Rationale And Objectives: This study investigated the utility of F-fluorodeoxyglucose positron emission tomography/computed tomography (F-FDG PET/CT) for predicting visceral pleural invasion (VPI) of subsolid nodule (SSN) stage I lung adenocarcinoma.
Materials And Methods: A retrospective analysis of F-FDG PET/CT data from 65 postsurgical cases with surgical pathology-confirmed SSN lung adenocarcinoma identified significant VPI predictors using multivariate logistic regression.
Results: Nodule and solid component sizes, solid component-to-tumor ratios, pleural indentations, distances between nodules and pleura, and maximum standardized uptake values (SUVmax) differed significantly between VPI-positive (n = 30) and VPI-negative (n = 35) cases on univariate analysis. The distance between the nodule and pleura and SUVmax were significant independent VPI predictors on multivariate analysis. Areas under the curve of the distance between the nodule and pleura and SUVmax on receiver operating characteristic curves were 0.76 and 0.79, respectively; both factors were 0.90. The area under the curve of combined predictors was significantly superior to the distance between the nodule and pleura only but not SUVmax alone. The threshold of the distance between the nodule and pleura, to predict VPI was 4.50 mm, with 96.67% sensitivity, and 57.14% specificity. The threshold of SUVmax to predict VPI was 1.05, with 100% sensitivity and 60% specificity. The sensitivity and specificity of model 2 using the independent predictive factors were 96.67%, and 71.43%, respectively.
Conclusion: Distance between the nodule and pleura and SUVmax are independent predictors of VPI in SSN stage I lung adenocarcinoma. Further, combining these factors improves their predictive ability.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.acra.2020.01.019 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Lightweight Lung-nodule Detection Model Combined with Multidimensional Attention Convolution.
Curr Med Imaging
January 2025
School of Optoelectronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China.
Background: Early and timely detection of pulmonary nodules and initiation treatment can substantially improve the survival rate of lung carcinoma. However, current detection methods based on convolutional neural networks (CNNs) cannot easily detect pulmonary nodules owing to low detection accuracy and the difficulty in detecting small-sized pulmonary nodules; meanwhile, more accurate CNN-based models are slow and require high hardware specifications.
Objective: The aim of this study is to develop a detection model that achieves both high accuracy and real-time performance, ensuring effective and timely results.
The geographic scale of population-level variation in growth and nodulation differs for two species of prairie clover.
Am J Bot
January 2025
Department of Ecology, Evolution and Behavior, University of Minnesota Twin Cities, St Paul, 55108, MN, USA.
Premise: Prairies are among the most threatened biomes due to changing patterns of climate and land use, yet information on genetic variation in key species that would inform conservation is often limited. We assessed evidence for the geographic scale of population-level variation in growth of two species of prairie clover and of their symbiotic associations with nitrogen-fixing bacteria.
Methods: Seed representing two species, Dalea candida and D.
An unsupervised automatic texture classification method for ultrasound images of thyroid nodules.
Phys Med Biol
January 2025
Beijing institute of control and electronic technology, 51 Beilijia, Muxidi, Xicheng District, Beijing 100038, Beijing, 100038, CHINA.
Objective Ultrasound is the predominant modality in medical practice for evaluating thyroid nodules. Currently, diagnosis is typically based on textural information. This study aims to develop an automated texture classification approach to aid physicians in interpreting ultrasound images of thyroid nodules.
View Article and Find Full Text PDFMulti-institutional development and testing of attention-enhanced deep learning segmentation of thyroid nodules on ultrasound.
Int J Comput Assist Radiol Surg
January 2025
Department of Radiology, University of Chicago, Chicago, IL, USA.
Purpose: Thyroid nodules are common, and ultrasound-based risk stratification using ACR's TIRADS classification is a key step in predicting nodule pathology. Determining thyroid nodule contours is necessary for the calculation of TIRADS scores and can also be used in the development of machine learning nodule diagnosis systems. This paper presents the development, validation, and multi-institutional independent testing of a machine learning system for the automatic segmentation of thyroid nodules on ultrasound.
View Article and Find Full Text PDFTowards safe and reliable deep learning for lung nodule malignancy estimation using out-of-distribution detection.
Comput Biol Med
December 2024
Diagnostic Imaging Analysis Group, Medical Imaging Department, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA, Nijmegen, the Netherlands.
Artificial Intelligence (AI) models may fail or suffer from reduced performance when applied to unseen data that differs from the training data distribution, referred to as dataset shift. Automatic detection of out-of-distribution (OOD) data contributes to safe and reliable clinical implementation of AI models. In this study, we propose a recognized OOD detection method that utilizes the Mahalanobis distance (MD) and compare its performance to widely known classical methods.
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!