{"title":"Editorial Comment: Large Language Models Have Potential to Improve Follow-Up But May Have Unforeseen Impact on Radiology Reporting.","authors":"Jonathan L Mezrich","doi":"10.2214/AJR.25.32734","DOIUrl":"https://doi.org/10.2214/AJR.25.32734","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143400848","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}
{"title":"Editorial Comment: Large Language Models Impacting the Radiology Workflow-We Are Itching to Have a Go.","authors":"Huan Zhang","doi":"10.2214/AJR.25.32748","DOIUrl":"https://doi.org/10.2214/AJR.25.32748","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143400849","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}
Yura Ahn, Sang Min Lee, Jooae Choe, Sehoon Choi, Kyung-Hyun Do, Joon Beom Seo
{"title":"Prognostic Implications of the Volume Doubling Time of the Solid Component in Lung Adenocarcinomas Manifesting as Part-Solid Lesions on Chest CT.","authors":"Yura Ahn, Sang Min Lee, Jooae Choe, Sehoon Choi, Kyung-Hyun Do, Joon Beom Seo","doi":"10.2214/AJR.24.32470","DOIUrl":"10.2214/AJR.24.32470","url":null,"abstract":"<p><p><b>Background:</b> In lung adenocarcinomas manifesting as part-solid lesions, evidence supports greater prognostic importance for the volume of the solid component than of the whole nodule. However, assessments of lesion growth rates have historically focused on the volume doubling time (VDT) of the whole lesion. <b>Objective:</b> To compare the prognostic utility of the VDT of the solid component versus of the whole lesion for resected lung adenocarcinomas manifesting as part-solid lesions on chest CT. <b>Methods:</b> This retrospective study included 122 patients (mean age, 64.0 ± 8.2years; 53 men, 69 women) with resected lung adenocarcinoma manifesting as a part-solid lesion who underwent at least two preoperative chest CT examinations showing either solid-component growth or at least 2 years of stability. Semiautomated software was used to perform 3D segmentations of whole lesions and their solid components, to derive corresponding whole-lesion and solid-component volumes. These volumes were used to compute for each patient VDT for the whole lesion (VDTw) and the lesion's solid component (VDTs). In 81 patients in whom the lesion's ground-glass component increased, VDT of the ground-glass component (VDTgg) was calculated, subtracting the solid-component volume from whole-lesion volume to derive the ground-glass component volume. The prognostic utility of VDTw, VDTs, and VDTgg (each as continuous variables and as binary variables at 200-day and 400-day cutoffs) for recurrence-free survival (RFS) and overall survival (OS) were evaluated using Cox proportional hazard models, adjusting for age, sex, and clinical variables associated with lung cancer survival. <b>Results:</b> Median VDTw, VDTs, and VDTgg, were 921, 455, and 1000 days, respectively. The only VDT metrics showing significant independent associations with RFS were VDTs as a continuous variable (HR=0.999; p=.02), VDTs <400 days (HR=2.68; p=.03), and VDTs <200 days (HR=3.68; p=.003). The only VDT metrics showing significant independent associations with OS were VDTs <200 days (HR=3.27; p=.047) and VDTw <200 days (HR=4.86; p=.03). <b>Conclusion:</b> In lung adenocarcinomas manifesting as part-solid lesions, VDTs less than 200 days was the only evaluated VDT metric showing significant independent associations with both RFS and OS. <b>Clinical Impact:</b> The findings support a focus on lesions' solid components when assessing growth rates of part-solid lesions.</p>","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143400852","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}
Seung-Seob Kim, Hyunseok Seo, Kihwan Choi, Sungwon Kim, Kyunghwa Han, Yeun-Yoon Kim, Nieun Seo, Jae-Joon Chung, Joon Seok Lim
{"title":"Artificial Intelligence Model for Detection of Colorectal Cancer on Routine Abdominopelvic CT Examinations: A Training and External-Testing Study.","authors":"Seung-Seob Kim, Hyunseok Seo, Kihwan Choi, Sungwon Kim, Kyunghwa Han, Yeun-Yoon Kim, Nieun Seo, Jae-Joon Chung, Joon Seok Lim","doi":"10.2214/AJR.24.32396","DOIUrl":"10.2214/AJR.24.32396","url":null,"abstract":"<p><p><b>Background:</b> Radiologists are prone to missing some colorectal cancers (CRCs) on routine abdominopelvic CT examinations that are in fact detectable on the images. <b>Objective:</b> To develop an artificial intelligence (AI) model to detect CRC on routine abdominopelvic CT examinations, performed without bowel preparation. <b>Methods:</b> This retrospective study included 3945 patients (2275 men, 1670 women; mean age, 62 years): a training set of 2662 patients from Severance Hospital with CRC who underwent routine contrast-enhanced abdominopelvic CT before treatment between January 2010 and December 2014; and internal (841 patients from Severance Hospital) and external (442 patients from Gangnam Severance Hospital) test sets of patients who underwent routine contrast-enhanced abdominopelvic CT for any indication and colonoscopy within a 2-month interval between January 2018 and June 2018. A radiologist, accessing colonoscopy reports, determined which CRCs were visible on CT and placed bounding boxes around lesions on all slices showing CRC, serving as the reference standard. A contemporary transformer-based object detection network was adapted and trained to create an AI model (https://github.com/boktae7/colorectaltumor) to automatically detect CT-visible CRC on unprocessed DICOM slices. AI performance was evaluated using alternative free-response ROC analysis, per-lesion sensitivity, and per-patient specificity; performance in the external test set was compared to that of two radiologist readers. Clinical radiology reports were also reviewed. <b>Results:</b> In the internal (93 CT-visible CRCs in 92 patients) and external (26 CT-visible CRCs in 26 patients) test sets, AI had AUC of 0.867 and 0.808, sensitivity of 79.6% and 80.8%, and specificity of 91.2% and 90.9%, respectively. In the external test set, the two radiologists had sensitivities of 73.1% and 80.8% (p=.74 and p>.99 vs AI) and specificities of 98.3% and 98.6% (both p<.001 vs AI); AI correctly detected five of nine CRCs missed by at least one reader. The clinical radiology reports raised suspicion for 75.9% of CRCs in the external test set. <b>Conclusion:</b> The findings demonstrate the AI model's utility for automated detection of CRC on routine abdominopelvic CT examinations. <b>Clinical Impact:</b> The AI model could help reduce the frequency of missed CRCs on routine examinations performed for reasons unrelated to CRC detection.</p>","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143400820","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}
{"title":"Wellness and the Family Medical Leave Act: <i>AJR</i> Podcast Series on Wellness, Episode 11.","authors":"Sherry S Wang, Elizabeth H Dibble","doi":"10.2214/AJR.25.32741","DOIUrl":"10.2214/AJR.25.32741","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143400867","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}
{"title":"Editorial Comment: Gadolinium in Photon-Counting Detector CT-Expanding the Possibilities for Liver Imaging.","authors":"Xinyan Zhou","doi":"10.2214/AJR.25.32754","DOIUrl":"https://doi.org/10.2214/AJR.25.32754","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143400827","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}
Stephan Rau, Thomas Stein, Alexander Rau, Sebastian Faby, Maximilian Frederik Russe, Gregor Jost, Michael Christian Doppler, Friederike Lang, Fabian Bamberg, Hubertus Pietsch, Jakob Weiss
{"title":"Use of Photon-Counting Detector CT to Visualize Liver-Specific Gadolinium-Based Contrast Agents: A Phantom Study.","authors":"Stephan Rau, Thomas Stein, Alexander Rau, Sebastian Faby, Maximilian Frederik Russe, Gregor Jost, Michael Christian Doppler, Friederike Lang, Fabian Bamberg, Hubertus Pietsch, Jakob Weiss","doi":"10.2214/AJR.24.32434","DOIUrl":"10.2214/AJR.24.32434","url":null,"abstract":"<p><p><b>Background:</b> The low clinically approved doses of gadolinium-based contrast agents (GBCA) do not generate sufficient enhancement on CT for diagnostic purposes. Photon-counting detector (PCD) CT offers improved spectral resolution and could potentially enable visualization of hepatocyte-specific GBCA given their associated high gadolinium concentrations within hepatocytes. <b>Objective:</b> To investigate the potential of gadoxetate disodium in combination with PCD CT and low-keV VMI reconstructions to achieve an increase in attenuation in a phantom. <b>Methods:</b> A series of solutions was prepared of diluted gadoxetate disodium (concentrations of 0.250-2.5 μmol/ml, corresponding with doses of 25-200 μmol/kg, respectively). These solutions, along with deionized water, were evaluated in an anthropomorphic abdominal phantom using a clinical PCD-CT scanner; virtual monoenergetic images (VMI) at 40, 50, 60, and 70 keV, along with virtual noncontrast (VMC) images, were generated. Attenuation measurements were obtained; a linear regression model combined these values with previously reported in vivo data to estimate hepatic enhancement and CNR across doses. <b>Results:</b> Attenuation increased with increasing concentration at a given energy level and with decreasing energy level for a given concentration; VNC images had lowest attenuation. The maximum attenuation reached was 45.2 HU for a concentration of 2.5 μmol/ml at 40 keV. A concentration of 0.25 μmol/ml had attenuation at 40 keV of 13.0 HU. The model yielded estimated in vivo hepatic enhancement at 40 keV of 4.9 HU for a dose of 25 μmol/kg, 19.9 HU for 100 μmol/kg, and 30.8 HU for 200 μmol/kg; corresponding CNRs were 0.13, 0.52, and 0.81, respectively. <b>Conclusion:</b> The combination of gadoxetate disodium and PCD CT could theoretically allow appreciable hepatic enhancement at a 200-μmol/kg dose; such effect was not observed for the clinically approved 25 μmol/kg dose. <b>Clinical Impact:</b> PCD CT achieved attenuation increases for gadoxetate disodium at considerably lower doses than previously documented for CT of GBCA, albeit approximately 8-times greater than clinical doses and thus too high for clinical use. Additional research exploiting PCD-CT technology could seek to reduce further doses required for sufficient visualization into a clinically feasible range, to potentially allow CT using a liver-specific agent.</p>","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191396","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}
{"title":"Radioactive Iodine in Intermediate-Risk Disease, Remnant Ablation, and Adjuvant Treatment: Counterpoint-High Dose for Improved Treatment Outcome.","authors":"Ismaheel O Lawal, Saima Muzahir","doi":"10.2214/AJR.24.32156","DOIUrl":"https://doi.org/10.2214/AJR.24.32156","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191393","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}
{"title":"Beyond the <i>AJR</i>: Supplemental Screening for Dense Breasts-Performance Affected by Facility Factors and Density Reporting Laws.","authors":"Sophia R O'Brien, Christine E Edmonds","doi":"10.2214/AJR.25.32702","DOIUrl":"https://doi.org/10.2214/AJR.25.32702","url":null,"abstract":"","PeriodicalId":55529,"journal":{"name":"American Journal of Roentgenology","volume":" ","pages":""},"PeriodicalIF":4.7,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191389","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}