scholarly journals The Applications of Artificial Intelligence in Chest Imaging of COVID-19 Patients: A Literature Review

Diagnostics ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1317
Author(s):  
Maria Elena Laino ◽  
Angela Ammirabile ◽  
Alessandro Posa ◽  
Pierandrea Cancian ◽  
Sherif Shalaby ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Literature Review ◽  
Diagnostic Imaging ◽  
Clinical Work ◽  
Rapid Expansion ◽  
Chest Imaging ◽  
Imaging Data ◽  
Prognostic Information ◽  
Quantitative Ct ◽  
Work Up

Diagnostic imaging is regarded as fundamental in the clinical work-up of patients with a suspected or confirmed COVID-19 infection. Recent progress has been made in diagnostic imaging with the integration of artificial intelligence (AI) and machine learning (ML) algorisms leading to an increase in the accuracy of exam interpretation and to the extraction of prognostic information useful in the decision-making process. Considering the ever expanding imaging data generated amid this pandemic, COVID-19 has catalyzed the rapid expansion in the application of AI to combat disease. In this context, many recent studies have explored the role of AI in each of the presumed applications for COVID-19 infection chest imaging, suggesting that implementing AI applications for chest imaging can be a great asset for fast and precise disease screening, identification and characterization. However, various biases should be overcome in the development of further ML-based algorithms to give them sufficient robustness and reproducibility for their integration into clinical practice. As a result, in this literature review, we will focus on the application of AI in chest imaging, in particular, deep learning, radiomics and advanced imaging as quantitative CT.

scholarly journals Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: advances in imaging towards to precision medicine

2019 ◽  
Vol 52 (6) ◽  
pp. 387-396 ◽  
Author(s):  
Marcel Koenigkam Santos ◽  
José Raniery Ferreira Júnior ◽  
Danilo Tadao Wada ◽  
Ariane Priscilla Magalhães Tenório ◽  
Marcello Henrique Nogueira Barbosa ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Diagnostic Imaging ◽  
Precision Medicine ◽  
Quantitative Information ◽  
Computer Aided Diagnosis ◽  
Rapid Expansion ◽  
Computer Aided ◽  
The Impact ◽  
Aided Diagnosis

Abstract The discipline of radiology and diagnostic imaging has evolved greatly in recent years. We have observed an exponential increase in the number of exams performed, subspecialization of medical fields, and increases in accuracy of the various imaging methods, making it a challenge for the radiologist to “know everything about all exams and regions”. In addition, imaging exams are no longer only qualitative and diagnostic, providing now quantitative information on disease severity, as well as identifying biomarkers of prognosis and treatment response. In view of this, computer-aided diagnosis systems have been developed with the objective of complementing diagnostic imaging and helping the therapeutic decision-making process. With the advent of artificial intelligence, “big data”, and machine learning, we are moving toward the rapid expansion of the use of these tools in daily life of physicians, making each patient unique, as well as leading radiology toward the concept of multidisciplinary approach and precision medicine. In this article, we will present the main aspects of the computational tools currently available for analysis of images and the principles of such analysis, together with the main terms and concepts involved, as well as examining the impact that the development of artificial intelligence has had on radiology and diagnostic imaging.

scholarly journals Myocardial fibrosis quantification by cardiac CT predicts outcome in severe aortic stenosis

2021 ◽  
Vol 22 (Supplement_1) ◽  
Author(s):  
P Scully ◽  
KP Patel ◽  
JB Augusto ◽  
E Klotz ◽  
G Lloyd ◽  
...  
Keyword(s):  
Myocardial Fibrosis ◽  
Severe Aortic Stenosis ◽  
Extracellular Volume ◽  
Clinical Work ◽  
Prognostic Information ◽  
Dose Length Product ◽  
Post Contrast ◽  
Entire Cohort ◽  
Cardiac Amyloid ◽  
Work Up

Abstract Funding Acknowledgements Type of funding sources: Foundation. Main funding source(s): British Heart Foundation Background Myocardial extracellular volume (ECV) increases with fibrosis, oedema or infiltration. ECV by CMR predicts all-cause and cardiovascular mortality in severe AS after valve intervention. Previous studies have shown that ECV can be reliably quantified by computed tomography (ECVCT), but these studies have not differentiated between ECV elevation due to fibrosis or cardiac amyloid deposition (13-16% of patients with severe AS).  Purpose We hypothesised that ECVCT quantification, performed as part of a transcatheter aortic valve implantation (TAVI) work-up CT, predicts survival in patients with severe AS without cardiac amyloid (lone AS). Methods Patients aged ≥75, with severe AS, referred for TAVI at Barts Heart Centre (as part of ATTRact-AS (NCT03029026)) underwent CT as part of their clinical work-up. All patients had 99mTc-3,3-diphosphono-1,2-propanodicarboxylic acid (DPD) scintigraphy and those with a positive result were excluded.  CT was performed on a 128-slice dual-source 3rdgeneration scanner (Siemens Somatom FORCE) and ECVCT was acquired during the TAVI work-up CT using additional pre- and 3-minute post-contrast ‘axial shuttle mode’ acquisitions (no additional contrast).  ECVCT was calculated from the Hounsfield units (HU) and a venous haematocrit (HCT): ECVCT = (1-HCT) x (ΔHUmyo/ΔHUblood). Results Following exclusion of 16 patients with cardiac uptake on DPD, 93 patients (41% male, aged 85 ± 5 years) were included in the study.  All patients had severe AS (AV Vmax 4.12 ± 0.63m/s, mean AV gradient 42 ± 14mmHg, AVA 0.71 ± 0.23cm2). The mean HCT was 0.38 ± 0.04 and total dose-length product for additional research scans was 364 ± 41 mGy.cm. 76 patients (82%) underwent TAVI. ECVCT was 32 ± 3% in the entire cohort, which we then split into those with a ‘higher’ ECVCT (>34%, n = 23, representing the highest quartile) and those with a ‘lower’ ECVCT (≤34%, n = 70, representing the lower quartiles). Over a median follow-up of 25 months (IQR 17-34 months) there were 27 deaths (29%), of whom 11 did not undergo TAVI (41%). There were 10 deaths in the 23 patients (44%) with a higher ECVCT, compared to 17 in the 70 patients (24%) with a lower ECVCT (p = 0.03, figure 1). This mortality difference remained significant when those patients who did not undergo TAVI were excluded (p = 0.03). Conclusions Myocardial fibrosis quantified by ECVCT is associated with a significantly worse prognosis in lone AS, even after patients with AS-amyloid are excluded. ECVCT can be performed as a simple addition to the TAVI work-up CT and provides additional prognostic information. Abstract Figure.

Clinical Work-Up, Diagnostic Imaging, and Biopsy

2021 ◽  
pp. 55-76
Author(s):  
Daniel Ryan ◽  
John M. Gross ◽  
Zach Pennington ◽  
Majid Khan
Keyword(s):  
Diagnostic Imaging ◽  
Clinical Work ◽  
Work Up

A Case Study of a Large and Rare Pleomorphic Liposarcoma in The Chest Area

2020 ◽  
Author(s):  
Yuanjun Cheng
Keyword(s):  
Delayed Diagnosis ◽  
Clinical Work ◽  
Radical Excision ◽  
Pathological Findings ◽  
Chest Tightness ◽  
Pleomorphic Liposarcoma ◽  
Left Chest ◽  
Specific Symptoms ◽  
Work Up

Pleomorphic liposarcoma rarely develops in the chest area. This report presents a primary pleomorphic liposarcoma that was discovered in the left chest area of a 74-year-old female patient. The patient had presented specific symptoms, including cough, chest tightness and shortness of breath. A radical excision of the tumor was performed. The tumor was extremely large (27 cm - 24 cm- 10 cm) and completely encapsulated. Upon histological examination, it was diagnosed as a giant, pleomorphic liposarcoma. Thereafter, non-specific radiological and endoscopic results during clinical work-up delayed diagnosis until post-operative histology were gathered. In this report, the case-specific clinical and radiological diagnostic challenges are discussed, as well as the relevant surgical and pathological findings.

Perceived Effectiveness of Artificial Intelligence based Decision Support System in a Clinical Setting: A Systematic Literature Review (Preprint)

2020 ◽  
Author(s):  
Avishek Choudhury
Keyword(s):  
Artificial Intelligence ◽  
Decision Making ◽  
Decision Support ◽  
Literature Review ◽  
Decision Support System ◽  
Support System ◽  
Clinical Setting ◽  
Clinical Decision Making ◽  
Theoretical Perspective ◽  
Care Providers

UNSTRUCTURED Objective: The potential benefits of artificial intelligence based decision support system (AI-DSS) from a theoretical perspective are well documented and perceived by researchers but there is a lack of evidence showing its influence on routine clinical practice and how its perceived by care providers. Since the effectiveness of AI systems depends on data quality, implementation, and interpretation. The purpose of this literature review is to analyze the effectiveness of AI-DSS in clinical setting and understand its influence on clinician’s decision making outcome. Materials and Methods: This review protocol follows the Preferred Reporting Items for Systematic Reviews and Meta- Analyses reporting guidelines. Literature will be identified using a multi-database search strategy developed in consultation with a librarian. The proposed screening process consists of a title and abstract scan, followed by a full-text review by two reviewers to determine the eligibility of articles. Studies outlining application of AI based decision support system in a clinical setting and its impact on clinician’s decision making, will be included. A tabular synthesis of the general study details will be provided, as well as a narrative synthesis of the extracted data, organised into themes. Studies solely reporting AI accuracy an but not implemented in a clinical setting to measure its influence on clinical decision making were excluded from further review. Results: We identified 8 eligible studies that implemented AI-DSS in a clinical setting to facilitate decisions concerning prostate cancer, post traumatic stress disorder, cardiac ailment, back pain, and others. Five (62.50%) out of 8 studies reported positive outcome of AI-DSS. Conclusion: The systematic review indicated that AI-enabled decision support systems, when implemented in a clinical setting and used by clinicians might not ensure enhanced decision making. However, there are very limited studies to confirm the claim that AI based decision support system can uplift clinicians decision making abilities.

scholarly journals Human-Centered Artificial Intelligence for Designing Accessible Cultural Heritage

2021 ◽  
Vol 11 (2) ◽  
pp. 870
Author(s):  
Galena Pisoni ◽  
Natalia Díaz-Rodríguez ◽  
Hannie Gijlers ◽  
Linda Tonolli
Keyword(s):  
Artificial Intelligence ◽  
Literature Review ◽  
Cultural Heritage ◽  
Conceptual Framework ◽  
Interaction Design ◽  
Participatory Design ◽  
Future Directions ◽  
Heritage Sites ◽  
Review Analysis

This paper reviews the literature concerning technology used for creating and delivering accessible museum and cultural heritage sites experiences. It highlights the importance of the delivery suited for everyone from different areas of expertise, namely interaction design, pedagogical and participatory design, and it presents how recent and future artificial intelligence (AI) developments can be used for this aim, i.e.,improving and widening online and in situ accessibility. From the literature review analysis, we articulate a conceptual framework that incorporates key elements that constitute museum and cultural heritage online experiences and how these elements are related to each other. Concrete opportunities for future directions empirical research for accessibility of cultural heritage contents are suggested and further discussed.

scholarly journals Applications of artificial intelligence to improve patient flow on mental health inpatient units - Narrative literature review

Heliyon ◽  
2021 ◽  
Vol 7 (4) ◽  
pp. e06626
Author(s):  
Paulina Cecula ◽  
Jiakun Yu ◽  
Fatema Mustansir Dawoodbhoy ◽  
Jack Delaney ◽  
Joseph Tan ◽  
...  
Keyword(s):  
Mental Health ◽  
Artificial Intelligence ◽  
Literature Review ◽  
Patient Flow ◽  
Narrative Literature ◽  
Narrative Literature Review ◽  
Inpatient Units ◽  
Improve Patient

Artificial intelligence and the radiologist: the future in the Armed Forces Medical Services

2019 ◽  
pp. jramc-2018-001055
Author(s):  
Debraj Sen ◽  
R Chakrabarti ◽  
S Chatterjee ◽  
D S Grewal ◽  
K Manrai
Keyword(s):  
Artificial Intelligence ◽  
Information Technology ◽  
Cyber Security ◽  
Tertiary Care ◽  
Armed Forces ◽  
Medical Services ◽  
Imaging Biomarkers ◽  
Imaging Data ◽  
Adequate Funding ◽  
Trained Manpower

Artificial intelligence (AI) involves computational networks (neural networks) that simulate human intelligence. The incorporation of AI in radiology will help in dealing with the tedious, repetitive, time-consuming job of detecting relevant findings in diagnostic imaging and segmenting the detected images into smaller data. It would also help in identifying details that are oblivious to the human eye. AI will have an immense impact in populations with deficiency of radiologists and in screening programmes. By correlating imaging data from millions of patients and their clinico-demographic-therapy-morbidity-mortality profiles, AI could lead to identification of new imaging biomarkers. This would change therapy and direct new research. However, issues of standardisation, transparency, ethics, regulations, training, accreditation and safety are the challenges ahead. The Armed Forces Medical Services has widely dispersed units, medical echelons and roles ranging from small field units to large static tertiary care centres. They can incorporate AI-enabled radiological services to subserve small remotely located hospitals and detachments without posted radiologists and ease the load of radiologists in larger hospitals. Early widespread incorporation of information technology and enabled services in our hospitals, adequate funding, regular upgradation of software and hardware, dedicated trained manpower to manage the information technology services and train staff, and cyber security are issues that need to be addressed.

How and where is artificial intelligence in the public sector going? A literature review and research agenda

2019 ◽  
Vol 36 (4) ◽  
pp. 101392 ◽  
Author(s):  
Weslei Gomes de Sousa ◽  
Elis Regina Pereira de Melo ◽  
Paulo Henrique De Souza Bermejo ◽  
Rafael Araújo Sousa Farias ◽  
Adalmir Oliveira Gomes
Keyword(s):  
Artificial Intelligence ◽  
Public Sector ◽  
Literature Review ◽  
Research Agenda ◽  
The Public
Sign in / Sign up

Export Citation Format

Share Document