Early prediction of distant metastasis in patients with uterine cervical cancer treated with definitive chemoradiotherapy by deep learning using pretreatment [ 18 F]fluorodeoxyglucose positron emission tomography/computed tomography.

OBJECTIVES: A deep learning (DL) model using image data from pretreatment [ 18 F]fluorodeoxyglucose ([ 18 F] FDG)-PET or computed tomography (CT) augmented with a novel imaging augmentation approach was developed for the early prediction of distant metastases in patients with locally advanced uterine cervical cancer. METHODS: This study used baseline [18F]FDG-PET/CT images of newly diagnosed uterine cervical cancer patients. Data from 186 to 25 patients were analyzed for training and validation cohort, respectively. All patients received chemoradiotherapy (CRT) and follow-up. PET and CT images were augmented by using three-dimensional techniques. The proposed model employed DL to predict distant metastases. Receiver operating characteristic (ROC) curve analysis was performed to measure the model's predictive performance. RESULTS: The area under the ROC curves of the training and validation cohorts were 0.818 and 0.830 for predicting distant metastasis, respectively. In the training cohort, the sensitivity, specificity, and accuracy were 80.0%, 78.0%, and 78.5%, whereas, the sensitivity, specificity, and accuracy for distant failure were 73.3%, 75.5%, and 75.2% in the validation cohort, respectively. CONCLUSION: Through the use of baseline [ 18 F]FDG-PET/CT images, the proposed DL model can predict the development of distant metastases for patients with locally advanced uterine cervical cancer treatment by CRT. External validation must be conducted to determine the model's predictive performance.

Statin and the Risk of Ischemic Stroke or Transient Ischemic Attack in Head and Neck Cancer Patients with Radiotherapy / 대한뇌졸중학회지

No abstract available.

Utility of 18F-FDG uptake in various regions of Waldeyer's ring to differentiate benign from malignant lesions in the midline roof of the nasopharynx.

PURPOSE: Lymphoid hyperplasia is not uncommon in the midline roof of the nasopharynx. Most nasopharyngeal carcinoma patients present with primary tumors in the midline of the nasopharynx. The aim of this study was to evaluate the efficacy of 2-[fluorine-18] fluoro-2-deoxy-D-glucose ((18)F-FDG) PET/computed tomography (CT) to differentiate between benign and malignant lesions in the midline roof of the nasopharynx. MATERIALS AND METHODS: The data from the (18)F-FDG PET/CT images of 4846 participants were analyzed. Visual uptake, the lesions' standard uptake values (SUVs), and any abnormalities on the PET/CT images were evaluated. RESULTS: Sixty-six individuals with benign lesions and 25 with nasopharyngeal carcinoma were included in the analysis. The participants with benign and malignant lesions displayed increased (18)F-FDG uptake (SUV; mean±SD) in the midline roof of the nasopharynx (4.16±1.92 and 6.65±2.81, respectively), with SUVs significantly differing between the two types of lesions (P<0.001). An associated increased (18)F-FDG uptake in Waldeyer's ring and the salivary glands occurred in benign but not in malignant lesions. The ratio of uptake in the midline roof of the nasopharynx and the palatine tonsil in the benign lesions (0.92±0.42) was significantly lower than that in the malignant lesions (1.76±0.93) (P<0.001). CONCLUSION: The analysis of the intensity and patterns of (18)F-FDG uptake in various regions of Waldeyer's ring provides a feasible modality for the differentiation between benign lesions and malignant nasopharyngeal midline roof lesions.

FDG PET or PET/CT in Evaluation of Renal Angiomyolipoma

OBJECTIVE: Angiomyolipoma is the most common benign kidney tumor. However, literature describing FDG PET findings on renal angiomyolipoma (AML) is limited. This study reports the FDG PET and PET/CT findings of 21 cases of renal AML. MATERIALS AND METHODS: The study reviews FDG PET and PET/CT images of 21 patients diagnosed with renal AML. The diagnosis is based on the classical appearance of an AML on CT scan with active surveillance for 6 months. The study is focused on the observation of clinical and radiographic features. RESULTS: Six men and 15 women were included in our study. The mean age of the patients was 57.14 +/- 9.67 years old. The mean diameter of 21 renal AML on CT scans was 1.76 +/- 1.00 cm (Min: 0.6 cm; Max: 4.4 cm). CT scans illustrated renal masses typical of AMLs, and the corresponding FDG PET scans showed minimal FDG activities in the area of the tumors. None of the 21 AMLs showed a maximum standardized uptake value (SUVmax) greater than 1.98. No statistically significant correlation was present between SUVmax and tumor size. CONCLUSION: Renal AMLs demonstrate very low to low uptake on FDG PET and PET/CT imaging in this study. When a fat-containing tumor in the kidney is found on a CT scan, it is critical to differentiate an AML from a malignant tumor including an RCC, liposarcoma, and Wilms tumor. This study suggests that FDG PET or PET/CT imaging is useful for differentiating a renal AML from a fat-containing malignant tumor.