American Journal of Roentgenology, Год журнала: 2024, Номер 223(4)
Опубликована: Авг. 28, 2024
Язык: Английский
Respiratory Research, Год журнала: 2025, Номер 26(1)
Опубликована: Апрель 11, 2025
The varying degrees of radiotherapy sensitivity tumors limit the efficacy tumor radiotherapy. In this research, based on single cell sequence data we used radiomics to help identify and screen feature signatures distinguish radiosensitivity in different regions target area non-small lung cancer can provide a new pattern assess assist clinical decision-making. This retrospective study included CT radiology from 454 patients diagnosed with multiple real-world cohorts prior primary was delineated training set (n = 154) segmented obtain radiogenomic signature. signature LCDigital-RT, which predict radiosensitivity, developed by combining transcriptome sequencing index validated two independent external validation sets 74) 160). Besides, also described single-cell landscape attempting explain potential biological mechanism at level. By constructing solely signature, pre LCDigital-RT effectively populations differences radiation cancer, AUCs 0.759, 0.728 0.745 for sets, respectively. However, has greater advantage, AUC 0.837, been well JXCH cohort (AUC 0.789) GDPH 0.791). With be divided into sensitive resistant groups, there is significant difference characteristics lesions between groups. We have enriched interpretability our features biology level, demonstrating their enormous value translational research. an LCDigital RT prediction tool that will risk differences. visualizing thermal map area, development plans, reduce occurrence toxicity events, improve efficacy. At same time, it provides reference basis evaluating imaging, genetics, other aspects.
Язык: Английский
Процитировано
0
Deleted Journal, Год журнала: 2024, Номер 1(1)
Опубликована: Янв. 1, 2024
Abstract The advent of radiomics has revolutionized medical image analysis, affording the extraction high dimensional quantitative data for detailed examination normal and abnormal tissues. Artificial intelligence (AI) can be used enhancement a series steps in pipeline, from acquisition preprocessing, to segmentation, feature extraction, selection, model development. aim this review is present most AI methods explaining advantages limitations methods. Some prominent architectures mentioned include Boruta, random forests, gradient boosting, generative adversarial networks, convolutional neural transformers. Employing these models process analysis significantly enhance quality effectiveness while addressing several that reduce predictions. Addressing enable clinical decisions wider adoption. Importantly, will highlight how assist overcoming major bottlenecks implementation, ultimately improving translation potential method.
Язык: Английский
Процитировано
3
Genes, Год журнала: 2024, Номер 15(6), С. 803 - 803
Опубликована: Июнь 18, 2024
Background: Radiomics, an evolving paradigm in medical imaging, involves the quantitative analysis of tumor features and demonstrates promise predicting treatment responses outcomes. This study aims to investigate predictive capacity radiomics for genetic alterations non-small cell lung cancer (NSCLC). Methods: exploratory, observational integrated radiomic perspectives using computed tomography (CT) genomic through next-generation sequencing (NGS) applied liquid biopsies. Associations between mutations were established Area Under Receiver Operating Characteristic curve (AUC-ROC). Machine learning techniques, including Support Vector (SVM) classification, aim predict based on features. The prognostic impact selected gene variants was assessed Kaplan–Meier curves Log-rank tests. Results: Sixty-six patients underwent screening, with fifty-seven being comprehensively characterized radiomically genomically. Predominantly males (68.4%), adenocarcinoma prevalent histological type (73.7%). Disease staging is distributed across I/II (38.6%), III (31.6%), IV (29.8%). Significant correlations identified ROS1 p.Thr145Pro (shape_Sphericity), p.Arg167Gln (glszm_ZoneEntropy, firstorder_TotalEnergy), p.Asp2213Asn (glszm_GrayLevelVariance, firstorder_RootMeanSquared), ALK p.Asp1529Glu (glcm_Imc1). Patients variant demonstrated markedly shorter median survival compared wild-type group (9.7 months vs. not reached, p = 0.0143; HR: 5.35; 95% CI: 1.39–20.48). Conclusions: exploration intersection genetics NSCLC only feasible but also holds potential improve predictions enhance accuracy.
Язык: Английский
Процитировано
2
Seminars in Radiation Oncology, Год журнала: 2024, Номер 34(4), С. 379 - 394
Опубликована: Сен. 11, 2024
Язык: Английский
Процитировано
1
LatIA, Год журнала: 2023, Номер 1, С. 17 - 17
Опубликована: Ноя. 30, 2023
This article explores how the artificial intelligence (IA) it is transforming education in natural sciences by means of strategies pedagogic innovators. The IA allows learning personalization, adjusting content and rhythm to individual necessities students, what improves understanding retention complex concepts significantly. Also, use simulations virtual models believe interactive visual environments, enriching educational experience. These tools also foment development critical creative skills, promoting a more active collaborative approach resolution scientific problems. On whole, these not only improve effectiveness learning, but rather they prepare students face challenges XXI century with solid base science technology.
Язык: Английский
Процитировано
3
American Journal of Roentgenology, Год журнала: 2024, Номер 223(4)
Опубликована: Авг. 28, 2024
Язык: Английский
Процитировано
0