Background: We developed a fully automated artificial intelligence (AI)AI-based-based method for detecting suspected lymph node metastases in prostate-specific membrane antigen (PSMA)(PSMA) positron emission tomography-computed tomography (PET-CT)(PET-CT) images of prostate cancer patients by using data augmentation that adds synthetic lymph node metastases to the images to expand the training set.
Methods: Synthetic data were derived from original training images to which new synthetic lymph node metastases were added. Thus, the original training set from a previous study (n = 420) was expanded by one synthetic image for every original image (n = 840), which was used to train an AI model. The performance of the AI model was compared to that of nuclear medicine physicians and a previously developed AI model. The human readers were alternately used as a reference and compared to either another reading or AI model.
Results: The new AI model had an average sensitivity of 84% for detecting lymph node metastases compared with 78% for human readings. Our previously developed AI method without synthetic data had an average sensitivity of 79%. The number of false positive lesions were slightly higher for the new AI model (average 3.3 instances per patient) compared to human readings and the previous AI model (average 2.8 instances per patient), while the number of false negative lesions was lower.
Conclusions: Creating synthetic lymph node metastases, as a form of data augmentation, on [18F]PSMA-1007F]PSMA-1007 PETPET-CT-CT images improved the sensitivity of an AI model for detecting suspected lymph node metastases. However, the number of false positive lesions increased somewhat.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1111/cpf.12879 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Development of a Prognostic Nomogram for Overall Survival in Gastric Cancer Patients Who Underwent Adjuvant Chemoradiotherapy.
J Gastrointest Cancer
January 2025
Department of Radiation Oncology, Hacettepe University Faculty of Medicine, Ankara, Turkey.
Purpose: The aim of this study was to identify prognostic factors influencing overall survival (OS) in patients with gastric cancer treated with adjuvant chemoradiotherapy (CRT) and to develop a predictive model.
Methods: We retrospectively evaluated 245 non-metastatic gastric cancer patients who received adjuvant CRT or radiotherapy from 2010 to 2020. Survival analyses were performed using the Kaplan-Meier method.
Aggressive Digital Papillary Adenocarcinoma: A Meta-Analysis of the Presentation, Treatment, and Outcomes of a Rare Hand Tumor.
Hand (N Y)
January 2025
Institute for Plastic Surgery, Southern Illinois University School of Medicine, Springfield, USA.
Background: Aggressive digital papillary adenocarcinoma (ADPA) is a rare skin adnexal tumor with a predilection for the hand. The presentation, treatment, and outcomes of ADPA remain poorly defined due to the scarcity of reports and low-level evidence of published findings.
Methods: We performed a meta-analysis following Preferred Reporting Items for Systematic reviews and Meta-Analyses guidelines with the intent to provide hand surgeons a better understanding of the diagnosis and treatment of the disease.
Visualizing lipid nanoparticle trafficking for mRNA vaccine delivery in non-human primates.
Mol Ther
January 2025
Department of Biological Engineering, Massachusetts Institute of Technology; Cambridge, MA, USA, 02139; Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology; Cambridge, MA, USA, 02139; Department of Chemical Engineering, Massachusetts Institute of Technology; Cambridge, MA, USA, 02139; Ragon Institute of Massachusetts General Hospital, Massachusetts Institute of Technology, and Harvard University; Cambridge, MA, USA, 02139; Howard Hughes Medical Institute; Chevy Chase, MD, USA, 20815; Department of Materials Science of Engineering; Massachusetts Institute of Technology; Cambridge, MA, USA, 02139. Electronic address:
mRNA delivered using lipid nanoparticles (LNPs) has become an important subunit vaccine modality, but mechanisms of action for mRNA vaccines remain incompletely understood. Here, we synthesized a metal chelator-lipid conjugate enabling positron emission tomography (PET) tracer labeling of LNP/mRNA vaccines for quantitative visualization of vaccine trafficking in live mice and non-human primates (NHPs). Following i.
View Article and Find Full Text PDFLocal excision for T1 rectal cancer: A population-based study of practice patterns and oncological outcomes.
Colorectal Dis
January 2025
Division of General Surgery, Department of Surgery, Queen's University, Kingston, Ontario, Canada.
Aim: Local excision (LE) for T1 rectal cancer may be recommended in those with low-risk disease, while resection is typically recommended in those with a high risk of luminal recurrence or lymph node metastasis. The aim of this work was to compare survival between resection and LE.
Method: This was a population-based retrospective cohort study set in the Canadian province of Ontario.
Node Reporting and Data System 1.0 (Node-RADS) for the Assessment of Oncological Patients' Lymph Nodes in Clinical Imaging.
J Clin Med
January 2025
Radiology, Multizonal Unit of Rovereto and Arco, APSS Provincia Autonoma Di Trento, 38123 Trento, Italy.
The assessment of lymph node (LN) involvement with clinical imaging is a key factor in cancer staging. Node Reporting and Data System 1.0 (Node-RADS) was introduced in 2021 as a new system specifically tailored for classifying and reporting LNs on computed tomography (CT) and magnetic resonance imaging scans.
View Article and Find Full Text PDFWant 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!