Purpose: To construct a deep convolutional neural network that generates virtual monochromatic images (VMIs) from single-energy computed tomography (SECT) images for improved pancreatic cancer imaging quality.
Materials And Methods: Fifty patients with pancreatic cancer underwent a dual-energy CT simulation and VMIs at 77 and 60 keV were reconstructed. A 2D deep densely connected convolutional neural network was modeled to learn the relationship between the VMIs at 77 (input) and 60 keV (ground-truth). Subsequently, VMIs were generated for 20 patients from SECT images using the trained deep learning model.
Results: The contrast-to-noise ratio was significantly improved (p < 0.001) in the generated VMIs (4.1 ± 1.8) compared to the SECT images (2.8 ± 1.1). The mean overall image quality (4.1 ± 0.6) and tumor enhancement (3.6 ± 0.6) in the generated VMIs assessed on a five-point scale were significantly higher (p < 0.001) than that in the SECT images (3.2 ± 0.4 and 2.8 ± 0.4 for overall image quality and tumor enhancement, respectively).
Conclusions: The quality of the SECT image was significantly improved both objectively and subjectively using the proposed deep learning model for pancreatic tumors in radiotherapy.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.ejmp.2021.03.035 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
ASO Visual Abstract: Survival of Patients with Resected Microsatellite Instability-High, Mismatch Repair Deficient, and Lynch Syndrome-Associated Pancreatic Ductal Adenocarcinomas.
Ann Surg Oncol
January 2025
Hepato-Pancreato-Biliary Service, Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
Improving molecular subtypes and prognosis of pancreatic cancer through multi group analysis and machine learning.
Discov Oncol
January 2025
Department of Laboratory, the Second Hospital of Shanxi Medical University, No. 382, Wuyi Road, Taiyuan, 030001, Shanxi, People's Republic of China.
Background: Pancreatic cancer (PAC) has a complex tumor immune microenvironment, and currently, there is a lack of accurate personalized treatment. Establishing a novel consensus machine learning driven signature (CMLS) that offers a unique predictive model and possible treatment targets for this condition was the goal of this study.
Methods: This study integrated multiple omics data of PAC patients, applied ten clustering techniques and ten machine learning approaches to construct molecular subtypes for PAC, and created a new CMLS.
mSphere of Influence: Seeking the unseen fungi in tumors.
mSphere
January 2025
State Key Laboratory of Systems Medicine for Cancer, Center for Single-Cell Omics, School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Ningning Liu works in the field of fungal infection and cancer progression, with a particular focus on the mechanism of host-pathogen interaction. In this mSphere of influence article, he reflects on how papers entitled "The fungal mycobiome promotes pancreatic oncogenesis via activation of MBL," by B. Aykut, S.
View Article and Find Full Text PDFConcerns about needle tract seeding after endoscopic ultrasound-guided tissue acquisition: A possibility not limited to pancreatic body and tail cancer.
J Hepatobiliary Pancreat Sci
January 2025
Department of Gastroenterology, Shizuoka General Hospital, Shizuoka, Japan.
Physical Activity and Incident Pancreatic Cancer: Results From the UK Biobank Prospective Cohort.
Cureus
January 2025
Hepato-Pancreato-Biliary (HPB) Unit, University Hospital Southampton NHS Foundation Trust, Southampton, GBR.
Background The relationship between physical activity and incident pancreatic cancer is poorly defined, and the evidence to date is inconsistent, largely due to small sample sizes and insufficient incident outcomes. Using the UK Biobank cohort dataset, the association between physical activity levels at recruitment and incident pancreatic ductal adenocarcinoma (PDAC) at follow-up was analysed. Method Physical activity, the key exposure, was quantified using Metabolic Equivalent Task (MET) values and categorised into walking, moderate, and vigorous activity.
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!