Early Prediction of Response of Hepatocellular Carcinoma to Yttrium-90 Radiation Segmentectomy Using a Machine Learning MR Imaging Radiomic Approach.

PURPOSE: To assess the accuracy of a machine learning (ML) approach based on magnetic resonance (MR) imaging radiomic quantification obtained before treatment and early after treatment for prediction of early hepatocellular carcinoma (HCC) response to yttrium-90 transarterial radioembolization (TARE). MATERIALS AND METHODS: In this retrospective single-center study of 76 patients with HCC, baseline and early (1-2 months) post-TARE MR images were collected. Semiautomated tumor segmentation facilitated extraction of shape, first-order histogram, and custom signal intensity-based radiomic features, which were then trained (n = 46) using a ML XGBoost model and validated on a separate cohort (n = 30) not used in training to predict treatment response assessed at 4-6 months (based on modified Response and Evaluation Criteria in Solid Tumors criteria). Performance of this ML radiomic model was compared with those of models comprising clinical parameters and standard imaging characteristics using area under the receiver operating curve (AUROC) analysis for prediction of complete response (CR). RESULTS: Seventy-six tumors with a mean (±SD) diameter of 2.6 cm ± 1.6 were included. Sixty, 12, 1, and 3 patients were classified as having CR, partial response, stable disease, and progressive disease, respectively, at 4-6 months posttreatment on the basis of MR images. In the validation cohort, the radiomic model showed good performance (AUROC, 0.89) for prediction of CR, compared with models comprising clinical and standard imaging criteria (AUROC, 0.58 and 0.59, respectively). Baseline imaging features appeared to be more heavily weighted in the radiomic model. CONCLUSIONS: The use of ML modeling of radiomic data combining baseline and early follow-up MR imaging could predict HCC response to TARE. These models need to be investigated further in an independent cohort.

Multi-timepoint imaging with PSMA-targeted [18F]F-Florastamin PET/CT: lesion detection and comparison to conventional imaging.

OBJECTIVE: The aims of this study were to investigate the utility of [18F]F-Florastamin, a novel prostate-specific membrane antigen (PSMA)-targeted PET radiotracer with facile radiochemistry, relative to the conventional imaging for the detection of sties of disease and evaluate the effect of multi-timepoint imaging with [18F]F-Florastamin PET on lesion detectability. METHODS: Eight prostate cancer patients with known or suspected recurrence who underwent [18F]F-Florastamin PET/CT at 1-h and 2-h imaging time-points were included in this prospective pilot study. [18F]F-Florastamin PET images were interpreted visually and quantitatively at both time points and compared with CIM. RESULTS: [18F]F-Florastamin PET was superior to CT in the detection of active osseous metastases and small-sized metastatic lymph nodes that do not fall under the anatomic imaging size criteria for metastasis. Multi-timepoint imaging showed a significant reduction in the blood pool, bone marrow and muscular uptake, and increase in liver uptake over time. There is a significant improvement in tumor-to-background ratio (TBR) at the 2-h imaging time-point (P = 0.04). The mean percentage change in TBR at 2-h was 21% (SD = 0.31). CONCLUSIONS: [18F]F-Florastamin is a promising new radioligand for PSMA-targeted PET with suitable lesion detectability and high TBR at both time points.

Asymptomatic SARS-CoV-2 infection: Incidental findings on FDG PET/CT.

RATIONALE AND OBJECTIVES: Identify the incidental findings of Covid-19 pneumonitis on 18F-FDG PET/CT scan in asymptomatic oncologic patients. The goal was to detect clinically unsuspected Covid-19 infections to prevent community spread. MATERIALS AND METHODS: Retrospective analysis was conducted to recognize the pattern of metabolic and radiographic alterations on 18F-FDG PET/CT scans in Covid-19 patients. 492 18F-FDG PET/CT scans were reviewed for pulmonary and systemic abnormalities. RESULTS: 18F-FDG PET/CT demonstrated new lung infiltrates in 29 asymptomatic patients. 13/29 patients had Covid-19 infection confirmed by nasopharyngeal nucleic acid PCR test. The most common lung abnormality was pure ground-glass opacity (GGO) (90%) in peripheral distribution (100%), involving 1 lobe in four patients (30.8%), 2-3 lobes in four patients, and 4-5 lobes in five patients (38.4%). Mean SUVmax was 4.7 (range 1.3-13.1). Ten patients developed symptoms, mainly fever, fatigue, and dry cough, within 6.4 ± 7.8 days (range 1-24). Of the available laboratory data of 12 patients, eight developed lymphopenia, and five patients had neutrophilia. Five patients required hospitalization, and two died of complications. CONCLUSION: For a given geographic region in the later stage of a pandemic, such as Covid-19, community spread of the disease is common. Therefore, it is not surprising to find it in asymptomatic being imaged for other indications. Recognition of its manifestation and effectively mounting mitigation protocols is essential to further reduce SARS-CoV-2 spread, especially to susceptible groups, predominantly the elderly and people with comorbidities.