Pub Date : 2024-07-05DOI: 10.3389/fradi.2024.1390774
Philipp Fervers, Robert Hahnfeldt, J. Kottlors, A. Wagner, D. Maintz, D. Pinto dos Santos, Simon Lennartz, T. Persigehl
To investigate the feasibility of the large language model (LLM) ChatGPT for classifying liver lesions according to the Liver Imaging Reporting and Data System (LI-RADS) based on MRI reports, and to compare classification performance on structured vs. unstructured reports.LI-RADS classifiable liver lesions were included from German written structured and unstructured MRI reports with report of size, location, and arterial phase contrast enhancement as minimum inclusion requirements. The findings sections of the reports were propagated to ChatGPT (GPT-3.5), which was instructed to determine LI-RADS scores for each classifiable liver lesion. Ground truth was established by two radiologists in consensus. Agreement between ground truth and ChatGPT was assessed with Cohen's kappa. Test-retest reliability was assessed by passing a subset of n = 50 lesions five times to ChatGPT, using the intraclass correlation coefficient (ICC).205 MRIs from 150 patients were included. The accuracy of ChatGPT at determining LI-RADS categories was poor (53% and 44% on unstructured and structured reports). The agreement to the ground truth was higher (k = 0.51 and k = 0.44), the mean absolute error in LI-RADS scores was lower (0.5 ± 0.5 vs. 0.6 ± 0.7, p < 0.05), and the test-retest reliability was higher (ICC = 0.81 vs. 0.50), in free-text compared to structured reports, respectively, although structured reports comprised the minimum required imaging features significantly more frequently (Chi-square test, p < 0.05).ChatGPT attained only low accuracy when asked to determine LI-RADS scores from liver imaging reports. The superior accuracy and consistency throughout free-text reports might relate to ChatGPT's training process.Our study indicates both the necessity of optimization of LLMs for structured clinical data input and the potential of LLMs for creating machine-readable labels based on large free-text radiological databases.
{"title":"ChatGPT yields low accuracy in determining LI-RADS scores based on free-text and structured radiology reports in German language","authors":"Philipp Fervers, Robert Hahnfeldt, J. Kottlors, A. Wagner, D. Maintz, D. Pinto dos Santos, Simon Lennartz, T. Persigehl","doi":"10.3389/fradi.2024.1390774","DOIUrl":"https://doi.org/10.3389/fradi.2024.1390774","url":null,"abstract":"To investigate the feasibility of the large language model (LLM) ChatGPT for classifying liver lesions according to the Liver Imaging Reporting and Data System (LI-RADS) based on MRI reports, and to compare classification performance on structured vs. unstructured reports.LI-RADS classifiable liver lesions were included from German written structured and unstructured MRI reports with report of size, location, and arterial phase contrast enhancement as minimum inclusion requirements. The findings sections of the reports were propagated to ChatGPT (GPT-3.5), which was instructed to determine LI-RADS scores for each classifiable liver lesion. Ground truth was established by two radiologists in consensus. Agreement between ground truth and ChatGPT was assessed with Cohen's kappa. Test-retest reliability was assessed by passing a subset of n = 50 lesions five times to ChatGPT, using the intraclass correlation coefficient (ICC).205 MRIs from 150 patients were included. The accuracy of ChatGPT at determining LI-RADS categories was poor (53% and 44% on unstructured and structured reports). The agreement to the ground truth was higher (k = 0.51 and k = 0.44), the mean absolute error in LI-RADS scores was lower (0.5 ± 0.5 vs. 0.6 ± 0.7, p < 0.05), and the test-retest reliability was higher (ICC = 0.81 vs. 0.50), in free-text compared to structured reports, respectively, although structured reports comprised the minimum required imaging features significantly more frequently (Chi-square test, p < 0.05).ChatGPT attained only low accuracy when asked to determine LI-RADS scores from liver imaging reports. The superior accuracy and consistency throughout free-text reports might relate to ChatGPT's training process.Our study indicates both the necessity of optimization of LLMs for structured clinical data input and the potential of LLMs for creating machine-readable labels based on large free-text radiological databases.","PeriodicalId":507441,"journal":{"name":"Frontiers in Radiology","volume":" 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141676365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-27DOI: 10.3389/fradi.2024.1385742
Moiz Khan Sherwani, Shyam Gopalakrishnan
The aim of this systematic review is to determine whether Deep Learning (DL) algorithms can provide a clinically feasible alternative to classic algorithms for synthetic Computer Tomography (sCT). The following categories are presented in this study: ∙ MR-based treatment planning and synthetic CT generation techniques. ∙ Generation of synthetic CT images based on Cone Beam CT images. ∙ Low-dose CT to High-dose CT generation. ∙ Attenuation correction for PET images. To perform appropriate database searches, we reviewed journal articles published between January 2018 and June 2023. Current methodology, study strategies, and results with relevant clinical applications were analyzed as we outlined the state-of-the-art of deep learning based approaches to inter-modality and intra-modality image synthesis. This was accomplished by contrasting the provided methodologies with traditional research approaches. The key contributions of each category were highlighted, specific challenges were identified, and accomplishments were summarized. As a final step, the statistics of all the cited works from various aspects were analyzed, which revealed that DL-based sCTs have achieved considerable popularity, while also showing the potential of this technology. In order to assess the clinical readiness of the presented methods, we examined the current status of DL-based sCT generation.
{"title":"A systematic literature review: deep learning techniques for synthetic medical image generation and their applications in radiotherapy","authors":"Moiz Khan Sherwani, Shyam Gopalakrishnan","doi":"10.3389/fradi.2024.1385742","DOIUrl":"https://doi.org/10.3389/fradi.2024.1385742","url":null,"abstract":"The aim of this systematic review is to determine whether Deep Learning (DL) algorithms can provide a clinically feasible alternative to classic algorithms for synthetic Computer Tomography (sCT). The following categories are presented in this study: ∙ MR-based treatment planning and synthetic CT generation techniques. ∙ Generation of synthetic CT images based on Cone Beam CT images. ∙ Low-dose CT to High-dose CT generation. ∙ Attenuation correction for PET images. To perform appropriate database searches, we reviewed journal articles published between January 2018 and June 2023. Current methodology, study strategies, and results with relevant clinical applications were analyzed as we outlined the state-of-the-art of deep learning based approaches to inter-modality and intra-modality image synthesis. This was accomplished by contrasting the provided methodologies with traditional research approaches. The key contributions of each category were highlighted, specific challenges were identified, and accomplishments were summarized. As a final step, the statistics of all the cited works from various aspects were analyzed, which revealed that DL-based sCTs have achieved considerable popularity, while also showing the potential of this technology. In order to assess the clinical readiness of the presented methods, we examined the current status of DL-based sCT generation.","PeriodicalId":507441,"journal":{"name":"Frontiers in Radiology","volume":"32 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140375520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-21DOI: 10.3389/fradi.2024.1294398
Yoko Kato, Wei Hao Lee, Makoto Natsumeda, B. Ambale-Venkatesh, Kensuke Takagi, Yuji Ikari, Joao A C Lima
Left atrial (LA) mechanics are strongly linked with left ventricular (LV) filling. The LA diastasis strain slope (LADSS), which spans between the passive and active LA emptying phases, may be a key indicator of the LA–LV interplay during diastole.This study aimed to investigate the LA–LV interdependencies in post-ST elevation myocardial infarction (STEMI), with particular focus on the LADSS.Patients with post-anterior STEMI who received primary percutaneous coronary intervention underwent contrast cardiac magnetic resonance imaging (MRI) during acute (5–9 days post-STEMI) and chronic (at 6 months) phases. The LADSS was categorized into three groups: Groups 1, 2, and 3 representing positive, flat, and negative slopes, respectively. Cross-sectional correlates of LADSS Group 2 or 3 compared to Group 1 were identified, adjusting for demographics, LA indices, and with or without LV indices. The associations of acute phase LADSS with the recovery of LV ejection fraction (LVEF) and scar amount were investigated.Sixty-six acute phase (86.4% male, 63.1 ± 11.8 years) and 59 chronic phase cardiac MRI images were investigated. The distribution across LADSS Groups 1, 2, and 3 in the acute phase was 24.2%, 28.9%, and 47.0%, respectively, whereas in the chronic phase, it was 33.9%, 22.0%, and 44.1%, respectively. LADSS Group 3 demonstrated a higher heart rate than Group 1 in the acute phase (61.9 ± 8.7 vs. 73.5 ± 11.9 bpm, p < 0.01); lower LVEF (48.7 ± 8.6 vs. 41.8 ± 9.9%, p = 0.041) and weaker LA passive strain rate (SR) (−1.1 ± 0.4 vs. −0.7 [−1.2 to −0.6] s−1, p = 0.037) in the chronic phase. Chronic phase Group 3 exhibited weaker LA passive SR [relative risk ratio (RRR) = 8.8, p = 0.012] than Group 1 after adjusting for demographics and LA indices; lower LVEF (RRR = 0.85, p < 0.01), higher heart rate (RRR = 1.1, p = 0.070), and less likelihood of being male (RRR = 0.08, p = 0.058) after full adjustment. Acute phase LADSS Groups 2 and 3 predicted poor recovery of LVEF when adjusted for demographics and LA indices; LADSS Group 2 remained a predictor in the fully adjusted model (β = −5.8, p = 0.013).The LADSS serves both as a marker of current LV hemodynamics and its recovery in post-anterior STEMI. The LADSS is an important index of LA–LV interdependency during diastole.https://clinicaltrials.gov/, identifier NCT03950310.
{"title":"Left atrial diastasis strain slope is a marker of hemodynamic recovery in post-ST elevation myocardial infarction: the Laser Atherectomy for STemi, Pci Analysis with Scintigraphy Study (LAST-PASS)","authors":"Yoko Kato, Wei Hao Lee, Makoto Natsumeda, B. Ambale-Venkatesh, Kensuke Takagi, Yuji Ikari, Joao A C Lima","doi":"10.3389/fradi.2024.1294398","DOIUrl":"https://doi.org/10.3389/fradi.2024.1294398","url":null,"abstract":"Left atrial (LA) mechanics are strongly linked with left ventricular (LV) filling. The LA diastasis strain slope (LADSS), which spans between the passive and active LA emptying phases, may be a key indicator of the LA–LV interplay during diastole.This study aimed to investigate the LA–LV interdependencies in post-ST elevation myocardial infarction (STEMI), with particular focus on the LADSS.Patients with post-anterior STEMI who received primary percutaneous coronary intervention underwent contrast cardiac magnetic resonance imaging (MRI) during acute (5–9 days post-STEMI) and chronic (at 6 months) phases. The LADSS was categorized into three groups: Groups 1, 2, and 3 representing positive, flat, and negative slopes, respectively. Cross-sectional correlates of LADSS Group 2 or 3 compared to Group 1 were identified, adjusting for demographics, LA indices, and with or without LV indices. The associations of acute phase LADSS with the recovery of LV ejection fraction (LVEF) and scar amount were investigated.Sixty-six acute phase (86.4% male, 63.1 ± 11.8 years) and 59 chronic phase cardiac MRI images were investigated. The distribution across LADSS Groups 1, 2, and 3 in the acute phase was 24.2%, 28.9%, and 47.0%, respectively, whereas in the chronic phase, it was 33.9%, 22.0%, and 44.1%, respectively. LADSS Group 3 demonstrated a higher heart rate than Group 1 in the acute phase (61.9 ± 8.7 vs. 73.5 ± 11.9 bpm, p < 0.01); lower LVEF (48.7 ± 8.6 vs. 41.8 ± 9.9%, p = 0.041) and weaker LA passive strain rate (SR) (−1.1 ± 0.4 vs. −0.7 [−1.2 to −0.6] s−1, p = 0.037) in the chronic phase. Chronic phase Group 3 exhibited weaker LA passive SR [relative risk ratio (RRR) = 8.8, p = 0.012] than Group 1 after adjusting for demographics and LA indices; lower LVEF (RRR = 0.85, p < 0.01), higher heart rate (RRR = 1.1, p = 0.070), and less likelihood of being male (RRR = 0.08, p = 0.058) after full adjustment. Acute phase LADSS Groups 2 and 3 predicted poor recovery of LVEF when adjusted for demographics and LA indices; LADSS Group 2 remained a predictor in the fully adjusted model (β = −5.8, p = 0.013).The LADSS serves both as a marker of current LV hemodynamics and its recovery in post-anterior STEMI. The LADSS is an important index of LA–LV interdependency during diastole.https://clinicaltrials.gov/, identifier NCT03950310.","PeriodicalId":507441,"journal":{"name":"Frontiers in Radiology","volume":"10 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139957794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-20DOI: 10.3389/fradi.2024.1346550
J. Wagenpfeil, P. Kupczyk, Philipp Bruners, Robert Siepmann, Emelie Guendel, J. Luetkens, A. Isaak, Carsten Meyer, Fabian Kuetting, Claus C Pieper, U. Attenberger, D. Kuetting
Due to a lack of data, there is an ongoing debate regarding the optimal frontline interventional therapy for unresectable hepatocellular carcinoma (HCC). The aim of the study is to compare the results of transarterial radioembolization (TARE) as the first-line therapy and as a subsequent therapy following prior transarterial chemoembolization (TACE) in these patients.A total of 83 patients were evaluated, with 38 patients having undergone at least one TACE session prior to TARE [27 male; mean age 67.2 years; 68.4% stage Barcelona clinic liver cancer (BCLC) B, 31.6% BCLC C]; 45 patients underwent primary TARE (33 male; mean age 69.9 years; 40% BCLC B, 58% BCLC C). Clinical [age, gender, BCLC stage, activity in gigabecquerel (GBq), Child–Pugh status, portal vein thrombosis, tumor volume] and procedural [overall survival (OS), local tumor control (LTC), and progression-free survival (PFS)] data were compared. A regression analysis was performed to evaluate OS, LTC, and PFS.No differences were found in OS (95% CI: 1.12, P = 0.289), LTC (95% CI: 0.003, P = 0.95), and PFS (95% CI: 0.4, P = 0.525). The regression analysis revealed a relationship between Child–Pugh score (P = 0.005), size of HCC lesions (>10 cm) (P = 0.022), and OS; neither prior TACE (Child–Pugh B patients; 95% CI: 0.120, P = 0.729) nor number of lesions (>10; 95% CI: 2.930, P = 0.087) correlated with OS.Prior TACE does not affect the outcome of TARE in unresectable HCC.
{"title":"Outcome of transarterial radioembolization in patients with hepatocellular carcinoma as a first-line interventional therapy and after a previous transarterial chemoembolization","authors":"J. Wagenpfeil, P. Kupczyk, Philipp Bruners, Robert Siepmann, Emelie Guendel, J. Luetkens, A. Isaak, Carsten Meyer, Fabian Kuetting, Claus C Pieper, U. Attenberger, D. Kuetting","doi":"10.3389/fradi.2024.1346550","DOIUrl":"https://doi.org/10.3389/fradi.2024.1346550","url":null,"abstract":"Due to a lack of data, there is an ongoing debate regarding the optimal frontline interventional therapy for unresectable hepatocellular carcinoma (HCC). The aim of the study is to compare the results of transarterial radioembolization (TARE) as the first-line therapy and as a subsequent therapy following prior transarterial chemoembolization (TACE) in these patients.A total of 83 patients were evaluated, with 38 patients having undergone at least one TACE session prior to TARE [27 male; mean age 67.2 years; 68.4% stage Barcelona clinic liver cancer (BCLC) B, 31.6% BCLC C]; 45 patients underwent primary TARE (33 male; mean age 69.9 years; 40% BCLC B, 58% BCLC C). Clinical [age, gender, BCLC stage, activity in gigabecquerel (GBq), Child–Pugh status, portal vein thrombosis, tumor volume] and procedural [overall survival (OS), local tumor control (LTC), and progression-free survival (PFS)] data were compared. A regression analysis was performed to evaluate OS, LTC, and PFS.No differences were found in OS (95% CI: 1.12, P = 0.289), LTC (95% CI: 0.003, P = 0.95), and PFS (95% CI: 0.4, P = 0.525). The regression analysis revealed a relationship between Child–Pugh score (P = 0.005), size of HCC lesions (>10 cm) (P = 0.022), and OS; neither prior TACE (Child–Pugh B patients; 95% CI: 0.120, P = 0.729) nor number of lesions (>10; 95% CI: 2.930, P = 0.087) correlated with OS.Prior TACE does not affect the outcome of TARE in unresectable HCC.","PeriodicalId":507441,"journal":{"name":"Frontiers in Radiology","volume":"7 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139958424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-19DOI: 10.3389/fradi.2024.1375443
E. Montin, Valentina D. A. Corino, Dimitri Martel, Giuseppe Carlucci, Davide Scaramuzza
{"title":"Editorial: Radiomics and AI for clinical and translational medicine","authors":"E. Montin, Valentina D. A. Corino, Dimitri Martel, Giuseppe Carlucci, Davide Scaramuzza","doi":"10.3389/fradi.2024.1375443","DOIUrl":"https://doi.org/10.3389/fradi.2024.1375443","url":null,"abstract":"","PeriodicalId":507441,"journal":{"name":"Frontiers in Radiology","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139958616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-15DOI: 10.3389/fradi.2024.1338418
C. Lucci, Ina Rissanen, R. Takx, A. G. van der Kolk, A. Harteveld, J. Dankbaar, Mirjam I. Geerlings, P. D. de Jong, J. Hendrikse
Arterial calcifications on unenhanced CT scans and vessel wall lesions on MRI are often used interchangeably to portray intracranial arterial disease. However, the extent of pathology depicted with each technique is unclear. We investigated the presence and distribution of these two imaging findings in patients with a history of cerebrovascular disease.We analyzed CT and MRI data from 78 patients admitted for stroke or TIA at our institution. Vessel wall lesions were assessed on 7 T MRI sequences, while arterial calcifications were assessed on CT scans. The number of vessel wall lesions, severity of intracranial internal carotid artery (iICA) calcifications, and overall presence and distribution of the two imaging findings were visually assessed in the intracranial arteries.At least one vessel wall lesion or arterial calcification was assessed in 69 (88%) patients. Only the iICA and vertebral arteries (VA) showed a substantial number of both calcifications and vessel wall lesions. The other vessels showed almost exclusively vessel wall lesions. The number of vessel wall lesions was associated with the severity of iICA calcification (p = 0.013).The number of vessel wall lesions increases with the severity of iICA calcifications. Nonetheless, the distribution of vessel wall lesions on MRI and arterial calcifications on CT shows remarkable differences. These findings support the need for a combined approach to examine intracranial arterial disease.
{"title":"Imaging of intracranial arterial disease: a comparison between MRI and unenhanced CT","authors":"C. Lucci, Ina Rissanen, R. Takx, A. G. van der Kolk, A. Harteveld, J. Dankbaar, Mirjam I. Geerlings, P. D. de Jong, J. Hendrikse","doi":"10.3389/fradi.2024.1338418","DOIUrl":"https://doi.org/10.3389/fradi.2024.1338418","url":null,"abstract":"Arterial calcifications on unenhanced CT scans and vessel wall lesions on MRI are often used interchangeably to portray intracranial arterial disease. However, the extent of pathology depicted with each technique is unclear. We investigated the presence and distribution of these two imaging findings in patients with a history of cerebrovascular disease.We analyzed CT and MRI data from 78 patients admitted for stroke or TIA at our institution. Vessel wall lesions were assessed on 7 T MRI sequences, while arterial calcifications were assessed on CT scans. The number of vessel wall lesions, severity of intracranial internal carotid artery (iICA) calcifications, and overall presence and distribution of the two imaging findings were visually assessed in the intracranial arteries.At least one vessel wall lesion or arterial calcification was assessed in 69 (88%) patients. Only the iICA and vertebral arteries (VA) showed a substantial number of both calcifications and vessel wall lesions. The other vessels showed almost exclusively vessel wall lesions. The number of vessel wall lesions was associated with the severity of iICA calcification (p = 0.013).The number of vessel wall lesions increases with the severity of iICA calcifications. Nonetheless, the distribution of vessel wall lesions on MRI and arterial calcifications on CT shows remarkable differences. These findings support the need for a combined approach to examine intracranial arterial disease.","PeriodicalId":507441,"journal":{"name":"Frontiers in Radiology","volume":"21 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139776317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-15DOI: 10.3389/fradi.2024.1338418
C. Lucci, Ina Rissanen, R. Takx, A. G. van der Kolk, A. Harteveld, J. Dankbaar, Mirjam I. Geerlings, P. D. de Jong, J. Hendrikse
Arterial calcifications on unenhanced CT scans and vessel wall lesions on MRI are often used interchangeably to portray intracranial arterial disease. However, the extent of pathology depicted with each technique is unclear. We investigated the presence and distribution of these two imaging findings in patients with a history of cerebrovascular disease.We analyzed CT and MRI data from 78 patients admitted for stroke or TIA at our institution. Vessel wall lesions were assessed on 7 T MRI sequences, while arterial calcifications were assessed on CT scans. The number of vessel wall lesions, severity of intracranial internal carotid artery (iICA) calcifications, and overall presence and distribution of the two imaging findings were visually assessed in the intracranial arteries.At least one vessel wall lesion or arterial calcification was assessed in 69 (88%) patients. Only the iICA and vertebral arteries (VA) showed a substantial number of both calcifications and vessel wall lesions. The other vessels showed almost exclusively vessel wall lesions. The number of vessel wall lesions was associated with the severity of iICA calcification (p = 0.013).The number of vessel wall lesions increases with the severity of iICA calcifications. Nonetheless, the distribution of vessel wall lesions on MRI and arterial calcifications on CT shows remarkable differences. These findings support the need for a combined approach to examine intracranial arterial disease.
{"title":"Imaging of intracranial arterial disease: a comparison between MRI and unenhanced CT","authors":"C. Lucci, Ina Rissanen, R. Takx, A. G. van der Kolk, A. Harteveld, J. Dankbaar, Mirjam I. Geerlings, P. D. de Jong, J. Hendrikse","doi":"10.3389/fradi.2024.1338418","DOIUrl":"https://doi.org/10.3389/fradi.2024.1338418","url":null,"abstract":"Arterial calcifications on unenhanced CT scans and vessel wall lesions on MRI are often used interchangeably to portray intracranial arterial disease. However, the extent of pathology depicted with each technique is unclear. We investigated the presence and distribution of these two imaging findings in patients with a history of cerebrovascular disease.We analyzed CT and MRI data from 78 patients admitted for stroke or TIA at our institution. Vessel wall lesions were assessed on 7 T MRI sequences, while arterial calcifications were assessed on CT scans. The number of vessel wall lesions, severity of intracranial internal carotid artery (iICA) calcifications, and overall presence and distribution of the two imaging findings were visually assessed in the intracranial arteries.At least one vessel wall lesion or arterial calcification was assessed in 69 (88%) patients. Only the iICA and vertebral arteries (VA) showed a substantial number of both calcifications and vessel wall lesions. The other vessels showed almost exclusively vessel wall lesions. The number of vessel wall lesions was associated with the severity of iICA calcification (p = 0.013).The number of vessel wall lesions increases with the severity of iICA calcifications. Nonetheless, the distribution of vessel wall lesions on MRI and arterial calcifications on CT shows remarkable differences. These findings support the need for a combined approach to examine intracranial arterial disease.","PeriodicalId":507441,"journal":{"name":"Frontiers in Radiology","volume":"180 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139835946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-12DOI: 10.3389/fradi.2024.1366704
Mojtaba Barzegar, Mark Schweitzer, Tiffany Y. So, Yongsheng Chen, Ş.M. Ertürk
{"title":"Editorial: Quantitative neuroradiology methods","authors":"Mojtaba Barzegar, Mark Schweitzer, Tiffany Y. So, Yongsheng Chen, Ş.M. Ertürk","doi":"10.3389/fradi.2024.1366704","DOIUrl":"https://doi.org/10.3389/fradi.2024.1366704","url":null,"abstract":"","PeriodicalId":507441,"journal":{"name":"Frontiers in Radiology","volume":"35 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139782463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-12DOI: 10.3389/fradi.2024.1366704
Mojtaba Barzegar, Mark Schweitzer, Tiffany Y. So, Yongsheng Chen, Ş.M. Ertürk
{"title":"Editorial: Quantitative neuroradiology methods","authors":"Mojtaba Barzegar, Mark Schweitzer, Tiffany Y. So, Yongsheng Chen, Ş.M. Ertürk","doi":"10.3389/fradi.2024.1366704","DOIUrl":"https://doi.org/10.3389/fradi.2024.1366704","url":null,"abstract":"","PeriodicalId":507441,"journal":{"name":"Frontiers in Radiology","volume":"77 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139842505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-12DOI: 10.3389/fradi.2023.1294068
Marko Milosevic, Qingchu Jin, Akarsh Singh, Saeed Amal
Data for healthcare is diverse and includes many different modalities. Traditional approaches to Artificial Intelligence for cardiovascular disease were typically limited to single modalities. With the proliferation of diverse datasets and new methods in AI, we are now able to integrate different modalities, such as magnetic resonance scans, computerized tomography scans, echocardiography, x-rays, and electronic health records. In this paper, we review research from the last 5 years in applications of AI to multi-modal imaging. There have been many promising results in registration, segmentation, and fusion of different magnetic resonance imaging modalities with each other and computer tomography scans, but there are still many challenges that need to be addressed. Only a few papers have addressed modalities such as x-ray, echocardiography, or non-imaging modalities. As for prediction or classification tasks, there have only been a couple of papers that use multiple modalities in the cardiovascular domain. Furthermore, no models have been implemented or tested in real world cardiovascular clinical settings.
医疗数据多种多样，包括许多不同的模式。针对心血管疾病的传统人工智能方法通常局限于单一模式。随着各种数据集和人工智能新方法的激增，我们现在能够整合不同的模式，如磁共振扫描、计算机断层扫描、超声心动图、X 光和电子健康记录。在本文中，我们将回顾过去 5 年人工智能在多模态成像中的应用研究。在不同磁共振成像模式之间以及计算机断层扫描之间的配准、分割和融合方面，已经取得了许多令人鼓舞的成果，但仍有许多挑战需要解决。只有少数论文涉及 X 光、超声心动图或非成像模式。至于预测或分类任务，只有几篇论文在心血管领域使用了多种模式。此外，还没有模型在真实的心血管临床环境中实施或测试过。
{"title":"Applications of AI in multi-modal imaging for cardiovascular disease","authors":"Marko Milosevic, Qingchu Jin, Akarsh Singh, Saeed Amal","doi":"10.3389/fradi.2023.1294068","DOIUrl":"https://doi.org/10.3389/fradi.2023.1294068","url":null,"abstract":"Data for healthcare is diverse and includes many different modalities. Traditional approaches to Artificial Intelligence for cardiovascular disease were typically limited to single modalities. With the proliferation of diverse datasets and new methods in AI, we are now able to integrate different modalities, such as magnetic resonance scans, computerized tomography scans, echocardiography, x-rays, and electronic health records. In this paper, we review research from the last 5 years in applications of AI to multi-modal imaging. There have been many promising results in registration, segmentation, and fusion of different magnetic resonance imaging modalities with each other and computer tomography scans, but there are still many challenges that need to be addressed. Only a few papers have addressed modalities such as x-ray, echocardiography, or non-imaging modalities. As for prediction or classification tasks, there have only been a couple of papers that use multiple modalities in the cardiovascular domain. Furthermore, no models have been implemented or tested in real world cardiovascular clinical settings.","PeriodicalId":507441,"journal":{"name":"Frontiers in Radiology","volume":"39 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139532129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：