Differential diagnosis of benign and lung adenocarcinoma presenting as larger solid nodules and masses based on multiscale CT radiomics DOI Creative Commons

Jiayue Xie,

Yifan He,

Siyu Che

et al.

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(10), P. e0309033 - e0309033

Published: Oct. 4, 2024

Purpose To develop a better radiomic model for the differential diagnosis of benign and lung adenocarcinoma lesions presenting as larger solid nodules masses based on multiscale computed tomography (CT) radiomics. Materials methods This retrospective study enrolled 205 patients with from Center 1 between January 2010 February 2022 2 2019 2022. After applying inclusion exclusion criteria, we retrospectively 165 two centers assigned them to training dataset (n = 115) or test 50). Radiomics features were extracted volumes interest CT images. A gradient boosting decision tree (GBDT) was used data dimensionality reduction perform final feature selection. Four models developed using clinical data, conventional imaging radiomics features, namely, image (CIM), plain (PRM), enhanced (ERM) combined (CM). Model performance evaluated determine best identifying masses. Results In dataset, areas under curve (AUCs) CIM, PRM, ERM, CM 0.718, 0.806, 0.819, 0.917, respectively. The diagnostic capability ERM than that PRM CIM. optimal. Intermediate junior radiologists respiratory physicians achieved improved obviously results model. senior showed slight after Conclusion may have potential be noninvasive tool

Language: Английский

CT-Based Radiomics Models for Differentiation of Benign and Malignant Thyroid Nodules: A Multicenter Development and Validation Study DOI

Shaofan Lin,

Ming Gao, Zehong Yang

et al.

American Journal of Roentgenology, Journal Year: 2024, Volume and Issue: 223(1)

Published: May 1, 2024

CT is increasingly detecting thyroid nodules. Prior studies indicated a potential role of CT-based radiomics models in characterizing nodules, although these lacked external validation.

Language: Английский

Citations

5
Risk factors for malignant solid pulmonary nodules: a meta-analysis DOI Creative Commons
Yantao Yang, Xiangnan Li,

Yaowu Duan

et al.

BMC Cancer, Journal Year: 2025, Volume and Issue: 25(1)

Published: Feb. 21, 2025

Previous studies have indicated that clinical and imaging features may assist in distinguishing between benign malignant solid lung nodules. Yet, the specific characteristics question continue to be debated. This meta-analysis aims identify risk factors for nodules, thereby supporting informed decision-making. A comprehensive search of databases including PubMed, Embase, Web Science, Cochrane Library, Scopus, Wanfang, CNKI, VIP, CBM was conducted up October 6, 2024. Only publications Chinese or English were considered. Data analysis performed using Stata 16.0 software. included 32 studies, comprising 7758 pulmonary which 3359 4399 malignant. It found incidence spiculate signs nodules (MSPN) higher than (BSPN) [OR = 3.06, 95% CI (2.35, 3.98), P < 0.05. Additionally, increases observed incidences vascular convergence[OR 16.57, (8.79, 31.24), 0.05], lobulated 5.17, (3.83, 6.98)], air bronchogram sign[OR 2.96, (1.62, 5.41), pleura traction sign 2.33, (1.65, 3.29), border blur 2.94, (1.47, 5.85), vacuole 5.25, (2.66, 10.37), family history cancer 3.85, (2.43, 6.12), 0.05] compared BSPN. Older age[OR 1.06, (1.04, 1.07), prevalence females 2.98, (2.27, 3.92), larger nodule diameters 1.25, (1.13, 1.38), lower calcification 0.21, (0.10, 0.48), also associated with MSPN. No significant differences MSPN BSPN regarding CEA emphysema (all > 0.05). highlights sign, convergence diameter, blur, age, gender, cancer, traction, are markers predicting malignancy SPNs, potentially influencing management. However, further well-designed, large-scale needed confirm these findings.

Language: Английский

Citations

0
Deep learning for malignancy risk estimation of incidental sub-centimeter pulmonary nodules on CT images DOI
Rui Zhang, Ying Wei, Denian Wang

et al.

European Radiology, Journal Year: 2023, Volume and Issue: 34(7), P. 4218 - 4229

Published: Dec. 20, 2023

Language: Английский

Citations

8
An Integrated Clinical and Computerized Tomography-Based Radiomic Feature Model to Separate Benign from Malignant Pleural Effusion DOI

Fangqi Cai,

Liwei Cheng,

Xiaoling Liao

et al.

Respiration, Journal Year: 2024, Volume and Issue: 103(7), P. 406 - 416

Published: Jan. 1, 2024

<b><i>Introduction:</i></b> Distinguishing between malignant pleural effusion (MPE) and benign (BPE) poses a challenge in clinical practice. We aimed to construct validate combined model integrating radiomic features factors using computerized tomography (CT) images differentiate MPE BPE. <b><i>Methods:</i></b> A retrospective inclusion of 315 patients with (PE) was conducted this study (training cohort: <i>n</i> = 220; test 95). Radiomic were extracted from CT images, the dimensionality reduction selection processes carried out obtain optimal features. Logistic regression (LR), support vector machine (SVM), random forest employed models. LR analyses utilized identify independent risk develop model. The created by predictive factors. discriminative ability each assessed receiver operating characteristic curves, calibration decision curve analysis (DCA). <b><i>Results:</i></b> Out total 1,834 extracted, 15 explicitly related picked Among models, SVM demonstrated highest performance [area under (AUC), training 0.876, 0.774]. Six clinically factors, including age, laterality, procalcitonin, carcinoembryonic antigen, carbohydrate antigen 125 (CA125), neuron-specific enolase (NSE), selected for constructing (AUC: 0.932, 0.870) exhibited superior cohorts compared 0.850, 0.820) 0.774). curves DCA further confirmed practicality <b><i>Conclusion:</i></b> This presented development validation distinguishing powerful tool assisting diagnosis PE patients.

Language: Английский

Citations

2
The scoring system combined with radiomics and imaging features in predicting the malignant potential of incidental indeterminate small (<20 mm) solid pulmonary nodules DOI Creative Commons

Bai-Qiang Qu,

Yun Wang, Yuepeng Pan

et al.

BMC Medical Imaging, Journal Year: 2024, Volume and Issue: 24(1)

Published: Sept. 6, 2024

Language: Английский

Citations

2
Recent Advances in the Field of Artificial Intelligence for Precision Medicine in Patients with a Diagnosis of Metastatic Cutaneous Melanoma DOI Creative Commons

Hayley Higgins,

Abanoub Nakhla,

Andrew Lotfalla

et al.

Diagnostics, Journal Year: 2023, Volume and Issue: 13(22), P. 3483 - 3483

Published: Nov. 20, 2023

Standard-of-care medical imaging techniques such as CT, MRI, and PET play a critical role in managing patients diagnosed with metastatic cutaneous melanoma. Advancements artificial intelligence (AI) techniques, radiomics, machine learning, deep could revolutionize the use of by enhancing individualized image-guided precision medicine approaches. In present article, we will decipher how AI/radiomics mine information from images, tumor volume, heterogeneity, shape, to provide insights into cancer biology that can be leveraged clinicians improve patient care both clinic clinical trials. More specifically, detail potential AI detection/diagnosis, staging, treatment planning, delivery, response assessment, toxicity monitoring Finally, explore these proof-of-concept results translated bench bedside describing implementation standardized for routine adoption settings worldwide predict outcomes great accuracy, reproducibility, generalizability

Language: Английский

Citations

4
A nomogram combining CT-based radiomic features with clinical features for the differentiation of benign and malignant cystic pulmonary nodules DOI Creative Commons

Yi Yao,

Yanhui Yang,

Qiuxia Hu

et al.

Journal of Cardiothoracic Surgery, Journal Year: 2024, Volume and Issue: 19(1)

Published: June 27, 2024

Currently, the differentiation between benign and malignant cystic pulmonary nodules poses a significant challenge for clinicians. The objective of this retrospective study was to construct predictive model determining likelihood malignancy in patients with nodules.

Language: Английский

Citations

1
Differentiating Immune Checkpoint Inhibitor-Related Pneumonitis From COVID-19 Pneumonia Using a CT-based Radiomics Nomogram DOI Creative Commons

Fengfeng Yang,

Zhengyang Li, Di Yin

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: March 29, 2024

Abstract Objectives This study aimed to develop and validate a radiomics nomogram that effectively distinguishes between immune checkpoint inhibitor-related pneumonitis (CIP) COVID-19 pneumonia using radiographic imaging features. Methods We included 97 patients in this study, identifying 269 lesions—159 from 110 CIP. The dataset was randomly divided into training set (70% of the data) validation (30%). We extracted features corticomedullary nephrographic phase-contrast computed tomography (CT) images, constructed signature, calculated score (Rad-score). Using these features, we built models with three classifiers assessed demographics CT findings create clinical factors model. then combines Rad-score independent evaluated its performance terms calibration, discrimination, usefulness. Results In constructing 33 were critical for differentiating CIP pneumonia. support vector machine classifier most accurate used. Rad-score, gender, lesion location, radiological borders nomogram. demonstrated superior predictive performance, significantly outperforming model (AUC comparison, p = 0.02638). Calibration curves indicated good fit both sets, displayed greater net benefit compared Conclusion emerges as noninvasive, quantitative tool significant potential differentiate It enhances diagnostic accuracy supports radiologists, especially overburdened medical systems, through use learning predictions.

Language: Английский

Citations

0
Effect of Deep Learning Image Reconstruction Algorithms on Radiomic Features of Pulmonary Nodules in Ultra-Low-Dose CT DOI

Zhijuan Zheng,

Yuying Liang, Zhehao Wu

et al.

Journal of Computer Assisted Tomography, Journal Year: 2024, Volume and Issue: 48(6), P. 943 - 950

Published: Aug. 2, 2024

Objective The purpose of this study is to explore the impact deep learning image reconstruction (DLIR) algorithm on quantification radiomic features in ultra-low-dose computed tomography (ULD-CT) compared with adaptive statistical iterative reconstruction-Veo (ASIR-V). Methods One hundred eighty-three patients pulmonary nodules underwent standard-dose (SDCT) (4.30 ± 0.36 mSv) and ULD-CT (UL-A, 0.57 0.09 mSv or UL-B, 0.33 0.04 mSv). SDCT was reference standard using (ASIR-V) at 50% strength (50%ASIR-V). reconstructed 50%ASIR-V, DLIR medium high (DLIR-M, DLIR-H). Radiomics analysis extracted 102 features, intraclass correlation coefficient (ICC) quantified reproducibility between by DLIR-M, DLIR-H for each feature. Results Among percentages were 48.04% (49/102), 49.02% (50/102), 52.94% (54/102), respectively. Shape first order demonstrated across different algorithms radiation doses, mean ICC values exceeding 0.75. In texture DLIR-M showed improved pure ground glass (pGGNs) from 0.69 0.23 0.75 0.18 0.81 0.12, respectively, 50%ASIR-V. Similarly, solid (SNs) increased 0.60 0.19 0.66 0.14 0.13, Additionally, pGGNs SNs both groups decreased reduced dose. Conclusions can improve ultra-low doses ASIR-V. addition, better than SNs.

Language: Английский

Citations

0
The application of metagenomics, radiomics and machine learning for diagnosis of sepsis DOI Creative Commons

Xiefei Hu,

Shenshen Zhi,

Wenyan Wu

et al.

Frontiers in Medicine, Journal Year: 2024, Volume and Issue: 11

Published: Sept. 20, 2024

Introduction Sepsis poses a serious threat to individual life and health. Early accessible diagnosis targeted treatment are crucial. This study aims explore the relationship between microbes, metabolic pathways, blood test indicators in sepsis patients develop machine learning model for clinical diagnosis. Methods Blood samples from were sequenced. α-diversity β-diversity analyses performed compare microbial diversity group normal group. Correlation analysis was conducted on indicators. In addition, developed based medical records radiomic features using algorithms. Results The results of showed that significantly higher than ( p &lt; 0.05). top 10 abundances groups Vitis vinifera, Mycobacterium canettii, Solanum pennellii, Ralstonia insidiosa, Ananas comosus, Moraxella osloensis, Escherichia coli, Staphylococcus hominis, Camelina sativa , Cutibacterium acnes . enriched pathways mainly included Protein families: genetic information processing, Translation, signaling cellular processes, Unclassified: processing. correlation revealed significant positive 0.05) IL-6 Membrane transport. Metabolism other amino acids with acnes, osloensis hominis comosus Poorly characterized metabolism. test-related negative microorganisms. Logistic regression (LR) used as optimal six models features. nomogram, calibration curves, AUC values demonstrated LR best prediction. Discussion provides insights into sepsis. shows potential aiding However, further research is needed validate improve model.

Language: Английский

Citations

0