Performance of ChatGPT-4 and Bard chatbots in responding to common patient questions on prostate cancer 177Lu-PSMA-617 therapy.

Background: Many patients use artificial intelligence (AI) chatbots as a rapid source of health information. This raises important questions about the reliability and effectiveness of AI chatbots in delivering accurate and understandable information. Purpose: To evaluate and compare the accuracy, conciseness, and readability of responses from OpenAI ChatGPT-4 and Google Bard to patient inquiries concerning the novel 177Lu-PSMA-617 therapy for prostate cancer. Materials and methods: Two experts listed the 12 most commonly asked questions by patients on 177Lu-PSMA-617 therapy. These twelve questions were prompted to OpenAI ChatGPT-4 and Google Bard. AI-generated responses were distributed using an online survey platform (Qualtrics) and blindly rated by eight experts. The performances of the AI chatbots were evaluated and compared across three domains: accuracy, conciseness, and readability. Additionally, potential safety concerns associated with AI-generated answers were also examined. The Mann-Whitney U and chi-square tests were utilized to compare the performances of AI chatbots. Results: Eight experts participated in the survey, evaluating 12 AI-generated responses across the three domains of accuracy, conciseness, and readability, resulting in 96 assessments (12 responses x 8 experts) for each domain per chatbot. ChatGPT-4 provided more accurate answers than Bard (2.95 ± 0.671 vs 2.73 ± 0.732, p=0.027). Bard's responses had better readability than ChatGPT-4 (2.79 ± 0.408 vs 2.94 ± 0.243, p=0.003). Both ChatGPT-4 and Bard achieved comparable conciseness scores (3.14 ± 0.659 vs 3.11 ± 0.679, p=0.798). Experts categorized the AI-generated responses as incorrect or partially correct at a rate of 16.6% for ChatGPT-4 and 29.1% for Bard. Bard's answers contained significantly more misleading information than those of ChatGPT-4 (p = 0.039). Conclusion: AI chatbots have gained significant attention, and their performance is continuously improving. Nonetheless, these technologies still need further improvements to be considered reliable and credible sources for patients seeking medical information on 177Lu-PSMA-617 therapy.

Impact of Universal Vasa Previa Screening With Color Doppler During the OB Ultrasound Anatomy Scan.

OBJECTIVES: Our institution introduced universal vasa previa (VP) screening utilizing transabdominal ultrasound with color Doppler for all pregnancies at the second trimester anatomy scan. Our study sought to describe the clinical impact of this intervention. METHODS: Radiology records from the 12 months pre- and post-intervention were queried for "vasa previa." Records included for analysis were those with a first-time diagnosis or discussion of VP at the anatomy scan. Cases were categorized by outcome: (Group 1) True VP, with subgroups A, unresolved by time of delivery and B, resolved by delivery; (Group 2) False positives; (Group 3) Possible VP without definitive diagnosis; and (Group 4) VP ruled out, for example, "no features of VP." Group size was expressed as a percentage of total anatomy scans during pre- or post-intervention periods respectively. Absolute and relative percent change were calculated for each group. RESULTS: In the pre-intervention period, 1 case (0.36% of total scans) was categorized in Group 1A, 1 case (0.36%) in Group 3, and 7 cases (2.53%) in Group 4. In the post-intervention period, 2 cases (0.30%) were in Group 1A, 4 cases (0.61%) in Group 1B, 2 cases (0.30%) in Group 2, 1 case (0.15%) in Group 3, and 7 cases (1.06%) in Group 4. There was a +153% relative change in true positives, from 0.36 to 0.91%. CONCLUSIONS: Universal color Doppler screening may have increased detection (sensitivity) while simultaneously increasing false positives (decreased specificity). While decreasing sensitivity is not ideal, this is acceptable given the potential catastrophic outcome of a missed VP.

Normal and Abnormal Appearances of the Ovaries during Assisted Reproduction: Multimodality Imaging Review.

Infertility is a common diagnosis that prompts many couples and individuals to seek assisted reproductive technology (ART) for assistance with conception. These technologies have become increasingly used in the United States in the past several decades, with 326 468 ART cycles performed in 2020, resulting in 75 023 live births. This ubiquity of ART also increases the likelihood that radiologists will encounter both normal and abnormal imaging findings associated with these treatments. Thus, radiologists of all subspecialties should be familiar with the multimodality appearance of the ovaries and pelvis in patients undergoing ART treatments. Furthermore, it is imperative that radiologists understand the appearance expected during different stages of the ART process. During stimulated ovulatory cycles, it is normal and expected for the ovaries to appear enlarged and to contain numerous cystic follicles, often with a small to moderate volume of pelvic free fluid. After oocyte retrieval, hemorrhagic ovarian follicles and a small to moderate volume of blood products in the cul-de-sac can be expected to be seen. Multiple nonemergency and emergency complications are related to ART, many of which can be seen at imaging. The most encountered emergency complications of ART include ovarian hyperstimulation syndrome, ectopic pregnancy, heterotopic pregnancy, multiple gestations, ovarian torsion, and procedural complications related to oocyte retrieval. These complications have important clinical implications, thus necessitating accurate and timely detection by the radiologist and the clinical team. ©RSNA, 2023 Supplemental material is available for this article. Quiz questions for this article are available through the Online Learning Center.

Potential applications of PET/MRI in non-oncologic conditions within the abdomen and pelvis.

PET/MRI is a relatively new imaging modality with several advantages over PET/CT that promise to improve imaging of the abdomen and pelvis for specific diagnostic tasks by combining the superior soft tissue characterization of MRI with the functional information acquired from PET. PET/MRI has an established role in staging and response assessment of multiple abdominopelvic malignancies, but the modality is not yet established for non-oncologic conditions of the abdomen and pelvis. In this review, potential applications of PET/MRI for non-oncologic conditions of abdomen and pelvis are outlined, and the available literature is reviewed to highlight promising areas for further research and translation into clinical practice.

Twitter Use by Academic Nuclear Medicine Programs: Pilot Content Analysis Study.

BACKGROUND: There is scant insight into the presence of nuclear medicine (NM) and nuclear radiology (NR) programs on social media. OBJECTIVE: Our purpose was to assess Twitter engagement by academic NM/NR programs in the United States. METHODS: We measured Twitter engagement by the academic NM/NR community, accounting for various NM/NR certification pathways. The Twitter presence of NM/NR programs at both the department and program director level was identified. Tweets by programs were cross-referenced against potential high-yield NM- or NR-related hashtags, and tabulated at a binary level. A brief survey was done to identify obstacles and benefits to Twitter use by academic NM/NR faculty. RESULTS: For 2019-2020, 88 unique programs in the United States offered NM/NR certification pathways. Of these, 52% (46/88) had Twitter accounts and 24% (21/88) had at least one post related to NM/NR. Only three radiology departments had unique Twitter accounts for the NM/molecular imaging division. Of the other 103 diagnostic radiology residency programs, only 16% (16/103) had a presence on Twitter and 5% (5/103) had tweets about NM/NR. Only 9% (8/88) of NM/NR program directors were on Twitter, and three program directors tweeted about NM/NR. The survey revealed a lack of clarity and resources around using Twitter, although respondents acknowledged the perceived value of Twitter engagement for attracting younger trainees. CONCLUSIONS: Currently, there is minimal Twitter engagement by the academic NM/NR community. The perceived value of Twitter engagement is counterbalanced by identifiable obstacles. Given radiologists' overall positive views of social media's usefulness, scant social media engagement by the NM community may represent a missed opportunity. More Twitter engagement and further research by trainees and colleagues should be encouraged, as well as the streamlined use of unique hashtags.

11C-choline positron emission tomography/computed tomography for detection of disease relapse in patients with history of biochemically recurrent prostate cancer and prostate-specific antigen ≤0.1 ng/ml.

OBJECTIVES: The objective was to evaluate the diagnostic performance of surveillance11 C-choline positron emission tomography/computed tomography (PET/CT) for the detection of disease relapse in patients with a history of biochemically recurrent (BCR) prostate cancer (PCa) and prostate-specific antigen (PSA) ≤0.1 ng/ml. MATERIALS AND METHODS: We included patients who had been treated for BCR PCa and had a surveillance11 C-choline PET/CT at serum PSA ≤0.1 ng/ml. Positive surveillance PET/CT was defined as a study that identified a new tracer-avid lesion or new tracer uptake in a previously treated lesion or both. Findings were confirmed against a composite radiologic-pathologic gold standard. Time to recurrence association analyses were performed for disease relapse risk with the use of Cox proportional hazards regression. RESULTS: In total, 13 (12.1%) of the 107 patients had positive surveillance PET/CT scans, confirmed on pathologic assessment (n = 5) and subsequent imaging (n = 8). Among these 13 patients, ten had distant metastases, two had local recurrence, and one had both. Nine of the ten patients with metastases had oligometastatic disease defined as the presence of ≤3 metastases. Serum PSA became detectable again in only seven patients with positive surveillance PET/CT, after a mean interval from surveillance PET/CT of 292 days (range: 105-543 days). We identified an association of N stage with increased risk of recurrence (hazard ratio = 3.85; P = 0.036) although this was not significant after accounting for multiple testing. CONCLUSIONS: Surveillance11 C-choline PET/CT can detect early disease relapse at serum PSA ≤0.1 ng/ml in patients with a history of BCR PCa.

Pitfalls of a Mixed Metabolic Response at PET/CT.

Although the term mixed metabolic response is commonly used in PET/CT reports, it should be a red flag to reconsider the assumptions made by the PET scan reader. Fluorine 18 fluorodeoxyglucose (FDG) PET/CT is recognized as an accurate imaging method for detecting response to cancer therapies. Critical clinical decisions regarding therapy are dependent on accurate interpretation of findings. The use of standardized terminology for response assessment, such as that in the Positron Emission Tomography Response Criteria in Solid Tumors (PERCIST), is highly recommended. With PERCIST, treatment response is categorized as complete metabolic response, partial metabolic response, stable metabolic disease, or progressive metabolic disease. Mixed metabolic response is not included in PERCIST. Rather, it is used colloquially to describe a scenario in which scanning performed after systemic cancer therapy reveals divergent findings, with some tumor foci responding and others not responding or even seen progressing. In PERCIST, mixed metabolic response should be described as stable metabolic disease or progressive metabolic disease. However, the PET/CT reader may also wish to suggest that individual tumors have heterogeneous genetic and/or other characteristics and consequently a mixed response to therapy. The concept of tumor heterogeneity is gaining momentum in cancer research and thus possibly leading to options for therapy targeted to oligometastases that are not responding. However, the authors suggest exercising extreme caution when PET/CT findings appear at first to reflect what some might call a mixed response. In addition, they have found that FDG PET/CT findings are often confounding owing to the simultaneous presence of two or more unrelated disease processes. Common examples include synchronous neoplasms, inflammatory processes, and treatment-related effects. Thus, an apparent mixed response is a red flag to reconsider whether all of the FDG-avid findings are actually metastases of the same cancer. Common mimics of a mixed metabolic response that do not represent true tumor heterogeneity are highlighted to improve the FDG PET/CT reader's recognition of these lesions.©RSNA, 2019.

Percutaneous Image-Guided Nodal Biopsy After 11C-Choline PET/CT for Biochemically Recurrent Prostate Cancer: Imaging Predictors of Disease and Clinical Implications.

PURPOSE: Management of recurrent prostate cancer necessitates timely diagnosis and accurate localization of the sites of recurrent disease. The purpose of this study was to assess predictors of histologic outcomes after 11C-choline positron emission tomography/computed tomography (CholPET) to increase the positive predictive value and specificity of CholPET in identifying imaging predictors of malignant and benign nodal disease to better inform clinical decision making regarding local therapy planning. MATERIALS AND METHODS: Retrospective review of patients undergoing CholPET followed by percutaneous core needle biopsy between January 1, 2010 and January 1, 2016. A total of 153 patients were identified who underwent 166 biopsy procedures. Patient, CholPET, procedural, and pathologic characteristics were recorded. RESULTS: A total of 157 biopsies were technically successful, and 110 (70.1%; 95% confidence interval, 62.2-77.1) yielded histologic results abnormal for metastatic prostate cancer. Lesion location, lesion maximum standardized uptake value (SUVmax), SUV ratio (calculated as the ratio of SUVmax to SUV mean in the right atrium), prostate-specific antigen, lesion short axis length, total Gleason score, and castration resistance were all associated with abnormal biopsy results (P values <.001, <.001, <.001, .02, .02, .02, and .015, respectively). External iliac, common iliac, and inguinal sites were associated with much lower rates of histologic positivity (mean [95% confidence interval], 51.2% [35.1-67.1], 46.2% [19.2-74.9], and 33.3% [7.5-70.1]), respectively. CONCLUSIONS: In a cohort of patients in whom core needle biopsy was performed after CholPET, characteristics of choline localization including node location, SUVmax, lesion-to-blood pool SUV ratio, prostate-specific antigen, total Gleason score, and castration resistance were significantly associated with abnormal biopsy results for metastatic disease on CholPET. Relatively high false positive rates were found in common iliac, external iliac, and inguinal lymph node locations. Histologic confirmation of these sites should be strongly considered in the appropriate clinical scenario before designing additional local therapy plans.

Multimodal Imaging Aids in the Diagnosis of Perineural Spread of Prostate Cancer.

BACKGROUND: The perineural spread of prostate cancer into pelvic peripheral nerves is a rare, but increasingly recognized, entity. This form of metastasis invades the lumbosacral plexus via the splanchnic nerves innervating the prostate. The prevalence of perineural spread is likely underappreciated, and further imaging-based studies are needed to elucidate its true frequency. METHODS: A retrospective review was performed using an institutional radiology database. Medical reports from patients with prostate cancer who had undergone positron emission tomography (PET) imaging were queried for terms suggestive of perineural spread. PET and magnetic resonance imaging (MRI) from the identified patients were blindly reviewed for peripheral nerve involvement by 2 nuclear medicine and 2 musculoskeletal radiologists. RESULTS: A total of 22 patients were identified. After review by the radiologists, 16 patients had positive findings of perineural spread found on PET and 15 had abnormalities found on MRI involving lumbosacral plexus neural elements. All patients with biopsy-proven neoplastic perineural spread (including 1 patient with malignant peripheral nerve sheath tumor) had positive findings on both PET and MRI. All patients with biopsy-proven inflammatory lesions had negative PET and variable MRI findings. CONCLUSIONS: The perineural spread of prostate cancer might be more common than previously thought. The use of multimodal imaging for patients suspected of having perineural spread should be a part of the treatment algorithm. Targeted fascicular biopsy might be indicated for patients with progressive neurological deficit and an unclear diagnosis.

ACR Appropriateness Criteria® First Trimester Vaginal Bleeding.

Vaginal bleeding is not uncommon in the first trimester of pregnancy. The majority of such patients will have a normal intrauterine pregnancy (IUP), a nonviable IUP, or an ectopic pregnancy. Ultrasound (US) is the primary imaging modality in evaluation of these patients. US, along with clinical observations and serum human chorionic gonadotropin levels, can usually distinguish these causes. Although it is important to diagnose ectopic pregnancies and nonviable IUPs, one should also guard against injury to normal pregnancies due to inappropriate treatment with methotrexate or surgical intervention. Less common causes of first trimester vaginal bleeding include gestational trophoblastic disease and arteriovenous malformations. Pulsed methods of Doppler US should generally be avoided in the first trimester when there is a normal, or a potentially normal, IUP. Once a normal IUP has been excluded, Doppler US may be useful when other diagnoses such as retained products of conception or arteriovenous malformations are suspected. MRI may occasionally be helpful as a problem-solving tool. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

18F-FDG PET response and clinical outcomes after stereotactic body radiation therapy for metastatic melanoma.

BACKGROUND: Clinical data that support stereotactic body radiation therapy (SBRT) metastatic malignant melanoma (MM) are limited. Furthermore, functional imaging with 18F-fludeoxyglucose positron emission tomography (PET) may offer a more accurate post-SBRT assessment. Therefore, we assessed the clinical outcomes and metabolic response of metastatic MM after SBRT. METHODS AND MATERIALS: Patients with MM who were treated with SBRT and had pre- and post-PET scans (>1) were included in this study. A total of 390 pre- and post-SBRT PET/computed tomography (CT) scans for 80 metastases were analyzed. The PET metabolic response was evaluated per the PET Response Criteria in Solid Tumors (PERCIST), version 1.0, criteria. Single-fraction equivalent dose (SFED) was calculated as per the standard. The Kaplan-Meier method was used for estimates of overall survival (OS) and progression-free survival. The cumulative incidence method was used to estimate metastasis control (MC). A Wilcoxon test was used to compare survival estimates. The prognostic factors for MC and OS were assessed using the Cox proportional hazards model, and the Likelihood Ratio was also used for comparisons between groups. RESULTS: A median of 6 PET scans (range, 2-6 scans) was evaluated for each metastasis. The median SFED was 42.8 Gy (range, 18-56.4 Gy) and the median biologically effective dose was 254.4 Gy2.5 (range, 100.8-540 Gy2.5). Twenty percent of patients received chemotherapy and 59% received immunotherapy: granulocyte-macrophage colony-stimulating factor (64%) and ipilimumab (34%). MC was 94% and 90% at 1 year and 3 years, respectively. The OS was 74% and 27% and 1 year and 3 years, respectively. Complete response was achieved in 90% at a median of 2.8 months (range, 0.4-25.2 months). SFED >24 Gy correlated with improved MC (93% vs 75%, P = .01). Acute and late grade 3+ toxicities were 4% and 11%, respectively, with no grade 5 toxicity. CONCLUSIONS: Post-SBRT PET/CT for extracranial metastatic MM resulted in high rates of complete response at a median of 2.8 months, and durable MC was achieved with SFED >24 Gy. SBRT, in addition to surgery and ablation, should be discussed with patients with MM, especially those with oligometastases.

FDG-PET parameters as predictors of pathologic response and nodal clearance in patients with stage III non-small cell lung cancer receiving neoadjuvant chemoradiation and surgery.

OBJECTIVE: Pathologic complete response (pCR) following neoadjuvant chemoradiation (CRT) is associated with improved outcomes in stage III non-small cell lung cancer. Conflicting results exist regarding the value of 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) in predicting pCR. This study evaluated the association between post-CRT FDG-PET and pCR using novel FDG-PET parameters. METHODS AND MATERIALS: This retrospective study included patients treated with CRT and resection. All underwent pre- and post-CRT FDG-PET imaging. Maximum standard uptake value (SUVmax), standard uptake ratio (SUR), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were measured. RESULTS: In total, 44 patients were included for review. The majority had cT2 disease (59.0%). Median radiation dose was 60 Gy (45-70.2 Gy). Rate of pCR and near-pCR within the primary lesion was 29.5% and 45.5%, respectively. Average reduction in SUVmax was 9.2, whereas SUR normalized to mediastinum and liver showed mean reductions of 4.7 and 3.5, respectively. No association was found between pCR and either MTV or TLG. Reduction in SUVmax and SUR were significantly associated with increased rate of pCR (P ≤ .02). A threshold of >75% decrease in SUR-liver showed significant association with near-pCR (diagnostic odds ratio [DOR]: 8.3; P = .007). No correlation was found between nodal FDG-PET parameters and nodal pCR. CONCLUSIONS: Our results indicate SUV and SUR have utility in predicting pCR after neoadjuvant CRT. SUR parameters trended toward higher DORs, suggesting improved predictive utility compared with SUVmax. Notably, no association was found with nodal pCR. Furthermore, MTV and TLG changes were not predictive, potentially resulting from inflammation after full-dose radiation, but this warrants further investigation.

Survival in Surgical and Nonsurgical Patients With Superior Sulcus Tumors.

BACKGROUND: Treatments for superior sulcus tumor (SST) have evolved, with induction chemoradiotherapy providing an improved R0 resection rate. We reviewed the treatment and outcomes of SSTs in a single institution to identify prognostic factors and optimal treatment strategy. METHODS: Details of patients who underwent any type of treatment for SST from 1997 through 2014 were retrospectively collected. Survival was calculated by the Kaplan-Meier method. Proportional hazards regression was used to test the prognostic significance of factors in univariate and multivariate models. RESULTS: Eighty-nine patients were identified, 8 of whom had M1 disease and were excluded from the analysis. Of the 48 surgical patients, 44 received preoperative induction treatments, with 12 (25%) achieving a pathologic complete response (pCR), 23 with minimal residual disease, and 9 with gross residual disease. Complete resection was achieved in 40 surgical cases. As expected, nonsurgical patients had worse survival than did surgical patients (median survival, 2.1 versus 5.8 years; nonsurgical versus surgical hazard ratio [HR], 2.1; 95% confidence interval [CI], 1.2-3.7; p = 0.01). By multivariable Cox analysis, smoking status (HR, 4.4; 95% CI, 1.5-13.0; p = 0.01) and previous or concurrent malignancy (HR, 4.73; 95% CI, 1.6-13.9; p = 0.0.005) were prognostic factors for surgical patients. There were no statistically significant prognostic factors for nonsurgical patients. CONCLUSIONS: Chemoradiotherapy followed by surgical treatment is our favored treatment for operable candidates. Preoperative induction treatments were associated with a 25% pCR rate for surgical patients. Candidates for surgical therapy are expected to have longer survival than those who are not candidates for resection.

Utility of PET/CT After Cryoablation for Early Identification of Local Tumor Progression in Osseous Metastatic Disease.

OBJECTIVE: The purpose of this study is to evaluate the utility of combined PET/CT for the detection of early local tumor progression after cryoablation of bone metastases. MATERIALS AND METHODS: A retrospective single-institution review revealed 61 consecutive patients with 80 separate bone metastases treated with cryoablation who were evaluated with a preablation PET/CT and at least two postablation PET/CT examinations between September 2007 and July 2015. Patients were excluded if they had local therapy or pathologic fracture after ablation. The patients were grouped according to postcryoablation disease status (i.e., local tumor progression or not) and PET radiotracer (i.e., 11C-choline or 18F-FDG) used. The maximum standardized uptake value (SUVmax) ratio (i.e., ratio of SUVmax to blood pool) was calculated within each osseous metastasis before and after cryoablation, and these were then compared between groups. RESULTS: Of the 61 patients and 80 ablations performed, 32 patients were imaged with FDG PET/CT and 29 were imaged with 11C-choline PET/CT. Twenty-three patients imaged with FDG and 13 patients imaged with 11C-choline had evidence of local tumor progression on all postablation PET/CT examinations. The SUVmax ratio was significantly higher in patients with local tumor progression on the first and most remote postcryoablation PET/CT examinations for both FDG and 11C-choline (p < 0.001 in all cases). There was no significant difference in the postablation systemic therapy between the groups with and without local tumor progression. CONCLUSION: Increased SUVmax ratio in patients after cryoablation for osseous metastatic disease should raise concern about local tumor progression independently of time after ablation.

Differential gene expression in primary human skin keratinocytes and fibroblasts in response to ionizing radiation.

Although skin is usually exposed during human exposures to ionizing radiation, there have been no thorough examinations of the transcriptional response of skin fibroblasts and keratinocytes to radiation. The transcriptional response of quiescent primary fibroblasts and keratinocytes exposed to from 10 cGy to 5 Gy and collected 4 h after treatment was examined. RNA was isolated and examined by microarray analysis for changes in the levels of gene expression. Exposure to ionizing radiation altered the expression of 279 genes across both cell types. Changes in RNA expression could be arranged into three main categories: (1) changes in keratinocytes but not in fibroblasts, (2) changes in fibroblasts but not in keratinocytes, and (3) changes in both. All of these changes were primarily of p53 target genes. Similar radiation-induced changes were induced in immortalized fibroblasts or keratinocytes. In separate experiments, protein was collected and analyzed by Western blotting for expression of proteins observed in microarray experiments to be overexpressed at the mRNA level. Both Q-PCR and Western blot analysis experiments validated these transcription changes. Our results are consistent with changes in the expression of p53 target genes as indicating the magnitude of cell responses to ionizing radiation.