Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review DOI Creative Commons
Gaia Ninatti, Margarita Kirienko, Emanuele Neri

et al.

Diagnostics, Journal Year: 2020, Volume and Issue: 10(6), P. 359 - 359

Published: May 30, 2020

The objective of this systematic review was to analyze the current state art imaging-derived biomarkers predictive genetic alterations and immunotherapy targets in lung cancer. We included original research studies reporting development validation imaging feature-based models. overall quality, standard advancements towards clinical practice were assessed. Eighteen out 24 selected articles classified as "high-quality" according Quality Assessment Diagnostic Accuracy Studies 2 (QUADAS-2). 18 "high-quality papers" adhered Transparent Reporting a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) with mean 62.9%. majority (16/18) phase II. most commonly used predictors radiomic features, followed by visual qualitative computed tomography (CT) convolutional neural network-based approaches positron emission (PET) parameters, all alone combined clinicopathologic features. (14/18) focused on epidermal growth factor receptor (EGFR) mutation. Thirty-five imaging-based models built predict EGFR status. model's performances ranged from weak (n = 5) acceptable 11), excellent 18) outstanding 1) set. Positive outcomes also reported ALK rearrangement, ALK/ROS1/RET fusions programmed cell death ligand 1 (PD-L1) expression. Despite promising results terms performance, image-based models, suffering methodological bias, require further before replacing traditional molecular pathology testing.

Language: Английский

Artificial intelligence-driven biomedical genomics DOI Open Access
Kairui Guo, Mengjia Wu,

Zelia Soo

et al.

Knowledge-Based Systems, Journal Year: 2023, Volume and Issue: 279, P. 110937 - 110937

Published: Sept. 7, 2023

Language: Английский

Citations

23
ARISE I Consensus Review on the Management of Intracranial Aneurysms DOI
Stavropoula Tjoumakaris, Ricardó A. Hanel, J Mocco

et al.

Stroke, Journal Year: 2024, Volume and Issue: 55(5), P. 1428 - 1437

Published: April 22, 2024

Intracranial aneurysms (IAs) remain a challenging neurological diagnosis associated with significant morbidity and mortality. There is plethora of microsurgical endovascular techniques for the treatment both ruptured unruptured aneurysms. no definitive consensus as to best option this cerebrovascular pathology. The Aneurysm, Arteriovenous Malformation, Chronic Subdural Hematoma Roundtable Discussion With Industry Stroke Experts discussed practices most promising approaches improve management brain

Language: Английский

Citations

12
Radiogenomics and machine learning predict oncogenic signaling pathways in glioblastoma DOI Creative Commons
Abdul Basit Ahanger, Syed Wajid Aalam, Tariq Masoodi

et al.

Journal of Translational Medicine, Journal Year: 2025, Volume and Issue: 23(1)

Published: Jan. 27, 2025

Language: Английский

Citations

1
A Review of Radiomics and Deep Predictive Modeling in Glioma Characterization DOI
Sonal Gore,

Tanay Chougule,

Jayant Jagtap

et al.

Academic Radiology, Journal Year: 2020, Volume and Issue: 28(11), P. 1599 - 1621

Published: July 10, 2020

Language: Английский

Citations

67
Imaging-Based Prediction of Molecular Therapy Targets in NSCLC by Radiogenomics and AI Approaches: A Systematic Review DOI Creative Commons
Gaia Ninatti, Margarita Kirienko, Emanuele Neri

et al.

Diagnostics, Journal Year: 2020, Volume and Issue: 10(6), P. 359 - 359

Published: May 30, 2020

The objective of this systematic review was to analyze the current state art imaging-derived biomarkers predictive genetic alterations and immunotherapy targets in lung cancer. We included original research studies reporting development validation imaging feature-based models. overall quality, standard advancements towards clinical practice were assessed. Eighteen out 24 selected articles classified as "high-quality" according Quality Assessment Diagnostic Accuracy Studies 2 (QUADAS-2). 18 "high-quality papers" adhered Transparent Reporting a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) with mean 62.9%. majority (16/18) phase II. most commonly used predictors radiomic features, followed by visual qualitative computed tomography (CT) convolutional neural network-based approaches positron emission (PET) parameters, all alone combined clinicopathologic features. (14/18) focused on epidermal growth factor receptor (EGFR) mutation. Thirty-five imaging-based models built predict EGFR status. model's performances ranged from weak (n = 5) acceptable 11), excellent 18) outstanding 1) set. Positive outcomes also reported ALK rearrangement, ALK/ROS1/RET fusions programmed cell death ligand 1 (PD-L1) expression. Despite promising results terms performance, image-based models, suffering methodological bias, require further before replacing traditional molecular pathology testing.

Language: Английский

Citations

65