examination level, AI aims at improving, simplifying, and standardizing image acquisition and processing. Systems for AI-driven automatic patient iso-centering before a computed tomography (CT) scan, patient-specific adaptation of image acquisition parameters, and creation of optimized and standardized visualizations, for example, automatic rib-unfolding, are discussed. At the reading and reporting levels, AI focuses on automatic detection and characterization of features and on automatic measurements in the images. A recently introduced AI system for chest CT imaging is presented that reports specific findings such as nodules, low-attenuation parenchyma, and coronary calcifications, including automatic measurements of, for example, aortic diameters. At the prediction and prescription levels, AI focuses on risk prediction and stratification, as opposed to merely detecting, measuring, and quantifying images. An AI-based approach for individualizing radiation dose in lung stereotactic body radiotherapy is discussed. The digital twin is presented as a concept of individualized computational modeling of human physiology, with AI-based CTfractional flow reserve modeling as a first example. Finally, at the cohort and population analysis levels, the focus of AI shifts from clinical decision-making to operational decisions.
Background: Because of the growing need to provide better global healthcare, computer-based and robotic healthcare equipment that depend on artificial intelligence have seen an increase in development. In order to evaluate artificial intelligence (AI) in computer technology, the Turing test was created. For evaluating the future generation of medical diagnostics and medical robots, it remains an essential qualitative instrument.Method: We propose a novel methodology to assess AI-based healthcare technology that provided verifiable diagnostic accuracy and statistical robustness. In order to run our test, we used a State-of-the-art AI model and compared it against radiologist for checking how generalized of the model is and if any biases are prevalent. Results: We achieved results that can evaluate the performance of our chosen model for this study in a clinical setting and we also applied a quantifiable methods for evaluating our modified turing test results using a meta-analytical e...
2021
Review question / Objective: The aim of this systematic review is to compare the accuracy of artificial intelligence algorithms with radiologist panels in CT interpretation in covid-19. Condition being studied: COVID-19 disease was reported as the cause of the outbreak of pneumonia at the end of 2019. One of the main complications of COVID-19 is pulmonary involvement which could be diagnosed by CT-scan dominantly. Because of the increasing rate of these patients along with considering patients in remote areas, CT interpretations are a heavy burden on radiologists. Therefore artificial intelligence algorithms have become critical and time-saving systems in decision-making for these patients.
Value assessment of artificial intelligence in medical imaging: a scoping review
BMC Medical Imaging, 2022
Background Artificial intelligence (AI) is seen as one of the major disrupting forces in the future healthcare system. However, the assessment of the value of these new technologies is still unclear, and no agreed international health technology assessment-based guideline exists. This study provides an overview of the available literature in the value assessment of AI in the field of medical imaging. Methods We performed a systematic scoping review of published studies between January 2016 and September 2020 using 10 databases (Medline, Scopus, ProQuest, Google Scholar, and six related databases of grey literature). Information about the context (country, clinical area, and type of study) and mentioned domains with specific outcomes and items were extracted. An existing domain classification, from a European assessment framework, was used as a point of departure, and extracted data were grouped into domains and content analysis of data was performed covering predetermined themes. Results Seventy-nine studies were included out of 5890 identified articles. An additional seven studies were identified by searching reference lists, and the analysis was performed on 86 included studies. Eleven domains were identified: (1) health problem and current use of technology, (2) technology aspects, (3) safety assessment, (4) clinical effectiveness, (5) economics, (6) ethical analysis, (7) organisational aspects, (8) patients and social aspects, (9) legal aspects, (10) development of AI algorithm, performance metrics and validation, and (11) other aspects. The frequency of mentioning a domain varied from 20 to 78% within the included papers. Only 15/86 studies were actual assessments of AI technologies. The majority of data were statements from reviews or papers voicing future needs or challenges of AI research, i.e. not actual outcomes of evaluations. Conclusions This review regarding value assessment of AI in medical imaging yielded 86 studies including 11 identified domains. The domain classification based on European assessment framework proved useful and current analysis added one new domain. Included studies had a broad range of essential domains about addressing AI technologies highlighting the importance of domains related to legal and ethical aspects.
Towards objective and systematic evaluation of bias in medical imaging AI
arXiv (Cornell University), 2023
Objective: Artificial intelligence (AI) models trained using medical images for clinical tasks often exhibit bias in the form of subgroup performance disparities. However, since not all sources of bias in real-world medical imaging data are easily identifiable, it is challenging to comprehensively assess their impacts. In this article, we introduce an analysis framework for systematically and objectively investigating the impact of biases in medical images on AI models. Materials and Methods: Our framework utilizes synthetic neuroimages with known disease effects and sources of bias. We evaluated the impact of bias effects and the efficacy of 3 bias mitigation strategies in counterfactual data scenarios on a convolutional neural network (CNN) classifier. Results: The analysis revealed that training a CNN model on the datasets containing bias effects resulted in expected subgroup performance disparities. Moreover, reweighing was the most successful bias mitigation strategy for this setup. Finally, we demonstrated that explainable AI methods can aid in investigating the manifestation of bias in the model using this framework. Discussion: The value of this framework is showcased in our findings on the impact of bias scenarios and efficacy of bias mitigation in a deep learning model pipeline. This systematic analysis can be easily expanded to conduct further controlled in silico trials in other investigations of bias in medical imaging AI. Conclusion: Our novel methodology for objectively studying bias in medical imaging AI can help support the development of clinical decisionsupport tools that are robust and responsible.
Diagnostics
The purpose of our work was to assess the independent and incremental value of AI-derived quantitative determination of lung lesions extent on initial CT scan for the prediction of clinical deterioration or death in patients hospitalized with COVID-19 pneumonia. 323 consecutive patients (mean age 65 ± 15 years, 192 men), with laboratory-confirmed COVID-19 and an abnormal chest CT scan, were admitted to the hospital between March and December 2020. The extent of consolidation and all lung opacities were quantified on an initial CT scan using a 3D automatic AI-based software. The outcome was known for all these patients. 85 (26.3%) patients died or experienced clinical deterioration, defined as intensive care unit admission. In multivariate regression based on clinical, biological and CT parameters, the extent of all opacities, and extent of consolidation were independent predictors of adverse outcomes, as were diabetes, heart disease, C-reactive protein, and neutrophils/lymphocytes r...