Cited by The Application of online medicine in the diagnosis and treatment of pulmonary nodules in thoracic surgery (Preprint)

Prognostic Value and Pathological Correlation of Peritumoral Radiomics in Surgically Resected Non-Small Cell Lung Cancer DOI

Masaki Tominaga,

Motohiko Yamazaki,

Hajime Umezu

et al.

Academic Radiology, Journal Year: 2024, Volume and Issue: 31(9), P. 3801 - 3810

Published: Feb. 23, 2024

Language: Английский

Citations

Radiomics as a new frontier in modern rheumatology: Chest pathology visualization advances and prospects DOI

Т. V. Beketova, Е. Л. Насонов,

M. A. Alekseev

et al.

Rheumatology Science and Practice, Journal Year: 2025, Volume and Issue: 63(1), P. 24 - 36

Published: March 2, 2025

The article discusses the modern trends in development of digital technologies medicine, exemplified by rheumatology, especially, significance radiomics, which combines radiology, mathematical modeling, and deep machine learning. Texture analysis computed tomography images other imaging methods provides a more deeply characterization pathophysiological features tissues can be considered as non-invasive “virtual biopsy”. It is shown that radiomics enhances quality diagnostic predictive modeling. potential application radiomic models for studying predicting chest organ lesions various pathological conditions, including immune mediated inflammatory diseases, systemic vasculitis. Progress diagnosis treatment rheumatic diseases may facilitated integration omics technologies. era, opens up vast prospects advancements will undoubtedly require complex solutions to new technical, legal, ethical challenges.

Language: Английский

Citations

Development and Validation of a Deep Learning Radiomics Model to Predict High-Risk Pathologic Pulmonary Nodules Using Preoperative Computed Tomography DOI

Guanchao Ye, Guangyao Wu, Kuo Li

et al.

Academic Radiology, Journal Year: 2023, Volume and Issue: 31(4), P. 1686 - 1697

Published: Oct. 5, 2023

Language: Английский

Citations

Super Resolution of Pulmonary Nodules Target Reconstruction Using a Two-Channel GAN Models DOI

Qinling Jiang, Hongbiao Sun, Wei Deng

et al.

Academic Radiology, Journal Year: 2024, Volume and Issue: 31(8), P. 3427 - 3437

Published: March 7, 2024

•We employed a cascading approach of two 2D networks to achieve the functionality 3D image pulmonary nodules super-resolution target reconstruction CT among three axes.•We used pre-trained model for mapping from normal-resolution images high-resolution images, which enhanced stability and convergence speed results.•In addition evaluation we also relevant diagnostic indicators, makes our results more valuable clinical application. Rationale ObjectivesTo develop Dual generative-adversarial-network (GAN) Cascaded Network (DGCN) generating computed tomography (SRCT) (NRCT) evaluate performance DGCN in multi-center datasets.Materials MethodsThis retrospective study included 278 patients with chest hospitals between January 2020 June 2023, each patient had all NRCT (512 × 512 matrix resolution 0.70 mm, mm,1.0 mm), (HRCT, 1024 0.35 ultra-high-resolution (UHRCT, 0.17 0.5 mm) examinations. Initially, deep residual network (DCRN) was built generate HRCT NRCT. Subsequently, DCRN as training further enhance along axes, ultimately yielding SRCT. PSNR, SSIM, FID, subjective scores, objective parameters related nodule segmentation testing set were recorded analyzed.ResultsDCRN obtained PSNR 52.16, SSIM 0.9941, FID 137.713, an average diameter difference 0.0981 mm. 46.50, 0.9990, 166.421, mm on 39 cases. There no significant differences SRCT UHRCT evaluation.ConclusionOur exhibited enhancement outperformed established methods regarding quality accuracy across both internal external datasets. To This analyzed. evaluation. Our

Language: Английский

Citations

Quantification of Intratumoral Heterogeneity: Distinguishing Histological Subtypes in Clinical T1 Stage Lung Adenocarcinoma Presenting as Pure Ground-Glass Nodules on Computed Tomography DOI

Jian Zhang,

Jinlu Sha,

Wen Liu

et al.

Academic Radiology, Journal Year: 2024, Volume and Issue: 31(10), P. 4244 - 4255

Published: April 15, 2024

Language: Английский

Citations

“Application of CT radiomics in brain metastasis of lung cancer: A systematic review and meta-analysis” DOI

Ting Li, Tian Gan, Jingting Wang

et al.

Clinical Imaging, Journal Year: 2024, Volume and Issue: 114, P. 110275 - 110275

Published: Sept. 2, 2024

Language: Английский

Citations

Clinical and Computed Tomography Characteristics of Inflammatory Solid Pulmonary Nodules with Morphology Suggesting Malignancy DOI

Weihua Zhao, Lijuan Zhang, Xian Li

et al.

Academic Radiology, Journal Year: 2024, Volume and Issue: 32(2), P. 1067 - 1077

Published: Sept. 21, 2024

Language: Английский

Citations

Impact of slice thickness on reproducibility of CT radiomic features of lung tumors DOI

Sudipta Sen Gupta,

Kaushik Nayak,

Saikiran Pendem

et al.

F1000Research, Journal Year: 2023, Volume and Issue: 12, P. 1319 - 1319

Published: Dec. 1, 2023

Background Radiomics posits that quantified characteristics from radiographic images reflect underlying pathophysiology. Lung cancer (LC) is one of the prevalent forms cancer, causing mortality. Slice thickness (ST) computed tomography (CT) a crucial factor influencing generalizability radiomic features (RF) in oncology. There scarcity research how ST affects variability RF LC. The present study helps identifying specific categories affected by variations and provides valuable insights for researchers clinicians working with field LC.Hence, aim to evaluate influence on reproducibility CT-RF lung tumors. Methods This prospective study, 32 patients confirmed histopathological diagnosis tumors were included. Contrast Enhanced CT (CECT) thorax was performed using 128- Incisive (Philips Health Care). image acquisition 5-mm 2 mm STwas reconstructed retrospectively. extracted CECT both ST. We conducted paired t-test disparity between two thicknesses. Lin’s Concordance Correlation Coefficient (CCC) identify Results Out 107 RF, 66 (61.6%) exhibited statistically significant distinction (p<0.05) when comparing while 41 (38.3%) did not show (p>0.05) measurements. 29 (CCC ≥ 0.90) showed excellent moderate reproducibility, 78 ≤ poor reproducibility. Among 7 categories, shape-based (57.1%) maximum whereas NGTDM-based negligible Conclusions had notable impact majority Shape based (57.1%). First order (44.4%) highest compared other categories.

Language: Английский

Citations

Impact of slice thickness on reproducibility of CT radiomic features of lung tumors DOI

Sudipta Sen Gupta,

Kaushik Nayak,

Saikiran Pendem

et al.

F1000Research, Journal Year: 2023, Volume and Issue: 12, P. 1319 - 1319

Published: Oct. 12, 2023

Background: Radiomics, a field of research, relies on the theory that quantified characteristics from radiographic images would reflect underlying pathophysiology. Lung cancer continues to stand as one prevalent and well-known forms cancer, causing mortality. The slice thickness (ST) computed tomography (CT) be key concern regarding generalizability radiomic features (RF) results in oncology. There is scarcity research has delved into how ST affects variability RF lung tumors. Hence, aim study evaluate influence reproducibility CT-RF for tumors. Methods: This prospective study, 32 patients with confirmed histopathological diagnosis tumors were included. Contrast Enhanced CT (CECT) thorax was performed using 128- Incisive (Philips Health Care). image acquisition 5-mm 2 mm ST, reconstructed retrospectively. extracted CECT 2-mm ST. We conducted paired t-test disparity between two thicknesses. Lin’s Concordance Correlation Coefficient (CCC) identify thicknesses. Results: Out 107 extracted, 66 (61.6%) exhibited statistically significant distinction (p<0.05) when comparing thicknesses while 41 (38.3%) did not show (p>0.05) measurements. 29 (CCC ≥ 0.90) showed excellent moderate reproducibility, 78 ≤ poor reproducibility. Among 7 categories, shape-based (57.1%) maximum whereas NGTDM-based negligible reproducibility. Conclusions: The had notable impact majority Shape based (57.1%). First order (44.4%) highest compared other categories.

Language: Английский

Citations

Comprehensive Potential of Artificial Intelligence for Predicting PD-L1 Expression and EGFR Mutations in Lung Cancer: A Systematic Review and Meta-Analysis DOI

Linyong Wu,

Dayou Wei,

Wubiao Chen

et al.

Journal of Computer Assisted Tomography, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 12, 2024

Objective To evaluate the methodological quality and predictive performance of artificial intelligence (AI) for predicting programmed death ligand 1 (PD-L1) expression epidermal growth factor receptors (EGFR) mutations in lung cancer (LC) based on systematic review meta-analysis. Methods AI studies PET/CT, CT, PET, immunohistochemistry (IHC)–whole-slide image (WSI) were included to predict PD-L1 or EGFR LC. The modified Quality Assessment Diagnostic Accuracy Studies (QUADAS-2) tool was used quality. A comprehensive meta-analysis conducted analyze overall area under curve (AUC). Cochrane diagnostic test I 2 statistics assess heterogeneity Results total 45 included, which 10 35 mutations. Based analysis using QUADAS-2 tool, 37 achieved a high-quality score 7. In levels, AUCs IHC-WSI 0.80 (95% confidence interval [CI], 0.77–0.84), 0.74 CI, 0.69–0.77), 0.95 0.93–0.97), respectively. For mutation status, PET 0.85 0.81–0.88), 0.83 0.80–0.86), 0.75 0.71–0.79), Test revealed an value exceeding 50%, indicating substantial meta-analyses. When combined with clinicopathological features, enhancement not substantial, whereas prediction showed improvement compared CT models, albeit significantly so PET/CT models. Conclusions LC has promising clinical implications.

Language: Английский

Citations