Опубликована: Янв. 1, 2024
Язык: Английский
Energy Economics, Год журнала: 2024, Номер 131, С. 107403 - 107403
Опубликована: Фев. 12, 2024
Язык: Английский
Процитировано
53
Cancers, Год журнала: 2024, Номер 16(6), С. 1130 - 1130
Опубликована: Март 12, 2024
Purpose: The authors aimed to develop and validate deep-learning-based radiogenomic (DLR) models radiomic signatures predict the EGFR mutation in patients with NSCLC, assess semantic clinical features that can contribute detecting mutations. Methods: Using 990 from two NSCLC trials, we employed an end-to-end pipeline analyzing CT images without precise segmentation. Two 3D convolutional neural networks segmented lung masses nodules. Results: combined radiomics DLR model achieved AUC of 0.88 ± 0.03 predicting status, outperforming individual models. Semantic further improved model’s accuracy, 0.05. were found be significantly associated mutations pure solid tumours no ground glass component (p < 0.03), absence peripheral emphysema presence pleural retraction = 0.004), fissure attachment 0.001), metastatic nodules both tumour-containing lobe 0.001) non-tumour-containing ipsilateral effusion 0.04), average enhancement tumour mass above 54 HU 0.001). Conclusions: This AI-based demonstrated high accuracy mutation, serving as a non-invasive user-friendly imaging biomarker for status prediction.
Язык: Английский
Процитировано
10
Electronics, Год журнала: 2025, Номер 14(6), С. 1058 - 1058
Опубликована: Март 7, 2025
Nucleus accurate segmentation is a crucial task in biomedical image analysis. While convolutional neural networks (CNNs) have achieved notable progress this field, challenges remain due to the complexity and heterogeneity of cell images, especially overlapping regions nuclei. To address limitations current methods, we propose mechanism multiple differential convolution local-variation attention CNNs, leading so-called U-Net (MDLA-UNet). The employs operators capture gradient direction information, improving network’s capability detect edges. utilizes Haar discrete wavelet transforms for level-1 decomposition obtain approximate features, then derives high-frequency features enhance global context local detail variation feature maps. results on MoNuSeg, TNBC, CryoNuSeg datasets demonstrated superior performance proposed method cells having complex boundaries details with respect existing methods. MDLA-UNet presents ability capturing fine edges maps thus improves nuclei blurred regions.
Язык: Английский
Процитировано
1
Current Oncology, Год журнала: 2024, Номер 31(9), С. 5255 - 5290
Опубликована: Сен. 6, 2024
Artificial intelligence (AI) is revolutionizing head and neck cancer (HNC) care by providing innovative tools that enhance diagnostic accuracy personalize treatment strategies. This review highlights the advancements in AI technologies, including deep learning natural language processing, their applications HNC. The integration of with imaging techniques, genomics, electronic health records explored, emphasizing its role early detection, biomarker discovery, planning. Despite noticeable progress, challenges such as data quality, algorithmic bias, need for interdisciplinary collaboration remain. Emerging innovations like explainable AI, AI-powered robotics, real-time monitoring systems are poised to further advance field. Addressing these fostering among experts, clinicians, researchers crucial developing equitable effective applications. future HNC holds significant promise, offering potential breakthroughs diagnostics, personalized therapies, improved patient outcomes.
Язык: Английский
Процитировано
9
Cancers, Год журнала: 2024, Номер 16(14), С. 2593 - 2593
Опубликована: Июль 19, 2024
Parathyroid pathologies are suspected based on the biochemical alterations and clinical manifestations, predominant roles of imaging in primary hyperparathyroidism localisation tumour within parathyroid glands, surgical planning, to look for any ectopic tissue setting recurrent disease. This article provides a comprehensive review embryology anatomical variations glands their relevance, anatomy differentiation between multiglandular disease, solitary adenoma, atypical tumour, carcinoma. The roles, advantages limitations ultrasound, four-dimensional computed tomography (4DCT), radiolabelled technetium-99 (99mTc) sestamibi or dual tracer 99mTc pertechnetate 99mTc-sestamibi with without single photon emission (SPECT) SPECT/CT, dynamic enhanced magnetic resonance (4DMRI), fluoro-choline positron (18F-FCH PET) [11C] Methionine (11C -MET) PET management lesions have been extensively discussed this article. role fluorodeoxyglucose (FDG-PET) has also elucidated Management guidelines carcinoma proposed by American Society Clinical Oncology (ASCO) described. An algorithm provided at end serve as quick reference guide radiologists, clinicians surgeons.
Язык: Английский
Процитировано
4
Indian journal of radiology and imaging - new series/Indian journal of radiology and imaging/Indian Journal of Radiology & Imaging, Год журнала: 2025, Номер 35(S 01), С. S119 - S127
Опубликована: Янв. 1, 2025
Abstract Evidence-based medicine integrates clinical research, personal expertise, and patient values. The most robust forms of evidence, such as randomized controlled trials (RCTs) prospective studies, provide the strongest support for medical decision-making. RCTs are vital in radiology evaluating new imaging technologies, contrast agents, therapeutic procedures, despite challenges translating preclinical findings to practice. This guide discusses history, principles, methodologies, applications radiology, highlighting their role advancing field supporting evidence-based
Язык: Английский
Процитировано
0
Journal for ImmunoTherapy of Cancer, Год журнала: 2025, Номер 13(4), С. e011692 - e011692
Опубликована: Апрель 1, 2025
Immunotherapy has revolutionized head and neck squamous cell carcinoma (HNSCC) treatment, with neoadjuvant chemoimmunotherapy showing promising pathological complete response rates (36–42%). Lin et al introduce a radiomics-clinical nomogram using MRI-derived intratumoral peritumoral features to predict pCR, addressing critical clinical gap. Their model, emphasizing the region (within 3 mm), achieved high predictive accuracy area under curve (AUC) >0.8. While multicenter design enhances generalizability, standardizing imaging protocols remains challenge. Integrating radiomics Neck Imaging Reporting Data System could refine post-treatment assessment. This study advances precision oncology in HNSCC, offering non-invasive tool for personalized treatment strategies. Future directions include artificial intelligence-driven radiogenomics enhance prediction patient selection.
Язык: Английский
Процитировано
0
Energy Economics, Год журнала: 2025, Номер unknown, С. 108550 - 108550
Опубликована: Май 1, 2025
Язык: Английский
Процитировано
0
BMC Medical Imaging, Год журнала: 2024, Номер 24(1)
Опубликована: Янв. 5, 2024
Abstract Background To investigate the role of CT radiomics in distinguishing Wilms tumor (WT) from clear cell sarcoma kidney (CCSK) pediatric patients. Methods We retrospectively enrolled 83 cases WT and 33 CCSK. These were randomly stratified into a training set ( n = 81) test 35). Several imaging features nephrographic phase analyzed, including maximum diameter, ratio value solid portion to mean contralateral renal vein (CTmax/CT vein), presence dilated peritumoral cysts. Radiomics corticomedullary extracted, selected, subsequently integrated logistic regression model. evaluated model's performance using area under curve (AUC), 95% confidence interval (CI), accuracy. Results In set, there statistically significant differences diameter P 0.021) cysts 0.005) between CCSK, whereas no observed > 0.05). The model, constructed four features, demonstrated strong with an AUC 0.889 (95% CI: 0.811–0.967) accuracy 0.864. Upon evaluation fivefold cross-validation remained high at 0.863 0.774–0.952), 0.852. model achieved 0.792 0.616–0.968) 0.857. Conclusion proves be diagnostically valuable for CCSK cases.
Язык: Английский
Процитировано
2
Frontiers in Public Health, Год журнала: 2023, Номер 11
Опубликована: Дек. 15, 2023
This paper pioneers the exploration of ocular cancer, and its management with help Artificial Intelligence (AI) technology. Existing literature presents a significant increase in new eye cancer cases 2023, experiencing higher incidence rate. Extensive research was conducted using online databases such as PubMed, ACM Digital Library, ScienceDirect, Springer. To conduct this review, Preferred Reporting Items for Systematic Reviews Meta-Analysis (PRISMA) guidelines are used. Of collected 62 studies, only 20 documents met inclusion criteria. The review study identifies seven types. Important challenges associated highlighted, including limited awareness about restricted healthcare access, financial barriers, insufficient infrastructure support. Financial barriers is one widely examined literature. potential role limitations ChatGPT discussed, emphasizing usefulness providing general information to physicians, noting inability deliver up-to-date information. concludes by presenting future applications advance on globally.
Язык: Английский
Процитировано
1