Pub Date : 2025-03-01DOI: 10.1016/j.acra.2024.09.031
Raquelle El Alam , Mark M. Hammer , Rachna Madan
Rationale and Objectives
To evaluate whether parathyroid adenomas can be detected by thoracic radiologists on routine chest CT.
Materials/Methods
This retrospective study included patients with hyperparathyroidism evaluated by parathyroid scans and a control group with normal calcium. All had enhanced chest CT within 36 months prior to parathyroid imaging. Chest CTs were reviewed by 3 blinded thoracic radiologists. We report diagnostic accuracy for all positive findings and findings > 8 mm.
Results
Our sample comprised 126 patients, 63 with confirmed hyperparathyroidism and 63 control patients; 6 parathyroid cases were excluded for being out of the field of view. Readers 1, 2, and 3 had sensitivity of 95%, 60%, and 35%, and specificity of 88%, 89%, and 97%, respectively. Specificity increased to 95%, 97%, and 98% when considering only findings larger than 8 mm. Review of false negative studies for reader 1 revealed 3 parathyroid adenomas visualized in retrospect. Review of the 7 false positive studies for reader 1 revealed candidate lesions in all of them attributed to exophytic thyroid nodules or lymph nodes. 90%, 67%, and 40% of the parathyroid adenoma patients had at least 1, 2, and 3 complications respectively. Most prevalent complications were nephrolithiasis (48%) and osteopenia (46%).
Conclusions
Routine contrast-enhanced chest CT can detect the majority of parathyroid adenomas with high specificity.
Clinical Relevance/Application
Increasing awareness of parathyroid adenomas by chest radiologists allow for detection of enlarged parathyroid glands, diagnosing hyperparathyroidism before clinical presentation.
{"title":"Incidental detection of parathyroid adenomas on chest CT before clinical presentation of hyperparathyroidism","authors":"Raquelle El Alam , Mark M. Hammer , Rachna Madan","doi":"10.1016/j.acra.2024.09.031","DOIUrl":"10.1016/j.acra.2024.09.031","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>To evaluate whether parathyroid adenomas can be detected by thoracic radiologists on routine chest CT.</div></div><div><h3>Materials/Methods</h3><div>This retrospective study included patients with hyperparathyroidism evaluated by parathyroid scans and a control group with normal calcium. All had enhanced chest CT within 36 months prior to parathyroid imaging. Chest CTs were reviewed by 3 blinded thoracic radiologists. We report diagnostic accuracy for all positive findings and findings > 8 mm.</div></div><div><h3>Results</h3><div>Our sample comprised 126 patients, 63 with confirmed hyperparathyroidism and 63 control patients; 6 parathyroid cases were excluded for being out of the field of view. Readers 1, 2, and 3 had sensitivity of 95%, 60%, and 35%, and specificity of 88%, 89%, and 97%, respectively. Specificity increased to 95%, 97%, and 98% when considering only findings larger than 8 mm. Review of false negative studies for reader 1 revealed 3 parathyroid adenomas visualized in retrospect. Review of the 7 false positive studies for reader 1 revealed candidate lesions in all of them attributed to exophytic thyroid nodules or lymph nodes. 90%, 67%, and 40% of the parathyroid adenoma patients had at least 1, 2, and 3 complications respectively. Most prevalent complications were nephrolithiasis (48%) and osteopenia (46%).</div></div><div><h3>Conclusions</h3><div>Routine contrast-enhanced chest CT can detect the majority of parathyroid adenomas with high specificity.</div></div><div><h3>Clinical Relevance/Application</h3><div>Increasing awareness of parathyroid adenomas by chest radiologists allow for detection of enlarged parathyroid glands, diagnosing hyperparathyroidism before clinical presentation.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1353-1359"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142331770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1016/j.acra.2024.09.039
Xianhong Wang , Cheng Deng , Ruize Kong , Zhimei Gong , Hongying Dai , Yang Song , Yunzhu Wu , Guoli Bi , Conghui Ai , Qiu Bi
Rationale and Objectives
To evaluate the validity of multiparametric MRI-based intratumoral and peritumoral habitat imaging for predicting cervical stromal invasion (CSI) in patients with early-stage endometrial carcinoma (EC) and to compare the performance of structural and functional habitats.
Materials and Methods
The preoperative MRI and clinical data of 680 patients with early-stage EC from three centers were retrospectively analyzed. Based on cohort-level, gaussian mixture model (GMM) algorithm was used for habitat clustering of MRI images. Structural habitats were clustered using T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CE-T1WI), and functional habitats were clustered using apparent diffusion coefficient (ADC) mapping and CE-T1WI. Habitat parameters were extracted from four volumes of interest (VOIs): intratumoral regions (ROI), peritumoral loops of 3 mm dilation (L3), intratumoral regions + peritumoral loops of 3 mm dilation (R3), and peritumoral loops of 3 mm dilation + peritumoral loops of 3 mm erosion (DE3). Clinical-habitat models were constructed by combining clinical independent predictors and optimal habitat models. The model performance was evaluated by the area under the curve (AUC).
Results
Deep myometrial invasion (DMI) was an independent predictor. L3 models showed the best performance for both structural and functional habitats, and the L3 functional habitat model had the highest average AUC (0.807) in external test groups, and the average AUC increased to 0.815 when combing with the clinical independent predictor.
Conclusion
Multiparametric MRI-based intratumoral and peritumoral habitat imaging provides a noninvasive approach to predict CSI in EC patients. The combination of the clinical predictor with the L3 functional habitat model improved predictive performance.
{"title":"Intratumoral and peritumoral habitat imaging based on multiparametric MRI to predict cervical stromal invasion in early-stage endometrial carcinoma","authors":"Xianhong Wang , Cheng Deng , Ruize Kong , Zhimei Gong , Hongying Dai , Yang Song , Yunzhu Wu , Guoli Bi , Conghui Ai , Qiu Bi","doi":"10.1016/j.acra.2024.09.039","DOIUrl":"10.1016/j.acra.2024.09.039","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>To evaluate the validity of multiparametric MRI-based intratumoral and peritumoral habitat imaging for predicting cervical stromal invasion (CSI) in patients with early-stage endometrial carcinoma (EC) and to compare the performance of structural and functional habitats.</div></div><div><h3>Materials and Methods</h3><div>The preoperative MRI and clinical data of 680 patients with early-stage EC from three centers were retrospectively analyzed. Based on cohort-level, gaussian mixture model (GMM) algorithm was used for habitat clustering of MRI images. Structural habitats were clustered using T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CE-T1WI), and functional habitats were clustered using apparent diffusion coefficient (ADC) mapping and CE-T1WI. Habitat parameters were extracted from four volumes of interest (VOIs): intratumoral regions (ROI), peritumoral loops of 3 mm dilation (L3), intratumoral regions + peritumoral loops of 3 mm dilation (R3), and peritumoral loops of 3 mm dilation + peritumoral loops of 3 mm erosion (DE3). Clinical-habitat models were constructed by combining clinical independent predictors and optimal habitat models. The model performance was evaluated by the area under the curve (AUC).</div></div><div><h3>Results</h3><div>Deep myometrial invasion (DMI) was an independent predictor. L3 models showed the best performance for both structural and functional habitats, and the L3 functional habitat model had the highest average AUC (0.807) in external test groups, and the average AUC increased to 0.815 when combing with the clinical independent predictor.</div></div><div><h3>Conclusion</h3><div>Multiparametric MRI-based intratumoral and peritumoral habitat imaging provides a noninvasive approach to predict CSI in EC patients. The combination of the clinical predictor with the L3 functional habitat model improved predictive performance.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1476-1487"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142378552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1016/j.acra.2024.09.003
Jiacheng Liu , Wei Yao , Yaowei Bai , Pengfei Chen , Jiankang Qin , Songlin Song , Xiaoming Liu , Yanqiao Ren , Feng Yuan , Chuansheng Zheng , Bin Liang
Rationale and Objectives
A consensus has not yet been reached regarding the optimal timing for the combination of transjugular intrahepatic portosystemic shunt (TIPS) and partial splenic embolization (PSE) in patients with cirrhosis-related variceal bleeding and hypersplenism. This study aimed to compare the clinical outcomes of patients who underwent either an early or late combination of TIPS and PSE.
Methods
A total of 84 consecutive patients with cirrhosis-related variceal bleeding and hypersplenism who underwent TIPS and PSE between September 2016 and April 2023 were included in this retrospective multicenter study. These patients were subsequently divided into early combination (n = 36) and late combination (n = 48) groups based on the timing of the combination therapy.
Results
Kaplan-Meier curves revealed a significant increase in cumulative survival in the late combination group, compared with that in the early combination group (log-rank P = 0.018). Additionally, the late combination group exhibited a lower cumulative incidence of overt hepatic encephalopathy (OHE), compared with the early combination group (log-rank P = 0.002). In Cox regression models, noninfarcted splenic volume (hazard ratio [HR] = 0.995, 95% confidence interval [CI] = 0.991–0.999, P = 0.044) and grouping (HR = 0.101, 95% CI = 0.011–0.921, P = 0.034) were identified as independent risk factors for mortality. Furthermore, the independent risk factors for OHE were serum albumin (ALB) level (P = 0.032) and grouping (P = 0.028).
Conclusion
The early combination of TIPS and PSE was associated with higher risks of death and OHE than the late combination.
理由和目标：关于肝硬化相关静脉曲张出血和脾功能亢进患者联合使用经颈静脉肝内门体分流术（TIPS）和部分脾栓塞术（PSE）的最佳时机，目前尚未达成共识。本研究旨在比较早期或晚期接受 TIPS 和 PSE 联合治疗的患者的临床疗效：这项回顾性多中心研究共纳入了2016年9月至2023年4月期间接受TIPS和PSE治疗的84例连续性肝硬化相关静脉曲张出血和脾功能亢进患者。随后，根据联合治疗的时间将这些患者分为早期联合组（36 人）和晚期联合组（48 人）：Kaplan-Meier曲线显示，与早期联合治疗组相比，晚期联合治疗组的累积生存期显著延长（log-rank P = 0.018）。此外，与早期联合治疗组相比，晚期联合治疗组的显性肝性脑病（OHE）累积发生率较低（log-rank P = 0.002）。在 Cox 回归模型中，非梗死脾脏体积（危险比 [HR] = 0.995，95% 置信区间 [CI] = 0.991-0.999，P = 0.044）和分组（HR = 0.101，95% CI = 0.011-0.921，P = 0.034）被确定为死亡率的独立危险因素。此外，血清白蛋白（ALB）水平（P = 0.032）和分组（P = 0.028）也是OHE的独立危险因素：结论：TIPS和PSE的早期组合比晚期组合具有更高的死亡和OHE风险。
{"title":"Optimal timing for TIPS and PSE combination treatment in patients with cirrhosis-related variceal bleeding and hypersplenism","authors":"Jiacheng Liu , Wei Yao , Yaowei Bai , Pengfei Chen , Jiankang Qin , Songlin Song , Xiaoming Liu , Yanqiao Ren , Feng Yuan , Chuansheng Zheng , Bin Liang","doi":"10.1016/j.acra.2024.09.003","DOIUrl":"10.1016/j.acra.2024.09.003","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>A consensus has not yet been reached regarding the optimal timing for the combination of transjugular intrahepatic portosystemic shunt (TIPS) and partial splenic embolization (PSE) in patients with cirrhosis-related variceal bleeding and hypersplenism. This study aimed to compare the clinical outcomes of patients who underwent either an early or late combination of TIPS and PSE.</div></div><div><h3>Methods</h3><div>A total of 84 consecutive patients with cirrhosis-related variceal bleeding and hypersplenism who underwent TIPS and PSE between September 2016 and April 2023 were included in this retrospective multicenter study. These patients were subsequently divided into early combination (n = 36) and late combination (n = 48) groups based on the timing of the combination therapy.</div></div><div><h3>Results</h3><div>Kaplan-Meier curves revealed a significant increase in cumulative survival in the late combination group, compared with that in the early combination group (log-rank <em>P</em> = 0.018). Additionally, the late combination group exhibited a lower cumulative incidence of overt hepatic encephalopathy (OHE), compared with the early combination group (log-rank <em>P</em> = 0.002). In Cox regression models, noninfarcted splenic volume (hazard ratio [HR] = 0.995, 95% confidence interval [CI] = 0.991–0.999, <em>P</em> = 0.044) and grouping (HR = 0.101, 95% CI = 0.011–0.921, <em>P</em> = 0.034) were identified as independent risk factors for mortality. Furthermore, the independent risk factors for OHE were serum albumin (ALB) level (<em>P</em> = 0.032) and grouping (<em>P</em> = 0.028).</div></div><div><h3>Conclusion</h3><div>The early combination of TIPS and PSE was associated with higher risks of death and OHE than the late combination.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1534-1546"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142395011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To investigate factors influencing the success and complication rate of percutaneous transhepatic biliary drainage (PTBD).
Materials and Methods
PTBD procedures between 2017 and 2022 were enrolled retrospectively. Success rate, complications, and technical considerations were compared using Mann–Whitney U-, X2-, and Fishers exact tests. The influence of the study center's experience (training-effect) on success and complication rates was assessed by linear regression categorized by year.
Results
In 398 patients, 499 PTBD procedures (337 men; mean age 66.2 +/- 12.5 years) were carried out, with a success rate of 83.2% (415/499). PTBD in dilated bile ducts was more successful than in non-dilated bile ducts (90.0%; 316/340 vs. 68.6%; 109/159; p < 0.001), with e.g. lower radiation doses (2787.52 +/- 4012.72 cGy*cm2 vs. 4679.25 +/- 4663.55 cGy*cm2; p < 0.001), and shorter total procedure time (33.42 +/- 24.03 min vs. 41.09 +/- 27.21 min; p < 0.001). Complications occurred in 34/499 (6.8%) procedures (major complications n = 25/34) with no significant difference in bile duct width. Right-sided PTBD revealed more complications (9.0%; 30/332 vs. 2.4%; 4/166; p = 0.006) and higher radiation doses (3679.47 +/- 4571.71 cGy*cm2 vs. 2819.01 +/- 3724.92 cGy*cm2; p = 0.001) than left-sided approaches. Linear regression showed a significant continuous increase in the technical success rate of 3.0% per year (2017–2022; 72.5%; 78.5%; 82.2%; 85.0%; 89.0%; 87.5%; p = 0.005), while the overall complication rate remained unaffected (p = 0.364).
Conclusion
Medical centers adopting PTBD procedures can potentially increase their success rate significantly within a short period of time. PTBD is a safe procedure, with left-sided approaches showing lower complication rates and radiation exposure, underscoring their often-underestimated advantages in clinical practice.
{"title":"Experience Matters: Impact on Technical Success and Complication Rate in Percutaneous Transhepatic Biliary Drainage","authors":"Felix Schön , Bennet Seidel , Sophia Freya Ulrike Blum , Kristina Fischer , Marie-Luise Kromrey , Carina Riediger , Steffen Löck , Ralf-Thorsten Hoffmann , Jens-Peter Kühn","doi":"10.1016/j.acra.2024.09.029","DOIUrl":"10.1016/j.acra.2024.09.029","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>To investigate factors influencing the success and complication rate of percutaneous transhepatic biliary drainage (PTBD).</div></div><div><h3>Materials and Methods</h3><div>PTBD procedures between 2017 and 2022 were enrolled retrospectively. Success rate, complications, and technical considerations were compared using Mann–Whitney U-, X<sup>2</sup>-, and Fishers exact tests. The influence of the study center's experience (training-effect) on success and complication rates was assessed by linear regression categorized by year.</div></div><div><h3>Results</h3><div>In 398 patients, 499 PTBD procedures (337 men; mean age 66.2 +/- 12.5 years) were carried out, with a success rate of 83.2% (415/499). PTBD in dilated bile ducts was more successful than in non-dilated bile ducts (90.0%; 316/340 vs. 68.6%; 109/159; p < 0.001), with e.g. lower radiation doses (2787.52 +/- 4012.72 cGy*cm<sup>2</sup> vs. 4679.25 +/- 4663.55 cGy*cm<sup>2</sup>; p < 0.001), and shorter total procedure time (33.42 +/- 24.03 min vs. 41.09 +/- 27.21 min; p < 0.001). Complications occurred in 34/499 (6.8%) procedures (major complications n = 25/34) with no significant difference in bile duct width. Right-sided PTBD revealed more complications (9.0%; 30/332 vs. 2.4%; 4/166; p = 0.006) and higher radiation doses (3679.47 +/- 4571.71 cGy*cm2 vs. 2819.01 +/- 3724.92 cGy*cm2; p = 0.001) than left-sided approaches. Linear regression showed a significant continuous increase in the technical success rate of 3.0% per year (2017–2022; 72.5%; 78.5%; 82.2%; 85.0%; 89.0%; 87.5%; p = 0.005), while the overall complication rate remained unaffected (p = 0.364).</div></div><div><h3>Conclusion</h3><div>Medical centers adopting PTBD procedures can potentially increase their success rate significantly within a short period of time. PTBD is a safe procedure, with left-sided approaches showing lower complication rates and radiation exposure, underscoring their often-underestimated advantages in clinical practice.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1525-1533"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142480004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1016/j.acra.2024.11.003
Dennis Robert , Saigopal Sathyamurthy , Anshul Kumar Singh , Sri Anusha Matta , Manoj Tadepalli , Swetha Tanamala , Vijay Bosemani , Joseph Mammarappallil , Bunty Kundnani
Rationale and Objectives
Missed nodules in chest radiographs (CXRs) are common occurrences. We assessed the effect of artificial intelligence (AI) as a second reader on the accuracy of radiologists and non-radiology physicians in lung nodule detection and localization in CXRs.
Materials and Methods
This retrospective study using the multi-reader multi-case design included 300 CXRs acquired from 40 hospitals across the US. All CXRs had a paired follow-up image (chest CT or CXR) to augment the ground truth establishment for the presence and location of nodules on CXRs by five independent thoracic radiologists. 15 readers (nine radiologists and six non-radiology physicians) read each CXR twice in a second-reader paradigm, once without AI and then immediately with AI assistance. The primary analysis assessed the difference in area-under-the-alternative-free-response-receiver-operating-characteristic-curve (AFROC) of readers with and without AI. Case-level area-under-the-receiver-operating-characteristic-curve (AUROC), sensitivity, and specificity were assessed in secondary analyses.
Results
A total of 300 CXRs (147 with nodules, 153 without nodules) from 300 patients (mean age, 64 years ± 15 [standard deviation]; 174 women) were included. The mean AFROC of readers was 0.73 without AI and 0.81 with AI (95% CI of difference, 0.05–0.10). Case-level AUROC was 0.77 without AI and 0.84 with AI (95% CI of difference, 0.04–0.09). Case-level sensitivity was 72.8% and 83.5% (95% CI of difference, 6.8–14.6) and specificity was 71.1% and 72.0% (95% CI of difference, −0.8–2.6) without and with AI, respectively.
Conclusion
Using AI, readers detected and localized more nodules without any significant difference in false positive interpretations.
{"title":"Effect of Artificial Intelligence as a Second Reader on the Lung Nodule Detection and Localization Accuracy of Radiologists and Non-radiology Physicians in Chest Radiographs: A Multicenter Reader Study","authors":"Dennis Robert , Saigopal Sathyamurthy , Anshul Kumar Singh , Sri Anusha Matta , Manoj Tadepalli , Swetha Tanamala , Vijay Bosemani , Joseph Mammarappallil , Bunty Kundnani","doi":"10.1016/j.acra.2024.11.003","DOIUrl":"10.1016/j.acra.2024.11.003","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>Missed nodules in chest radiographs (CXRs) are common occurrences. We assessed the effect of artificial intelligence (AI) as a second reader on the accuracy of radiologists and non-radiology physicians in lung nodule detection and localization in CXRs.</div></div><div><h3>Materials and Methods</h3><div>This retrospective study using the multi-reader multi-case design included 300 CXRs acquired from 40 hospitals across the US. All CXRs had a paired follow-up image (chest CT or CXR) to augment the ground truth establishment for the presence and location of nodules on CXRs by five independent thoracic radiologists. 15 readers (nine radiologists and six non-radiology physicians) read each CXR twice in a second-reader paradigm, once without AI and then immediately with AI assistance. The primary analysis assessed the difference in area-under-the-alternative-free-response-receiver-operating-characteristic-curve (AFROC) of readers with and without AI. Case-level area-under-the-receiver-operating-characteristic-curve (AUROC), sensitivity, and specificity were assessed in secondary analyses.</div></div><div><h3>Results</h3><div>A total of 300 CXRs (147 with nodules, 153 without nodules) from 300 patients (mean age, 64 years ± 15 [standard deviation]; 174 women) were included. The mean AFROC of readers was 0.73 without AI and 0.81 with AI (95% CI of difference, 0.05–0.10). Case-level AUROC was 0.77 without AI and 0.84 with AI (95% CI of difference, 0.04–0.09). Case-level sensitivity was 72.8% and 83.5% (95% CI of difference, 6.8–14.6) and specificity was 71.1% and 72.0% (95% CI of difference, −0.8–2.6) without and with AI, respectively.</div></div><div><h3>Conclusion</h3><div>Using AI, readers detected and localized more nodules without any significant difference in false positive interpretations.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1706-1717"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142734343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1016/j.acra.2024.11.046
Boah Kim PhD, Tejas Sudharshan Mathai PhD, Kimberly Helm, Pritam Mukherjee PhD, Jianfei Liu PhD, Ronald M. Summers MD, PhD
Rationale and Objectives
Multi-parametric MRI (mpMRI) studies of the body are routinely acquired in clinical practice. However, a standardized naming convention for MRI protocols and series does not exist currently. Conflicts in the series descriptions present in the DICOM headers arise due to myriad MRI scanners from various manufacturers used for imaging, wide variations in imaging practices across institutions, and technologist preferences. These conflicts affect the hanging protocol, which dictates the arrangement of sequences for the reading radiologist. At present, clinician supervision is necessary to ensure that the correct sequence is being read and used for diagnosis. This pilot work seeks to classify five different series in mpMRI studies acquired at the levels of the chest, abdomen, and pelvis.
Materials and Methods
First, 2D and 3D classification networks were compared using data acquired by Siemens scanners and the optimal network was identified. Then, its performance was analyzed when trained with different training data quantities. The out-of-distribution (OOD) robustness on data acquired by a Philips scanner was also measured. In addition, the effect of data augmentation on model training was studied. The model was also tested with smaller input volumes through downsampling or cropping. Finally, the model was trained on combined data from both Siemens and Philips scanners to bridge the performance gap between different scanners.
Results
Among 2D and 3D networks of ResNet-50, ResNet-101, DenseNet- 121, and EfficientNet-BN0, the 3D DenseNet-121 ensemble achieved an F1 score of 99.5% when tested on data from the Siemens scanners. The model performed well on OOD data from the Philips scanner and achieved an F1 score of 86.5%. There was no statistically significant difference between the models trained with and without data augmentation, and between the models trained with original-sized input and with smaller-sized input. When training the model with combined data, the F1 score improved to 98.8% for the Philips test set and 99.3% for the Siemens test set respectively.
Conclusion
Our pilot work is useful for the classification of MRI sequences in studies acquired at the level of the chest, abdomen, and pelvis. It has the potential for robust automation of hanging protocols and the creation of large-scale data cohorts for pre-clinical research.
{"title":"Automated Classification of Body MRI Sequences Using Convolutional Neural Networks","authors":"Boah Kim PhD, Tejas Sudharshan Mathai PhD, Kimberly Helm, Pritam Mukherjee PhD, Jianfei Liu PhD, Ronald M. Summers MD, PhD","doi":"10.1016/j.acra.2024.11.046","DOIUrl":"10.1016/j.acra.2024.11.046","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>Multi-parametric MRI (mpMRI) studies of the body are routinely acquired in clinical practice. However, a standardized naming convention for MRI protocols and series does not exist currently. Conflicts in the series descriptions present in the DICOM headers arise due to myriad MRI scanners from various manufacturers used for imaging, wide variations in imaging practices across institutions, and technologist preferences. These conflicts affect the hanging protocol, which dictates the arrangement of sequences for the reading radiologist. At present, clinician supervision is necessary to ensure that the correct sequence is being read and used for diagnosis. This pilot work seeks to classify five different series in mpMRI studies acquired at the levels of the chest, abdomen, and pelvis.</div></div><div><h3>Materials and Methods</h3><div>First, 2D and 3D classification networks were compared using data acquired by Siemens scanners and the optimal network was identified. Then, its performance was analyzed when trained with different training data quantities. The out-of-distribution (OOD) robustness on data acquired by a Philips scanner was also measured. In addition, the effect of data augmentation on model training was studied. The model was also tested with smaller input volumes through downsampling or cropping. Finally, the model was trained on combined data from both Siemens and Philips scanners to bridge the performance gap between different scanners.</div></div><div><h3>Results</h3><div>Among 2D and 3D networks of ResNet-50, ResNet-101, DenseNet- 121, and EfficientNet-BN0, the 3D DenseNet-121 ensemble achieved an <em>F</em><sub>1</sub> score of 99.5% when tested on data from the Siemens scanners. The model performed well on OOD data from the Philips scanner and achieved an <em>F</em><sub>1</sub> score of 86.5%. There was no statistically significant difference between the models trained with and without data augmentation, and between the models trained with original-sized input and with smaller-sized input. When training the model with combined data, the <em>F</em><sub>1</sub> score improved to 98.8% for the Philips test set and 99.3% for the Siemens test set respectively.</div></div><div><h3>Conclusion</h3><div>Our pilot work is useful for the classification of MRI sequences in studies acquired at the level of the chest, abdomen, and pelvis. It has the potential for robust automation of hanging protocols and the creation of large-scale data cohorts for pre-clinical research.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1192-1203"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142792758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1016/j.acra.2024.11.036
M. Elizabeth Oates MD, FAAWR, FACR , Michelle Brugger , David Laszakovits MBA
Launched on July 1, 2017, the redesigned American Board of Radiology 16-month Pathway in Nuclear Radiology is flourishing. The original goal of this accelerated training pathway was to help meet the ever-growing demand for nuclear radiology subspecialists in academic and community practices. As of March 1, 2024, 125 graduates of the 16-month pathway had achieved specialty certification in either diagnostic radiology or interventional radiology/diagnostic radiology; nearly 60% had also attained advanced certification in nuclear radiology and/or nuclear medicine. Between March and May 2024, we surveyed this group of 125 specialty board-certified pathway graduates to evaluate the impact of the pathway on their individual careers and on the overall workforce; 69/125 (55%) respondents completed the survey. The vast majority (86%) pursued at least one traditional fellowship after residency, thus becoming multi-subspecialized. The majority (62%) currently work in an academic setting. The vast majority (80%) currently practice nuclear radiology; 40% of those reported that nuclear radiology comprises at least 50% of their time or typical workload. PET/CT represents the predominant modality/service (59%) and a significant minority (11%) perform radiotheranostics/radiopharmaceutical therapies; the vast majority (80%) practice nuclear cardiology. We anticipate that the ABR 16-month pathway will continue to thrive and that its graduates will continue to bring their expertise in this rapidly expanding domain to their clinical practices and research pursuits to the benefit of radiology, medicine, patients, and society.
{"title":"The Redesigned American Board of Radiology 16-month Pathway in Nuclear Radiology: Initial Outcomes (2017–2022)","authors":"M. Elizabeth Oates MD, FAAWR, FACR , Michelle Brugger , David Laszakovits MBA","doi":"10.1016/j.acra.2024.11.036","DOIUrl":"10.1016/j.acra.2024.11.036","url":null,"abstract":"<div><div>Launched on July 1, 2017, the redesigned American Board of Radiology 16-month Pathway in Nuclear Radiology is flourishing. The original goal of this accelerated training pathway was to help meet the ever-growing demand for nuclear radiology subspecialists in academic and community practices. As of March 1, 2024, 125 graduates of the 16-month pathway had achieved specialty certification in either diagnostic radiology or interventional radiology/diagnostic radiology; nearly 60% had also attained advanced certification in nuclear radiology and/or nuclear medicine. Between March and May 2024, we surveyed this group of 125 specialty board-certified pathway graduates to evaluate the impact of the pathway on their individual careers and on the overall workforce; 69/125 (55%) respondents completed the survey. The vast majority (86%) pursued at least one traditional fellowship after residency, thus becoming multi-subspecialized. The majority (62%) currently work in an academic setting. The vast majority (80%) currently practice nuclear radiology; 40% of those reported that nuclear radiology comprises at least 50% of their time or typical workload. PET/CT represents the predominant modality/service (59%) and a significant minority (11%) perform radiotheranostics/radiopharmaceutical therapies; the vast majority (80%) practice nuclear cardiology. We anticipate that the ABR 16-month pathway will continue to thrive and that its graduates will continue to bring their expertise in this rapidly expanding domain to their clinical practices and research pursuits to the benefit of radiology, medicine, patients, and society.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1757-1764"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142792769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1016/j.acra.2024.11.061
Rebecca H. Chun MD , Akriti Khanna MD , Katrina N. Glazebrook MBChB , Judith Jebastin Thangaiah MBBS, MD , Christin A. Tiegs-Heiden MD
Rationale and Objectives
Angioleiomyomas are benign perivascular tumors that originate from the tunica media of blood vessels. While frequently described in the head, neck, and uterus, angioleiomyomas can manifest in various regions throughout the body. The purpose of this study was to review the history and imaging features of angioleiomyomas of the trunk and extremities.
Materials and Methods
Patients with pathologically proven angioleiomyomas at our institution were retrospectively identified. Clinical information was obtained by chart review. Any available imaging of the tumor was reviewed.
Results
This study includes 191 patients with angioleiomyoma of the trunk or extremities, 87 with imaging of the tumor. Mean age at presentation was 55.5 years and 59.7% of patients were female. The tumor was painful in 88.9% of patients. Most lesions were in the lower extremity (79.1%), followed by the upper extremity (17.8%) and trunk (3.1%). A nonspecific soft tissue mass was visible radiographically in 27.4% of cases, with calcifications in 1.8%. On ultrasound, the tumor was always hypoechoic, with internal vascularity in 93.8%. Most tumors were T1 isointense and T2 hyperintense relative to skeletal muscle (92.9%) and enhanced (95.8%). CT showed a soft tissue density mass in all cases. On cross-sectional imaging, the mass was directly adjacent to a blood vessel in 83.1% of cases.
Discussion
Key imaging features of angioleiomyomas include a soft tissue mass with adjacent blood vessel on cross-sectional imaging. Ultrasound shows a hypoechoic mass with internal vascularity. They are typically T1 isointense, T2 hyperintense enhancing masses which may have a dark reticular sign and/or hypointense peripheral rim. Recognizing these features may help include angioleiomyoma in the differential diagnosis.
{"title":"Angioleiomyomas of the Extremities and Trunk: An Observational Study","authors":"Rebecca H. Chun MD , Akriti Khanna MD , Katrina N. Glazebrook MBChB , Judith Jebastin Thangaiah MBBS, MD , Christin A. Tiegs-Heiden MD","doi":"10.1016/j.acra.2024.11.061","DOIUrl":"10.1016/j.acra.2024.11.061","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>Angioleiomyomas are benign perivascular tumors that originate from the tunica media of blood vessels. While frequently described in the head, neck, and uterus, angioleiomyomas can manifest in various regions throughout the body. The purpose of this study was to review the history and imaging features of angioleiomyomas of the trunk and extremities.</div></div><div><h3>Materials and Methods</h3><div>Patients with pathologically proven angioleiomyomas at our institution were retrospectively identified. Clinical information was obtained by chart review. Any available imaging of the tumor was reviewed.</div></div><div><h3>Results</h3><div>This study includes 191 patients with angioleiomyoma of the trunk or extremities, 87 with imaging of the tumor. Mean age at presentation was 55.5 years and 59.7% of patients were female. The tumor was painful in 88.9% of patients. Most lesions were in the lower extremity (79.1%), followed by the upper extremity (17.8%) and trunk (3.1%). A nonspecific soft tissue mass was visible radiographically in 27.4% of cases, with calcifications in 1.8%. On ultrasound, the tumor was always hypoechoic, with internal vascularity in 93.8%. Most tumors were T1 isointense and T2 hyperintense relative to skeletal muscle (92.9%) and enhanced (95.8%). CT showed a soft tissue density mass in all cases. On cross-sectional imaging, the mass was directly adjacent to a blood vessel in 83.1% of cases.</div></div><div><h3>Discussion</h3><div>Key imaging features of angioleiomyomas include a soft tissue mass with adjacent blood vessel on cross-sectional imaging. Ultrasound shows a hypoechoic mass with internal vascularity. They are typically T1 isointense, T2 hyperintense enhancing masses which may have a dark reticular sign and/or hypointense peripheral rim. Recognizing these features may help include angioleiomyoma in the differential diagnosis.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1554-1561"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142824742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1016/j.acra.2024.09.040
Yuan Chen , Mali Liu , Deqing Huang , Ziyi Liu , Aisen Yang , Na Qin , Jian Shu
Rationale and Objectives
This study aimed to address the challenge of predicting treatment outcomes for patients with uterine fibroids undergoing high-intensity focused ultrasound (HIFU) ablation. We developed medical-assisted diagnostic models to accurately predict the ablation rates and volume reduction rates, thus assessing both short-term and long-term treatment effects of fibroids.
Materials and Methods
For the ablation rate prediction, our study included 348 fibroids, categorized into 181 fully ablated and 167 inadequately ablated fibroids. Using multimodal MRI sequences and clinical characteristics, coupled with data preprocessing steps such as feature extraction, testing, and screening, we constructed an ensemble model for predicting preoperative ablation rates. In the volume reduction rate study, we analyzed 253 fibroids, divided into 142 high-volume responders and 111 low-volume responders. Based on clinical characteristics and T2-weighted image (T2WI) sequences, along with lesion delineation, feature normalization, and other preprocessing steps, we developed an inter-slice information fusion model for predicting preoperative volume reduction rates.
Results
The ensemble model demonstrated an accuracy of 0.800 and an area under the curve (AUC) of 0.830 on the test set, while the inter-slice information fusion model achieved an accuracy of 0.808 and an AUC of 0.891. Both models showed superior predictive performance compared to existing models.
Conclusion
The ensemble and inter-slice information fusion models developed in this study exhibit robust predictive capabilities, offering valuable support for clinicians in selecting patients for HIFU treatment. These models hold potential for enhancing patient outcomes through tailored treatment planning.
{"title":"Predicting Short-term and Long-term Efficacy of HIFU Treatment for Uterine Fibroids Based on Clinical Information and MRI: A Retrospective Study","authors":"Yuan Chen , Mali Liu , Deqing Huang , Ziyi Liu , Aisen Yang , Na Qin , Jian Shu","doi":"10.1016/j.acra.2024.09.040","DOIUrl":"10.1016/j.acra.2024.09.040","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>This study aimed to address the challenge of predicting treatment outcomes for patients with uterine fibroids undergoing high-intensity focused ultrasound (HIFU) ablation. We developed medical-assisted diagnostic models to accurately predict the ablation rates and volume reduction rates, thus assessing both short-term and long-term treatment effects of fibroids.</div></div><div><h3>Materials and Methods</h3><div>For the ablation rate prediction, our study included 348 fibroids, categorized into 181 fully ablated and 167 inadequately ablated fibroids. Using multimodal MRI sequences and clinical characteristics, coupled with data preprocessing steps such as feature extraction, testing, and screening, we constructed an ensemble model for predicting preoperative ablation rates. In the volume reduction rate study, we analyzed 253 fibroids, divided into 142 high-volume responders and 111 low-volume responders. Based on clinical characteristics and T2-weighted image (T2WI) sequences, along with lesion delineation, feature normalization, and other preprocessing steps, we developed an inter-slice information fusion model for predicting preoperative volume reduction rates.</div></div><div><h3>Results</h3><div>The ensemble model demonstrated an accuracy of 0.800 and an area under the curve (AUC) of 0.830 on the test set, while the inter-slice information fusion model achieved an accuracy of 0.808 and an AUC of 0.891. Both models showed superior predictive performance compared to existing models.</div></div><div><h3>Conclusion</h3><div>The ensemble and inter-slice information fusion models developed in this study exhibit robust predictive capabilities, offering valuable support for clinicians in selecting patients for HIFU treatment. These models hold potential for enhancing patient outcomes through tailored treatment planning.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1488-1499"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142559321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1016/j.acra.2024.10.018
Zhibin Huang , Mengyun Wang , Hongtian Tian , Guoqiu Li , Huaiyu Wu , Jing Chen , Yao Kong , Sijie Mo , Shuzhen Tang , Yunqing Yin , Jinfeng Xu , Fajin Dong
Rationale and Objectives
This study aims to assess the predictive ability of photoacoustic (PA) imaging-based radiomics combined with clinical characteristics for axillary lymph node (ALN) status in early-stage breast cancer patients and to compare performance in different peritumoral regions.
Methods
This study involved 369 patients from Shenzhen People’s Hospital, divided into a training set of 295 and a testing set of 74. PA imaging data were collected from all participants, and radiomics analysis was performed on intratumoral and various peritumoral regions. Features extracted from the training set were analyzed using LASSO regression to construct a model integrating radiomics features with clinical characteristics. Clinical factors were determined through multivariate logistic regression analysis. A radiomics nomogram was developed using logistic regression classifiers, combining radiomics features and clinical factors. The predictive efficacy of the model was evaluated using the areas under curves (AUC), and its clinical utility and accuracy were assessed through decision curve analysis and calibration curves, respectively.
Results
The developed nomogram combines 5 mm peritumoral data with intratumoral and clinical features and shows excellent diagnostic performance, achieving an AUC of 0.972 in the training set and in the testing achieved 0.905. They both showed good calibrations. The model outperformed models based solely on clinical features or other radiomics methods, with the 5 mm surrounding tumor area proving most effective in identifying positive versus negative ALN in breast cancer patients.
Conclusion
The established nomogram is a prospective clinical prediction tool for non-invasive assessment of ALN status. It has the ability to enhance the accuracy of early-stage breast cancer treatment.
Summary
This study highlights the effectiveness of combining photoacoustic radiomics with clinical parameters to predict axillary lymph node status in breast cancer, identifying a 5 mm peritumoral model as particularly potent. Future research should aim to enhance this model's robustness by expanding the sample size and advancing imaging technologies for broader clinical application.
{"title":"Enhancing Axillary Lymph Node Diagnosis in Breast Cancer with a Novel Photoacoustic Imaging-Based Radiomics Nomogram: A Comparative Study of Peritumoral Regions","authors":"Zhibin Huang , Mengyun Wang , Hongtian Tian , Guoqiu Li , Huaiyu Wu , Jing Chen , Yao Kong , Sijie Mo , Shuzhen Tang , Yunqing Yin , Jinfeng Xu , Fajin Dong","doi":"10.1016/j.acra.2024.10.018","DOIUrl":"10.1016/j.acra.2024.10.018","url":null,"abstract":"<div><h3>Rationale and Objectives</h3><div>This study aims to assess the predictive ability of photoacoustic (PA) imaging-based radiomics combined with clinical characteristics for axillary lymph node (ALN) status in early-stage breast cancer patients and to compare performance in different peritumoral regions.</div></div><div><h3>Methods</h3><div>This study involved 369 patients from Shenzhen People’s Hospital, divided into a training set of 295 and a testing set of 74. PA imaging data were collected from all participants, and radiomics analysis was performed on intratumoral and various peritumoral regions. Features extracted from the training set were analyzed using LASSO regression to construct a model integrating radiomics features with clinical characteristics. Clinical factors were determined through multivariate logistic regression analysis. A radiomics nomogram was developed using logistic regression classifiers, combining radiomics features and clinical factors. The predictive efficacy of the model was evaluated using the areas under curves (AUC), and its clinical utility and accuracy were assessed through decision curve analysis and calibration curves, respectively.</div></div><div><h3>Results</h3><div>The developed nomogram combines 5 mm peritumoral data with intratumoral and clinical features and shows excellent diagnostic performance, achieving an AUC of 0.972 in the training set and in the testing achieved 0.905. They both showed good calibrations. The model outperformed models based solely on clinical features or other radiomics methods, with the 5 mm surrounding tumor area proving most effective in identifying positive versus negative ALN in breast cancer patients.</div></div><div><h3>Conclusion</h3><div>The established nomogram is a prospective clinical prediction tool for non-invasive assessment of ALN status. It has the ability to enhance the accuracy of early-stage breast cancer treatment.</div></div><div><h3>Summary</h3><div>This study highlights the effectiveness of combining photoacoustic radiomics with clinical parameters to predict axillary lymph node status in breast cancer, identifying a 5 mm peritumoral model as particularly potent. Future research should aim to enhance this model's robustness by expanding the sample size and advancing imaging technologies for broader clinical application.</div></div>","PeriodicalId":50928,"journal":{"name":"Academic Radiology","volume":"32 3","pages":"Pages 1274-1286"},"PeriodicalIF":3.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142631707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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