In radiomics research, the issue of different instruments being used is significant. In this study, we compared three correction methods to reduce the batch effects in radiogenomic data from fluorodeoxyglucose (FDG) PET/CT images of lung cancer patients. Texture features of the FDG PET/CT images and genomic data were retrospectively obtained. The features were corrected with different methods: phantom correction, ComBat method, and Limma method. Batch effects were estimated using three analytic tools: principal component analysis (PCA), the k-nearest neighbor batch effect test (kBET), and the silhouette score. Finally, the associations of features and gene mutations were compared between each correction method. Although the kBET rejection rate and silhouette score were lower in the phantom-corrected data than in the uncorrected data, a PCA plot showed a similar variance. ComBat and Limma methods provided correction with low batch effects, and there was no significant difference in the results of the two methods. In ComBat- and Limma-corrected data, more texture features exhibited a significant association with the TP53 mutation than in those in the phantom-corrected data. This study suggests that correction with ComBat or Limma methods can be more effective or equally as effective as the phantom method in reducing batch effects.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10600181PMC
http://dx.doi.org/10.1038/s41598-023-45296-9DOI Listing

Publication Analysis

Top Keywords

batch effects
16
fdg pet/ct
12
correction methods
8
radiogenomic data
8
lung cancer
8
cancer patients
8
pet/ct images
8
texture features
8
correction combat
8
silhouette score
8

Similar Publications

Background: The field of single cell technologies has rapidly advanced our comprehension of the human immune system, offering unprecedented insights into cellular heterogeneity and immune function. While cryopreserved peripheral blood mononuclear cell (PBMC) samples enable deep characterization of immune cells, challenges in clinical isolation and preservation limit their application in underserved communities with limited access to research facilities. We present CryoSCAPE (Cryopreservation for Scalable Cellular And Proteomic Exploration), a scalable method for immune studies of human PBMC with multi-omic single cell assays using direct cryopreservation of whole blood.

View Article and Find Full Text PDF

Assessment of the impact of different SARS-CoV-2 inactivation operations on colistin sulfate plasma concentration results.

BMC Infect Dis

January 2025

Department of Cardiac Surgery, Second Hospital of Hebei Medical University, No.215 of Heping West Road,Xinhua District, Shijiazhuang, 050000, China.

Objective: To evaluate the effects of different SARS-CoV-2 inactivation methods on the blood concentration of colistin sulfate.

Methods: A colistin sulfate reference substance, a quality control plasma sample, and a clinically measured sample were transferred and heated in a 56 °C water batch for 30 min or irradiated under an ultraviolet (UV) lamp for 60 min to examine the stability of the reference solution and quality control plasma sample. Statistical analysis was conducted for the concentration of the clinically measured sample before and after inactivation with the intraclass correlation coefficient (ICC) method, the Passing-Bablok regression, and the Bland-Altman analysis.

View Article and Find Full Text PDF

A Faster Privacy-Preserving Medical Image Diagnosis Scheme with Machine Learning.

J Imaging Inform Med

January 2025

College of Computer, Chongqing University, No. 55 Daxuecheng South Rd, Shapingba, 401331, Chongqing, China.

Convolutional neural networks (CNNs) have become indispensable to medical image diagnosis research, enabling the automated differentiation of diseased images from extensive medical image datasets. Due to their efficacy, these methods raise significant privacy concerns regarding patient images and diagnostic models. To address these issues, some researchers have explored privacy-preserving medical image diagnosis schemes using fully homomorphic encryption (FHE).

View Article and Find Full Text PDF

Wu-Mei-Wan enhances brown adipose tissue function and white adipose browning in obese mice via upregulation of HSF1.

Chin Med

January 2025

Department of Integrated Traditional Chinese and Western Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, Hubei, China.

Background: This research aims to explore the anti-obesity potential of Wu-Mei-Wan (WMW), particularly its effects on adipose tissue regulation in obese mice induced by a high-fat diet (HFD). The study focuses on understanding the role of heat shock factor 1 (HSF1) in mediating these effects.

Methods: HFD-induced obese mice were treated with WMW.

View Article and Find Full Text PDF

Background: Huntington's disease (HD) is an autosomal dominant condition causing severe neurodegeneration in the striatum and the entorhinal cortex (EC). An epigenome wide association study of DNA methylation in HD by our group, identified potential hypomethylation at the PTGDS gene in the striatum. We aimed to validate this result through pyrosequencing, examining the locus in fine detail, and to assess the signal specificity by profiling multiple neurodegenerative diseases.

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!