1
|
Cohen I, Sorin V, Lekach R, Raskin D, Segev M, Klang E, Eshed I, Barash Y. Artificial intelligence for detection of effusion and lipo-hemarthrosis in X-rays and CT of the knee. Eur J Radiol 2024; 175:111460. [PMID: 38608501 DOI: 10.1016/j.ejrad.2024.111460] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2024] [Revised: 03/29/2024] [Accepted: 04/08/2024] [Indexed: 04/14/2024]
Abstract
BACKGROUND Traumatic knee injuries are challenging to diagnose accurately through radiography and to a lesser extent, through CT, with fractures sometimes overlooked. Ancillary signs like joint effusion or lipo-hemarthrosis are indicative of fractures, suggesting the need for further imaging. Artificial Intelligence (AI) can automate image analysis, improving diagnostic accuracy and help prioritizing clinically important X-ray or CT studies. OBJECTIVE To develop and evaluate an AI algorithm for detecting effusion of any kind in knee X-rays and selected CT images and distinguishing between simple effusion and lipo-hemarthrosis indicative of intra-articular fractures. METHODS This retrospective study analyzed post traumatic knee imaging from January 2016 to February 2023, categorizing images into lipo-hemarthrosis, simple effusion, or normal. It utilized the FishNet-150 algorithm for image classification, with class activation maps highlighting decision-influential regions. The AI's diagnostic accuracy was validated against a gold standard, based on the evaluations made by a radiologist with at least four years of experience. RESULTS Analysis included CT images from 515 patients and X-rays from 637 post traumatic patients, identifying lipo-hemarthrosis, simple effusion, and normal findings. The AI showed an AUC of 0.81 for detecting any effusion, 0.78 for simple effusion, and 0.83 for lipo-hemarthrosis in X-rays; and 0.89, 0.89, and 0.91, respectively, in CTs. CONCLUSION The AI algorithm effectively detects knee effusion and differentiates between simple effusion and lipo-hemarthrosis in post-traumatic patients for both X-rays and selected CT images further studies are needed to validate these results.
Collapse
Affiliation(s)
- Israel Cohen
- Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel; Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
| | - Vera Sorin
- Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel; Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
| | - Ruth Lekach
- Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel; Department of Nuclear Medicine, Sourasky Medical Center, Tel-Aviv, Israel.
| | - Daniel Raskin
- Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel; Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
| | - Maria Segev
- Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel; Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
| | - Eyal Klang
- Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel; Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
| | - Iris Eshed
- Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel; Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
| | - Yiftach Barash
- Department of Diagnostic Imaging, Sheba Medical Center, Tel Hashomer, Israel; Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
| |
Collapse
|
2
|
Bradley D, Harrison J, Goodall M, Dobrashian R. Are Advanced Clinical Practitioners perfectly placed to re-report neuroimages to support clinical diagnosis of dementia? INTERNATIONAL JOURNAL FOR ADVANCING PRACTICE 2023; 1:146-150. [PMID: 38229770 PMCID: PMC7615529 DOI: 10.12968/ijap.2023.1.3.146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/18/2024]
Abstract
With the ageing population, the prevalence of dementia is increasing worldwide. There is an emphasis on early, timely diagnosis and treatment options for people with a dementia yet wait times from referral to diagnosis have increased. Neuroimaging performed by radiologists is utilised to support dementia diagnosis and some patients will already have a CT scan from a pre-existing condition such as stroke. The purpose of this commentary is to consider whether ACPs who specialise in dementia, are perfectly placed to re-report on pre-existing neuroimages to support the clinical diagnosis of dementia.
Collapse
Affiliation(s)
| | - Joanna Harrison
- Synthesis Economic Evaluation and Decision Science (SEEDS) Group, University of Central Lancashire
| | - Mark Goodall
- Institute of Population Health, University of Liverpool
| | | |
Collapse
|
3
|
Schierenbeck M, Grözinger M, Reichardt B, Jansen O, Kauczor HU, Campbell GM, Sedaghat S. Detecting Bone Marrow Edema of the Extremities on Spectral Computed Tomography Using a Three-Material Decomposition. Diagnostics (Basel) 2023; 13:2745. [PMID: 37685282 PMCID: PMC10486895 DOI: 10.3390/diagnostics13172745] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2023] [Revised: 08/04/2023] [Accepted: 08/17/2023] [Indexed: 09/10/2023] Open
Abstract
BACKGROUND Detecting bone marrow edema (BME) as a sign of acute fractures is challenging on conventional computed tomography (CT). This study evaluated the diagnostic performance of a three-material decomposition (TMD) approach for detecting traumatic BME of the extremities on spectral computed tomography (SCT). METHODS This retrospective diagnostic study included 81 bone compartments with and 80 without BME. A TMD application to visualize BME was developed in collaboration with Philips Healthcare. The following bone compartments were included: distal radius, proximal femur, proximal tibia, distal tibia and fibula, and long bone diaphysis. Two blinded radiologists reviewed each case independently in random order for the presence or absence of BME. RESULTS The interrater reliability was 0.84 (p < 0.001). The different bone compartments showed sensitivities of 86.7% to 93.8%, specificities of 84.2% to 94.1%, positive predictive values of 82.4% to 94.7%, negative predictive values of 87.5% to 93.3%, and area under the curve (AUC) values of 85.7% to 93.1%. The distal radius showed the highest sensitivity and the proximal femur showed the lowest sensitivity, while the proximal femur presented the highest specificity and the distal tibia presented the lowest specificity. CONCLUSIONS Our TMD approach provides high diagnostic performance for detecting BME of the extremities. Therefore, this approach could be used routinely in the emergency setting.
Collapse
Affiliation(s)
- Marie Schierenbeck
- Department for Radiology and Neuroradiology, University Hospital Schleswig-Holstein Campus Kiel, 24105 Kiel, Germany
| | - Martin Grözinger
- German Cancer Research Center, University Hospital Heidelberg, 69120 Heidelberg, Germany
| | - Benjamin Reichardt
- Department of Interventional Radiology and Neuroradiology, Klinikum Hochsauerland, 59821 Arnsberg, Germany
| | - Olav Jansen
- Department for Radiology and Neuroradiology, University Hospital Schleswig-Holstein Campus Kiel, 24105 Kiel, Germany
| | - Hans-Ulrich Kauczor
- Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, 69120 Heidelberg, Germany
| | | | - Sam Sedaghat
- Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg, 69120 Heidelberg, Germany
| |
Collapse
|
4
|
D'Angelo T, Albrecht MH, Caudo D, Mazziotti S, Vogl TJ, Wichmann JL, Martin S, Yel I, Ascenti G, Koch V, Cicero G, Blandino A, Booz C. Virtual non-calcium dual-energy CT: clinical applications. Eur Radiol Exp 2021; 5:38. [PMID: 34476640 PMCID: PMC8413416 DOI: 10.1186/s41747-021-00228-y] [Citation(s) in RCA: 23] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2020] [Accepted: 06/11/2021] [Indexed: 12/15/2022] Open
Abstract
Dual-energy CT (DECT) has emerged into clinical routine as an imaging technique with unique postprocessing utilities that improve the evaluation of different body areas. The virtual non-calcium (VNCa) reconstruction algorithm has shown beneficial effects on the depiction of bone marrow pathologies such as bone marrow edema. Its main advantage is the ability to substantially increase the image contrast of structures that are usually covered with calcium mineral, such as calcified vessels or bone marrow, and to depict a large number of traumatic, inflammatory, infiltrative, and degenerative disorders affecting either the spine or the appendicular skeleton. Therefore, VNCa imaging represents another step forward for DECT to image conditions and disorders that usually require the use of more expensive and time-consuming techniques such as magnetic resonance imaging, positron emission tomography/CT, or bone scintigraphy. The aim of this review article is to explain the technical background of VNCa imaging, showcase its applicability in the different body regions, and provide an updated outlook on the clinical impact of this technique, which goes beyond the sole improvement in image quality.
Collapse
Affiliation(s)
- Tommaso D'Angelo
- Department of Biomedical Sciences and Morphological and Functional Imaging, University Hospital Messina, Messina, Italy
| | - Moritz H Albrecht
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany.
| | - Danilo Caudo
- Department of Biomedical Sciences and Morphological and Functional Imaging, University Hospital Messina, Messina, Italy
| | - Silvio Mazziotti
- Department of Biomedical Sciences and Morphological and Functional Imaging, University Hospital Messina, Messina, Italy
| | - Thomas J Vogl
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Julian L Wichmann
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Simon Martin
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Ibrahim Yel
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Giorgio Ascenti
- Department of Biomedical Sciences and Morphological and Functional Imaging, University Hospital Messina, Messina, Italy
| | - Vitali Koch
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Giuseppe Cicero
- Department of Biomedical Sciences and Morphological and Functional Imaging, University Hospital Messina, Messina, Italy
| | - Alfredo Blandino
- Department of Biomedical Sciences and Morphological and Functional Imaging, University Hospital Messina, Messina, Italy
| | - Christian Booz
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| |
Collapse
|