A whirl of radiomics-based biomarkers in cancer immunotherapy, why is large scale validation still lacking? DOI Creative Commons
Marta Ligero,

B. Gielen,

Vı́ctor Navarro

et al.

npj Precision Oncology, Journal Year: 2024, Volume and Issue: 8(1)

Published: Feb. 21, 2024

Abstract The search for understanding immunotherapy response has sparked interest in diverse areas of oncology, with artificial intelligence (AI) and radiomics emerging as promising tools, capable gathering large amounts information to identify suitable patients treatment. application AI radiology grown, driven by the hypothesis that images capture tumor phenotypes thus could provide valuable insights into likelihood. However, despite rapid growth studies, no algorithms field have reached clinical implementation, mainly due lack standardized methods, hampering study comparisons reproducibility across different datasets. In this review, we performed a comprehensive assessment published data sources variability design hinder comparison model performance and, therefore, implementation. Subsequently, conducted use-case meta-analysis using homogenous studies assess overall estimating programmed death-ligand 1 (PD-L1) expression. Our findings indicate that, numerous attempts predict response, only limited number share comparable methodologies report sufficient about cohorts methods be meta-analysis. Nevertheless, although few meet these criteria, their results underscore importance ongoing standardization benchmarking efforts. This review highlights uniformity reporting. Such is crucial enable meaningful demonstrate validity biomarkers populations, facilitating implementation patient selection process.

Language: Английский

Predicting EGFR Mutation Status in Non–Small Cell Lung Cancer Using Artificial Intelligence: A Systematic Review and Meta-Analysis DOI
Hung Song Nguyen, Dang Khanh Ngan Ho, Nam Nhat Nguyen

et al.

Academic Radiology, Journal Year: 2023, Volume and Issue: 31(2), P. 660 - 683

Published: April 28, 2023

Language: Английский

Citations

63
Artificial intelligence-based prediction of clinical outcome in immunotherapy and targeted therapy of lung cancer DOI

Xiaomeng Yin,

Hu Liao,

Yun Hong

et al.

Seminars in Cancer Biology, Journal Year: 2022, Volume and Issue: 86, P. 146 - 159

Published: Aug. 11, 2022

Language: Английский

Citations

64
Explainable artificial intelligence (XAI) in radiology and nuclear medicine: a literature review DOI Creative Commons
Bart M. de Vries, Gerben J. C. Zwezerijnen, George L. Burchell

et al.

Frontiers in Medicine, Journal Year: 2023, Volume and Issue: 10

Published: May 12, 2023

Rational Deep learning (DL) has demonstrated a remarkable performance in diagnostic imaging for various diseases and modalities therefore high potential to be used as clinical tool. However, current practice shows low deployment of these algorithms practice, because DL lack transparency trust due their underlying black-box mechanism. For successful employment, explainable artificial intelligence (XAI) could introduced close the gap between medical professionals algorithms. In this literature review, XAI methods available magnetic resonance (MR), computed tomography (CT), positron emission (PET) are discussed future suggestions made. Methods PubMed, Embase.com Clarivate Analytics/Web Science Core Collection were screened. Articles considered eligible inclusion if was (and well described) describe behavior model MR, CT PET imaging. Results A total 75 articles included which 54 17 described post ad hoc methods, respectively, 4 both methods. Major variations is seen Overall, lacks ability provide class-discriminative target-specific explanation. Ad seems tackle its intrinsic explain. quality control rarely applied systematic comparison difficult. Conclusion There currently no clear consensus on how should deployed order implementation. We advocate technical assessment Also, ensure end-to-end unbiased safe integration workflow, (anatomical) data minimization included.

Language: Английский

Citations

39
Predicting gene mutation status via artificial intelligence technologies based on multimodal integration (MMI) to advance precision oncology DOI Creative Commons
Jun Shao, Jiechao Ma, Qin Zhang

et al.

Seminars in Cancer Biology, Journal Year: 2023, Volume and Issue: 91, P. 1 - 15

Published: Feb. 20, 2023

Personalized treatment strategies for cancer frequently rely on the detection of genetic alterations which are determined by molecular biology assays. Historically, these processes typically required single-gene sequencing, next-generation or visual inspection histopathology slides experienced pathologists in a clinical context. In past decade, advances artificial intelligence (AI) technologies have demonstrated remarkable potential assisting physicians with accurate diagnosis oncology image-recognition tasks. Meanwhile, AI techniques make it possible to integrate multimodal data such as radiology, histology, and genomics, providing critical guidance stratification patients context precision therapy. Given that mutation is unaffordable time-consuming considerable number patients, predicting gene mutations based routine radiological scans whole-slide images tissue AI-based methods has become hot issue actual practice. this review, we synthesized general framework integration (MMI) intelligent diagnostics beyond standard techniques. Then summarized emerging applications prediction mutational profiles common cancers (lung, brain, breast, other tumor types) pertaining radiology histology imaging. Furthermore, concluded there truly exist multiple challenges way its real-world application medical field, including curation, feature fusion, model interpretability, practice regulations. Despite challenges, still prospect implementation highly decision-support tool aid oncologists future management.

Language: Английский

Citations

38
Computed Tomography-derived intratumoral and peritumoral radiomics in predicting EGFR mutation in lung adenocarcinoma DOI Creative Commons
Youlan Shang, Weidao Chen, Ge Li

et al.

La radiologia medica, Journal Year: 2023, Volume and Issue: 128(12), P. 1483 - 1496

Published: Sept. 25, 2023

Abstract Objective To investigate the value of Computed Tomography (CT) radiomics derived from different peritumoral volumes interest (VOIs) in predicting epidermal growth factor receptor (EGFR) mutation status lung adenocarcinoma patients. Materials and methods A retrospective cohort 779 patients who had pathologically confirmed were enrolled. 640 randomly divided into a training set, validation an internal testing set (3:1:1), remaining 139 defined as external set. The intratumoral VOI (VOI_I) was manually delineated on thin-slice CT images, seven VOIs (VOI_P) automatically generated with 1, 2, 3, 4, 5, 10, 15 mm expansion along VOI_I. 1454 radiomic features extracted each VOI. t -test, least absolute shrinkage selection operator (LASSO), minimum redundancy maximum relevance (mRMR) algorithm used for feature selection, followed by construction models (VOI_I model, VOI_P model combined model). performance evaluated area under curve (AUC). Results 399 classified EGFR mutant (EGFR+), while 380 wild-type (EGFR−). In sets, VOI4 (intratumoral 4 mm) achieved best predictive performance, AUCs 0.877, 0.727, 0.701, respectively, outperforming VOI_I (AUCs 0.728, 0.698, 0.653, respectively). Conclusions Radiomics region can add extra patients, optimal range mm.

Language: Английский

Citations

29
Deep learning in radiology for lung cancer diagnostics: A systematic review of classification, segmentation, and predictive modeling techniques DOI
Anirudh Atmakuru, Subrata Chakraborty, Oliver Faust

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 255, P. 124665 - 124665

Published: July 5, 2024

Language: Английский

Citations

11
AI models for the identification of prognostic and predictive biomarkers in lung cancer: a systematic review and meta-analysis DOI Creative Commons

Hind Alosaimi,

Aseel M. Alshilash,

Layan K. Al-Saif

et al.

Frontiers in Oncology, Journal Year: 2025, Volume and Issue: 15

Published: Feb. 26, 2025

This systematic review and meta-analysis aim to evaluate the efficacy of artificial intelligence (AI) models in identifying prognostic predictive biomarkers lung cancer. With increasing complexity cancer subtypes need for personalized treatment strategies, AI-driven approaches offer a promising avenue biomarker discovery clinical decision-making. A comprehensive literature search was conducted multiple electronic databases identify relevant studies published up date. Studies investigating AI identification were included. Data extraction, quality assessment, performed according PRISMA guidelines. total 34 met inclusion criteria, encompassing diverse methodologies targets. models, particularly deep learning machine algorithms demonstrated high accuracy predicting status. Most developed prediction EGFR, followed by PD-L1 ALK Internal external validation techniques confirmed robustness generalizability predictions across heterogeneous patient cohorts. According our results, pooled sensitivity specificity 0.77 (95% CI: 0.72 - 0.82) 0.79 0.78 0.84). The findings this highlight significant potential facilitating non-invasive assessment By enhancing diagnostic guiding selection, have revolutionize oncology improve outcomes management. Further research is warranted validate optimize utility large-scale prospective studies.

Language: Английский

Citations

1
A Thorough Review of the Clinical Applications of Artificial Intelligence in Lung Cancer DOI Open Access
Serafeim‐Chrysovalantis Kotoulas,

Dionysios Spyratos,

Κonstantinos Porpodis

et al.

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

Citations

1
Artificial intelligence for prediction of response to cancer immunotherapy DOI
Yuhan Yang, Yunuo Zhao,

Xici Liu

et al.

Seminars in Cancer Biology, Journal Year: 2022, Volume and Issue: 87, P. 137 - 147

Published: Nov. 11, 2022

Language: Английский

Citations

34
Systematic Review, Meta-Analysis and Radiomics Quality Score Assessment of CT Radiomics-Based Models Predicting Tumor EGFR Mutation Status in Patients with Non-Small-Cell Lung Cancer DOI Open Access
Mehdi Felfli, Yan Liu, Fadila Zerka

et al.

International Journal of Molecular Sciences, Journal Year: 2023, Volume and Issue: 24(14), P. 11433 - 11433

Published: July 14, 2023

Assessment of the quality and current performance computed tomography (CT) radiomics-based models in predicting epidermal growth factor receptor (EGFR) mutation status patients with non-small-cell lung carcinoma (NSCLC). Two medical literature databases were systematically searched, articles presenting original studies on CT for EGFR retrieved. Forest plots related statistical tests performed to summarize model inter-study heterogeneity. The methodological selected was assessed via Radiomics Quality Score (RQS). evaluated using area under curve (ROC AUC). range Risk RQS across varied from 11 24, indicating a notable heterogeneity methodology included studies. average score 15.25, which accounted 42.34% maximum possible score. pooled Area Under Curve (AUC) value 0.801, accuracy status. show promising results as non-invasive alternatives NSCLC patients. However, varies widely, further harmonization prospective validation are needed before generalization these models.

Language: Английский

Citations

18