Burkett, Brian

Abstract INTRODUCTION Alzheimer's disease neuropathologic change (ADNC) classification identifies not/low and intermediate/high levels of neuropathology. Our goal was to assess how frequently a positive amyloid positron emission tomography (PET) scan indicates not/low ADNC and whether this autopsy finding can occur >10 years after a positive amyloid PET. METHODS Participants with positive amyloid PET scans were categorized by levels of ADNC at autopsy, grouped by time from initial positive amyloid PET to time of death (<5 years, 5 to <10 years, or 10+ years). RESULTS Among those with a positive amyloid PET scan, the majority had intermediate/high ADNC at autopsy (234/259, 90%). In the group with 10+ years between a positive amyloid PET and death ( n = 39) not/low ADNC occurred in 3/39 (8%). DISCUSSION Not/low ADNC is uncommon among those with positive amyloid PET scans. After 10+ years, it is possible but rare for a positive amyloid PET scan to represent an indolent state of neuropathology.

Abstract In epilepsy patients lacking magnetic resonance imaging‐visible lesions such as focal cortical dysplasia (FCD), surgical resections target regions with abnormal electroencephalographic (EEG) activity. However, histopathological identification of subtle cortical architectural abnormalities in these specimens remains challenging. We investigated whether artificial intelligence (AI)‐based morphometric and spatial analysis of NeuN‐stained cortical sections could detect neuronal architectural disorganization in epilepsy resections, including regions without definitive histologic dysplasia. Whole slide images were generated from 83 FCD regions and 19 neurologically normal autopsy controls. Regions of interest were annotated in QuPath as FCD, FCD‐adjacent, FCD‐distant, apparently normal (abnormal EEG without histologic dysplasia), and true normal (autopsy controls). NeuN‐positive neurons were detected using QuPath (90% sensitivity, 12% false positive rate). Spatial and morphometric features—including neuronal clustering, distribution inhomogeneity, and nuclear morphology—were extracted and used to train a multinomial, Least Absolute Shrinkage and Selection Operator‐regularized regression classifier. The classifier achieved 70.6% accuracy in subregion classification and 88.2% accuracy in overall specimen diagnosis. Notably, regions with abnormal EEG but lacking histologic dysplasia exhibited quantifiable architectural disorganization similar to those seen in areas adjacent to FCD and distinct from control tissue. AI‐driven analysis of neuronal morphology and spatial distribution reveals subtle cortical disorganization in epilepsy resections, including in histologically ambiguous regions. Further investigation is warranted to determine if this methodology can enhance the diagnostic yield of neuropathological evaluation and support more precise surgical targeting in epilepsy.

Abstract 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.

Positron emission tomography (PET) imaging in prostate cancer has advanced significantly in the past decade with prostate cancer targeted radiopharmaceuticals now playing a growing role in diagnosis, staging, and treatment. This narrative review focuses on the most commonly used PET radiopharmaceuticals in the USA: prostate-specific membrane antigen (PSMA), fluciclovine, and choline. 18F-fluorodeoxyglucose (FDG) is used in many other malignancies, but rarely in prostate cancer. Previous literature is discussed regarding each radiopharmaceutical’s utility in the settings of screening/diagnosis, initial staging, biochemical recurrence, advanced disease, and evaluation prior to targeted radiopharmaceutical therapy and radiation therapy. PET imaging has demonstrated utility over traditional imaging in various scenarios; however, there are few head-to-head studies comparing PET radiopharmaceuticals. PSMA radiopharmaceuticals are the newest tracers developed and have unique properties and uses, especially at low prostate-specific antigen (PSA) levels. However, each PET radiopharmaceutical has different properties which can affect image interpretation. Choline and fluciclovine have minimal urinary activity, whereas PSMA agents can have high urinary activity which may affect locoregional disease evaluation. Of the three radiopharmaceuticals, only PSMA is approved for both diagnostic and therapeutic indications with 177 Lu-PSMA. A variety of diagnostic PET radiotracers for prostate cancer allows for increased flexibility, especially in the setting of supply chain and medication shortages. For the time being, keeping a diverse group of PET radiopharmaceuticals for prostate cancer is justifiable.

Abstract Given the prevalence of dementia and the development of pathology-specific disease-modifying therapies, high-value biomarker strategies to inform medical decision-making are critical. In vivo tau-PET is an ideal target as a biomarker for Alzheimer’s disease diagnosis and treatment outcome measure. However, tau-PET is not currently widely accessible to patients compared to other neuroimaging methods. In this study, we present a convolutional neural network (CNN) model that imputes tau-PET images from more widely available cross-modality imaging inputs. Participants (n = 1192) with brain T1-weighted MRI (T1w), fluorodeoxyglucose (FDG)-PET, amyloid-PET and tau-PET were included. We found that a CNN model can impute tau-PET images with high accuracy, the highest being for the FDG-based model followed by amyloid-PET and T1w. In testing implications of artificial intelligence-imputed tau-PET, only the FDG-based model showed a significant improvement of performance in classifying tau positivity and diagnostic groups compared to the original input data, suggesting that application of the model could enhance the utility of the metabolic images. The interpretability experiment revealed that the FDG- and T1w-based models utilized the non-local input from physically remote regions of interest to estimate the tau-PET, but this was not the case for the Pittsburgh compound B-based model. This implies that the model can learn the distinct biological relationship between FDG-PET, T1w and tau-PET from the relationship between amyloid-PET and tau-PET. Our study suggests that extending neuroimaging’s use with artificial intelligence to predict protein specific pathologies has great potential to inform emerging care models.

AbstractPurposeDental amalgam contains mercury and is commonly used in dental restorations. The impact of MRI on mercury excretion from dental amalgam is not well understood across clinical field strengths, especially 7T. We investigated the effects of MRI exposure on mercury excretion using fresh, lab‐created dental amalgam restorations and in extracted teeth with old, pre‐existing restorations.MethodsDonated, unfilled human teeth (n = 120) were restored with amalgam before being stored in saline, artificial saliva, or a dry box prior to MRI scanning. The teeth were placed in individual tubes of fresh artificial saliva and scanned at 1.5T, 3T, or 7T or left unscanned as controls. Mercury concentrations were measured 24–30 h later. Donated teeth with pre‐existing restorations (n = 40) were stored in artificial saliva, scanned at 7T or left unscanned as controls, and mercury concentration tested.ResultsFor teeth extracted and restored in a laboratory, no significant difference was found (F = 2.42, P = 0.072) between mean mercury concentrations of unscanned teeth (13.72 μg/L) and teeth scanned at 1.5T (10.88 μg/L), 3T (12.65 μg/L), or 7T (8.88 μg/L). For teeth extracted with previously placed restorations, no significant difference (P = 0.288) was found between unscanned controls (4.28 μg/L) and teeth scanned at 7T (6.63 μg/L).ConclusionMRI of dental amalgam does not significantly increase mercury excretion at 1.5T, 3T, or 7T compared to unscanned teeth. This holds true for controlled laboratory restorations as well as for those placed and lived with prior to extraction and scanning, demonstrating no added risk to the clinical patient or research subject.