Search

Objective: To create the 3D convolutional neural network (CNN)-based system that can use whole-body [18F]FDG PET for recurrence/post-therapy surveillance in ovarian cancer (OC). Methods: In this study, 1224 image sets from OC patients who underwent whole-body [18F]FDG PET/CT at Kowsar Hospital between April 2019 and May 2022 were investigated. For recurrence/post-therapy surveillance, diagnostic classification as cancerous, and non-cancerous and staging as stage III, and stage IV were determined by pathological diagnosis and specialists' interpretation. New deep neural network algorithms, the OCDAc-Net, and the OCDAs-Net were developed for diagnostic classification and staging of OC patients using [18F]FDG PET/CT images. Examinations were divided into independent training (75%), validation (10%), and testing (15%) subsets. Results: This study included 37 women (mean age 56.3 years; age range 36–83 years). Data augmentation techniques were applied to the images in two phases. There were 1224 image sets for diagnostic classification and staging. For the test set, 170 image sets were considered for diagnostic classification and staging. The OCDAc-Net areas under the receiver operating characteristic curve (AUCs) and overall accuracy for diagnostic classification were 0.990 and 0.92, respectively. The OCDAs-Net achieved areas under the receiver operating characteristic curve (AUCs) of 0.995 and overall accuracy of 0.94 for staging. Conclusions: The proposed 3D CNN-based models provide potential tools for recurrence/post-therapy surveillance in OC. The OCDAc-Net and the OCDAs-Net model provide a new prognostic analysis method that can utilize PET images without pathological findings for diagnostic classification and staging. [ABSTRACT FROM AUTHOR]

In most patients with ovarian carcinoma, the diagnosis is reached when the disease is long past the initial stages, presenting already an advanced stage, and they usually have a very bad prognosis. Cytoreductive or debulking surgical procedures, platinum-based chemotherapy and targeted agents are key therapeutic elements. However, around 7 out of 10 patients present recurrent disease within 36 months from the initial diagnosis. The metastatic spread in ovarian cancer follows three pathways: contiguous dissemination across the peritoneum, dissemination through the lymphatic drainage and, although less importantly in this case, through the bloodstream. Radiological imaging, including ultrasound, CT and MRI, are the main imaging techniques in which management decisions are supported, CT being considered the best available technique for presurgical evaluation and staging purposes. Regarding 2-[18F]FDG PET/CT, the evidence available in the literature demonstrates efficacy in primary detection, disease staging and establishing the prognosis and especially for relapse detection. There is limited evidence when considering the evaluation of therapeutic response. This guideline summarizes the level of evidence and grade of recommendation for the clinical indications of 2-[18F]FDG PET/CT in each disease stage of ovarian carcinoma. [ABSTRACT FROM AUTHOR]

Purpose & Methods: Neuroendocrine neoplasms are a heterogenous group of tumours, for which nuclear medicine plays an important role in the diagnostic work-up as well as in the targeted therapeutic options. This guideline is aimed to assist nuclear medicine physicians in recommending, performing, reporting and interpreting the results of somatostatin receptor (SSTR) PET/CT imaging using Ga-DOTA-conjugated peptides, as well as F-DOPA imaging for various neuroendocrine neoplasms. Results & Conclusion: The previous procedural guideline by EANM regarding the use PET/CT tumour imaging with Ga-conjugated peptides has been revised and updated with the relevant and recent literature in the field with contribution of distinguished experts. [ABSTRACT FROM AUTHOR]