EMI-LTI: An Enhanced Integrated Model for Lung Tumor Identification using Gabor Filter and ROI

MethodsX, Journal Year: 2025, Volume and Issue: 14, P. 103247 - 103247

Published: Feb. 28, 2025

Language: Английский

---

A Thorough Review of the Clinical Applications of Artificial Intelligence in Lung Cancer

Cancers, Journal Year: 2025, Volume and Issue: 17(5), P. 882 - 882

Published: March 4, 2025

According to data from the World Health Organization (WHO), lung cancer is becoming a global epidemic. It particularly high in list of leading causes death not only developed countries, but also worldwide; furthermore, it holds place terms cancer-related mortality. Nevertheless, many breakthroughs have been made last two decades regarding its management, with one most prominent being implementation artificial intelligence (AI) various aspects disease management. We included 473 papers this thorough review, which published during 5-10 years, order describe these breakthroughs. In screening programs, AI capable detecting suspicious nodules different imaging modalities-such as chest X-rays, computed tomography (CT), and positron emission (PET) scans-but discriminating between benign malignant well, success rates comparable or even better than those experienced radiologists. Furthermore, seems be able recognize biomarkers that appear patients who may develop cancer, years before event. Moreover, can assist pathologists cytologists recognizing type tumor, well specific histologic genetic markers play key role treating disease. Finally, treatment field, guide development personalized options for patients, possibly improving their prognosis.

Language: Английский

---

Accurate Diagnosis of High-Risk Pulmonary Nodules Using a Non-Invasive Epigenetic Biomarker Test

Cancers, Journal Year: 2025, Volume and Issue: 17(6), P. 916 - 916

Published: March 7, 2025

Background/Objectives: Accurate non-invasive tests to improve early detection and diagnosis of lung cancer are urgently needed. However, no regulatory-approved blood available for this purpose. We aimed pulmonary nodule classification identify malignant nodules in a high-prevalence patient group. Methods: This study involved 806 participants with undiagnosed larger than 5 mm, focusing on assessing nucleosome levels histone modifications (H3.1 H3K27Me3) circulating blood. Nodules were classified as or benign. For model development, the data randomly divided into training (n = 483) validation 121) datasets. The model’s performance was then evaluated using separate testing dataset 202). Results: Among patients, 755 (93.7%) had tissue diagnosis. overall malignancy rate 80.4%. all datasets, areas under curves follows: training, 0.74; validation, 0.86; test, 0.79 (accuracy range: 0.80–0.88). Sensitivity showed consistent results across datasets (0.91, 0.95, 0.93, respectively), whereas specificity ranged from 0.37 0.64. smaller (5–10 mm), recorded accuracy values 0.76, 0.88, 0.85. sensitivity 0.91, 1.00, 0.94 further highlight robust diagnostic capability model. reporting system (RADS) categories demonstrated accuracy. Conclusions: Our epigenetic biomarker panel detected non-small-cell high-risk group high particularly effective identifying nodules, including small, part-solid, non-solid provided evidence validation.

Language: Английский

---

Patient Attitudes Toward Artificial Intelligence in Cancer Care: A Scoping Review

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: March 17, 2025

Abstract PURPOSE To synthesize existing literature on patient attitudes toward AI in cancer care and identify knowledge gaps that can inform future research clinical implementation. DESIGN A scoping review was conducted following PRISMA-ScR guidelines. MEDLINE, EMBASE, PsycINFO, CINAHL were searched for peer-reviewed primary studies published until February 1, 2025. The Population-Concept-Context framework guided study selection, focusing adult patients with their AI. Studies quantitative or qualitative data included. Two independent reviewers screened studies, a third resolving disagreements. Data synthesized into tabular narrative summaries. RESULTS Our search yielded 1,240 citations, of which 19 met the inclusion criteria, representing 2,114 across 15 countries. Most used methods (n=9) such as questionnaires surveys. most studied cancers prostate, melanoma, breast, colorectal cancer. While generally supported when physician-guided tool, concerns about depersonalization, treatment bias, security highlighted challenges Trust shaped by physician endorsement familiarity, greater trust physician-guided. Geographic differences observed, acceptance Asia, while skepticism more prevalent North America Europe. Additionally, metastatic underrepresented, limiting insights perceptions this population. CONCLUSION This provides first synthesis all types highlights unique to Clinicians use these findings enhance positioning it tool ensuring its integration aligns values expectations.

Language: Английский

---

Smart nanomedicines powered by artificial intelligence: a breakthrough in lung cancer diagnosis and treatment

Medical Oncology, Journal Year: 2025, Volume and Issue: 42(5)

Published: March 25, 2025

Language: Английский

---

Preliminary exploratory study on differential diagnosis between benign and malignant peripheral lung tumors: based on deep learning networks

Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 12

Published: March 27, 2025

Background Deep learning has shown considerable promise in the differential diagnosis of lung lesions. However, majority previous studies have focused primarily on X-ray, computed tomography (CT), and magnetic resonance imaging (MRI), with relatively few investigations exploring predictive value ultrasound imaging. Objective This study aims to develop a deep model based differentiate between benign malignant peripheral tumors. Methods A retrospective analysis was conducted cohort 371 patients who underwent ultrasound-guided percutaneous tumor procedures across two centers. The dataset divided into training set ( n = 296) test 75) an 8:2 ratio for further evaluation. Five distinct models were developed using ResNet152, ResNet101, ResNet50, ResNet34, ResNet18 algorithms. Receiver Operating Characteristic (ROC) curves generated, Area Under Curve (AUC) calculated assess diagnostic performance each model. DeLong’s employed compare differences groups. Results Among five models, one algorithm demonstrated highest performance. It exhibited statistically significant advantages accuracy p < 0.05) compared ResNet34 Specifically, showed superior discriminatory power. Quantitative evaluation through Net Reclassification Improvement (NRI) revealed that NRI values model, when 0.180, 0.240, 0.186, 0.221, respectively. All corresponding -values less than 0.05 comparison), confirming significantly outperformed other four reclassification ability. Moreover, its outcomes led marked improvements risk stratification classification accuracy. Conclusion ResNet18-based distinguishing tumors, providing effective non-invasive tool early detection cancer.

Language: Английский

---

Hypermetabolic pulmonary lesions detection and diagnosis based on PET/CT imaging and deep learning models

European Journal of Nuclear Medicine and Molecular Imaging, Journal Year: 2025, Volume and Issue: unknown

Published: April 4, 2025

Language: Английский

---

Decoding Lung Cancer Radiogenomics: A Custom Clustering/Classification Methodology to Simultaneously Identify Important Imaging Features and Relevant Genes

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(7), P. 4053 - 4053

Published: April 7, 2025

Background: This study evaluated a custom algorithm that sought to perform radiogenomic analysis on lung cancer genetic and imaging data, specifically by using machine learning see whether clustering/classification method could simultaneously identify features from data correspond markers. Methods: CT mutation for 281 subjects with NSCLC were collected the CPTAC-LUAD TCGA-LUSC databases TCIA. The was run as follows: (1) clusters initialized random clusters, binary matrix factorization, or k-means; (2) image classification these clusters; (3) misclassified re-classified based algorithm; (4) until an accuracy of 90% no improvement after 10 runs. Input mutations potential medical treatments severity provide clinical relevance. Results: able achieve >90% nine runs grouped starting five four final where better than every initial clustered accuracy. These stable across all three test A total thirty-eight genes top hundred each subject identified specific treatment data; twelve are listed. Conclusion: small pilot presented way patterns methodology group images labels only partial future problems.

Language: Английский

---

Advancing the frontier of artificial intelligence on emerging technologies to redefine cancer diagnosis and care

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 191, P. 110178 - 110178

Published: April 14, 2025

Language: Английский

---

Habitat Radiomics and Deep Learning Features Based on CT for Predicting Lymphovascular Invasion in T1-stage Lung Adenocarcinoma: A Multicenter Study

Academic Radiology, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

---