Pub Date : 2023-09-19DOI: 10.1016/j.redii.2023.100034
William Wantz , Julien Le Roy , Cédric Lukas , Catherine Cyteval , Maxime Pastor
Purpose
To compare tomosynthesis performance to radiography for the differentiation of sacroiliitis versus normal or degenerative changes in sacroiliac joints in patients with suspected axial spondyloarthritis (SpA).
Materials and methods
Radiography, tomosynthesis and CT of sacroiliac joints (29 patients) were performed on the same day in consecutive patients with suspected SpA. The examinations were retrospectively read independently, blinded by two radiologists (one junior and one senior, and twice by one junior). Interobserver and intraobserver agreement was evaluated using the kappa coefficient. Effective doses for each imaging sensitivity, specificity and accuracy were assessed and compared with CT as gold standard.
Results
CT detected 15/58 joints with sacroiliitis. The imaging sensitivity, specificity and accuracy were 60%, 84% and 44%, respectively, for radiography and 87%, 91% and 77% for tomosynthesis. The mean effective dose for tomosynthesis was significantly lower than that of CT (5-fold less) and significantly higher than that of radiography (8-fold more).
Conclusion
Tomosynthesis is superior to radiography for sacroiliitis detection in patients with suspected SpA, with 5-fold less radiation exposure than CT.
{"title":"Tomosynthesis performance compared to radiography and computed tomography for sacroiliac joint structural damage detection in patients with suspected axial spondyloarthritis","authors":"William Wantz , Julien Le Roy , Cédric Lukas , Catherine Cyteval , Maxime Pastor","doi":"10.1016/j.redii.2023.100034","DOIUrl":"https://doi.org/10.1016/j.redii.2023.100034","url":null,"abstract":"<div><h3>Purpose</h3><p>To compare tomosynthesis performance to radiography for the differentiation of sacroiliitis versus normal or degenerative changes in sacroiliac joints in patients with suspected axial spondyloarthritis (SpA).</p></div><div><h3>Materials and methods</h3><p>Radiography, tomosynthesis and CT of sacroiliac joints (29 patients) were performed on the same day in consecutive patients with suspected SpA. The examinations were retrospectively read independently, blinded by two radiologists (one junior and one senior, and twice by one junior). Interobserver and intraobserver agreement was evaluated using the kappa coefficient. Effective doses for each imaging sensitivity, specificity and accuracy were assessed and compared with CT as gold standard.</p></div><div><h3>Results</h3><p>CT detected 15/58 joints with sacroiliitis. The imaging sensitivity, specificity and accuracy were 60%, 84% and 44%, respectively, for radiography and 87%, 91% and 77% for tomosynthesis. The mean effective dose for tomosynthesis was significantly lower than that of CT (5-fold less) and significantly higher than that of radiography (8-fold more).</p></div><div><h3>Conclusion</h3><p>Tomosynthesis is superior to radiography for sacroiliitis detection in patients with suspected SpA, with 5-fold less radiation exposure than CT.</p></div>","PeriodicalId":74676,"journal":{"name":"Research in diagnostic and interventional imaging","volume":"8 ","pages":"Article 100034"},"PeriodicalIF":0.0,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50186806","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 : 2023-09-01DOI: 10.1016/j.redii.2023.100032
Juan Manuel Marquez-Romero , Marco Zenteno , Antonio Arauz
Objective
Describe the incidence of contrast-induced acute renal injury (CI-AKI) and the changes in hematocrit in a cohort of patients undergoing elective cerebral digital subtraction angiography (DSA).
Methods
In this prospective study, patients undergoing cerebral DSA were assessed for hematocrit level and CI-AKI risk factors before the procedure and for developing CI-AKI 72 h after exposure to the contrast media.
Results
Among 215 patients (109 men, mean age 36.6 years). The most frequently found CI-AKI risk factor was hypertension. There were no cases of permanent renal impairment after 14 days. Significant changes were observed in hematocrit (45.7 ± 4.9, vs. 44.5 ± 4.6, p = 0.001), estimated creatinine clearance (129.7 ± 48.3, vs. 123.1 ± 40.5, p = 0.002), and serum creatinine (0.72 ± 0.19, vs 0.74 ± 0.18, p = 0.031). The mean change in serum creatinine 72 h after contrast administration was +0.27 ± 0.10 mg/dL (p < 0.05).
Conclusions
The incidence of CI-AKI after elective cerebral DSA was 1.4%. A significant decrease in hematocrit was observed up to 72 h after the procedure.
{"title":"Changes in blood and renal function in patients after cerebral digital subtraction angiography","authors":"Juan Manuel Marquez-Romero , Marco Zenteno , Antonio Arauz","doi":"10.1016/j.redii.2023.100032","DOIUrl":"10.1016/j.redii.2023.100032","url":null,"abstract":"<div><h3>Objective</h3><p>Describe the incidence of contrast-induced acute renal injury (CI-AKI) and the changes in hematocrit in a cohort of patients undergoing elective cerebral digital subtraction angiography (DSA).</p></div><div><h3>Methods</h3><p>In this prospective study, patients undergoing cerebral DSA were assessed for hematocrit level and CI-AKI risk factors before the procedure and for developing CI-AKI 72 h after exposure to the contrast media.</p></div><div><h3>Results</h3><p>Among 215 patients (109 men, mean age 36.6 years). The most frequently found CI-AKI risk factor was hypertension. There were no cases of permanent renal impairment after 14 days. Significant changes were observed in hematocrit (45.7 ± 4.9, vs. 44.5 ± 4.6, <em>p</em> = 0.001), estimated creatinine clearance (129.7 ± 48.3, vs. 123.1 ± 40.5, <em>p</em> = 0.002), and serum creatinine (0.72 ± 0.19, vs 0.74 ± 0.18, <em>p</em> = 0.031). The mean change in serum creatinine 72 h after contrast administration was +0.27 ± 0.10 mg/dL (<em>p</em> < 0.05).</p></div><div><h3>Conclusions</h3><p>The incidence of CI-AKI after elective cerebral DSA was 1.4%. A significant decrease in hematocrit was observed up to 72 h after the procedure.</p></div>","PeriodicalId":74676,"journal":{"name":"Research in diagnostic and interventional imaging","volume":"7 ","pages":"Article 100032"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46198082","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 : 2023-09-01DOI: 10.1016/j.redii.2023.100033
Justyna Kłos , Reina W. Kloet , Hiska L. van der Weide , Kelvin Ng Wei Siang , Peter F. Sinnige , Miranda C.A. Kramer , Rudi A.J.O. Dierckx , Ronald J.H. Borra , Anouk van der Hoorn
Background and purpose
Cerebral microbleeds (CMBs) and fluid-attenuated-inversion recovery (FLAIR) hyperintensities on brain MRI scans after radiotherapy (RT) are considered markers for microvascular damage and related cognitive changes. However, the spatial distribution using existing scoring systems as well as colocation of these imaging biomarkers remain unclear, hampering clinical interpretation. This study aims to elucidate the distribution and colocation of these markers in patients with lower grade glioma (LGG).
Materials and methods
CMBs were spatially classified on retrospective 1.5 T susceptibility weighted MRI scans according to the existing Microbleed Anatomical Rating Scale (MARS) and were additionally scored for being located in hippocampus, amygdala, cortex, white matter (WM), grey matter (GM), WM/GM junction and for their spatial relation to FLAIR hyperintensities. Scoring was performed for whole, ipsilateral and contralateral cerebrum (with respect to tumour bulk).
Results
Fifty-one scans were included of which 28 had at least one CMB. The majority of CMBs were localized in the lobar area and in deep and periventricular white matter (DPWM) - generally in WM. Only few CMBs were found in GM. In scans obtained up to 7 years after RT completion the majority of CMBs were not colocalized with FLAIR hyperintensities.
Conclusion
CMBs and FLAIR hyperintensities appear to be separate imaging biomarkers for radiation therapy induced microvascular damage, as they are not colocalized in patients with LGG, especially not early on after completion of RT.
{"title":"Spatial distribution of cerebral microbleeds and FLAIR hyperintensities on follow-up MRI after radiotherapy for lower grade glioma","authors":"Justyna Kłos , Reina W. Kloet , Hiska L. van der Weide , Kelvin Ng Wei Siang , Peter F. Sinnige , Miranda C.A. Kramer , Rudi A.J.O. Dierckx , Ronald J.H. Borra , Anouk van der Hoorn","doi":"10.1016/j.redii.2023.100033","DOIUrl":"10.1016/j.redii.2023.100033","url":null,"abstract":"<div><h3>Background and purpose</h3><p>Cerebral microbleeds (CMBs) and fluid-attenuated-inversion recovery (FLAIR) hyperintensities on brain MRI scans after radiotherapy (RT) are considered markers for microvascular damage and related cognitive changes. However, the spatial distribution using existing scoring systems as well as colocation of these imaging biomarkers remain unclear, hampering clinical interpretation. This study aims to elucidate the distribution and colocation of these markers in patients with lower grade glioma (LGG).</p></div><div><h3>Materials and methods</h3><p>CMBs were spatially classified on retrospective 1.5 T susceptibility weighted MRI scans according to the existing Microbleed Anatomical Rating Scale (MARS) and were additionally scored for being located in hippocampus, amygdala, cortex, white matter (WM), grey matter (GM), WM/GM junction and for their spatial relation to FLAIR hyperintensities. Scoring was performed for whole, ipsilateral and contralateral cerebrum (with respect to tumour bulk).</p></div><div><h3>Results</h3><p>Fifty-one scans were included of which 28 had at least one CMB. The majority of CMBs were localized in the lobar area and in deep and periventricular white matter (DPWM) - generally in WM. Only few CMBs were found in GM. In scans obtained up to 7 years after RT completion the majority of CMBs were not colocalized with FLAIR hyperintensities.</p></div><div><h3>Conclusion</h3><p>CMBs and FLAIR hyperintensities appear to be separate imaging biomarkers for radiation therapy induced microvascular damage, as they are not colocalized in patients with LGG, especially not early on after completion of RT.</p></div>","PeriodicalId":74676,"journal":{"name":"Research in diagnostic and interventional imaging","volume":"7 ","pages":"Article 100033"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42593350","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}
Crohn's disease (CD) is a chronic disorder that often starts at a young age and involves periods of remission and relapse. Prompt diagnosis of relapses through screening is crucial due to the potential morbid complications of untreated active inflammation. Magnetic resonance enterography (MRE) is a noninvasive technique to screen for active inflammation. The standard protocol involves intravenous injection of contrast agents with potential side effects. Some abbreviated non-contrast-enhanced MRE protocols are proposed as alternatives for conventional MRE to identify active inflammation. Currently, there is controversy regarding the applicability and accuracy of these protocols. This study aims to describe and compare these protocols and evaluate their accuracy in detecting active inflammation and CD complications.
Methods
Results from a systematic search of three databases in August 2022 were queried and screened by abstract and full text. Eligible studies were qualitatively and quantitatively analyzed by diagnostic test accuracy meta-analysis.
Results
59 studies entered the systematic review, and 37 were eligible for meta-analysis. Diffusion-weighted imaging (DWI) and fast T2-weighted (T2w) sequences were most frequently used in abbreviated protocols and showed non-inferior accuracy compared to the full protocol in detecting active inflammation. ADC and qualitative DWI had pooled sensitivity of 90% (CI: 82–95%) and 89% (CI:82–93%) and pooled specificity of 94% (CI: 88–97%) and 89% (CI: 79–94%), respectively for detecting active inflammation. Moreover, T2w and combined T2w+DWI sequences had pooled sensitivity of 80% (CI: 64–90%) and 76% (CI: 61–86%) and pooled specificity of 90% (CI: 80–95%) and 87% (CI: 74 – 94%), respectively. Unenhanced protocols show relatively poor diagnostic accuracy in detecting penetrating complications of CD. Magnetization transfer imaging (MTI) has demonstrated excellent accuracy in detecting fibrosis. High heterogeneity was observed in all subgroups, and accuracy was reported to be highly operator dependent in most studies.
Conclusion
An abbreviated protocol consisting of DWI and fast T2w imaging can potentially replace the full protocol MRE. Full protocol MRE will still have its role in identifying penetrating complications. MTI should be indicated in case of suspected fibrostenotic disease.
{"title":"Role of abbreviated non-contrast-enhanced MR-enterography in the evaluation of Crohn's disease activity and complications as an alternative for full protocol contrast-enhanced study: A systematic review and meta-analysis","authors":"Payam Jannatdoust , Parya Valizadeh , Mahshad Razaghi , Maedeh Rouzbahani , Amirbahador Abbasi , Arvin Arian","doi":"10.1016/j.redii.2023.100030","DOIUrl":"10.1016/j.redii.2023.100030","url":null,"abstract":"<div><h3>Background</h3><p>Crohn's disease (CD) is a chronic disorder that often starts at a young age and involves periods of remission and relapse. Prompt diagnosis of relapses through screening is crucial due to the potential morbid complications of untreated active inflammation. Magnetic resonance enterography (MRE) is a noninvasive technique to screen for active inflammation. The standard protocol involves intravenous injection of contrast agents with potential side effects. Some abbreviated non-contrast-enhanced MRE protocols are proposed as alternatives for conventional MRE to identify active inflammation. Currently, there is controversy regarding the applicability and accuracy of these protocols. This study aims to describe and compare these protocols and evaluate their accuracy in detecting active inflammation and CD complications.</p></div><div><h3>Methods</h3><p>Results from a systematic search of three databases in August 2022 were queried and screened by abstract and full text. Eligible studies were qualitatively and quantitatively analyzed by diagnostic test accuracy meta-analysis.</p></div><div><h3>Results</h3><p>59 studies entered the systematic review, and 37 were eligible for meta-analysis. Diffusion-weighted imaging (DWI) and fast T2-weighted (T2w) sequences were most frequently used in abbreviated protocols and showed non-inferior accuracy compared to the full protocol in detecting active inflammation. ADC and qualitative DWI had pooled sensitivity of 90% (CI: 82–95%) and 89% (CI:82–93%) and pooled specificity of 94% (CI: 88–97%) and 89% (CI: 79–94%), respectively for detecting active inflammation. Moreover, T2w and combined T2w+DWI sequences had pooled sensitivity of 80% (CI: 64–90%) and 76% (CI: 61–86%) and pooled specificity of 90% (CI: 80–95%) and 87% (CI: 74 – 94%), respectively. Unenhanced protocols show relatively poor diagnostic accuracy in detecting penetrating complications of CD. Magnetization transfer imaging (MTI) has demonstrated excellent accuracy in detecting fibrosis. High heterogeneity was observed in all subgroups, and accuracy was reported to be highly operator dependent in most studies.</p></div><div><h3>Conclusion</h3><p>An abbreviated protocol consisting of DWI and fast T2w imaging can potentially replace the full protocol MRE. Full protocol MRE will still have its role in identifying penetrating complications. MTI should be indicated in case of suspected fibrostenotic disease.</p></div>","PeriodicalId":74676,"journal":{"name":"Research in diagnostic and interventional imaging","volume":"6 ","pages":"Article 100030"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45689370","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 : 2023-06-01DOI: 10.1016/j.redii.2023.100028
Chaan S. Ng , Adam G. Chandler , Yanwen Chen , Wei Wei , Nizar M. Tannir , Brian P. Hobbs
Objective
CT perfusion (CTp) values are affected by CT scan acquisition duration (tacq); their reproducibility is adversely affected by uncertainty in their measurement. The objectives were to assess the effects of tacq on CTp parameter values in metastases from renal cell carcinoma (mRCC) in thoracic and abdominal locations.
Materials and Methods
131 CTp evaluations in 53 patients with mRCC were retrospectively analyzed by distributed parameter modeling to yield tissue blood flow (BF), blood volume (BV), mean transit time (MTT), permeability (PS), and also hepatic arterial perfusion (HAP) and hepatic arterial fraction (HAF) for liver metastases and normal liver, with tacq from 25 to 590 s. Penalized piecewise polynomial regression (SPLINE) characterized functional relationships between CTp parameters and acquisition duration, tacq. Evidence for time-invariance was evaluated for each parameter at multiple time points by conducting inference on the fitted derivative to assess its proximity to zero as a function of acquisition time. Equivalence testing was implemented with three levels of confidence (low (20%), moderate (70%), high (95%)).
Results
Systematic and non-systematic variability was observed for CTp parameter values with limited tacq. All parameters in all locations approached increasing stability with increasing tacq. PS, HAP and HAF required longer acquisition times than BF, BV and MTT to attain comparable levels of stability. Stabilization tended to require longer acquisition in liver than other tissues. tacq=380 s was required to obtain at least moderate level of confidence for all parameters and organs.
Conclusion
Increasing tacq yields increasingly more stable CT perfusion parameters, and thereby better reproducibility.
{"title":"Effect of scan duration on CT perfusion values in metastases from renal cell carcinoma","authors":"Chaan S. Ng , Adam G. Chandler , Yanwen Chen , Wei Wei , Nizar M. Tannir , Brian P. Hobbs","doi":"10.1016/j.redii.2023.100028","DOIUrl":"10.1016/j.redii.2023.100028","url":null,"abstract":"<div><h3>Objective</h3><p>CT perfusion (CTp) values are affected by CT scan acquisition duration (t<sub>acq</sub>); their reproducibility is adversely affected by uncertainty in their measurement. The objectives were to assess the effects of t<sub>acq</sub> on CTp parameter values in metastases from renal cell carcinoma (mRCC) in thoracic and abdominal locations.</p></div><div><h3>Materials and Methods</h3><p>131 CTp evaluations in 53 patients with mRCC were retrospectively analyzed by distributed parameter modeling to yield tissue blood flow (BF), blood volume (BV), mean transit time (MTT), permeability (PS), and also hepatic arterial perfusion (HAP) and hepatic arterial fraction (HAF) for liver metastases and normal liver, with t<sub>acq</sub> from 25 to 590 s. Penalized piecewise polynomial regression (SPLINE) characterized functional relationships between CTp parameters and acquisition duration, t<sub>acq</sub>. Evidence for time-invariance was evaluated for each parameter at multiple time points by conducting inference on the fitted derivative to assess its proximity to zero as a function of acquisition time. Equivalence testing was implemented with three levels of confidence (low (20%), moderate (70%), high (95%)).</p></div><div><h3>Results</h3><p>Systematic and non-systematic variability was observed for CTp parameter values with limited t<sub>acq</sub>. All parameters in all locations approached increasing stability with increasing t<sub>acq</sub>. PS, HAP and HAF required longer acquisition times than BF, BV and MTT to attain comparable levels of stability. Stabilization tended to require longer acquisition in liver than other tissues. t<sub>acq</sub>=380 s was required to obtain at least moderate level of confidence for all parameters and organs.</p></div><div><h3>Conclusion</h3><p>Increasing t<sub>acq</sub> yields increasingly more stable CT perfusion parameters, and thereby better reproducibility.</p></div>","PeriodicalId":74676,"journal":{"name":"Research in diagnostic and interventional imaging","volume":"6 ","pages":"Article 100028"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42229046","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 : 2023-06-01DOI: 10.1016/j.redii.2023.100026
Robert Janiszewski , Nathan Law , Ryan Walters , Tami DenOtter
{"title":"Diagnosing sarcopenia with semi-automated skeletal muscle computed tomography cutoff values and the association of these muscle metrics with long-term physical exercise","authors":"Robert Janiszewski , Nathan Law , Ryan Walters , Tami DenOtter","doi":"10.1016/j.redii.2023.100026","DOIUrl":"10.1016/j.redii.2023.100026","url":null,"abstract":"","PeriodicalId":74676,"journal":{"name":"Research in diagnostic and interventional imaging","volume":"6 ","pages":"Article 100026"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47671942","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 : 2023-06-01DOI: 10.1016/j.redii.2023.100029
Clémence ROZWAG , Franck VALENTINI , Anne COTTEN , Xavier DEMONDION , Philippe PREUX , Thibaut JACQUES
Rationale and Objectives
To develop a model using artificial intelligence (A.I.) able to detect post-traumatic injuries on pediatric elbow X-rays then to evaluate its performances in silico and its impact on radiologists’ interpretation in clinical practice.
Material and Methods
A total of 1956 pediatric elbow radiographs performed following a trauma were retrospectively collected from 935 patients aged between 0 and 18 years. Deep convolutional neural networks were trained on these X-rays. The two best models were selected then evaluated on an external test set involving 120 patients, whose X-rays were performed on a different radiological equipment in another time period. Eight radiologists interpreted this external test set without then with the help of the A.I. models .
Results
Two models stood out: model 1 had an accuracy of 95.8% and an AUROC of 0.983 and model 2 had an accuracy of 90.5% and an AUROC of 0.975. On the external test set, model 1 kept a good accuracy of 82.5% and AUROC of 0.916 while model 2 had a loss of accuracy down to 69.2% and of AUROC to 0.793. Model 1 significantly improved radiologist's sensitivity (0.82 to 0.88, P = 0.016) and accuracy (0.86 to 0.88, P = 0,047) while model 2 significantly decreased specificity of readers (0.86 to 0.83, P = 0.031).
Conclusion
End-to-end development of a deep learning model to assess post-traumatic injuries on elbow X-ray in children was feasible and showed that models with close metrics in silico can unpredictably lead radiologists to either improve or lower their performances in clinical settings.
{"title":"Elbow trauma in children: development and evaluation of radiological artificial intelligence models","authors":"Clémence ROZWAG , Franck VALENTINI , Anne COTTEN , Xavier DEMONDION , Philippe PREUX , Thibaut JACQUES","doi":"10.1016/j.redii.2023.100029","DOIUrl":"10.1016/j.redii.2023.100029","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><p>To develop a model using artificial intelligence (A.I.) able to detect post-traumatic injuries on pediatric elbow X-rays then to evaluate its performances in silico and its impact on radiologists’ interpretation in clinical practice.</p></div><div><h3>Material and Methods</h3><p>A total of 1956 pediatric elbow radiographs performed following a trauma were retrospectively collected from 935 patients aged between 0 and 18 years. Deep convolutional neural networks were trained on these X-rays. The two best models were selected then evaluated on an external test set involving 120 patients, whose X-rays were performed on a different radiological equipment in another time period. Eight radiologists interpreted this external test set without then with the help of the A.I. models .</p></div><div><h3>Results</h3><p>Two models stood out: model 1 had an accuracy of 95.8% and an AUROC of 0.983 and model 2 had an accuracy of 90.5% and an AUROC of 0.975. On the external test set, model 1 kept a good accuracy of 82.5% and AUROC of 0.916 while model 2 had a loss of accuracy down to 69.2% and of AUROC to 0.793. Model 1 significantly improved radiologist's sensitivity (0.82 to 0.88, <em>P</em> = 0.016) and accuracy (0.86 to 0.88, <em>P</em> = 0,047) while model 2 significantly decreased specificity of readers (0.86 to 0.83, <em>P</em> = 0.031).</p></div><div><h3>Conclusion</h3><p>End-to-end development of a deep learning model to assess post-traumatic injuries on elbow X-ray in children was feasible and showed that models with close metrics in silico can unpredictably lead radiologists to either improve or lower their performances in clinical settings.</p></div>","PeriodicalId":74676,"journal":{"name":"Research in diagnostic and interventional imaging","volume":"6 ","pages":"Article 100029"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49070855","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 : 2023-06-01DOI: 10.1016/j.redii.2023.100027
Émilien Jupin-Delevaux , Aissam Djahnine , François Talbot , Antoine Richard , Sylvain Gouttard , Adeline Mansuy , Philippe Douek , Salim Si-Mohamed , Loïc Boussel
Rationale and objectives
To develop a Natural Language Processing (NLP) method based on Bidirectional Encoder Representations from Transformers (BERT) adapted to French CT reports and to evaluate its performance to calculate the diagnostic yield of CT in patients with clinical suspicion of pulmonary embolism (PE).
Materials and methods
All the CT reports performed in our institution in 2019 (99,510 reports, training and validation dataset) and 2018 (94,559 reports, testing dataset) were included after anonymization. Two BERT-based NLP sentence classifiers were trained on 27.700, manually labeled, sentences from the training dataset. The first one aimed to classify the reports’ sentences into three classes (“Non chest”, “Healthy chest”, and "Pathological chest" related sentences), the second one to classify the last class into eleven sub classes pathologies including "pulmonary embolism". F1-score was reported on the validation dataset. These NLP classifiers were then applied to requested CT reports for pulmonary embolism from the testing dataset. Sensitivity, specificity, and accuracy for detection of the presence of a pulmonary embolism were reported in comparison to human analysis of the reports.
Results
The F1-score for the 3-Classes and 11-SubClasses classifiers was 0.984 and 0.985, respectively. 4,042 examinations from the testing dataset were requested for pulmonary embolism of which 641 (15.8%) were positively evaluated by radiologists. The sensitivity, specificity, and accuracy of the NLP network for identifying pulmonary embolism in these reports were 98.2%, 99.3% and 99.1%, respectively.
Conclusion
BERT-based NLP sentences classifier enables the analysis of large databases of radiological reports to accurately determine the diagnostic yield of CT screening.
{"title":"BERT-based natural language processing analysis of French CT reports: Application to the measurement of the positivity rate for pulmonary embolism","authors":"Émilien Jupin-Delevaux , Aissam Djahnine , François Talbot , Antoine Richard , Sylvain Gouttard , Adeline Mansuy , Philippe Douek , Salim Si-Mohamed , Loïc Boussel","doi":"10.1016/j.redii.2023.100027","DOIUrl":"10.1016/j.redii.2023.100027","url":null,"abstract":"<div><h3>Rationale and objectives</h3><p>To develop a Natural Language Processing (NLP) method based on Bidirectional Encoder Representations from Transformers (BERT) adapted to French CT reports and to evaluate its performance to calculate the diagnostic yield of CT in patients with clinical suspicion of pulmonary embolism (PE).</p></div><div><h3>Materials and methods</h3><p>All the CT reports performed in our institution in 2019 (99,510 reports, training and validation dataset) and 2018 (94,559 reports, testing dataset) were included after anonymization. Two BERT-based NLP sentence classifiers were trained on 27.700, manually labeled, sentences from the training dataset. The first one aimed to classify the reports’ sentences into three classes (“Non chest”, “Healthy chest”, and \"Pathological chest\" related sentences), the second one to classify the last class into eleven sub classes pathologies including \"pulmonary embolism\". F1-score was reported on the validation dataset. These NLP classifiers were then applied to requested CT reports for pulmonary embolism from the testing dataset. Sensitivity, specificity, and accuracy for detection of the presence of a pulmonary embolism were reported in comparison to human analysis of the reports.</p></div><div><h3>Results</h3><p>The F1-score for the 3-Classes and 11-SubClasses classifiers was 0.984 and 0.985, respectively. 4,042 examinations from the testing dataset were requested for pulmonary embolism of which 641 (15.8%) were positively evaluated by radiologists. The sensitivity, specificity, and accuracy of the NLP network for identifying pulmonary embolism in these reports were 98.2%, 99.3% and 99.1%, respectively.</p></div><div><h3>Conclusion</h3><p>BERT-based NLP sentences classifier enables the analysis of large databases of radiological reports to accurately determine the diagnostic yield of CT screening.</p></div>","PeriodicalId":74676,"journal":{"name":"Research in diagnostic and interventional imaging","volume":"6 ","pages":"Article 100027"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44997288","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 : 2023-03-01DOI: 10.1016/j.redii.2022.100019
Jens Borgbjerg , Nis Elbrønd Larsen , Ivar Mjåland Salte , Niklas Revold Grønli , Elise Klæstrup , Anne Negård
{"title":"Radiation dose in CT-based active surveillance of small renal masses may be reduced by 75%: A retrospective exploratory multiobserver study","authors":"Jens Borgbjerg , Nis Elbrønd Larsen , Ivar Mjåland Salte , Niklas Revold Grønli , Elise Klæstrup , Anne Negård","doi":"10.1016/j.redii.2022.100019","DOIUrl":"10.1016/j.redii.2022.100019","url":null,"abstract":"","PeriodicalId":74676,"journal":{"name":"Research in diagnostic and interventional imaging","volume":"5 ","pages":"Article 100019"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49336767","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 : 2023-03-01DOI: 10.1016/j.redii.2022.100021
Jia Jiang , Lei Chen , Xiaowei Ji , Xuan Zheng , Junjie Hong , Kun Tang , Xiangwu Zheng
Objective
To evaluate the diagnostic performance of (18F)-PSMA-1007 PET/CT in prostate cancer patients with biochemical recurrence (BCR) after radical prostatectomy and the effect of (18F)-PSMA-1007 PET/CT on treatment strategy.
Methods
A total of 114 patients with BCR after radical prostatectomy who performed (18F)-PSMA-1007 PET/CT were retrospectively analyzed. The Gleason scores (GS), maximum standardized uptake values (SUVmax) and the diagnostic performance were compared according to different prostate-specific antigen (PSA) groups. To evaluate the impact of (18F)-PSMA-1007 PET/CT on treatment management, we also collected subjects’ therapy before and after PET/CT. The PSA value was monitored to evaluate the biochemical response.
Results
(18F)-PSMA-1007PET/CT was positive in 92/114 patients (80.7%). The detection rates were 20/34 (58.8%), 13/17 (76.5%), 15/17 (88.2%) and 44/46 (95.7%) for PSA levels of 0.2-<0.5, 0.5-<1, 1-<2, ≥2 ng/ml. The positive lesions on PET/CT revealed local recurrence in 24/114 (21.1%) patients, lymph nodes metastases in 54/114 (47.4%) and metastatic sites in bone, lung, and others in 75/114 (65.8%). A significant positive correlation was observed between the GS/ SUVmax and PSA level (r1 = 0.375, r2 = 0.336, P<0.001). As a result of the (18F)-PSMA-1007 PET/CT, therapeutic decision-making changed in 60/114 (52.6%) patients. With a follow-up of 11.0 ± 6.4 months, 81/114 PSA were collected after treatment guided by (18F)-PSMA-1007 PET/CT, and in 42/81 (51.9%) of patients, serum PSA levels decreased of more than 60%.
Conclusion
(18F)-PSMA-1007 PET/CT has a high lesion detection rate for recurrent prostate cancer (PCa) and could have significant implications in decision-making treatment plan for the majority of PCa patients.
{"title":"(18F)-PSMA-1007PET/CT in patients with biochemical recurrence after radical prostatectomy: Diagnostic performance and impact on treatment management","authors":"Jia Jiang , Lei Chen , Xiaowei Ji , Xuan Zheng , Junjie Hong , Kun Tang , Xiangwu Zheng","doi":"10.1016/j.redii.2022.100021","DOIUrl":"10.1016/j.redii.2022.100021","url":null,"abstract":"<div><h3>Objective</h3><p>To evaluate the diagnostic performance of (<sup>18</sup>F)-PSMA-1007 PET/CT in prostate cancer patients with biochemical recurrence (BCR) after radical prostatectomy and the effect of (<sup>18</sup>F)-PSMA-1007 PET/CT on treatment strategy.</p></div><div><h3>Methods</h3><p>A total of 114 patients with BCR after radical prostatectomy who performed (<sup>18</sup>F)-PSMA-1007 PET/CT were retrospectively analyzed. The Gleason scores (GS), maximum standardized uptake values (SUV<sub>max</sub>) and the diagnostic performance were compared according to different prostate-specific antigen (PSA) groups. To evaluate the impact of (<sup>18</sup>F)-PSMA-1007 PET/CT on treatment management, we also collected subjects’ therapy before and after PET/CT. The PSA value was monitored to evaluate the biochemical response.</p></div><div><h3>Results</h3><p>(<sup>18</sup>F)-PSMA-1007PET/CT was positive in 92/114 patients (80.7%). The detection rates were 20/34 (58.8%), 13/17 (76.5%), 15/17 (88.2%) and 44/46 (95.7%) for PSA levels of 0.2-<0.5, 0.5-<1, 1-<2, ≥2 ng/ml. The positive lesions on PET/CT revealed local recurrence in 24/114 (21.1%) patients, lymph nodes metastases in 54/114 (47.4%) and metastatic sites in bone, lung, and others in 75/114 (65.8%). A significant positive correlation was observed between the GS/ SUV<sub>max</sub> and PSA level (r<sub>1</sub> = 0.375, r<sub>2</sub> = 0.336, <em>P</em><0.001). As a result of the (<sup>18</sup>F)-PSMA-1007 PET/CT, therapeutic decision-making changed in 60/114 (52.6%) patients. With a follow-up of 11.0 ± 6.4 months, 81/114 PSA were collected after treatment guided by (<sup>18</sup>F)-PSMA-1007 PET/CT, and in 42/81 (51.9%) of patients, serum PSA levels decreased of more than 60%.</p></div><div><h3>Conclusion</h3><p>(<sup>18</sup>F)-PSMA-1007 PET/CT has a high lesion detection rate for recurrent prostate cancer (PCa) and could have significant implications in decision-making treatment plan for the majority of PCa patients.</p></div>","PeriodicalId":74676,"journal":{"name":"Research in diagnostic and interventional imaging","volume":"5 ","pages":"Article 100021"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41492858","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号