AmyloidPETNet: Classification of Amyloid Positivity in Brain PET Imaging Using End-to-End Deep Learning.

Background Visual assessment of amyloid PET scans relies on the availability of radiologist expertise, whereas quantification of amyloid burden typically involves MRI for processing and analysis, which can be computationally expensive. Purpose To develop a deep learning model to classify minimally processed brain PET scans as amyloid positive or negative, evaluate its performance on independent data sets and different tracers, and compare it with human visual reads. Materials and Methods This retrospective study used 8476 PET scans (6722 patients) obtained from late 2004 to early 2023 that were analyzed across five different data sets. A deep learning model, AmyloidPETNet, was trained on 1538 scans from 766 patients, validated on 205 scans from 95 patients, and internally tested on 184 scans from 95 patients in the Alzheimer's Disease Neuroimaging Initiative (ADNI) fluorine 18 (18F) florbetapir (FBP) data set. It was tested on ADNI scans using different tracers and scans from independent data sets. Scan amyloid positivity was based on mean cortical standardized uptake value ratio cutoffs. To compare with model performance, each scan from both the Centiloid Project and a subset of the Anti-Amyloid Treatment in Asymptomatic Alzheimer's Disease (A4) study were visually interpreted with a confidence level (low, intermediate, high) of amyloid positivity/negativity. The area under the receiver operating characteristic curve (AUC) and other performance metrics were calculated, and Cohen κ was used to measure physician-model agreement. Results The model achieved an AUC of 0.97 (95% CI: 0.95, 0.99) on test ADNI 18F-FBP scans, which generalized well to 18F-FBP scans from the Open Access Series of Imaging Studies (AUC, 0.95; 95% CI: 0.93, 0.97) and the A4 study (AUC, 0.98; 95% CI: 0.98, 0.98). Model performance was high when applied to data sets with different tracers (AUC ≥ 0.97). Other performance metrics provided converging evidence. Physician-model agreement ranged from fair (Cohen κ = 0.39; 95% CI: 0.16, 0.60) on a sample of mostly equivocal cases from the A4 study to almost perfect (Cohen κ = 0.93; 95% CI: 0.86, 1.0) on the Centiloid Project. Conclusion The developed model was capable of automatically and accurately classifying brain PET scans as amyloid positive or negative without relying on experienced readers or requiring structural MRI. Clinical trial registration no. NCT00106899 © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Bryan and Forghani in this issue.

New horizon of radiopharmaceuticals in management of neuroendocrine tumors.

Neuroendocrine neoplasms are rare and heterogenous group of tumors with varying degrees of clinical presentations and involvement of multiple organ systems in the body. In the modern clinical practice somatostatin receptor molecular imaging and targeted radioligand therapy plays a vital role in the diagnosis and management of the disease. Several new and promising radiotracers for NET imaging and theranostics, belonging to various groups and classes are being studied and investigated. This exponential growth of radiotracers poses concerns about the indication, clinical benefit, and safety profile of the agents. We discuss the basis behind these radiotracers clinical use, receptor targeting and intra and inter tumor heterogeneity. Furthermore, role of dual tracer imaging, combination therapy and potential applications of dosimetry in predicting treatment outcome and safety profile is reviewed. Individualized precision medicine with better tumor characterization, maximum therapeutic benefit and minimum toxicity is the way forward for future medicine.

Use of 18 F-PSMA PET to Distinguish Cerebral Radiation Necrosis From Tumor Recurrence.

ABSTRACT: Brain metastasis in prostate adenocarcinoma is extremely rare and usually arises in the setting of widespread osseous and visceral metastases. Surgical resection and radiation therapy, including stereotactic radiosurgery, are the mainstays of treatment for brain metastasis. Radiation necrosis is a common complication of radiotherapy for brain metastasis, and distinguishing it from tumor recurrence by MRI is difficult because of overlapping findings. We present a 73-year-old man with prostate cancer with a solitary brain metastasis where PET with 18 F-piflufolostat helped detect disease recurrence in the setting of ambiguous MRI findings.

Comparing Tau PET Visual Interpretation with Tau PET Quantification, Cerebrospinal Fluid Biomarkers, and Longitudinal Clinical Assessment.

BACKGROUND: 18F-flortaucipir PET received FDA approval to visualize aggregated neurofibrillary tangles (NFTs) in brains of adult patients with cognitive impairment being evaluated for Alzheimer's disease (AD). However, manufacturer's guidelines for visual interpretation of 18F-flortaucipir PET differ from how 18F-flortaucipir PET has been measured in research settings using standardized uptake value ratios (SUVRs). How visual interpretation relates to 18F-flortaucipir PET SUVR, cerebrospinal fluid (CSF) biomarkers, or longitudinal clinical assessment is not well understood. OBJECTIVE: We compare various diagnostic methods in participants enrolled in longitudinal observational studies of aging and memory (n = 189, 23 were cognitively impaired). METHODS: Participants had tau PET, Aß PET, MRI, and clinical and cognitive evaluation within 18 months (n = 189); the majority (n = 144) also underwent lumbar puncture. Two radiologists followed manufacturer's guidelines for 18F-flortaucipir PET visual interpretation. RESULTS: Visual interpretation had high agreement with SUVR (98.4%)and moderate agreement with CSF p-tau181 (86.1%). Two participants demonstrated 18F-flortaucipir uptake from meningiomas. Visual interpretation could not predict follow-up clinical assessment in 9.52% of cases. CONCLUSION: Visual interpretation was highly consistent with SUVR (discordant participants had hemorrhagic infarcts or occipital-predominant AD NFT deposition) and moderately consistent with CSF p-tau181 (discordant participants had AD pathophysiology not detectable on tau PET). However, close association between AD NFT deposition and clinical onset in group-level studies does not necessarily hold at the individual level, with discrepancies arising from atypical AD, vascular dementia, or frontotemporal dementia. A better understanding of relationships across imaging, CSF biomarkers, and clinical assessment is needed to provide appropriate diagnoses for these individuals.

Heterogeneity Diffusion Imaging of gliomas: Initial experience and validation.

OBJECTIVES: Primary brain tumors are composed of tumor cells, neural/glial tissues, edema, and vasculature tissue. Conventional MRI has a limited ability to evaluate heterogeneous tumor pathologies. We developed a novel diffusion MRI-based method-Heterogeneity Diffusion Imaging (HDI)-to simultaneously detect and characterize multiple tumor pathologies and capillary blood perfusion using a single diffusion MRI scan. METHODS: Seven adult patients with primary brain tumors underwent standard-of-care MRI protocols and HDI protocol before planned surgical resection and/or stereotactic biopsy. Twelve tumor sampling sites were identified using a neuronavigational system and recorded for imaging data quantification. Metrics from both protocols were compared between World Health Organization (WHO) II and III tumor groups. Cerebral blood volume (CBV) derived from dynamic susceptibility contrast (DSC) perfusion imaging was also compared with the HDI-derived perfusion fraction. RESULTS: The conventional apparent diffusion coefficient did not identify differences between WHO II and III tumor groups. HDI-derived slow hindered diffusion fraction was significantly elevated in the WHO III group as compared with the WHO II group. There was a non-significantly increasing trend of HDI-derived tumor cellularity fraction in the WHO III group, and both HDI-derived perfusion fraction and DSC-derived CBV were found to be significantly higher in the WHO III group. Both HDI-derived perfusion fraction and slow hindered diffusion fraction strongly correlated with DSC-derived CBV. Neither HDI-derived cellularity fraction nor HDI-derived fast hindered diffusion fraction correlated with DSC-derived CBV. CONCLUSIONS: Conventional apparent diffusion coefficient, which measures averaged pathology properties of brain tumors, has compromised accuracy and specificity. HDI holds great promise to accurately separate and quantify the tumor cell fraction, the tumor cell packing density, edema, and capillary blood perfusion, thereby leading to an improved microenvironment characterization of primary brain tumors. Larger studies will further establish HDI's clinical value and use for facilitating biopsy planning, treatment evaluation, and noninvasive tumor grading.

A Role of PET Agents Beyond FDG in Gynecology.

Gynecologic cancers comprise a varied group of malignancies with diverse clinical presentations and prognosis. Positron emission tomography (PET) with [18F]fluorodeoxyglucose (FDG), the most commonly used functional imaging for staging, treatment planning, and therapy response evaluation in gynecological cancers, is limited in providing information about the unique biological features of these tumors. There is an increasing need to noninvasively determine the patient's distinct tumor biological features in order to select the most appropriate therapy. This article presents an overview of the key PET biomarkers other than FDG that have been used for imaging of the three most common gynecological malignancies; cervical, endometrial, and ovarian cancers. These functional molecular imaging applications by PET have the potential to be translated to clinical practice for more complete evaluations of these cancers.

18F-FDOPA PET/MRI for monitoring early response to bevacizumab in children with recurrent brain tumors.

BACKGROUND: Noninvasively predicting early response to therapy in recurrent pediatric brain tumors provides a challenge. 3,4-dihydroxy-6-[18F]fluoro-L-phenylalanine (18F-FDOPA) PET/MRI has not been previously studied as a tool to evaluate early response to antiangiogenic therapy in children. The purpose of this study was to evaluate the safety and feasibility of using 18F-FDOPA PET/MRI to assess response to bevacizumab in children with relapsed brain tumors. MATERIALS AND METHODS: Six patients with recurrent gliomas (5 low-grade, 1 high-grade) planned to undergo treatment with bevacizumab were enrolled. 18F-FDOPA PET/MRI scans were obtained prior to and 4 weeks following the start of treatment, and these were compared with the clinical response determined at the 3-month MRI. The primary PET measure was metabolic tumor volume (MTV) at 10 to 15 min after 18F-FDOPA injection. For each tumor, the MTV was determined by manually defining initial tumor volumes of interest (VOI) and then applying a 1.5-fold threshold relative to the mean standardized uptake value (SUV) of a VOI in the frontal lobe contralateral to the tumor. RESULTS: 18F-FDOPA PET/MRI was well tolerated by all patients. All tumors were well visualized with 18F-FDOPA on the initial study, with peak tumor uptake occurring approximately 10 min after injection. Maximum and mean SUVs as well as tumor-to-brain ratios were not predictors of response at 3 months. Changes in MTVs after therapy ranged from 23% to 98% (n = 5). There is a trend towards the percent MTV change seen on the 4-week scan correlating with progression-free survival. CONCLUSION: 18F-FDOPA PET/MRI was well tolerated in pediatric patients and merits further investigation as an early predictor of response to therapy.

Multiparametric MRI and [18F]Fluorodeoxyglucose Positron Emission Tomography Imaging Is a Potential Prognostic Imaging Biomarker in Recurrent Glioblastoma.

PURPOSE/OBJECTIVES: Multiparametric advanced MR and [18F]fluorodeoxyglucose (FDG)-positron emission tomography (PET) imaging may be important biomarkers for prognosis as well for distinguishing recurrent glioblastoma multiforme (GBM) from treatment-related changes. METHODS/MATERIALS: We retrospectively evaluated 30 patients treated with chemoradiation for GBM and underwent advanced MR and FDG-PET for confirmation of tumor progression. Multiparametric MRI and FDG-PET imaging metrics were evaluated for their association with 6-month overall (OS) and progression-free survival (PFS) based on pathological, radiographic, and clinical criteria. RESULTS: 17 males and 13 females were treated between 2001 and 2014, and later underwent FDG-PET at suspected recurrence. Baseline FDG-PET and MRI imaging was obtained at a median of 7.5 months [interquartile range (IQR) 3.7-12.4] following completion of chemoradiation. Median follow-up after FDG-PET imaging was 10 months (IQR 7.2-13.0). Receiver-operator characteristic curve analysis identified that lesions characterized by a ratio of the SUVmax to the normal contralateral brain (SUVmax/NB index) >1.5 and mean apparent diffusion coefficient (ADC) value of ≤1,400 × 10-6 mm2/s correlated with worse 6-month OS and PFS. We defined three patient groups that predicted the probability of tumor progression: SUVmax/NB index >1.5 and ADC ≤1,400 × 10-6 mm2/s defined high-risk patients (n = 7), SUVmax/NB index ≤1.5 and ADC >1,400 × 10-6 mm2/s defined low-risk patients (n = 11), and intermediate-risk (n = 12) defined the remainder of the patients. Median OS following the time of the FDG-PET scan for the low, intermediate, and high-risk groups were 23.5, 10.5, and 3.8 months (p < 0.01). Median PFS were 10.0, 4.4, and 1.9 months (p = 0.03). Rates of progression at 6-months in the low, intermediate, and high-risk groups were 36, 67, and 86% (p = 0.04). CONCLUSION: Recurrent GBM in the molecular era is associated with highly variable outcomes. Multiparametric MR and FDG-PET biomarkers may provide a clinically relevant, non-invasive and cost-effective method of predicting prognosis and improving clinical decision making in the treatment of patients with suspected tumor recurrence.

The Emerging Role of PET/MR Imaging in Gynecologic Cancers.

This article summarizes recent advances in PET/MR imaging in gynecologic cancers and the emerging clinical value of PET/MR imaging in the management of the 3 most common gynecologic malignancies: cervical, endometrial, and ovarian cancers. PET/MR imaging offers superior soft tissue contrast, improved assessment of primary tumor involvement because of high-resolution multiplanar reformats, and functional MR techniques such as diffusion-weighted MR imaging and dynamic contrast-enhanced MR imaging. This article discusses the challenges, future directions, and technical advances of PET/MR imaging, and the emerging new multimodality, multiparametric imaging techniques for integrating morphologic, functional, and molecular imaging data.

Evaluation of diagnostic performance of whole-body simultaneous PET/MRI in pediatric lymphoma.

BACKGROUND: Whole-body (18)F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) is the standard of care for lymphoma. Simultaneous PET/MRI (magnetic resonance imaging) is a promising new modality that combines the metabolic information of PET with superior soft-tissue resolution and functional imaging capabilities of MRI while decreasing radiation dose. There is limited information on the clinical performance of PET/MRI in the pediatric setting. OBJECTIVE: This study evaluated the feasibility, dosimetry, and qualitative and quantitative diagnostic performance of simultaneous whole-body FDG-PET/MRI in children with lymphoma compared to PET/CT. MATERIALS AND METHODS: Children with lymphoma undergoing standard of care FDG-PET/CT were prospectively recruited for PET/MRI performed immediately after the PET/CT. Images were evaluated for quality, lesion detection and anatomical localization of FDG uptake. Maximum and mean standardized uptake values (SUVmax/mean) of normal organs and SUVmax of the most FDG-avid lesions were measured for PET/MRI and PET/CT. Estimation of radiation exposure was calculated using specific age-related factors. RESULTS: Nine PET/MRI scans were performed in eight patients (mean age: 15.3 years). The mean time interval between PET/CT and PET/MRI was 51 ± 10 min. Both the PET/CT and PET/MRI exams had good image quality and alignment with complete (9/9) concordance in response assessment. The SUVs from PET/MRI and PET/CT were highly correlated for normal organs (SUVmean r(2): 0.88, P<0.0001) and very highly for FDG-avid lesions (SUVmax r(2): 0.94, P=0.0002). PET/MRI demonstrated an average percent radiation exposure reduction of 39% ± 13% compared with PET/CT. CONCLUSION: Simultaneous whole-body PET/MRI is clinically feasible in pediatric lymphoma. PET/MRI performance is comparable to PET/CT for lesion detection and SUV measurements. Replacement of PET/CT with PET/MRI can significantly decrease radiation dose from diagnostic imaging in children.