Diagnostic Performance of Machine Learning Models Based on 18F-FDG PET/CT Radiomic Features in the Classification of Solitary Pulmonary Nodules.

Objectives: This study aimed to evaluate the ability of 18fluorine-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) radiomic features combined with machine learning methods to distinguish between benign and malignant solitary pulmonary nodules (SPN). Methods: Data of 48 patients with SPN detected on 18F-FDG PET/CT scan were evaluated retrospectively. The texture feature extraction from PET/CT images was performed using an open-source application (LIFEx). Deep learning and classical machine learning algorithms were used to build the models. Final diagnosis was confirmed by pathology and follow-up was accepted as the reference. The performances of the models were assessed by the following metrics: Sensitivity, specificity, accuracy, and area under the receiver operator characteristic curve (AUC). Results: The predictive models provided reasonable performance for the differential diagnosis of SPNs (AUCs ~0.81). The accuracy and AUC of the radiomic models were similar to the visual interpretation. However, when compared to the conventional evaluation, the sensitivity of the deep learning model (88% vs. 83%) and specificity of the classic learning model were higher (86% vs. 79%). Conclusion: Machine learning based on 18F-FDG PET/CT texture features can contribute to the conventional evaluation to distinguish between benign and malignant lung nodules.

PET/CT Findings of a Patient with Striped Muscle Metastasis of Invasive Breast Carcinoma

A 37-year-old female with a history of invasive breast carcinoma was referred to our department for an 18flor-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography whole-body scan. An intense 18F-FDG uptake in striped muscles anterior to the left thigh region was noted. Excisional biopsy outcome from the left vastus medialis muscle was found to be consistent with striped muscle metastasis from breast carcinoma.

Intraoperative ultrasound imaging and sono-scintigraphic concordance improves success rates of minimally invasive parathyroidectomy

Background/aim: This study aimed to evaluate the effect of sono-scintigraphic correlation on the success of minimal invasive parathyroidectomy (MIP) via surgeon performed continuous intraoperative sonographic guidance in patients operated for primary hyperparathyroidism (PHPT) without intact parathormone (PTH) measurement. Materials and methods: A retrospective analysis of a prospective database was conducted to review patients who underwent MIP (July 2017-October 2019). The screened parameters were preoperative PTH level, preoperative ultrasonography (US), preoperative scintigraphy, intraoperative US, intraoperative frozen section analysis, postoperative PTH level, and permanent pathology rep ort. Intraoperative intact PTH measurement was not employed due to institutional policy. Results: Preoperative US alone localized the specific side (right/left, inferior/superior) of abnormality in 54 out of 74 (72.97%) cases. Scintigraphy alone localized the specific side in 58 (78.37%) cases. The sensitivity of preoperative US and scintigraphy alone was 76.05% and 86.56%, respectively. Sono-scintigraphic discordance was present in 6 cases (8.1%) and intraoperative real-time US predicted accurate localization of adenoma in 4 (66.6%) and scintigraphy in 2 (44.4%) patients. The frozen section analysis confirmed parathyroid cells in all cases evaluated. Conclusion: Sono-scintigraphic concordance with intraoperative real-time imaging increases surgical success rates in cases where MIP is planned under the circumstances of limited resources regarding unavailability of intact PTH measurement.