Here, we aimed to develop and validate a fully automated artificial intelligence (AI)-based method for the detection and quantification of suspected prostate tumour/local recurrence, lymph node metastases, and bone metastases from [F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) images. Images from 660 patients were included. Segmentations by one expert reader were ground truth. A convolutional neural network (CNN) was developed and trained on a training set, and the performance was tested on a separate test set of 120 patients. The AI method was compared with manual segmentations performed by several nuclear medicine physicians. Assessment of tumour burden (total lesion volume (TLV) and total lesion uptake (TLU)) was performed. The sensitivity of the AI method was, on average, 79% for detecting prostate tumour/recurrence, 79% for lymph node metastases, and 62% for bone metastases. On average, nuclear medicine physicians' corresponding sensitivities were 78%, 78%, and 59%, respectively. The correlations of TLV and TLU between AI and nuclear medicine physicians were all statistically significant and ranged from R = 0.53 to R = 0.83. In conclusion, the development of an AI-based method for prostate cancer detection with sensitivity on par with nuclear medicine physicians was possible. The developed AI tool is freely available for researchers.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9497460PMC
http://dx.doi.org/10.3390/diagnostics12092101DOI Listing

Publication Analysis

Top Keywords

nuclear medicine
16
medicine physicians
12
fully automated
8
prostate cancer
8
ai-based method
8
lymph node
8
node metastases
8
bone metastases
8
total lesion
8
metastases
5

Similar Publications

The molar dose of FAPI administered impacts on the FAP-targeted PET imaging and therapy in mouse syngeneic tumor models.

Eur J Nucl Med Mol Imaging

January 2025

Department of Nuclear Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, 1095 Jiefang Ave, Wuhan, 430030, China.

Purpose: Since fibroblast activation protein (FAP), one predominant biomarker of cancer associated fibroblasts (CAFs), is highly expressed in the tumor stroma of various epidermal-derived cancers, targeting FAP for tumor diagnosis and treatment has shown substantial potentials in both preclinical and clinical studies. However, in preclinical settings, tumor-bearing mice exhibit relatively low absolute FAP expression levels, leading to challenges in acquiring high-quality PET images using radiolabeled FAP ligands (FAPIs) with low molar activity, because of which a saturation effect in imaging is prone to happen. Moreover, how exactly the molar dose of FAPI administered to a mouse influences the targeted PET imaging and radiotherapy remains unclear now.

View Article and Find Full Text PDF

Cardiac amyloidosis represents a unique disease process characterized by amyloid fibril deposition within the myocardial extracellular space. Advances in multimodality cardiac imaging enable accurate diagnosis and facilitate prompt initiation of disease-modifying therapies. Furthermore, rapid advances in multimodality imaging have enriched understanding of the underlying pathogenesis, enhanced prognostication, and resulted in the development of imaging-based markers that reflect the amyloid burden, which is of increasing importance when assessing the response to treatment.

View Article and Find Full Text PDF

Molecular Stratification of Light-Chain Cardiac Amyloidosis With F-Florbetapir and Ga-FAPI-04 for Enhanced Prognostic Precision.

JACC Cardiovasc Imaging

January 2025

Department of Nuclear Medicine, Beijing Key Laboratory of Molecular Targeted Diagnosis and Therapy in Nuclear Medicine, State Key Laboratory of Complex Severe and Rare Diseases, Center for Rare Diseases Research, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.

Background: Cardiac involvement in amyloid light chain (AL) amyloidosis significantly influences prognosis, necessitating timely diagnosis and meticulous risk stratification.

Objectives: This prospective study aimed to delineate the molecular phenotypes of AL cardiac amyloidosis (AL-CA) by characterizing fibro-amyloid deposition using F-florbetapir and gallium-68-labeled fibroblast activation protein inhibitor-04 (Ga-FAPI-04) positron emission tomography (PET)/computed tomography (CT) imaging. The authors also proposed a novel molecular stratification methodology for prognosis.

View Article and Find Full Text PDF

Biocompatibility of Phosphorus Dendrimers and Their Antibacterial Properties as Potential Agents for Supporting Wound Healing.

Mol Pharm

January 2025

Department of General Biophysics, Faculty of Biology and Environmental Protection, University of Lodz, 141/143 Pomorska St., 90-236 Lodz, Poland.

Dendrimers are a wide range of nanoparticles with desirable properties that can be used in many areas of medicine. However, little is known about their potential use in wound healing. This study examined the properties of phosphorus dendrimers that were built on a cyclotriphosphazene core and pyrrolidinium (DPP) or piperidinium (DPH) terminated groups, to be used as potential factors that support wound healing ().

View Article and Find Full Text PDF

Vernonolide A, a Sesquiterpene Lactone with a Unique Carbon Skeleton from .

Org Lett

January 2025

Department of Pharmaceutical Sciences, Daniel K. Inouye College of Pharmacy, University of Hawai'i at Hilo, Hilo, Hawai'i 96720, United States.

A novel sesquiterpene lactone derivative, vernonolide A (), featuring an unprecedented carbon skeleton, along with its plausible biosynthetic precursor, vercinolide I (), and eight known sesquiterpene lactones (-) were isolated and characterized from the whole plants of (L.). The structures of and were elucidated using nuclear magnetic resonance spectroscopic analysis and calculated and experimental electronic circular dichroism spectra.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!