RESUMEN
PURPOSE: To assess the accuracy, reliability, and readability of publicly available large language models in answering fundamental questions on hepatocellular carcinoma diagnosis and management. METHODS: Twenty questions on liver cancer diagnosis and management were asked in triplicate to ChatGPT-3.5 (OpenAI), Gemini (Google), and Bing (Microsoft). Responses were assessed by six fellowship-trained physicians from three academic liver transplant centers who actively diagnose and/or treat liver cancer. Responses were categorized as accurate (score 1; all information is true and relevant), inadequate (score 0; all information is true, but does not fully answer the question or provides irrelevant information), or inaccurate (score - 1; any information is false). Means with standard deviations were recorded. Responses were considered as a whole accurate if mean score was > 0 and reliable if mean score was > 0 across all responses for the single question. Responses were also quantified for readability using the Flesch Reading Ease Score and Flesch-Kincaid Grade Level. Readability and accuracy across 60 responses were compared using one-way ANOVAs with Tukey's multiple comparison tests. RESULTS: Of the twenty questions, ChatGPT answered nine (45%), Gemini answered 12 (60%), and Bing answered six (30%) questions accurately; however, only six (30%), eight (40%), and three (15%), respectively, were both accurate and reliable. There were no significant differences in accuracy between any chatbot. ChatGPT responses were the least readable (mean Flesch Reading Ease Score 29; college graduate), followed by Gemini (30; college) and Bing (40; college; p < 0.001). CONCLUSION: Large language models provide complex responses to basic questions on hepatocellular carcinoma diagnosis and management that are seldomly accurate, reliable, or readable.
RESUMEN
This study evaluated an updated diagnostic algorithm for distinguishing HCA subtypes and FNH on gadoxetate disodiumenhanced MRI. The algorithm included a pathway recommending biopsy for indeterminate lesions that could represent HCA with beta-catenin mutations (which are at risk of malignant transformation) or I-HCA with an atypical MRI appearance.
RESUMEN
OBJECTIVE: To assess the performance of computed tomography (CT)/magnetic resonance imaging (MRI) Liver Imaging Reporting and Data System (LI-RADS) among patients with non-cirrhotic steatotic liver disease (SLD). MATERIALS AND METHODS: This IRB-approved, retrospective study included 119 observations from 77 adult patients (36 women, 41 men; median 64 years) who underwent liver CT or MRI from 2010 to 2023. All patients had histopathologic evidence of SLD without cirrhosis. Three board-certified abdominal radiologists blinded to tissue diagnosis and imaging follow-up assessed observations with LI-RADS. The positive predictive value (PPV), sensitivity, specificity, accuracy, and inter-reader agreement were calculated. RESULTS: Seventy-five observations (63%) were benign and 44 (37%) were malignant. PPV for hepatocellular carcinoma (HCC) was 0-0% for LR-1, 0-0% for LR-2, 0-7% for LR-3, 11-20% for LR-4, 75-88% for LR-5, 0-8% for LR-M, and 50-75% for LR-TIV. For LR-5 in identifying HCC, sensitivity was 79-83%, specificity was 91-97%, and accuracy was 89-92%. For composite categories of LR-5, LR-M, or LR-TIV in identifying malignancy, sensitivity was 86-89%, specificity was 85-96%, and accuracy was 86-93%. The most common false positives for LR-5 were hepatocellular adenomas. Only 59-65% of HCCs showed non-peripheral washout at CT versus 67-83% at MRI, though nearly all had an enhancing capsule. PPV and accuracy of LR-5 for HCC did not differ by modality. Inter-reader agreement for major features ranged from 0.667 to 0.830 and was 0.766 for the final category. CONCLUSION: Despite challenges such as the lower prevalence of non-peripheral washout at CT and overlapping imaging features between HCC and hepatocellular adenomas, LI-RADS may serve as an effective tool in assessing focal liver lesions in SLD. CLINICAL RELEVANCE STATEMENT: LI-RADS in non-cirrhotic steatotic liver disease can effectively diagnose hepatocellular carcinoma and malignancy at computed tomography and magnetic resonance imaging, thereby guiding clinical management decisions and expediting patient care pathways. KEY POINTS: Performance of LI-RADS is unknown in non-cirrhotic patients with steatotic liver disease. LI-RADS 5 category showed a high pooled specificity of 91-97% for hepatocellular carcinoma. LI-RADS can non-invasively risk stratify focal liver observations in non-cirrhotic patients with steatotic liver disease.
RESUMEN
RATIONALE AND OBJECTIVES: To compare follow-up imaging and surgical cost implications of the Society of Radiologists in Ultrasound (SRU) guidelines, 2017 and 2022 European (EUR) guidelines, 2020 Canadian Association of Radiologists (CAR) recommendations, and 2013 American College of Radiology (ACR) White Paper for managing incidentally detected gallbladder polyps. MATERIALS AND METHODS: 253 consecutive patients with gallbladder polyps identified on ultrasound were independently reviewed by three radiologists for polyp size and morphology. Electronic medical records were reviewed for patient demographics, cholecystectomy (if performed) pathological findings, or any subsequent diagnosis of gallbladder cancer. For each patient, the following were calculated for each of the 5 guidelines studied: 1) number of recommended follow-up ultrasounds based on initial presentation, 2) number of surgical consultations recommended based on initial presentation, 3) number of surgical consultations recommended based on growth, and 4) associated imaging and surgical costs. Interrater agreement was calculated. RESULTS: The SRU 2022 guidelines suggested significantly fewer follow-up ultrasounds and surgical consultations, leading to a cost reduction of 96.5 % and 96.7 % compared to European 2022 and 2017, respectively; 86.5 % compared to CAR; and 86.2 % compared to ACR guidelines. With SRU Recommendations, the majority of gallbladder polyps would be classified as extremely low risk (68.4 %), 30.8 % low risk, and 0.8 % indeterminate risk. In our cohort, a single case of gallbladder cancer was identified (26 mm) which would be recommended for surgical consult by all guidelines. CONCLUSION: The SRU 2022 guidelines can lead to significant savings for patients, health systems, and society, while reducing unnecessary medical interventions for managing incidentally detected gallbladder polyps.
RESUMEN
Abdominal US is currently the best-validated surveillance strategy for hepatocellular carcinoma (HCC) in at-risk patients. It is the only modality shown to have completed all five phases of validation and can achieve high sensitivity and specificity for HCC detection, especially when conducted by expert sonographers in high-volume centers. However, US also has limitations, including operator dependency and varying sensitivity in clinical practice. Further, the sensitivity of US for early-stage HCC detection is lower in patients with obesity or nonviral liver disease, increasingly common populations undergoing surveillance. Imaging-based and blood-based surveillance strategies, including abbreviated MRI and biomarker panels, may overcome some limitations of US-based surveillance. Both strategies have promising test performance in phase II and phase III biomarker studies and are undergoing prospective validation. Considering the variation in HCC risk and test performance between patients, there will likely be a shift away from a one-size-fits-all approach and toward precision screening, in which the "best" test is selected based on individual patient characteristics. In this upcoming era of precision HCC screening among patients with cirrhosis, US will likely continue to have an important, albeit reduced, surveillance role.
Asunto(s)
Carcinoma Hepatocelular , Neoplasias Hepáticas , Ultrasonografía , Humanos , Neoplasias Hepáticas/diagnóstico por imagen , Carcinoma Hepatocelular/diagnóstico por imagen , Ultrasonografía/métodos , Sensibilidad y Especificidad , Imagen por Resonancia Magnética/métodosRESUMEN
In this video article, Dr. Aya Kamaya, cochair of the LI-RADS Ultrasound Surveillance Working Group, discusses the new LI-RADS Ultrasound Surveillance version 2024 recommendations.
Asunto(s)
Ultrasonografía , Humanos , Ultrasonografía/métodos , Sistemas de Información RadiológicaRESUMEN
Liver congestion is increasingly encountered in clinical practice and presents diagnostic pitfalls of which radiologists must be aware. The complex altered hemodynamics associated with liver congestion leads to diffuse parenchymal changes and the development of benign and malignant nodules. Distinguishing commonly encountered benign hypervascular lesions, such as focal nodular hyperplasia (FNH)-like nodules, from hepatocellular carcinoma (HCC) can be challenging due to overlapping imaging features. FNH-like lesions enhance during the hepatic arterial phase and remain isoenhancing relative to the background liver parenchyma but infrequently appear to wash out at delayed phase imaging, similar to what might be seen with HCC. Heterogeneity, presence of an enhancing capsule, washout during the portal venous phase, intermediate signal intensity at T2-weighted imaging, restricted diffusion, and lack of uptake at hepatobiliary phase imaging point toward the diagnosis of HCC, although these features are not sensitive individually. It is important to emphasize that the Liver Imaging Reporting and Data System (LI-RADS) algorithm cannot be applied in congested livers since major LI-RADS features lack specificity in distinguishing HCC from benign hypervascular lesions in this population. Also, the morphologic changes and increased liver stiffness caused by congestion make the imaging diagnosis of cirrhosis difficult. The authors discuss the complex liver macro- and microhemodynamics underlying liver congestion; propose a more inclusive approach to and conceptualization of liver congestion; describe the pathophysiology of liver congestion, hepatocellular injury, and the development of benign and malignant nodules; review the imaging findings and mimics of liver congestion and hypervascular lesions; and present a diagnostic algorithm for approaching hypervascular liver lesions. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.
Asunto(s)
Carcinoma Hepatocelular , Hiperplasia Nodular Focal , Neoplasias Hepáticas , Enfermedades Vasculares , Humanos , Carcinoma Hepatocelular/diagnóstico por imagen , Carcinoma Hepatocelular/patología , Neoplasias Hepáticas/diagnóstico por imagen , Neoplasias Hepáticas/patología , Medios de Contraste , Hígado/diagnóstico por imagen , Hígado/patología , Hiperplasia Nodular Focal/diagnóstico , Hiperplasia Nodular Focal/patología , Imagen por Resonancia Magnética/métodos , Sensibilidad y Especificidad , Estudios RetrospectivosRESUMEN
Gallbladder (GB) polyps are a common incidental finding on sonography, but only a small fraction of polyps become GB cancer. The Society of Radiologists in Ultrasound (SRU) consensus committee recently performed an extensive literature review and published guidelines for GB polyp follow-up/management to provide clarity among the many heterogeneous recommendations that are available to clinicians. As these guidelines have become adopted into clinical practice, challenging clinical scenarios have arisen including GB polyps in primary sclerosing cholangitis (PSC), high risk geographic/genetic patient populations, shrinking polyps, pedunculated vs sessile polyps, thin vs thick stalked polyps, vascular polyps and multiple polyps. According to the SRU guidelines, clinicians should refer to gastroenterology guidelines when managing GB polyps in patients with known PSC. If patients at high geographic/genetic risk develop GB polyps, 'extremely low risk' polyps may be managed as 'low risk' and 10-14 mm 'extremely low risk' or '7-14 mm' low risk polyps that decrease in size by ≥ 4 mm require no follow-up. Thin-stalked or pedunculated polyps are 'extremely low risk' and thick-stalked pedunculated polyps are 'low risk'. Sessile polyps are 'low risk' but should receive immediate specialist referral if features suggestive of GB cancer are present. Neither polyp multiplicity nor vascularity impact risk of GB cancer and follow up should be based on morphology alone.
RESUMEN
BACKGROUND AND AIMS: The objective of this study is to determine the diagnostic accuracy of the American College of Radiology Contrast-Enhanced Ultrasound (CEUS) Liver Imaging Reporting and Data System LR-5 characterization for HCC diagnosis in North American or European patients. APPROACH AND RESULTS: A prospective multinational cohort study was performed from January 2018 through November 2022 at 11 academic and nonacademic centers in North America and Europe. Patients at risk for HCC with at least 1 liver observation not previously treated, identified on ultrasound (US), or multiphase CT or MRI performed as a part of standard clinical care were eligible for the study. All participants were examined with CEUS of the liver within 4 weeks of CT/MRI or tissue diagnosis to characterize up to 2 liver nodules per participant using ACR CEUS Liver Imaging Reporting and Data System. Definite HCC diagnosis on the initial CT/MRI, imaging follow-up, or histology for CT/MRI-indeterminate nodules were used as reference standards. A total of 545 nodules had confirmed reference standards in 480 patients, 73.8% were HCC, 5.5% were other malignancies, and 20.7% were nonmalignant. The specificity of CEUS LR-5 for HCC was 95.1% (95% CI 90.1%-97.7%), sensitivity 62.9% (95% CI 57.9%-67.7%), positive predictive value 97.3% (95% CI 94.5%-98.7%), and negative predictive value 47.7% (95% CI 41.7%-53.8%). In addition, benign CEUS characterization (LR-1 or LR-2) had 100% specificity and 100% positive predictive value for nonmalignant liver nodules. CONCLUSIONS: CEUS Liver Imaging Reporting and Data System provides an accurate categorization of liver nodules in participants at risk for HCC.
Asunto(s)
Carcinoma Hepatocelular , Neoplasias Hepáticas , Humanos , Carcinoma Hepatocelular/patología , Neoplasias Hepáticas/patología , Estudios Prospectivos , Estudios de Cohortes , Medios de Contraste , Estudios Retrospectivos , Reproducibilidad de los Resultados , Imagen por Resonancia Magnética/métodos , Europa (Continente) , América del Norte , Sensibilidad y EspecificidadRESUMEN
Point-of-care ultrasound (POCUS) is rapidly accelerating in adoption and applications outside the traditional realm of diagnostic radiology departments. Although the use of this imaging technology in a distributed fashion has great potential, there are many associated challenges. To address these challenges, the authors developed an enterprise-wide POCUS program at their institution (Stanford Health Care). Here, the authors share their experience, the governance organization, and their approaches to device and information security, training, and quality assurance. The authors also share the basic principles they use to guide their approach to manage these challenges. Through their work, the authors have learned that a foundational framework of defining POCUS and the different levels of POCUS use and delineating program management elements are critical. The authors hope that their experience will be helpful to others who are also interested in POCUS or in the process of creating POCUS programs at their institutions. With a clearly established framework, patient safety and quality of care are improved for everyone.
RESUMEN
OBJECTIVES: The aims of the study are to describe the growth kinetics of pathologically proven, treatment-naive pancreatic neuroendocrine neoplasms (panNENs) at imaging surveillance and to determine their association with histopathologic grade and Ki-67. METHODS: This study included 100 panNENs from 95 patients who received pancreas protocol computed tomography or magnetic resonance imaging from January 2005 to July 2022. All masses were treatment-naive, had histopathologic correlation, and were imaged with at least 2 computed tomography or magnetic resonance imaging at least 90 days apart. Growth kinetics was assessed using linear and specific growth rate, stratified by grade and Ki-67. Masses were also assessed qualitatively to determine other possible imaging predictors of grade. RESULTS: There were 76 grade 1 masses, 17 grade 2 masses, and 7 grade 3 masses. Median (interquartile range) linear growth rates were 0.06 cm/y (0-0.20), 0.40 cm/y (0.22-1.06), and 2.70 cm/y (0.41-3.89) for grade 1, 2, and 3 masses, respectively (P < 0.001). Linear growth rate correlated with Ki-67 with r2 of 0.623 (P < 0.001). At multivariate analyses, linear growth rate was the only imaging feature significantly associated with grade (P = 0.009). CONCLUSIONS: Growth kinetics correlate with Ki-67 and grade. Grade 1 panNENs grow slowly versus grade 2-3 panNENs.
RESUMEN
BACKGROUND. In 2022, a five-tiered CT algorithm was proposed for predicting whether a small (cT1a) solid renal mass represents clear cell renal cell carcinoma (ccRCC). OBJECTIVE. The purpose of this external validation study was to evaluate the proposed CT algorithm for diagnosis of ccRCC among small solid renal masses. METHODS. This retrospective study included 93 patients (median age, 62 years; 42 women, 51 men) with 97 small solid renal masses that were seen on corticomedullary phase contrast-enhanced CT performed between January 2012 and July 2022 and subsequently underwent surgical resection. Five readers (three attending radiologists, two clinical fellows) independently evaluated masses for the mass-to-cortex corticomedullary attenuation ratio and heterogeneity score; these scores were used to derive the CT score by use of the previously proposed CT algorithm. The CT score's sensitivity, specificity, and PPV for ccRCC were calculated at threshold of 4 or greater, and the NPV for ccRCC was calculated at a threshold of 3 or greater (consistent with thresholds in studies of the MRI-based clear cell likelihood score and the CT algorithm's initial study). The CT score's sensitivity and specificity for papillary RCC were calculated at a threshold of 2 or less. Interreader agreement was assessed using the Gwet agreement coefficient (AC1). RESULTS. Overall, 61 of 97 masses (63%) were malignant and 43 of 97 (44%) were ccRCC. Across readers, CT score had sensitivity ranging from 47% to 95% (pooled sensitivity, 74% [95% CI, 68-80%]), specificity ranging from 19% to 83% (pooled specificity, 59% [95% CI, 52-67%]), PPV ranging from 48% to 76% (pooled PPV, 59% [95% CI, 49-71%]), and NPV ranging from 83% to 100% (pooled NPV, 90% [95% CI, 84-95%]), for ccRCC. A CT score of 2 or less had sensitivity ranging from 44% to 100% and specificity ranging from 77% to 98% for papillary RCC (representing nine of 97 masses). Interreader agreement was substantial for attenuation score (AC1 = 0.70), poor for heterogeneity score (AC1 = 0.17), fair for five-tiered CT score (AC1 = 0.32), and fair for dichotomous CT score at a threshold of 4 or greater (AC1 = 0.24 [95% CI, 0.14-0.33]). CONCLUSION. The five-tiered CT algorithm for evaluation of small solid renal masses was tested in an external sample and showed high NPV for ccRCC. CLINICAL IMPACT. The CT algorithm may be used for risk stratification and patient selection for active surveillance by identifying patients unlikely to have ccRCC.
Asunto(s)
Carcinoma de Células Renales , Neoplasias Renales , Masculino , Humanos , Femenino , Persona de Mediana Edad , Carcinoma de Células Renales/diagnóstico por imagen , Carcinoma de Células Renales/patología , Estudios Retrospectivos , Neoplasias Renales/diagnóstico por imagen , Neoplasias Renales/patología , Diagnóstico Diferencial , Algoritmos , Tomografía Computarizada Multidetector/métodosRESUMEN
ChatGPT did not reliably provide accurate information to 20 questions about liver cancer surveillance and diagnosis, as assessed by six physicians who actively diagnose and/or treat liver cancer. Answers deemed inaccurate commonly related to questions on specific LI-RADS categories and included contradictory or falsely reassuring, if not wrong, information.
Asunto(s)
Carcinoma Hepatocelular , Neoplasias Hepáticas , Humanos , Neoplasias Hepáticas/diagnóstico por imagenRESUMEN
OBJECTIVE: To evaluate the prevalence of angular interface and the "drooping" sign in exophytic renal angiomyolipomas (AMLs) and the diagnostic performance in differentiating exophytic lipid-poor AMLs from other solid renal masses. METHODS: This IRB-approved, two-center study included 185 patients with 188 exophytic solid renal masses < 4 cm with histopathology and pre-operative CT within 30 days of surgical resection or biopsy. Images were reviewed for the presence of angular interface and the "drooping" sign qualitatively by three readers blinded to the final diagnosis, with majority rules applied. Both features were assessed quantitatively by cohort creators (who are not readers) independently. Free-marginal kappa was used to assess inter-reader agreement and agreement between two methods assessing each feature. Fisher's exact test, Mann-Whitney test, and multivariable logistic regression with two-tailed p < 0.05 were used to determine statistical significance. Diagnostic performance was assessed. RESULTS: Ninety-four patients had 96 AMLs, and 91 patients had 92 non-AMLs. Seventy-four (77%) of AMLs were lipid-poor based on quantitative assessment on CT. The presence of angular interface and the "drooping" sign by both qualitative and quantitative assessment were statistically significantly associated with AMLs (39% (qualitative) and 45% (quantitative) vs 15% (qualitative) and 13% (quantitative), and 48% (qualitative) and 43% (quantitative) vs 4% (qualitative) and 1% (quantitative), respectively, all p < 0.001) in univariable analysis. In multivariable analysis, only the "drooping" sign in either qualitative or quantitative assessment was a statistically significant predictor of AMLs (both p < 0.001). Inter-reader agreement for the "drooping" sign was moderate (k = 0.55) and for angular interface was fair (k = 0.33). Agreement between the two methods of assessing the "drooping" sign was substantial (k = 0.84) and of assessing the angular interface was moderate (k = 0.59). The "drooping" sign both qualitatively and quantitatively, alone or in combination of angular interface, had very high specificity (96-100%) and positive predictive value (PPV) (89-100%), moderate negative predictive value (62-68%), but limited sensitivity (23-49%) for lipid-poor AMLs. CONCLUSION: The "drooping" sign by both qualitative and quantitative assessment is highly specific for lipid-rich and lipid-poor AMLs. This feature alone or in combination with angular interface can aid in CT diagnosis of lipid-poor AMLs with very high specificity and PPV.
Asunto(s)
Angiomiolipoma , Carcinoma de Células Renales , Neoplasias Renales , Humanos , Neoplasias Renales/diagnóstico por imagen , Neoplasias Renales/patología , Angiomiolipoma/diagnóstico por imagen , Angiomiolipoma/patología , Carcinoma de Células Renales/patología , Sensibilidad y Especificidad , Diagnóstico Diferencial , Tomografía Computarizada por Rayos X/métodos , Lípidos , Estudios RetrospectivosRESUMEN
Hepatocellular adenomas (HCAs) are a family of liver tumors that are associated with variable prognoses. Since the initial description of these tumors, the classification of HCAs has expanded and now includes eight distinct genotypic subtypes based on molecular analysis findings. These genotypic subtypes have unique derangements in their cellular biologic makeup that determine their clinical course and may allow noninvasive identification of certain subtypes. Multiphasic MRI performed with hepatobiliary contrast agents remains the best method to noninvasively detect, characterize, and monitor HCAs. HCAs are generally hypointense during the hepatobiliary phase; the ß-catenin-mutated exon 3 subtype and up to a third of inflammatory HCAs are the exception to this characterization. It is important to understand the appearances of HCAs beyond their depictions at MRI, as these tumors are typically identified with other imaging modalities first. The two most feared related complications are bleeding and malignant transformation to hepatocellular carcinoma, although the risk of these complications depends on tumor size, subtype, and clinical factors. Elective surgical resection is recommended for HCAs that are persistently larger than 5 cm, adenomas of any size in men, and all ß-catenin-mutated exon 3 HCAs. Thermal ablation and transarterial embolization are potential alternatives to surgical resection. In the acute setting of a ruptured HCA, patients typically undergo transarterial embolization with or without delayed surgical resection. This update on HCAs includes a review of radiologic-pathologic correlations by subtype and imaging modality, related complications, and management recommendations. © RSNA, 2023 Online supplemental material is available for this article. Quiz questions for this article are available through the Online Learning Center.
Asunto(s)
Adenoma de Células Hepáticas , Adenoma , Carcinoma Hepatocelular , Neoplasias Hepáticas , Humanos , Adenoma de Células Hepáticas/patología , beta Catenina , Carcinoma Hepatocelular/patología , Neoplasias Hepáticas/patología , Imagen por Resonancia Magnética/métodosRESUMEN
Since its initial release in 2011, the Liver Imaging Reporting and Data System (LI-RADS) has evolved and expanded in scope. It started as a single algorithm for hepatocellular carcinoma (HCC) diagnosis with CT or MRI with extracellular contrast agents and has grown into a multialgorithm network covering all major liver imaging modalities and contexts of use. Furthermore, it has developed its own lexicon, report templates, and supplementary materials. This article highlights the major achievements of LI-RADS in the past 11 years, including adoption in clinical care and research across the globe, and complete unification of HCC diagnostic systems in the United States. Additionally, the authors discuss current gaps in knowledge, which include challenges in surveillance, diagnostic population definition, perceived complexity, limited sensitivity of LR-5 (definite HCC) category, management implications of indeterminate observations, challenges in reporting, and treatment response assessment following radiation-based therapies and systemic treatments. Finally, the authors discuss future directions, which will focus on mitigating the current challenges and incorporating advanced technologies. Tha authors envision that LI-RADS will ultimately transform into a probability-based system for diagnosis and prognostication of liver cancers that will integrate patient characteristics and quantitative imaging features, while accounting for imaging modality and contrast agent.