Validation of automated whole-body analysis of metabolic and morphological parameters from an integrated FDG-PET/MRI acquisition

Imaging modalities for measuring body composition in patients with cancer: opportunities and challenges

Body composition assessment (ie, the measurement of muscle and adiposity) impacts several cancer-related outcomes including treatment-related toxicities, treatment responses, complications, and prognosis. Traditional modalities for body composition measurement include body mass index, body circumference, skinfold thickness, and bioelectrical impedance analysis; advanced imaging modalities include dual energy x-ray absorptiometry, computerized tomography, magnetic resonance imaging, and positron emission tomography. Each modality has its advantages and disadvantages, thus requiring an individualized approach in identifying the most appropriate measure for specific clinical or research situations. Advancements in imaging approaches have led to an abundance of available data, however, the lack of standardized thresholds for classification of abnormal muscle mass or adiposity has been a barrier to adopting these measurements widely in research and clinical care. In this review, we discuss the different modalities in detail and provide guidance on their unique opportunities and challenges.

The utilization of positron emission tomography in the evaluation of renal health and disease

Purpose

Positron emission tomography (PET) is a nuclear imaging technique that uses radiotracers to visualize metabolic processes of interest across different organs, to diagnose and manage diseases, and monitor therapeutic response. This systematic review aimed to characterize the value of PET for the assessment of renal metabolism and function in subjects with non-oncological metabolic disorders.

Methods

This review was conducted and reported in accordance with the PRISMA statement. Research articles reporting “kidney” or “renal” metabolism evaluated with PET imaging between 1980 and 2021 were systematically searched in Medline/PubMed, Science Direct, and the Cochrane Library. Search results were exported and stored in RefWorks, the duplicates were removed, and eligible studies were identified, evaluated, and summarized.

Results

Thirty reports met the inclusion criteria. The majority of the studies were prospective (73.33%, n = 22) in nature. The most utilized PET radiotracers were 15O-labeled radio water (H215O, n = 14) and 18F-fluorodeoxyglucose (18F-FDG, n = 8). Other radiotracers used in at least one study were 14(R,S)-(18)F-fluoro-6-thia-heptadecanoic acid (18F-FTHA), 18F-Sodium Fluoride (18F-NaF), 11C-acetate, 68-Gallium (68Ga), 13N-ammonia (13N-NH3), Rubidium-82 (82Rb), radiolabeled cationic ferritin (RadioCF), 11C‐para-aminobenzoic acid (11C-PABA), Gallium-68 pentixafor (68Ga-Pentixafor), 2-deoxy-2-F-fluoro-d-sorbitol (F-FDS) and 55Co-ethylene diamine tetra acetic acid (55Co-EDTA).

Conclusion

PET imaging provides an effective modality for evaluating a range of metabolic functions including glucose and fatty acid uptake, oxygen consumption and renal perfusion. Multiple positron emitting radiolabeled racers can be used for renal imaging in clinical settings. PET imaging thus holds the potential to improve the diagnosis of renal disorders, and to monitor disease progression and treatment response.

Classification of Myocardial 18F-FDG PET Uptake Patterns Using Deep Learning

Purpose

To perform automated myocardial segmentation and uptake classification from whole-body fluorine 18 fluorodeoxyglucose (FDG) PET.

Materials and Methods

In this retrospective study, consecutive patients who underwent FDG PET imaging for oncologic indications were included (July-August 2018). The left ventricle (LV) on whole-body FDG PET images was manually segmented and classified as showing no myocardial uptake, diffuse uptake, or partial uptake. A total of 609 patients (mean age, 64 years ± 14 [standard deviation]; 309 women) were included and split between training (60%, 365 patients), validation (20%, 122 patients), and testing (20%, 122 patients) datasets. Two sequential neural networks were developed to automatically segment the LV and classify the myocardial uptake pattern using segmentation and classification training data provided by human experts. Linear regression was performed to correlate findings from human experts and deep learning. Classification performance was evaluated using receiver operating characteristic (ROC) analysis.

Results

There was moderate agreement of uptake pattern between experts and deep learning (as a fraction of correctly categorized images) with 78% (36 of 46) for no uptake, 71% (34 of 48) for diffuse uptake, and 71% (20 of 28) for partial uptake. There was no bias in LV volume for partial or diffuse uptake categories (P = .56); however, deep learning underestimated LV volumes in the no uptake category. There was good correlation for LV volume (R ² = 0.35, b = .71). ROC analysis showed the area under the curve for classifying no uptake and diffuse uptake was high (> 0.90) but lower for partial uptake (0.77). The feasibility of a myocardial uptake index (MUI) for quantifying the degree of myocardial activity patterns was shown, and there was excellent visual agreement between MUI and uptake patterns.

Conclusion

Deep learning was able to segment and classify myocardial uptake patterns on FDG PET images.Keywords: PET, Heart, Computer Aided Diagnosis, Computer Application-Detection/DiagnosisSupplemental material is available for this article.©RSNA, 2021.