Samantha M Stott, Yujie Wu, Shahob Hosseinpour, Chaojun Chen, Khashayar Namdar, Afsaneh Amirabadi, Manohar Shroff, Farzad Khalvati, Andrea S Doria
{"title":"Correlative Assessment of Machine Learning-Based Cobb Angle Measurements and Human-Based Measurements in Adolescent Idiopathic and Congenital Scoliosis.","authors":"Samantha M Stott, Yujie Wu, Shahob Hosseinpour, Chaojun Chen, Khashayar Namdar, Afsaneh Amirabadi, Manohar Shroff, Farzad Khalvati, Andrea S Doria","doi":"10.1177/08465371241231577","DOIUrl":"10.1177/08465371241231577","url":null,"abstract":"<p><p><b>Purpose:</b> Scoliosis is a complex spine deformity with direct functional and cosmetic impacts on the individual. The reference standard for assessing scoliosis severity is the Cobb angle which is measured on radiographs by human specialists, carrying interobserver variability and inaccuracy of measurements. These limitations may result in lack of timely referral for management at a time the scoliotic deformity progression can be saved from surgery. We aimed to create a machine learning (ML) model for automatic calculation of Cobb angles on 3-foot standing spine radiographs of children and adolescents with clinical suspicion of scoliosis across 2 clinical scenarios (idiopathic, group 1 and congenital scoliosis, group 2). <b>Methods:</b> We retrospectively measured Cobb angles of 130 patients who had a 3-foot spine radiograph for scoliosis within a 10-year period for either idiopathic or congenital anomaly scoliosis. Cobb angles were measured both manually by radiologists and by an ML pipeline (segmentation-based approach-Augmented U-Net model with non-square kernels). <b>Results:</b> Our Augmented U-Net architecture achieved a Symmetric Mean Absolute Percentage Error (SMAPE) of 11.82% amongst a combined idiopathic and congenital scoliosis cohort. When stratifying for idiopathic and congenital scoliosis individually a SMAPE of 13.02% and 11.90% were achieved, respectively. <b>Conclusion:</b> The ML model used in this study is promising at providing automated Cobb angle measurement in both idiopathic scoliosis and congenital scoliosis. Nevertheless, larger studies are needed in the future to confirm the results of this study prior to translation of this ML algorithm into clinical practice.</p>","PeriodicalId":55290,"journal":{"name":"Canadian Association of Radiologists Journal-Journal De L Association Canadienne Des Radiologistes","volume":" ","pages":"751-760"},"PeriodicalIF":2.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140307851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Artificial Intelligence in Acute Abdominal Imaging: Are We Reaching the Grail?","authors":"Philippe Soyer","doi":"10.1177/08465371241261060","DOIUrl":"10.1177/08465371241261060","url":null,"abstract":"","PeriodicalId":55290,"journal":{"name":"Canadian Association of Radiologists Journal-Journal De L Association Canadienne Des Radiologistes","volume":" ","pages":"702-703"},"PeriodicalIF":2.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141302181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Driving Change: Direct Patient Access to Medical Imaging Reports and the Need for Radiologist Involvement in Decision-Making.","authors":"Ryan L Smith, Judy Rowe, Daria Manos","doi":"10.1177/08465371241245567","DOIUrl":"10.1177/08465371241245567","url":null,"abstract":"","PeriodicalId":55290,"journal":{"name":"Canadian Association of Radiologists Journal-Journal De L Association Canadienne Des Radiologistes","volume":" ","pages":"700-701"},"PeriodicalIF":2.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140337759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Liver Observation Segmentation on Contrast-Enhanced MRI: SAM and MedSAM Performance in Patients With Probable or Definite Hepatocellular Carcinoma.","authors":"Ashirbani Saha, Christian B van der Pol","doi":"10.1177/08465371241250215","DOIUrl":"10.1177/08465371241250215","url":null,"abstract":"<p><p><b>Purpose:</b> To evaluate factors impacting the Segment Anything Model (SAM) and variant MedSAM performance for segmenting liver observations on contrast-enhanced (CE) magnetic resonance imaging (MRI) in high-risk patients with probable hepatocellular carcinoma (HCC) (LR-4) and definite HCC (LR-5). <b>Methods:</b> A retrospective cohort of liver observations (LR-4/LR-5) on CE-MRI from 97 patients at high-risk for HCC was derived (2013-2018). Using bounding-boxes as prompts under 5-fold cross-validation, segmentation performance was evaluated at the model and liver observation-levels for: (1) model types: SAM versus MedSAM, (2) image sizes: 256 × 256 versus 512 × 512, (3) image channel composition: CE sequences at 3 phases of enhancement independently and combined, (4) liver observation size: >10 mm versus >20 mm, (5) certainty of diagnosis: LR-4 versus LR-5, and (6) contrast-agent type: hepatobiliary versus extracellular. Segmentation performance, quantified using Dice coefficient, were compared using univariate (Wilcoxon signed-rank and <i>t</i>-test) and multivariable analyses (multiple correspondence analysis and subsequent linear modelling). <b>Results:</b> MedSAM trained on 512 × 512 combined CE sequences performed best with mean Dice coefficient 0.68 (95% confidence interval 0.66, 0.69). Overall, all factors except contrast-agent type affected performance, with larger image size resulting in the highest performance improvement (512 × 512: 0.57, 256 × 256: 0.26, <i>P</i> < .001) at the model-level. Contrast-agents affected performance for patients with LR-4 observations using MedSAM-based models (<i>P</i> < .03). Larger observation size, image size, and higher certainty of diagnosis were associated with better segmentation on multivariable analysis. <b>Conclusion:</b> A variety of factors were found to impact SAM/MedSAM performance for segmenting liver observations in patients with probable and definite HCC on CE-MRI. Future models may be optimized by accounting for these factors.</p>","PeriodicalId":55290,"journal":{"name":"Canadian Association of Radiologists Journal-Journal De L Association Canadienne Des Radiologistes","volume":" ","pages":"771-779"},"PeriodicalIF":2.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140877966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chloe DesRoche, Jeannie Callum, Aiden Scholey, Omar I Hajjaj, Jennifer Flemming, Ben Mussari, Emidio Tarulli, Amir Reza Nasirzadeh, Alexandre Menard
{"title":"Platelet and INR Thresholds and Bleeding Risk in Ultrasound Guided Percutaneous Liver Biopsy: A Before-After Implementation of the 2019 Society of Interventional Radiology Guidelines Observational Quality Improvement Study.","authors":"Chloe DesRoche, Jeannie Callum, Aiden Scholey, Omar I Hajjaj, Jennifer Flemming, Ben Mussari, Emidio Tarulli, Amir Reza Nasirzadeh, Alexandre Menard","doi":"10.1177/08465371241252059","DOIUrl":"10.1177/08465371241252059","url":null,"abstract":"<p><p><b>Purpose:</b> To evaluate if implementation of the 2019 Society of Interventional Radiology (SIR) guidelines for periprocedural management of bleeding risk in patients undergoing percutaneous ultrasound guided liver biopsy is associated with increased haemorrhagic adverse events, change in pre-procedural blood product utilization, and evaluation of guideline compliance rate at a single academic institution. <b>Methods:</b> Ultrasound guided percutaneous liver biopsies from (January 2019-January 2023) were retrospectively reviewed (n = 504), comparing biopsies performed using the 2012 SIR pre-procedural coagulation guidelines (n = 266) to those after implementation of the 2019 SIR pre-procedural guidelines (n = 238). Demographic, preprocedural transfusion, laboratory, and clinical data were reviewed. Chart review was conducted to evaluate the incidence of major bleeding adverse events defined as those resulting in transfusion, embolization, surgery, or death. <b>Results:</b> Implementation of the 2019 SIR periprocedural guidelines resulted in reduced guideline non-compliance related to the administration of blood products, from 5.3% to 1.7% (<i>P</i> = .01). The rate of pre-procedural transfusion remained the same pre and post guidelines at 0.8%. There was no statistically significant change in the incidence of bleeding adverse events, 0.8% pre guidelines versus 0.4% post (<i>P</i> = 1.0). <b>Conclusion:</b> Implementation of the 2019 SIR guidelines for periprocedural management of bleeding risk in patients undergoing percutaneous ultrasound guided liver biopsy did not result in an increase in bleeding adverse events or pre-procedural transfusion rates. The guidelines can be safely implemented in clinical practice with no increase in major adverse events.</p>","PeriodicalId":55290,"journal":{"name":"Canadian Association of Radiologists Journal-Journal De L Association Canadienne Des Radiologistes","volume":" ","pages":"931-938"},"PeriodicalIF":2.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140961041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Quality Improvement in Interventional Radiology: A Critical Look at Modern Bleeding Risk Guideline Implementation.","authors":"Blair E Warren, Arash Jaberi, Sebastian C Mafeld","doi":"10.1177/08465371241268405","DOIUrl":"10.1177/08465371241268405","url":null,"abstract":"","PeriodicalId":55290,"journal":{"name":"Canadian Association of Radiologists Journal-Journal De L Association Canadienne Des Radiologistes","volume":" ","pages":"710-711"},"PeriodicalIF":2.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141861739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Konstantinos Zormpas-Petridis, Marica Vagni, Matteo Mancino, Evis Sala
{"title":"Editorial Comment: Integrating Morphomics in Clinical Practice for Personalized Medicine: A Paradigm Shift Toward Holistic Care.","authors":"Konstantinos Zormpas-Petridis, Marica Vagni, Matteo Mancino, Evis Sala","doi":"10.1177/08465371241264248","DOIUrl":"10.1177/08465371241264248","url":null,"abstract":"","PeriodicalId":55290,"journal":{"name":"Canadian Association of Radiologists Journal-Journal De L Association Canadienne Des Radiologistes","volume":" ","pages":"706-707"},"PeriodicalIF":2.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141762798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Juan Martín Leguízamo-Isaza, Gonzalo Andrés Montaño-Rozo, Laura Cristina Morales-Cifuentes, Hernán Darío Paez-Rueda
{"title":"Implementing Strategies to Transition Towards Sustainable Medical Imaging in Radiology Departments.","authors":"Juan Martín Leguízamo-Isaza, Gonzalo Andrés Montaño-Rozo, Laura Cristina Morales-Cifuentes, Hernán Darío Paez-Rueda","doi":"10.1177/08465371241268070","DOIUrl":"10.1177/08465371241268070","url":null,"abstract":"","PeriodicalId":55290,"journal":{"name":"Canadian Association of Radiologists Journal-Journal De L Association Canadienne Des Radiologistes","volume":" ","pages":"955-956"},"PeriodicalIF":2.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141789877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cinematic Rendering of Pancreatic Neuroendocrine Tumours: Opportunities for Clinical Implementation: Part 1: Tumour Detection and Characterization.","authors":"Taha M Ahmed, Elliot K Fishman, Linda C Chu","doi":"10.1177/08465371241239037","DOIUrl":"10.1177/08465371241239037","url":null,"abstract":"<p><p>Pancreatic neuroendocrine tumours (PNETs) are a rare subset of pancreatic tumours that have historically comprised up to 3% of all clinically detected pancreatic tumours. In recent decades, however, advancements in imaging have led to an increased incidental detection rate of PNETs and imaging has played an increasingly central role in the initial diagnostics and surgical planning of these tumours. Cinematic rendering (CR) is a 3D post-processing technique that generates highly photorealistic images through more realistically modelling the path of photons through the imaged volume. This allows for more comprehensive visualization, description, and interpretation of anatomical structures. In this 2-part review article, we present the first description of the various CR appearances of PNETs in the reported literature while providing commentary on the unique clinical opportunities afforded by the adjunctive utilization of CR in the workup of these rare tumours. The first of these 2 instalments highlights the utility of CR in optimizing PNET detection and characterization.</p>","PeriodicalId":55290,"journal":{"name":"Canadian Association of Radiologists Journal-Journal De L Association Canadienne Des Radiologistes","volume":" ","pages":"780-786"},"PeriodicalIF":2.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140177860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pierre-Luc Gagnon, Éric Thérasse, Nicolas Voizard, Michel Dubé, Véronique Caty
{"title":"Uterine Fibroid Embolization Survey in Canada: Challenges, Opportunities, and Differences in Practices Across the Country.","authors":"Pierre-Luc Gagnon, Éric Thérasse, Nicolas Voizard, Michel Dubé, Véronique Caty","doi":"10.1177/08465371241252307","DOIUrl":"10.1177/08465371241252307","url":null,"abstract":"<p><p><b>Purpose:</b> To assess the current practices surrounding Uterine Fibroid Embolization (UFE) in Canada. <b>Methods:</b> An online survey was sent to Canadian Association for Interventional Radiology (CAIR) members. It included questions on symptoms prompting UFE, patient awareness, investigation, UFE settings, the number of UFE procedures, and post-UFE care. The findings were discussed at CAIR's 2023 annual meeting by an expert panel. <b>Results:</b> Out of 792 surveys sent, 87 were filled (11%). Menorrhagia is the most common indication for UFE (87%). Women's awareness of UFE as a treatment option for fibroids is viewed as poor or average by 94% of our survey respondents. Most respondents see patients in clinics (92%) before the procedure and evaluate fibroids with MRI pre-UFE (76%). There is variability in care post-UFE, with 33% of procedures being performed as day surgery while 67% lead to overnight stay. For pain management, intravenous analgesia (including patient-controlled analgesia) is used in 76% (63/83) of cases while 19% (16/83) of respondents mentioned using epidural analgesia. Finally, there is an even split between embolic agent used; non-spherical polyvinyl alcohol (50%) and spherical particles (50%). <b>Conclusion:</b> Respondents believe patients in Canada still have limited awareness of UFE. Interventional radiologists are increasingly involved in the entire patient care trajectory, overseeing pre-and post-procedure care and hospitalizing patients. For pain management after UFE, it is observed that while epidural analgesia has been demonstrated more effective than alternatives, it is not widely used as the primary method.</p>","PeriodicalId":55290,"journal":{"name":"Canadian Association of Radiologists Journal-Journal De L Association Canadienne Des Radiologistes","volume":" ","pages":"939-945"},"PeriodicalIF":2.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140961044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}