1
|
Gurgitano M, Angileri SA, Rodà GM, Liguori A, Pandolfi M, Ierardi AM, Wood BJ, Carrafiello G. Interventional Radiology ex-machina: impact of Artificial Intelligence on practice. LA RADIOLOGIA MEDICA 2021; 126:998-1006. [PMID: 33861421 PMCID: PMC8050998 DOI: 10.1007/s11547-021-01351-x] [Citation(s) in RCA: 56] [Impact Index Per Article: 18.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/20/2020] [Accepted: 03/24/2021] [Indexed: 12/17/2022]
Abstract
Artificial intelligence (AI) is a branch of Informatics that uses algorithms to tirelessly process data, understand its meaning and provide the desired outcome, continuously redefining its logic. AI was mainly introduced via artificial neural networks, developed in the early 1950s, and with its evolution into "computational learning models." Machine Learning analyzes and extracts features in larger data after exposure to examples; Deep Learning uses neural networks in order to extract meaningful patterns from imaging data, even deciphering that which would otherwise be beyond human perception. Thus, AI has the potential to revolutionize the healthcare systems and clinical practice of doctors all over the world. This is especially true for radiologists, who are integral to diagnostic medicine, helping to customize treatments and triage resources with maximum effectiveness. Related in spirit to Artificial intelligence are Augmented Reality, mixed reality, or Virtual Reality, which are able to enhance accuracy of minimally invasive treatments in image guided therapies by Interventional Radiologists. The potential applications of AI in IR go beyond computer vision and diagnosis, to include screening and modeling of patient selection, predictive tools for treatment planning and navigation, and training tools. Although no new technology is widely embraced, AI may provide opportunities to enhance radiology service and improve patient care, if studied, validated, and applied appropriately.
Collapse
Affiliation(s)
- Martina Gurgitano
- Operative Unit of Radiology, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico di Milano, via Francesco Sforza 35, 20122, Milan, Italia.
| | - Salvatore Alessio Angileri
- Operative Unit of Radiology, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico di Milano, via Francesco Sforza 35, 20122, Milan, Italia
| | - Giovanni Maria Rodà
- Postgraduation School in Radiodiagnostics, Università Degli Studi di Milano, via Festa del Perdono, 20122, Milan, Italy
| | - Alessandro Liguori
- Operative Unit of Radiology, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico di Milano, via Francesco Sforza 35, 20122, Milan, Italia
| | - Marco Pandolfi
- Operative Unit of Radiology, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico di Milano, via Francesco Sforza 35, 20122, Milan, Italia
| | - Anna Maria Ierardi
- Operative Unit of Radiology, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico di Milano, via Francesco Sforza 35, 20122, Milan, Italia
| | - Bradford J Wood
- Center for Interventional Oncology, National Institutes of Health Clinical Center and National Cancer Institute, National Institutes of Health, 10 Center Dr., Room 1C-341, MSC 1182, Bethesda, MD, 20892, USA
| | - Gianpaolo Carrafiello
- Operative Unit of Radiology, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico di Milano, via Francesco Sforza 35, 20122, Milan, Italia
- Department of Health Sciences, Università Degli Studi di Milano, Milan, Italy
| |
Collapse
|
2
|
Kao YCJ, Oyarzabal EA, Zhang H, Faber JE, Shih YYI. Role of Genetic Variation in Collateral Circulation in the Evolution of Acute Stroke: A Multimodal Magnetic Resonance Imaging Study. Stroke 2017; 48:754-761. [PMID: 28188261 DOI: 10.1161/strokeaha.116.015878] [Citation(s) in RCA: 20] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2016] [Revised: 12/05/2016] [Accepted: 12/08/2016] [Indexed: 12/13/2022]
Abstract
BACKGROUND AND PURPOSE No studies have determined the effect of differences in pial collateral extent (number and diameter), independent of differences in environmental factors and unknown genetic factors, on severity of stroke. We examined ischemic tissue evolution during acute stroke, as measured by magnetic resonance imaging and histology, by comparing 2 congenic mouse strains with otherwise identical genetic backgrounds but with different alleles of the Determinant of collateral extent-1 (Dce1) genetic locus. We also optimized magnetic resonance perfusion and diffusion-deficit thresholds by using histological measures of ischemic tissue. METHODS Perfusion, diffusion, and T2-weighted magnetic resonance imaging were performed on collateral-poor (congenic-Bc) and collateral-rich (congenic-B6) mice at 1, 5, and 24 hours after permanent middle cerebral artery occlusion. Magnetic resonance imaging-derived penumbra and ischemic core volumes were confirmed by histology in a subset of mice at 5 and 24 hours after permanent middle cerebral artery occlusion. RESULTS Although perfusion-deficit volumes were similar between strains 1 hour after permanent middle cerebral artery occlusion, diffusion-deficit volumes were 32% smaller in collateral-rich mice. At 5 hours, collateral-rich mice had markedly restored perfusion patterns showing reduced perfusion-deficit volumes, smaller infarct volumes, and smaller perfusion-diffusion mismatch volumes compared with the collateral-poor mice (P<0.05). At 24 hours, collateral-rich mice had 45% smaller T2-weighted lesion volumes (P<0.005) than collateral-poor mice, with no difference in perfusion-diffusion mismatch volumes because of penumbral death occurring 5 to 24 hours after permanent middle cerebral artery occlusion in collateral-poor mice. CONCLUSIONS Variation in collateral extent significantly alters infarct volume expansion, transiently affects perfusion and diffusion magnetic resonance imaging signatures, and impacts salvage of ischemic penumbra after stroke onset.
Collapse
Affiliation(s)
- Yu-Chieh Jill Kao
- From the Department of Neurology (Y.-C.J.K., E.A.O.), Biomedical Research Imaging Center (Y.-C.J.K., E.A.O., Y.-Y.I.S.), Neurobiology Curriculum (E.A.O., J.E.F.), Department of Cell Biology and Physiology (H.Z., J.E.F.), McAllister Heart Institute (H.Z., J.E.F., Y.-Y.I.S.), and Department of Biomedical Engineering (Y.-Y.I.S.), University of North Carolina, Chapel Hill; and Translational Imaging Research Center (Y.-C.J.K.) and Department of Radiology, School of Medicine (Y.-C.J.K.), College of Medicine, Taipei Medical University, Taiwan
| | - Esteban A Oyarzabal
- From the Department of Neurology (Y.-C.J.K., E.A.O.), Biomedical Research Imaging Center (Y.-C.J.K., E.A.O., Y.-Y.I.S.), Neurobiology Curriculum (E.A.O., J.E.F.), Department of Cell Biology and Physiology (H.Z., J.E.F.), McAllister Heart Institute (H.Z., J.E.F., Y.-Y.I.S.), and Department of Biomedical Engineering (Y.-Y.I.S.), University of North Carolina, Chapel Hill; and Translational Imaging Research Center (Y.-C.J.K.) and Department of Radiology, School of Medicine (Y.-C.J.K.), College of Medicine, Taipei Medical University, Taiwan
| | - Hua Zhang
- From the Department of Neurology (Y.-C.J.K., E.A.O.), Biomedical Research Imaging Center (Y.-C.J.K., E.A.O., Y.-Y.I.S.), Neurobiology Curriculum (E.A.O., J.E.F.), Department of Cell Biology and Physiology (H.Z., J.E.F.), McAllister Heart Institute (H.Z., J.E.F., Y.-Y.I.S.), and Department of Biomedical Engineering (Y.-Y.I.S.), University of North Carolina, Chapel Hill; and Translational Imaging Research Center (Y.-C.J.K.) and Department of Radiology, School of Medicine (Y.-C.J.K.), College of Medicine, Taipei Medical University, Taiwan
| | - James E Faber
- From the Department of Neurology (Y.-C.J.K., E.A.O.), Biomedical Research Imaging Center (Y.-C.J.K., E.A.O., Y.-Y.I.S.), Neurobiology Curriculum (E.A.O., J.E.F.), Department of Cell Biology and Physiology (H.Z., J.E.F.), McAllister Heart Institute (H.Z., J.E.F., Y.-Y.I.S.), and Department of Biomedical Engineering (Y.-Y.I.S.), University of North Carolina, Chapel Hill; and Translational Imaging Research Center (Y.-C.J.K.) and Department of Radiology, School of Medicine (Y.-C.J.K.), College of Medicine, Taipei Medical University, Taiwan
| | - Yen-Yu Ian Shih
- From the Department of Neurology (Y.-C.J.K., E.A.O.), Biomedical Research Imaging Center (Y.-C.J.K., E.A.O., Y.-Y.I.S.), Neurobiology Curriculum (E.A.O., J.E.F.), Department of Cell Biology and Physiology (H.Z., J.E.F.), McAllister Heart Institute (H.Z., J.E.F., Y.-Y.I.S.), and Department of Biomedical Engineering (Y.-Y.I.S.), University of North Carolina, Chapel Hill; and Translational Imaging Research Center (Y.-C.J.K.) and Department of Radiology, School of Medicine (Y.-C.J.K.), College of Medicine, Taipei Medical University, Taiwan.
| |
Collapse
|
3
|
Abstract
PURPOSE OF REVIEW This article provides an overview of the recent literature regarding the application of in-vivo brain imaging techniques to animal models of ischemic stroke. RECENT FINDINGS Major breakthroughs concerned the effects of sensory stimulation on neuronal function, local hemodynamics, and tissue outcome in the hyperacute phase of stroke; the novel application to stroke of hybrid scanners allowing simultaneous PET and magnetic resonance; the refinements of magnetic resonance-based oxygen imaging, allowing to map the ischemic penumbra in a completely noninvasive way; the implementation of new PET ligands to selectively map poststroke neuronal death and neuroinflammation; and the use of novel mesoscale imaging techniques to demonstrate the major role of interhemispheric connectivity in poststroke plasticity and functional recovery. SUMMARY The array of techniques to map in vivo the key pathophysiological brain processes involved in stroke is currently enlarging at an amazing pace. This is paralleled by ever-increasing sophistication in postprocessing tools. The combination of techniques allowing simultaneous access to several variables is particularly powerful as it affords unprecedented insights into the intimate processes underlying the tissue and neuronal changes that follow a stroke. These major leaps forward will hopefully lead to therapeutic breakthroughs aiming at improving functional outcome after stroke.
Collapse
|
4
|
Beard DJ, Logan CL, McLeod DD, Hood RJ, Pepperall D, Murtha LA, Spratt NJ. Ischemic penumbra as a trigger for intracranial pressure rise - A potential cause for collateral failure and infarct progression? J Cereb Blood Flow Metab 2016; 36:917-27. [PMID: 26759431 PMCID: PMC4853839 DOI: 10.1177/0271678x15625578] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/17/2015] [Accepted: 12/04/2015] [Indexed: 11/17/2022]
Abstract
We have recently shown that intracranial pressure (ICP) increases dramatically 24 h after minor intraluminal thread occlusion with reperfusion, independent of edema. Some of the largest ICP rises were observed in rats with the smallest final infarcts. A possible alternate mechanism for this ICP rise is an increase of cerebrospinal fluid (CSF) volume secondary to choroid plexus damage (a known complication of the intraluminal stroke model used). Alternatively, submaximal injury may be needed to induce ICP elevation. Therefore, we aimed to determine (a) if choroid plexus damage contributes to the ICP elevation, (b) if varying the patency of an important internal collateral supply to the middle cerebral artery (MCA), the anterior choroidal artery (AChA), produces different volumes of ischemic penumbra and (c) if presence of ischemic penumbra (submaximal injury) is associated with ICP elevation. We found (a) no association between choroid plexus damage and ICP elevation, (b) animals with a good internal collateral supply through the AChA during MCAo had significantly larger penumbra volumes and (c) ICP elevation at ≈24 h post-stroke only occurred in rats with submaximal injury, shown in two different stroke models. We conclude that active cellular processes within the ischemic penumbra may be required for edema-independent ICP elevation.
Collapse
Affiliation(s)
- Daniel J Beard
- School of Biomedical Sciences and Pharmacy, University of Newcastle, New South Wales, Australia Hunter Medical Research Institute, New Lambton, New South Wales, Australia
| | - Caitlin L Logan
- School of Biomedical Sciences and Pharmacy, University of Newcastle, New South Wales, Australia Hunter Medical Research Institute, New Lambton, New South Wales, Australia
| | - Damian D McLeod
- School of Biomedical Sciences and Pharmacy, University of Newcastle, New South Wales, Australia Hunter Medical Research Institute, New Lambton, New South Wales, Australia
| | - Rebecca J Hood
- School of Biomedical Sciences and Pharmacy, University of Newcastle, New South Wales, Australia Hunter Medical Research Institute, New Lambton, New South Wales, Australia
| | - Debbie Pepperall
- School of Biomedical Sciences and Pharmacy, University of Newcastle, New South Wales, Australia Hunter Medical Research Institute, New Lambton, New South Wales, Australia
| | - Lucy A Murtha
- School of Biomedical Sciences and Pharmacy, University of Newcastle, New South Wales, Australia Hunter Medical Research Institute, New Lambton, New South Wales, Australia
| | - Neil J Spratt
- School of Biomedical Sciences and Pharmacy, University of Newcastle, New South Wales, Australia Hunter Medical Research Institute, New Lambton, New South Wales, Australia Department of Neurology, John Hunter Hospital, Hunter New England Local Health District, New South Wales, Australia
| |
Collapse
|
5
|
Ergul A, Hafez S, Fouda A, Fagan SC. Impact of Comorbidities on Acute Injury and Recovery in Preclinical Stroke Research: Focus on Hypertension and Diabetes. Transl Stroke Res 2016; 7:248-60. [PMID: 27026092 DOI: 10.1007/s12975-016-0464-8] [Citation(s) in RCA: 54] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2015] [Revised: 03/15/2016] [Accepted: 03/21/2016] [Indexed: 10/22/2022]
Abstract
Human ischemic stroke is very complex, and no single preclinical model can comprise all the variables known to contribute to stroke injury and recovery. Hypertension, diabetes, and hyperlipidemia are leading comorbidities in stroke patients. The use of predominantly young adult and healthy animals in experimental stroke research has created a barrier for translation of findings to patients. As such, more and more disease models are being incorporated into the research design. This review highlights the major strengths and weaknesses of the most commonly used animal models of these conditions in preclinical stroke research. The goal is to provide guidance in choosing, reporting, and executing appropriate disease models that will be subjected to different models of stroke injury.
Collapse
Affiliation(s)
- Adviye Ergul
- Charlie Norwood Veterans Administration Medical Center, University of Georgia, Athens, GA, USA. .,Program in Clinical and Experimental Therapeutics, College of Pharmacy, University of Georgia, Athens, GA, USA. .,Department of Physiology, Augusta University, CA2094, Augusta, GA, 30912, USA.
| | - Sherif Hafez
- Charlie Norwood Veterans Administration Medical Center, University of Georgia, Athens, GA, USA.,Program in Clinical and Experimental Therapeutics, College of Pharmacy, University of Georgia, Athens, GA, USA.,Department of Physiology, Augusta University, CA2094, Augusta, GA, 30912, USA
| | - Abdelrahman Fouda
- Charlie Norwood Veterans Administration Medical Center, University of Georgia, Athens, GA, USA.,Program in Clinical and Experimental Therapeutics, College of Pharmacy, University of Georgia, Athens, GA, USA
| | - Susan C Fagan
- Charlie Norwood Veterans Administration Medical Center, University of Georgia, Athens, GA, USA.,Program in Clinical and Experimental Therapeutics, College of Pharmacy, University of Georgia, Athens, GA, USA.,Department of Neurology, Augusta University, Augusta, GA, USA
| |
Collapse
|
6
|
Tovedal T, Thelin S, Lennmyr F. Cerebral oxygen saturation during pulsatile and non-pulsatile cardiopulmonary bypass in patients with carotid stenosis. Perfusion 2015; 31:72-7. [PMID: 25948696 DOI: 10.1177/0267659115586280] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Pulsatile and non-pulsatile cardiopulmonary bypass (CPB) flows may have different impact on cerebral oxygen saturation in patients with restricted cerebral arterial blood supply. Twenty patients, ten diagnosed with carotid stenosis (CS, n = 10) and ten without known carotid disease (Controls, n = 10), were subjected to one period of pulsatile and one period of non-pulsatile flow (6-8 min each) during CPB at 32°C. Cerebral oxygen saturation was registered by near-infrared light spectroscopy (NIRS).The mean arterial pressure (MAP) was significantly lowered by pulsatile CPB flow. The NIRS tissue oxygenation index (TOI) tended to decrease in the CS group and increase in the Controls during pulsatile flow compared with non-pulsatile; however, the changes were not statistically significant.No significant correlations were seen between the changes in MAP and TOI across the observation periods.In conclusion, pulsatile CPB flow caused slightly decreased mean arterial pressure while the effect on cerebral oxygenation was unclear. Pulsatile flow was not found superior to non-pulsatile flow in patients with or without carotid stenosis.
Collapse
Affiliation(s)
- T Tovedal
- Department of Surgical Sciences, Section for Anaesthesiology and Intensive Care, Uppsala University, Uppsala, Sweden
| | - S Thelin
- Department of Surgical Sciences, Section for Thoracic Surgery, Uppsala University, Uppsala, Sweden
| | - F Lennmyr
- Department of Surgical Sciences, Section for Anaesthesiology and Intensive Care, Uppsala University, Uppsala, Sweden
| |
Collapse
|
7
|
Dynamic perfusion and diffusion MRI of cortical spreading depolarization in photothrombotic ischemia. Neurobiol Dis 2014; 71:131-9. [PMID: 25066776 DOI: 10.1016/j.nbd.2014.07.005] [Citation(s) in RCA: 28] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2014] [Revised: 06/15/2014] [Accepted: 07/16/2014] [Indexed: 11/21/2022] Open
Abstract
Cortical spreading depolarization (CSD) is known to exacerbate ischemic damage, as the number of CSDs correlates with the final infarct volumes and suppressing CSDs improves functional outcomes. To investigate the role of CSD in ischemic damage, we developed a novel rat model of photothrombotic ischemia using a miniature implantable optic fiber that allows lesion induction inside the magnetic resonance imaging (MRI) scanner. We were able to precisely control the location and the size of the ischemic lesion, and continuously monitor dynamic perfusion and diffusion MRI signal changes at high temporal resolution before, during and after the onset of focal ischemia. Our model showed that apparent diffusion coefficient (ADC) and cerebral blood flow (CBF) in the ischemic core dropped immediately after lesion onset by 20±6 and 41±23%, respectively, and continually declined over the next 5h. Meanwhile, CSDs were observed in all animals (n=36) and displayed either a transient decrease of ADC by 17±3% or an increase of CBF by 104±15%. All CSDs were initiated from the rim of the ischemic core, propagated outward, and confined to the ipsilesional cortex. Additionally, we demonstrated that by controlling the size of perfusion-diffusion mismatch (which approximates the penumbra) in our model, the number of CSDs correlated with the mismatch area rather than the final infarct volume. This study introduces a novel platform to study CSDs in real-time with high reproducibility using MRI.
Collapse
|