Pub Date : 2024-09-23DOI: 10.1016/j.clinimag.2024.110305
Rebecca T. Sivarajah , Trevor R. Bean , Alison L. Chetlen
Many benign and malignant breast entities can present with diffuse unilateral magnetic resonance imaging (MRI) findings. The unilateral breast findings can be broken down into three broad categories including asymmetric diffuse masses/non-mass enhancement (NME), diffuse unilateral skin thickening, and diffuse asymmetric background enhancement. Although correlation with clinical history is always necessary, biopsy is often needed to make a definitive diagnosis. There are some findings on MRI which can help narrow the differential including morphology, distribution, T2W signal, enhancement kinetics, and associated skin thickening. Malignant entities which will be discussed in this review include ductal carcinoma in situ, invasive ductal carcinoma, invasive lobular carcinoma, Paget disease, inflammatory breast cancer, and locally advanced breast cancer. Benign entities which will be discussed in this review include idiopathic granulomatous mastitis (IGM), infectious mastitis, pseudoangiomatous stromal hyperplasia, giant fibroadenoma, early and late radiation changes, unilateral breast feeding, and central venous obstruction, all which have varied MRI appearances. It is important for radiologists to be familiar with the common entities that can present with diffuse asymmetric unilateral MRI breast findings to ensure the correct diagnosis and management is undertaken.
{"title":"Diffuse unilateral MRI breast entities","authors":"Rebecca T. Sivarajah , Trevor R. Bean , Alison L. Chetlen","doi":"10.1016/j.clinimag.2024.110305","DOIUrl":"10.1016/j.clinimag.2024.110305","url":null,"abstract":"<div><div>Many benign and malignant breast entities can present with diffuse unilateral magnetic resonance imaging (MRI) findings. The unilateral breast findings can be broken down into three broad categories including asymmetric diffuse masses/non-mass enhancement (NME), diffuse unilateral skin thickening, and diffuse asymmetric background enhancement. Although correlation with clinical history is always necessary, biopsy is often needed to make a definitive diagnosis. There are some findings on MRI which can help narrow the differential including morphology, distribution, T2W signal, enhancement kinetics, and associated skin thickening. Malignant entities which will be discussed in this review include ductal carcinoma in situ, invasive ductal carcinoma, invasive lobular carcinoma, Paget disease, inflammatory breast cancer, and locally advanced breast cancer. Benign entities which will be discussed in this review include idiopathic granulomatous mastitis (IGM), infectious mastitis, pseudoangiomatous stromal hyperplasia, giant fibroadenoma, early and late radiation changes, unilateral breast feeding, and central venous obstruction, all which have varied MRI appearances. It is important for radiologists to be familiar with the common entities that can present with diffuse asymmetric unilateral MRI breast findings to ensure the correct diagnosis and management is undertaken.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"115 ","pages":"Article 110305"},"PeriodicalIF":1.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-21DOI: 10.1016/j.clinimag.2024.110304
Stephen J. Sozio , Arevik Abramyan , Andrew Soliman , Gaurav Gupta , Hai Sun , Emad Nourollah-Zadeh , Sudipta Roychowdhury , Sri Hari Sundararajan
Carotid blowout syndrome (CBS) is a potentially life-threatening complication in patients suffering head and neck cancer, in which rupture of the carotid artery and/or its branches can rapidly lead to life-threatening hemorrhage, shock, and death. CBS is categorized into three subtypes, which are characterized by extent of disease as evidenced by clinical presentation, physical exam findings, and imaging characteristics. Given the high morbidity and mortality associated with CBS, prompt recognition and treatment remains pivotal, as early intervention is associated with longer survival and lower complication rates. In turn, we present an overview of the hallmark imaging findings of CBS through a retrospective review of our institution's findings of these characteristic imaging findings in all patients who underwent evaluation and management of CBS at our facility across a 10-year period.
颈动脉爆裂综合征（CBS）是头颈部癌症患者的一种可能危及生命的并发症，颈动脉和/或其分支破裂可迅速导致大出血、休克和死亡，危及生命。CBS 可分为三个亚型，其特点是根据临床表现、体格检查结果和影像学特征确定的疾病程度。鉴于 CBS 的高发病率和高死亡率，及时识别和治疗仍然至关重要，因为早期干预可延长患者生存期并降低并发症发生率。接下来，我们将通过回顾性分析本机构在 10 年间对所有接受评估和治疗的 CBS 患者的特征性影像学检查结果，概述 CBS 的标志性影像学检查结果。
{"title":"CTA and DSA findings in carotid blowout syndrome: An overview and approach to imaging diagnosis","authors":"Stephen J. Sozio , Arevik Abramyan , Andrew Soliman , Gaurav Gupta , Hai Sun , Emad Nourollah-Zadeh , Sudipta Roychowdhury , Sri Hari Sundararajan","doi":"10.1016/j.clinimag.2024.110304","DOIUrl":"10.1016/j.clinimag.2024.110304","url":null,"abstract":"<div><div>Carotid blowout syndrome (CBS) is a potentially life-threatening complication in patients suffering head and neck cancer, in which rupture of the carotid artery and/or its branches can rapidly lead to life-threatening hemorrhage, shock, and death. CBS is categorized into three subtypes, which are characterized by extent of disease as evidenced by clinical presentation, physical exam findings, and imaging characteristics. Given the high morbidity and mortality associated with CBS, prompt recognition and treatment remains pivotal, as early intervention is associated with longer survival and lower complication rates. In turn, we present an overview of the hallmark imaging findings of CBS through a retrospective review of our institution's findings of these characteristic imaging findings in all patients who underwent evaluation and management of CBS at our facility across a 10-year period.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"115 ","pages":"Article 110304"},"PeriodicalIF":1.8,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142378518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Insight, words of wisdom and advice to the future generations are shared through storytelling and introspection from women radiologists who have personally impacted my own career and journey as a woman radiologist. Through historical data review and self-reported narratives on an electronically submitted questionnaire, noteworthy accomplishments of female radiologists whom I personally know or know through association over the last hundred and twenty-nine years are described, as well as the obstacles they had faced throughout their academic years of training and practice of radiology.
{"title":"Practicing radiology for 1000 years…by women","authors":"Judith Korek Amorosa , Anupriya Barot , Houda Bouhmam , Rebecca Scalabrino , Deborah Reede","doi":"10.1016/j.clinimag.2024.110300","DOIUrl":"10.1016/j.clinimag.2024.110300","url":null,"abstract":"<div><div>Insight, words of wisdom and advice to the future generations are shared through storytelling and introspection from women radiologists who have personally impacted my own career and journey as a woman radiologist. Through historical data review and self-reported narratives on an electronically submitted questionnaire, noteworthy accomplishments of female radiologists whom I personally know or know through association over the last hundred and twenty-nine years are described, as well as the obstacles they had faced throughout their academic years of training and practice of radiology.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"115 ","pages":"Article 110300"},"PeriodicalIF":1.8,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142394954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alzheimer's disease (AD) is a common neurodegenerative disorder that primarily affects older individuals. Due to its high incidence, an accurate and efficient stratification system could greatly aid in the clinical diagnosis and prognosis of AD patients. Convolutional neural networks (CNN) approaches have demonstrated exceptional performance in the automated stratification of AD, mild cognitive impairment (MCI) and cognitively normal (CN) participants using MRI, owing to their high predictive accuracy and reliability. Therefore, we aimed to develop an algorithm based on CNN and radiomic features derived from ROIs of bilateral hippocampus and amygdala in brain MRI for stratification between AD, MCI and CN.
Methods
In this study, we proposed a CNN and radiomic features-based algorithm using the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. T1-weighted images were used. We utilized three datasets, including AD (199 cases, 602 images), MCI (200 cases, 948 images), and CN (200 cases, 853 images), to perform binary classification (AD vs. CN, AD vs. MCI, and MCI vs. CN). Finally, we obtained the accuracy (ACC) and the area under the curve of the receiver operating characteristic curve (AUC) to evaluate the performance of the algorithm.
Results
Our proposed algorithm achieved acceptable overall discrimination accuracy. In the term of AD vs CN, radiomic-based algorithm alone obtained ACC of 82.6 % and AUC of 88.8, CNN-based algorithm obtained ACC of 80 % and AUC of 87.2 and their fusion showed ACC of 84.4 % and AUC of 90. In the term of MCI vs CN, radiomic-based algorithm alone obtained ACC of 71.6 % and AUC of 77.8, CNN-based algorithm obtained ACC of 69 % and AUC of 75 and their fusion showed ACC of 72.7 % and AUC of 80. In the term of AD vs MCI, radiomic-based algorithm alone obtained ACC of 57 % and AUC of 57.5, CNN-based algorithm obtained ACC of 56.6 % and AUC of 57.7 and their fusion showed ACC of 58 % and AUC of 59.5.
Conclusion
In conclusion, it has been determined that hippocampus and amygdala-based stratification using CNN features and radiomic features-based algorithm is a promising method for the classification of AD, MCI, and CN participants.
Advances in knowledge
This study proposed an automated procedures based on MRI-derived radiomic features and CNN for classification between AD, MCI and CN.
{"title":"Automated classification of Alzheimer's disease, mild cognitive impairment, and cognitively normal patients using 3D convolutional neural network and radiomic features from T1-weighted brain MRI: A comparative study on detection accuracy","authors":"Amin Zarei , Ahmad Keshavarz , Esmail Jafari , Reza Nemati , Akram Farhadi , Ali Gholamrezanezhad , Habib Rostami , Majid Assadi","doi":"10.1016/j.clinimag.2024.110301","DOIUrl":"10.1016/j.clinimag.2024.110301","url":null,"abstract":"<div><h3>Objectives</h3><p>Alzheimer's disease (AD) is a common neurodegenerative disorder that primarily affects older individuals. Due to its high incidence, an accurate and efficient stratification system could greatly aid in the clinical diagnosis and prognosis of AD patients. Convolutional neural networks (CNN) approaches have demonstrated exceptional performance in the automated stratification of AD, mild cognitive impairment (MCI) and cognitively normal (CN) participants using MRI, owing to their high predictive accuracy and reliability. Therefore, we aimed to develop an algorithm based on CNN and radiomic features derived from ROIs of bilateral hippocampus and amygdala in brain MRI for stratification between AD, MCI and CN.</p></div><div><h3>Methods</h3><p>In this study, we proposed a CNN and radiomic features-based algorithm using the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. T1-weighted images were used. We utilized three datasets, including AD (199 cases, 602 images), MCI (200 cases, 948 images), and CN (200 cases, 853 images), to perform binary classification (AD vs. CN, AD vs. MCI, and MCI vs. CN). Finally, we obtained the accuracy (ACC) and the area under the curve of the receiver operating characteristic curve (AUC) to evaluate the performance of the algorithm.</p></div><div><h3>Results</h3><p>Our proposed algorithm achieved acceptable overall discrimination accuracy. In the term of AD vs CN, radiomic-based algorithm alone obtained ACC of 82.6 % and AUC of 88.8, CNN-based algorithm obtained ACC of 80 % and AUC of 87.2 and their fusion showed ACC of 84.4 % and AUC of 90. In the term of MCI vs CN, radiomic-based algorithm alone obtained ACC of 71.6 % and AUC of 77.8, CNN-based algorithm obtained ACC of 69 % and AUC of 75 and their fusion showed ACC of 72.7 % and AUC of 80. In the term of AD vs MCI, radiomic-based algorithm alone obtained ACC of 57 % and AUC of 57.5, CNN-based algorithm obtained ACC of 56.6 % and AUC of 57.7 and their fusion showed ACC of 58 % and AUC of 59.5.</p></div><div><h3>Conclusion</h3><p>In conclusion, it has been determined that hippocampus and amygdala-based stratification using CNN features and radiomic features-based algorithm is a promising method for the classification of AD, MCI, and CN participants.</p></div><div><h3>Advances in knowledge</h3><p>This study proposed an automated procedures based on MRI-derived radiomic features and CNN for classification between AD, MCI and CN.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"115 ","pages":"Article 110301"},"PeriodicalIF":1.8,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142274721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-16DOI: 10.1016/j.clinimag.2024.110302
Yang Xu , Jing Lin , Jin-Mei Gao , Yu Yuan
Objective
To explore the ultrasonographic features and influencing factors of free-floating thrombus (FFT) detachment in the lower extremity deep veins (LEDVs) of patients with fractures.
Methods
Clinical data of patients diagnosed with FFT in the LEDVs and implanted with an inferior vena cava filter (IVCF) in our hospital between July 2021 and August 2023 were retrospectively analysed. The patients were divided into the thrombus detachment group (the experimental group, n = 92) and the non-thrombus detachment group (the control group, n = 103) based on the presence of detached thrombus in the IVCF. The effects of thrombus echogenicity, floating degree, thrombus location, thrombin time, D-dimer and fibrinogen on thrombus shedding were analysed. The nomogram method was used to establish the model and predict the probability of delayed postoperative recovery.
Results
The proportions of patients with extremely hypoechoic thrombus and medium and high floating degrees increased in the experimental group compared with those in the control group, and the differences between the two groups were statistically significant (P < 0.05). Extremely hypoechoic thrombus (P = 0.021, 95 % CI: 1.109–13.748) and high (P = 0.001, 95 % CI: 3.854–28.573) and medium floating degrees (P = 0.004, 95 % CI: 1.792–13.453) were risk factors for deep veins FFT (DV FFT) detachment. The results of receiver operating characteristic curve analysis showed that the area under the curve of the model was 0.893, with a 95 % CI of 0.856–0.937, indicating a high prediction accuracy.
Conclusion
Ultrasonographic parameters, including thrombus echogenicity and floating degree, are valuable in predicting DV FFT detachment in patients with traumatic fractures, providing references for IVCF implantation.
{"title":"Ultrasonographic assessment of the risk of free-floating thrombus detachment in the lower extremity deep veins in patients with fracture","authors":"Yang Xu , Jing Lin , Jin-Mei Gao , Yu Yuan","doi":"10.1016/j.clinimag.2024.110302","DOIUrl":"10.1016/j.clinimag.2024.110302","url":null,"abstract":"<div><h3>Objective</h3><div>To explore the ultrasonographic features and influencing factors of free-floating thrombus (FFT) detachment in the lower extremity deep veins (LEDVs) of patients with fractures.</div></div><div><h3>Methods</h3><div>Clinical data of patients diagnosed with FFT in the LEDVs and implanted with an inferior vena cava filter (IVCF) in our hospital between July 2021 and August 2023 were retrospectively analysed. The patients were divided into the thrombus detachment group (the experimental group, <em>n</em> = 92) and the non-thrombus detachment group (the control group, <em>n</em> = 103) based on the presence of detached thrombus in the IVCF. The effects of thrombus echogenicity, floating degree, thrombus location, thrombin time, D-dimer and fibrinogen on thrombus shedding were analysed. The nomogram method was used to establish the model and predict the probability of delayed postoperative recovery.</div></div><div><h3>Results</h3><div>The proportions of patients with extremely hypoechoic thrombus and medium and high floating degrees increased in the experimental group compared with those in the control group, and the differences between the two groups were statistically significant (<em>P</em> < 0.05). Extremely hypoechoic thrombus (<em>P</em> = 0.021, 95 % <em>CI:</em> 1.109–13.748) and high (<em>P</em> = 0.001, 95 % <em>CI:</em> 3.854–28.573) and medium floating degrees (<em>P</em> = 0.004, 95 % <em>CI:</em> 1.792–13.453) were risk factors for deep veins FFT (DV FFT) detachment. The results of receiver operating characteristic curve analysis showed that the area under the curve of the model was 0.893, with a 95 % CI of 0.856–0.937, indicating a high prediction accuracy.</div></div><div><h3>Conclusion</h3><div>Ultrasonographic parameters, including thrombus echogenicity and floating degree, are valuable in predicting DV FFT detachment in patients with traumatic fractures, providing references for IVCF implantation.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"115 ","pages":"Article 110302"},"PeriodicalIF":1.8,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0899707124002328/pdfft?md5=d4056d1e4a75a361b939a9c840e5d508&pid=1-s2.0-S0899707124002328-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142312609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-11DOI: 10.1016/j.clinimag.2024.110278
Sachin Chitalkar , Dipak Thakor , Ali Sheikhy , Jamie Cole , Sarah Fangmeyer , Fatemeh Nasri , Abdelmonem Ahmed , Ashkan Monfared , Md Reza Taheri
Purpose
The diagnosis of idiopathic intracranial hypertension (IIH) is often challenging in patients who do not present with classic symptoms. Brain MRI can play a pivotal role, as several imaging findings, such as an empty sella appearance (ESA), have been shown to be associated with IIH. Yet, none of the MRI signs have been shown to have a high sensitivity and specificity. In this study, we tested the hypothesis that presence of a geniculate ganglion diverticulum (GGD) is a potential imaging marker for the detection of IIH.
Materials and methods
This is an IRB-approved, single-institution, retrospective, observational study. Brain MRI examinations of patients referred to Radiology by Otology clinic over a period of 10 years were reviewed. 244 MRI exams fulfilling inclusion and exclusion criteria were independently screened for the presence of GGD and ESA by two Neuroradiology fellows. Electronic medical records (EMR) of patients in this study were reviewed for presence of clinical manifestations of IIH. Receiver operator characteristic (ROC) curves were generated to estimate the accuracy of each covariate in diagnosing IIH. The area under each ROC curve (AUC) was calculated to identify an accurate prognostic covariate. Statistical analysis was done using R programming language V 4.2.2.
Results
GGD was identified in MRI exams of 51 patients. A 2:1 propensity score (PS) matching for age, gender, and Body Mass Index (BMI) was used to select non-GGD control group for comparison with the GGD group. There was strong agreement between the 2 reviewers (kappa = 0.81, agreement = 95 %). Twelve patients in this study were diagnosed with IIH. There was a high incidence of GGD (OR = 12.19, 95 % CI (2.56, 58.10)) and ESA (OR = 4.97, 95 % CI (1.47, 16.74)) in IIH patients. The AUC observed in GGD for predicting IIH was 0.771 (0.655–0.888), specificity = 0.709 (0.638–0.780), and sensitivity = 0.833 (0.583–1). The AUC observed for ESA in predicting IIH was 0.682 (0.532–0.831), specificity = 0.780 (0.709–0.844), and sensitivity = 0.583 (0.333–0.833).
Conclusion
GGD is potentially a novel imaging marker of IIH with sensitivity higher than and specificity comparable to that of ESA.
Clinical relevance statement
Presence of GGD should raise the possibility of IIH.
{"title":"Geniculate ganglion diverticulum: a potential imaging marker in patients with idiopathic intracranial hypertension","authors":"Sachin Chitalkar , Dipak Thakor , Ali Sheikhy , Jamie Cole , Sarah Fangmeyer , Fatemeh Nasri , Abdelmonem Ahmed , Ashkan Monfared , Md Reza Taheri","doi":"10.1016/j.clinimag.2024.110278","DOIUrl":"10.1016/j.clinimag.2024.110278","url":null,"abstract":"<div><h3>Purpose</h3><p>The diagnosis of idiopathic intracranial hypertension (IIH) is often challenging in patients who do not present with classic symptoms. Brain MRI can play a pivotal role, as several imaging findings, such as an empty sella appearance (ESA), have been shown to be associated with IIH. Yet, none of the MRI signs have been shown to have a high sensitivity and specificity. In this study, we tested the hypothesis that presence of a geniculate ganglion diverticulum (GGD) is a potential imaging marker for the detection of IIH.</p></div><div><h3>Materials and methods</h3><p>This is an IRB-approved, single-institution, retrospective, observational study. Brain MRI examinations of patients referred to Radiology by Otology clinic over a period of 10 years were reviewed. 244 MRI exams fulfilling inclusion and exclusion criteria were independently screened for the presence of GGD and ESA by two Neuroradiology fellows. Electronic medical records (EMR) of patients in this study were reviewed for presence of clinical manifestations of IIH. Receiver operator characteristic (ROC) curves were generated to estimate the accuracy of each covariate in diagnosing IIH. The area under each ROC curve (AUC) was calculated to identify an accurate prognostic covariate. Statistical analysis was done using R programming language V 4.2.2.</p></div><div><h3>Results</h3><p>GGD was identified in MRI exams of 51 patients. A 2:1 propensity score (PS) matching for age, gender, and Body Mass Index (BMI) was used to select non-GGD control group for comparison with the GGD group. There was strong agreement between the 2 reviewers (kappa = 0.81, agreement = 95 %). Twelve patients in this study were diagnosed with IIH. There was a high incidence of GGD (OR = 12.19, 95 % CI (2.56, 58.10)) and ESA (OR = 4.97, 95 % CI (1.47, 16.74)) in IIH patients. The AUC observed in GGD for predicting IIH was 0.771 (0.655–0.888), specificity = 0.709 (0.638–0.780), and sensitivity = 0.833 (0.583–1). The AUC observed for ESA in predicting IIH was 0.682 (0.532–0.831), specificity = 0.780 (0.709–0.844), and sensitivity = 0.583 (0.333–0.833).</p></div><div><h3>Conclusion</h3><p>GGD is potentially a novel imaging marker of IIH with sensitivity higher than and specificity comparable to that of ESA.</p></div><div><h3>Clinical relevance statement</h3><p>Presence of GGD should raise the possibility of IIH.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"115 ","pages":"Article 110278"},"PeriodicalIF":1.8,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142274720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The O-RADS MRI score stratifies adnexal mass risk with characteristics of T1-weighted, T2-weighed and dynamic contrast-enhanced (DCE) images. We explored a modified approach to evaluate the value of incorporation DWI/ADC with non-DCE-MRI in ORADS scoring system, and to assess the diagnostic performance and interreader consistency in differentiating ovarian neoplasm with different types.
Methods
This retrospective study included 218 women who underwent pelvic MRI with 221 ovarian tumors between January 2017 and December 2021. Two radiologists independently assessed each lesion using the original and modified O-RADS approach (incorporating DWI/ADC with non-DCE). Cohen's weighted-kappa and ROC analyses were employed to assess interreader consistency and diagnostic efficiency across all lesions and three ovarian neoplasms categories.
Results
The area under the ROC curve (AUC) of the original protocol was 0.945 for all lesions and 0.947, 0.992, and 0.758 for the epithelial cell, germ cell and sex cord-stromal neoplasms. The modified approach achieved AUCs of 0.959 for all lesions and 0.962, 0.997, and 0.837 for the three categories. The interreader agreement was ‘excellent’ for all lesions and ‘good’ for the subgroups with the original protocol, improving to ‘excellent’ for all categories with the modified approach.
Conclusion
A modified O-RADS incorporating DWI/ADC with non-DCE MRI yields high diagnostic performance in differentiation of different types of ovarian neoplasms. It further improves consistency in subgroup interpretation. The modified approach can serve as an effective diagnostic tool without DCE, further promoting its adoption in primary hospitals.
{"title":"Assessment of the O-RADS scoring system for the differentiation of different types of ovarian neoplasms: A modified approach with non-DCE-MRI","authors":"Tong Chen , Xujun Qian , Zhi Zhu , Yueyue Zhang , Chaogang Wei , Xiaohong Shen , Caiyuan Zhang , Junkang Shen","doi":"10.1016/j.clinimag.2024.110285","DOIUrl":"10.1016/j.clinimag.2024.110285","url":null,"abstract":"<div><h3>Purpose</h3><div>The O-RADS MRI score stratifies adnexal mass risk with characteristics of T1-weighted, T2-weighed and dynamic contrast-enhanced (DCE) images. We explored a modified approach to evaluate the value of incorporation DWI/ADC with non-DCE-MRI in ORADS scoring system, and to assess the diagnostic performance and interreader consistency in differentiating ovarian neoplasm with different types.</div></div><div><h3>Methods</h3><div>This retrospective study included 218 women who underwent pelvic MRI with 221 ovarian tumors between January 2017 and December 2021. Two radiologists independently assessed each lesion using the original and modified O-RADS approach (incorporating DWI/ADC with non-DCE). Cohen's weighted-kappa and ROC analyses were employed to assess interreader consistency and diagnostic efficiency across all lesions and three ovarian neoplasms categories.</div></div><div><h3>Results</h3><div>The area under the ROC curve (AUC) of the original protocol was 0.945 for all lesions and 0.947, 0.992, and 0.758 for the epithelial cell, germ cell and sex cord-stromal neoplasms. The modified approach achieved AUCs of 0.959 for all lesions and 0.962, 0.997, and 0.837 for the three categories. The interreader agreement was ‘excellent’ for all lesions and ‘good’ for the subgroups with the original protocol, improving to ‘excellent’ for all categories with the modified approach.</div></div><div><h3>Conclusion</h3><div>A modified O-RADS incorporating DWI/ADC with non-DCE MRI yields high diagnostic performance in differentiation of different types of ovarian neoplasms. It further improves consistency in subgroup interpretation. The modified approach can serve as an effective diagnostic tool without DCE, further promoting its adoption in primary hospitals.</div></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"116 ","pages":"Article 110285"},"PeriodicalIF":1.8,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142445626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-10DOI: 10.1016/j.clinimag.2024.110283
Martin B.G. Mutonga , Annabella Shewarega , Moritz Gross , Vinzent H. Kahl , David C. Madoff
Purpose
Favorable clinical outcomes have been reported with the adjunct use of beta-blockers in cancer treatment, hypothetically secondary to their anti-angiogenic/anti-proliferative effects. Hereby, we investigate whether there is synergy between beta-blockers and TACE in the treatment of HCC.
Methods
36 HCC patients on beta-blockers (mean dose of 48 mg daily) at the time of first-line treatment with TACE at our institution were retrospectively identified out of a cohort of 221 patients between 2008 and 2019. Using propensity scoring, a matched cohort of 36 patients not exposed to beta-blockers was generated based on age, gender, ethnicity, etiology of liver disease, BCLC, child Pugh score, PS/ECOG, cirrhosis, largest mass treated, type of TACE and treated liver segments. Tumor response was assessed at 1st and 2nd post-TACE imaging timepoints (1.4 and 4.1 months on average respectively). Variables were compared using chi-square test and Student's t-test. Kaplan-Meier transplant-free survival plots were generated using IBM® SPSS® software. Cox regression analysis was used to evaluate survival predictors. A p values < 0.05 was considered significant.
Results
Comparing the control and beta-blocker cohorts, there were no differences in baseline characteristics, post-TACE imaging timepoints, tumor response or transplant free survival (p > 0.05). Tumor size was found to be a predictor of survival when the two cohorts were combined (p = 0.03).
Conclusion
Transplant-free survival and HCC response to first-line TACE treatment were similar in the control and beta-blocker groups. Large tumor sizes were associated with higher mortality in combined analysis of the cohorts.
{"title":"Investigating synergy between beta-blockers and transarterial chemoembolization in the treatment of hepatocellular carcinoma: preliminary data from a propensity matched analysis","authors":"Martin B.G. Mutonga , Annabella Shewarega , Moritz Gross , Vinzent H. Kahl , David C. Madoff","doi":"10.1016/j.clinimag.2024.110283","DOIUrl":"10.1016/j.clinimag.2024.110283","url":null,"abstract":"<div><h3>Purpose</h3><p>Favorable clinical outcomes have been reported with the adjunct use of beta-blockers in cancer treatment, hypothetically secondary to their anti-angiogenic/anti-proliferative effects. Hereby, we investigate whether there is synergy between beta-blockers and TACE in the treatment of HCC.</p></div><div><h3>Methods</h3><p>36 HCC patients on beta-blockers (mean dose of 48 mg daily) at the time of first-line treatment with TACE at our institution were retrospectively identified out of a cohort of 221 patients between 2008 and 2019. Using propensity scoring, a matched cohort of 36 patients not exposed to beta-blockers was generated based on age, gender, ethnicity, etiology of liver disease, BCLC, child Pugh score, PS/ECOG, cirrhosis, largest mass treated, type of TACE and treated liver segments. Tumor response was assessed at 1st and 2nd post-TACE imaging timepoints (1.4 and 4.1 months on average respectively). Variables were compared using chi-square test and Student's <em>t</em>-test. Kaplan-Meier transplant-free survival plots were generated using IBM® SPSS® software. Cox regression analysis was used to evaluate survival predictors. A <em>p</em> values < 0.05 was considered significant.</p></div><div><h3>Results</h3><p>Comparing the control and beta-blocker cohorts, there were no differences in baseline characteristics, post-TACE imaging timepoints, tumor response or transplant free survival (<em>p</em> > 0.05). Tumor size was found to be a predictor of survival when the two cohorts were combined (<em>p</em> = 0.03).</p></div><div><h3>Conclusion</h3><p>Transplant-free survival and HCC response to first-line TACE treatment were similar in the control and beta-blocker groups. Large tumor sizes were associated with higher mortality in combined analysis of the cohorts.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"115 ","pages":"Article 110283"},"PeriodicalIF":1.8,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142229986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-10DOI: 10.1016/j.clinimag.2024.110282
Adam E.M. Eltorai , Dominick J. Parris , Mary Jo Tarrant , William W. Mayo-Smith , Katherine P. Andriole
Objective
AI adoption requires perceived value by end-users. AI-enabled opportunistic CT screening (OS) detects incidental clinically meaningful imaging risk markers on CT for potential preventative health benefit. This investigation assesses radiologists' perspectives on AI and OS.
Methods
An online survey was distributed to 7500 practicing radiologists among ACR membership of which 4619 opened the emails. Familiarity with and views of AI applications were queried and tabulated, as well as knowledge of OS and inducements and impediments to use.
Results
Respondent (n = 211) demographics: mean age 55 years, 73 % male, 91 % diagnostic radiologists, 46 % in private practice. 68 % reported using AI in practice, while 52 % were only somewhat familiar with AI. 70 % viewed AI positively though only 46 % reported AI's overall accuracy met expectations. 57 % were unfamiliar with OS, with 52 % of those familiar having a positive opinion. Patient perceptions were the most commonly reported (25 %) inducement for OS use. Provider (44 %) and patient (40 %) costs were the most common impediments. Respondents reported that osteoporosis/osteopenia (81 %), fatty liver (78 %), and atherosclerotic cardiovascular disease risk (76 %) could be well assessed by OS. Most indicated OS output requires radiologist oversight/signoff and should be included in a separate “screening” section in the Radiology report. 28 % indicated willingness to spend 1–3 min reviewing AI-generated output while 18 % would not spend any time. Society guidelines/recommendations were most likely to impact OS implementation.
Discussion
Radiologists' perspectives on AI and OS provide practical insights on AI implementation. Increasing end-user familiarity with AI-enabled applications and development of society guidelines/recommendations are likely essential prerequisites for Radiology AI adoption.
{"title":"AI implementation: Radiologists' perspectives on AI-enabled opportunistic CT screening","authors":"Adam E.M. Eltorai , Dominick J. Parris , Mary Jo Tarrant , William W. Mayo-Smith , Katherine P. Andriole","doi":"10.1016/j.clinimag.2024.110282","DOIUrl":"10.1016/j.clinimag.2024.110282","url":null,"abstract":"<div><h3>Objective</h3><p>AI adoption requires perceived value by end-users. AI-enabled opportunistic CT screening (OS) detects incidental clinically meaningful imaging risk markers on CT for potential preventative health benefit. This investigation assesses radiologists' perspectives on AI and OS.</p></div><div><h3>Methods</h3><p>An online survey was distributed to 7500 practicing radiologists among ACR membership of which 4619 opened the emails. Familiarity with and views of AI applications were queried and tabulated, as well as knowledge of OS and inducements and impediments to use.</p></div><div><h3>Results</h3><p>Respondent (n = 211) demographics: mean age 55 years, 73 % male, 91 % diagnostic radiologists, 46 % in private practice. 68 % reported using AI in practice, while 52 % were only somewhat familiar with AI. 70 % viewed AI positively though only 46 % reported AI's overall accuracy met expectations. 57 % were unfamiliar with OS, with 52 % of those familiar having a positive opinion. Patient perceptions were the most commonly reported (25 %) inducement for OS use. Provider (44 %) and patient (40 %) costs were the most common impediments. Respondents reported that osteoporosis/osteopenia (81 %), fatty liver (78 %), and atherosclerotic cardiovascular disease risk (76 %) could be well assessed by OS. Most indicated OS output requires radiologist oversight/signoff and should be included in a separate “screening” section in the Radiology report. 28 % indicated willingness to spend 1–3 min reviewing AI-generated output while 18 % would not spend any time. Society guidelines/recommendations were most likely to impact OS implementation.</p></div><div><h3>Discussion</h3><p>Radiologists' perspectives on AI and OS provide practical insights on AI implementation. Increasing end-user familiarity with AI-enabled applications and development of society guidelines/recommendations are likely essential prerequisites for Radiology AI adoption.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"115 ","pages":"Article 110282"},"PeriodicalIF":1.8,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142167654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1016/j.clinimag.2024.110276
Daniel Nguyen , Allison MacKenzie , Young H. Kim
Large Language Models (LLM) like ChatGPT-4 hold significant promise in medical application, especially in the field of radiology. While previous studies have shown the promise of ChatGTP-4 in textual-based scenarios, its performance on image-based response remains suboptimal. This study investigates the impact of prompt engineering on ChatGPT-4's accuracy on the 2022 American College of Radiology In Training Test Questions for Diagnostic Radiology Residents that include textual and visual-based questions. Four personas were created, each with unique prompts, and evaluated using ChatGPT-4. Results indicate that encouraging prompts and those disclaiming responsibility led to higher overall accuracy (number of questions answered correctly) compared to other personas. Personas that threaten the LLM with legal action or mounting clinical responsibility were not only found to score less, but also refrain of answering questions at a higher rate. These findings highlight the importance of prompt context in optimizing LLM responses and the need for further research to integrate AI responsibly into medical practice.
{"title":"Encouragement vs. liability: How prompt engineering influences ChatGPT-4's radiology exam performance","authors":"Daniel Nguyen , Allison MacKenzie , Young H. Kim","doi":"10.1016/j.clinimag.2024.110276","DOIUrl":"10.1016/j.clinimag.2024.110276","url":null,"abstract":"<div><p>Large Language Models (LLM) like ChatGPT-4 hold significant promise in medical application, especially in the field of radiology. While previous studies have shown the promise of ChatGTP-4 in textual-based scenarios, its performance on image-based response remains suboptimal. This study investigates the impact of prompt engineering on ChatGPT-4's accuracy on the 2022 American College of Radiology In Training Test Questions for Diagnostic Radiology Residents that include textual and visual-based questions. Four personas were created, each with unique prompts, and evaluated using ChatGPT-4. Results indicate that encouraging prompts and those disclaiming responsibility led to higher overall accuracy (number of questions answered correctly) compared to other personas. Personas that threaten the LLM with legal action or mounting clinical responsibility were not only found to score less, but also refrain of answering questions at a higher rate. These findings highlight the importance of prompt context in optimizing LLM responses and the need for further research to integrate AI responsibly into medical practice.</p></div>","PeriodicalId":50680,"journal":{"name":"Clinical Imaging","volume":"115 ","pages":"Article 110276"},"PeriodicalIF":1.8,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142241583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","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