How AI Responds to Common Lung Cancer Questions: ChatGPT vs Google Bard.

Background The recent release of large language models (LLMs) for public use, such as ChatGPT and Google Bard, has opened up a multitude of potential benefits as well as challenges. Purpose To evaluate and compare the accuracy and consistency of responses generated by publicly available ChatGPT-3.5 and Google Bard to non-expert questions related to lung cancer prevention, screening, and terminology commonly used in radiology reports based on the recommendation of Lung Imaging Reporting and Data System (Lung-RADS) v2022 from American College of Radiology and Fleischner society. Materials and Methods Forty of the exact same questions were created and presented to ChatGPT-3.5 and Google Bard experimental version as well as Bing and Google search engines by three different authors of this paper. Each answer was reviewed by two radiologists for accuracy. Responses were scored as correct, partially correct, incorrect, or unanswered. Consistency was also evaluated among the answers. Here, consistency was defined as the agreement between the three answers provided by ChatGPT-3.5, Google Bard experimental version, Bing, and Google search engines regardless of whether the concept conveyed was correct or incorrect. The accuracy among different tools were evaluated using Stata. Results ChatGPT-3.5 answered 120 questions with 85 (70.8%) correct, 14 (11.7%) partially correct, and 21 (17.5%) incorrect. Google Bard did not answer 23 (19.1%) questions. Among the 97 questions answered by Google Bard, 62 (51.7%) were correct, 11 (9.2%) were partially correct, and 24 (20%) were incorrect. Bing answered 120 questions with 74 (61.7%) correct, 13 (10.8%) partially correct, and 33 (27.5%) incorrect. Google search engine answered 120 questions with 66 (55%) correct, 27 (22.5%) partially correct, and 27 (22.5%) incorrect. The ChatGPT-3.5 is more likely to provide correct or partially answer than Google Bard, approximately by 1.5 folds (OR = 1.55, P = 0.004). ChatGPT-3.5 and Google search engine were more likely to be consistent than Google Bard by approximately 7 and 29 folds (OR = 6.65, P = 0.002 for ChatGPT and OR = 28.83, P = 0.002 for Google search engine, respectively). Conclusion Although ChatGPT-3.5 had a higher accuracy in comparison with the other tools, neither ChatGPT nor Google Bard, Bing and Google search engines answered all questions correctly and with 100% consistency.

Vascularized Lymph Node Transfer: A Primer for the Radiologist.

Lymphedema, the accumulation of lymphatic fluid in the tissues, is a chronic disease and a major cause of long-term morbidity and disability. Lymphedema is usually a secondary condition, often caused by prior oncologic therapy, such as surgery for cancers, radiation therapy, and chemotherapy. Treatment for lymphedema has traditionally been conservative and limited, but new surgical and microsurgical procedures have arisen in recent years. Vascularized lymph node transfer (VLNT) is one of the most promising new microsurgeries. VLNT involves the transfer of functional lymph nodes (LNs) from a healthy donor site to an area of the body with damaged or diseased lymphatic drainage. The goal of the transplant is to restore physiologic LN drainage and improve lymphedema. Donor LNs are commonly found in the groin, axilla, neck, omentum, or submental region. Imaging can be used for preoperative planning to identify donor sites with the richest number of LNs. This can help identify those patients who may be candidates for VLNT and can help identify the best anatomic site for surgical harvest in those candidates. Imaging can be performed with US, CT, or MRI. VLNT preoperative imaging often requires acquisition techniques and reconstruction parameters that differ from those used in routine diagnostic imaging. Furthermore, to properly identify target LNs, the radiologist must be aware of surgical anatomic landmarks. Online supplemental material is available for this article. ©RSNA, 2020.

Recent Innovations in Renal Vascular Imaging.

Noninvasive imaging of the vascular renal system is a common request in diagnostic radiology. Typical indications include suspected renovascular hypertension, vasculitis, neoplasm, vascular malformation, and structural diseases of the kidney. Profound knowledge of the renal anatomy, including vascular supply and variants, is mandatory for radiologists and allows for optimized protocolling and interpretation of imaging studies. Besides renal ultrasound, computed tomography and MR imaging are commonly requested cross-sectional studies for renal and renal vascular imaging. This article discusses basic renal vascular anatomy, common imaging findings, and current and potential future imaging protocols for various renovascular pathologic conditions.

Radiomics in Pulmonary Lesion Imaging.

OBJECTIVE: Diagnostic imaging has traditionally relied on a limited set of qualitative imaging characteristics for the diagnosis and management of lung cancer. Radiomics-the extraction and analysis of quantitative features from imaging-can identify additional imaging characteristics that cannot be seen by the eye. These features can potentially be used to diagnose cancer, identify mutations, and predict prognosis in an accurate and noninvasive fashion. This article provides insights about trends in radiomics of lung cancer and challenges to widespread adoption. CONCLUSION: Radiomic studies are currently limited to a small number of cancer types. Its application across various centers are nonstandardized, leading to difficulties in comparing and generalizing results. The tools available to apply radiomics are specialized and limited in scope, blunting widespread use and clinical integration in the general population. Increasing the number of multicenter studies and consortiums and inclusion of radiomics in resident training will bring more attention and clarity to the growing field of radiomics.

Anatomical Basis of the Gastroepiploic Vascularized Lymph Node Transfer: A Radiographic Evaluation Using Computed Tomographic Angiography.

BACKGROUND: The omentum, nourished by the gastroepiploic vessels, has gained popularity as an option for vascularized lymph node transfer. The anatomy of the gastroepiploic vessels, omentum, and lymph nodes has not been investigated. The purpose of this article is to describe the right gastroepiploic artery and related structures by using computed tomographic angiography. METHODS: A retrospective analysis was conducted on 34 patients who underwent computed tomographic angiography. Statistical models were applied to identify right gastroepiploic artery and lymph node anatomical characteristics. RESULTS: The right gastroepiploic artery was identified in 33 of 34 patients. It was found to have a diameter of 2.49 ± 0.66 mm at its origin. The gastroduodenal artery length before right gastroepiploic artery takeoff was 3.09 ± 1.31 cm. Twenty-five patients had lymph nodes in the right gastroepiploic artery lymphosome. There were 2.7 ± 2.12 lymph nodes identified per patient. The distance from the right gastroepiploic artery origin to the most proximal lymph node was 3.99 ± 2.21 cm. The distance from the gastroepiploic artery origin to the third lymph node was 9.12 ± 5.06 cm. Each lymph node was within 7.00 ± 6.2 mm of the right gastroepiploic artery. CONCLUSIONS: When using the right gastroepiploic artery donor site for vascularized lymph node transfer, the plastic surgeon should anticipate using a pedicle length of 4 cm, a total flap length of 9 cm, and 3 cm of surrounding tissue to obtain at least three lymph nodes for transfer. Computed tomographic angiography is an effective imaging modality that can be used for patient-specific surgical navigation before vascularized lymph node transfer.

Forward-Projected Model-Based Iterative Reconstruction in Screening Low-Dose Chest CT: Comparison With Adaptive Iterative Dose Reduction 3D.

OBJECTIVE: The objective of this study is to compare forward-projected model-based iterative reconstruction solution (FIRST), a newer fully iterative CT reconstruction method, with adaptive iterative dose reduction 3D (AIDR 3D) in low-dose screening CT for lung cancer. Differences in image noise, image quality, and pulmonary nodule detection, size, and characterization were specifically evaluated. MATERIALS AND METHODS: Low-dose chest CT images obtained for 50 consecutive patients between December 2015 and January 2016 were retrospectively reviewed. Images were reconstructed using FIRST and AIDR 3D for both lung and soft-tissue reconstruction. Images were independently reviewed to assess image noise, subjective image quality (with use of a 5-point Likert scale, with 1 denoting far superior image quality; 2, superior quality; 3, equivalent quality; 4, inferior quality; and 5, far inferior quality), pulmonary nodule count, size of the largest pulmonary nodule, and characterization of the largest pulmonary nodule (i.e., solid, part solid, or ground glass). RESULTS: Across all 50 cases, measured image noise was lower with FIRST than with AIDR 3D (lung window, 44% reduction, 41 ± 7 vs 74 ± 8 HU, respectively; soft-tissue window, 32% reduction, 11 ± 2 vs 16 ± 2 HU, respectively). Readers subjectively rated images obtained with FIRST as comparable to images obtained with AIDR 3D (mean [± SD] Likert score for FIRST vs AIDR 3D, 3.2 ± 0.3 for soft-tissue reconstructions and 3.0 ± 0.3 for lung reconstructions). For each reader, very good agreement regarding nodule count was noted between FIRST and AIDR 3D (interclass correlation coefficient [ICC], 0.83 for reader 1 and 0.78 for reader 2). Excellent agreement regarding nodule size (ICC, 0.99 for reader 1 and 0.99 for reader 2) and characterization of the largest nodule (kappa value, 0.92 for reader 1 and 0.82 for reader 2) also existed. CONCLUSION: Images reconstructed with FIRST are superior to those reconstructed AIDR 3D with regard to image noise and are equivalent with regard to subjective image quality, pulmonary nodule count, and nodule characterization.

Comprehensive Cross-sectional Imaging of the Pulmonary Veins.

The pulmonary veins carry oxygenated blood from the lungs to the heart, but their importance to the radiologist extends far beyond this seemingly straightforward function. The anatomy of the pulmonary veins is variable among patients, with several noteworthy variant and anomalous patterns, including supernumerary pulmonary veins, a common ostium, anomalous pulmonary venous return, and levoatriocardinal veins. Differences in pulmonary vein anatomy and the presence of variant or anomalous anatomy can be of critical importance, especially for preoperative planning of pulmonary and cardiac surgery. The enhancement or lack of enhancement of the pulmonary veins can be a clue to clinically important disease, and the relationship of masses to the pulmonary veins can herald cardiac invasion. The pulmonary veins are also an integral part of thoracic interventions, including lung transplantation, pneumonectomy, and radiofrequency ablation for atrial fibrillation. This fact creates a requirement for radiologists to have knowledge of the pre- and postoperative imaging appearances of the pulmonary veins. Many of these procedures are associated with important potential complications involving the pulmonary veins, for which diagnostic imaging plays a critical role. A thorough knowledge of the pulmonary veins and a proper radiologic approach to their evaluation is critical for the busy radiologist who must incorporate the pulmonary veins into a routine "search pattern" at computed tomography (CT) and magnetic resonance imaging. This article is a comprehensive CT-based imaging review of the pulmonary veins, including their embryology, anatomy (typical and anomalous), surgical implications, pulmonary vein thrombosis, pulmonary vein stenosis, pulmonary vein pseudostenosis, and the relationship of tumors to the pulmonary veins. Online supplemental material is available for this article. ©RSNA, 2017.

Fibrous Skeleton of the Heart: Anatomic Overview and Evaluation of Pathologic Conditions with CT and MR Imaging.

The fibrous skeleton is concentrated at the base of the ventricular mass. It provides electrical insulation at the atrioventricular level and fibrous continuity for the leaflets of the mitral, aortic, and tricuspid valves. Its components include the fibrous trigones, the fibrous area of aortic-mitral continuity, the subvalvar collar of the mitral valve, the membranous septum, the interleaflet triangles, the tendon of Todaro, and likely the conus ligament. The majority of the mitral annulus is fibrous, but the only true fibrous part of the tricuspid annulus is where the valvar leaflets are attached to the central fibrous body. At the aortic annulus, the fibrous elements support only the noncoronary aortic sinus and parts of the right and left coronary sinuses. The ring-shaped annulus of the arterioventricular valves as localized with imaging techniques (imaging annulus) differs from the crown-shaped hemodynamic annulus of the arterial valves. The imaging annulus corresponds to the plane passing through the nadirs of the hinge-lines of the leaflets. The hinges of the pulmonary valve are not part of the fibrous skeleton. Computed tomography (CT) and magnetic resonance (MR) imaging are excellent modalities for evaluation of the anatomy, physiologic variations, and pathologic conditions of the fibrous skeleton. The submillimeter isotropic three-dimensional datasets obtained with CT and the high contrast resolution of MR imaging are the main advantages of these modalities in assessing anatomy. The function of the valves and associated annuli can best be studied with MR imaging. Pathologic conditions involving the area, including paravalvar leaks, abscesses, perforation, and pseudoaneurysms, usually occur as a complication of infective endocarditis or extensive calcifications after valvar surgery. MR imaging and CT can demonstrate these lesions equally well. CT is the preferred technique for showing the extent of calcifications in the fibrous skeleton. Large calcifications involving the central fibrous body can cause heart block by interfering with the normal function of the His bundle and its branches. ©RSNA, 2017.

Septal Atrioventricular Junction Region: Comprehensive Imaging in Adults.

The septal atrioventricular junction is a centrally located region of the heart where the septal components of the atria and ventricles meet the aortic, mitral, and tricuspid valves. Important structures in this region include the membranous septum, the central fibrous body, the Koch triangle, the inferior pyramidal space, and the base of the interventricular septum. This small area is the home of the atrioventricular node and the atrioventricular conduction axis and has enormous importance to electrophysiologists owing to its prime role in the conduction system of the heart. The atrioventricular node lies within the triangle of Koch; and the atrioventricular bundle, or bundle of His, exits the atrioventricular node and penetrates the right fibrous trigone and runs underneath the membranous septum. The septal atrioventricular junction is a common location for intracardiac shunts such as membranous and perimembranous septal defects. Imaging classification of these defects can have important implications before surgical closure, because the atrioventricular conduction axis passes along the posteroinferior margin of most perimembranous defects. Extracardiac inflammatory and malignant pathologic conditions can extend from the mediastinum toward the inferior pyramidal space in this region through the epicardial fat planes. Although the anatomic structures are complicated, the components can be shown in exquisite detail with computed tomography (CT). In this review, the anatomic boundaries and important anatomic landmarks are examined with CT and magnetic resonance imaging. Also described are the anatomic variants of the membranous septum pertinent to percutaneous aortic valve implantation, the vascular anatomic variants, and commonly encountered pathologic conditions related to the septal atrioventricular junction. ©RSNA, 2016.

A case of multisystem endometriosis.

Catamenial pneumothorax is a rare complication secondary to pleural endometriosis. We present a case of a 37-year-old-female with a history of recurrent pneumothoraces with an associated temporal relationship to the onset of her menses. In addition to her recurrent pneumothoraces, on further evaluation, she was found to have multiple nodular masses within the omentum. A thoracoscopic biopsy was subsequently performed, which showed endometrial implants within the pleural space and within the omental cavity. The radiological features and pathogenesis of this rare disease are reviewed and discussed with reference to relevant literature.

Bochdalek hernia with obstructive uropathy.

Bochdalek hernias are postero-medial diaphragmatic defects that usually contain peritoneal fat and often remain asymptomatic. We present a unique case in which involvement of the adjacent ureter in the hernia defect resulted in obstructive uropathy.