Application of CT-based foundational AI and radiomics models for prediction of outcome for non-small-cell lung cancer patients treated on the NRG/RTOG 0617 clinical trial DOI Creative Commons
Taman Upadhaya, Indrin J. Chetty, Elizabeth McKenzie

et al.

BJR|Open, Journal Year: 2023, Volume and Issue: 6(1)

Published: Dec. 12, 2023

Abstract Objectives To apply CT-based foundational artificial intelligence (AI) and radiomics models for predicting overall survival (OS) patients with locally advanced non-small cell lung cancer (NSCLC). Methods Data 449 retrospectively treated on the NRG Oncology/Radiation Therapy Oncology Group (RTOG) 0617 clinical trial were analyzed. Foundational AI, radiomics, features evaluated using univariate cox regression correlational analyses to determine independent predictors of survival. Several fit these model performance was nested cross-validation unseen test datasets via area under receiver-operator-characteristic curves, AUCs. Results For all patients, combined AI achieved AUCs 0.67 Random Forest (RF) model. The RF 0.66. In low-dose arm, alone AUC 0.67, while ensemble 0.65 support vector machine (SVM). high-dose values 0.66 Conclusions This study demonstrated encouraging results application prediction outcomes. More research is warranted understand value toward improving complementary information. Advances in knowledge Using radiomics-based we able identify significant signatures outcomes NSCLC a national cooperative group trial. Associated will be important prospective patients.

Language: Английский

A Historical Survey of Key Epidemiological Studies of Ionizing Radiation Exposure DOI
Mark P. Little, D. Bаzyка, Amy Berrington de González

et al.

Radiation Research, Journal Year: 2024, Volume and Issue: 202(2)

Published: July 18, 2024

In this article we review the history of key epidemiological studies populations exposed to ionizing radiation. We highlight historical and recent findings regarding radiation-associated risks for incidence mortality cancer non-cancer outcomes with emphasis on study design methods exposure assessment dose estimation along brief consideration sources bias a few more important studies. examine from Japanese atomic bomb survivors, persons radiation diagnostic or therapeutic purposes, those environmental including Chornobyl other reactor accidents, occupationally cohorts. also summarize results pooled These summaries are necessarily brief, but provide references detailed information. discuss possible future directions study, include susceptible populations, new data sources, designs analysis.

Language: Английский

Citations

7
Lung Cancer Research and Treatment: Global Perspectives and Strategic Calls to Action DOI
May-Lucie Meyer,

S. Peters,

Tony Mok

et al.

Annals of Oncology, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 1, 2024

Language: Английский

Citations

7
Image quality in radiomics for enhanced medical diagnostics: A metrology overview with a critical approach DOI Creative Commons

Francesco Felicetti,

Sandra Costanzo, Domenico Luca Carní

et al.

Measurement Sensors, Journal Year: 2025, Volume and Issue: unknown, P. 101656 - 101656

Published: Jan. 1, 2025

Language: Английский

Citations

0
Prognostic significance of the mEPE score in intermediate-risk prostate cancer patients undergoing ultrahypofractionated robotic SBRT DOI Creative Commons
Lucas Mose, Laura I. Loebelenz,

Alexander Althaus

et al.

Strahlentherapie und Onkologie, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 14, 2025

Language: Английский

Citations

0
Dual-radiomics based on SHapley additive explanations for predicting hematologic toxicity in concurrent chemoradiotherapy patients DOI Creative Commons

Luqiao Chen,

Zhipeng He,

Qianxi Ni

et al.

Discover Oncology, Journal Year: 2025, Volume and Issue: 16(1)

Published: April 16, 2025

Language: Английский

Citations

0
Advancements and implications of artificial intelligence for early detection, diagnosis and tailored treatment of cancer DOI
Sonia Chadha, Sayali Mukherjee, Somali Sanyal

et al.

Seminars in Oncology, Journal Year: 2025, Volume and Issue: 52(3), P. 152349 - 152349

Published: May 8, 2025

Language: Английский

Citations

0
Multimodality radiomics prediction of radiotherapy-induced the early proctitis and cystitis in rectal cancer patients: a machine learning study DOI
Samira Abbaspour, Maedeh Barahman, Hamid Abdollahi

et al.

Biomedical Physics & Engineering Express, Journal Year: 2023, Volume and Issue: 10(1), P. 015017 - 015017

Published: Nov. 23, 2023

Abstract Purpose. This study aims to predict radiotherapy-induced rectal and bladder toxicity using computed tomography (CT) magnetic resonance imaging (MRI) radiomics features in combination with clinical dosimetric cancer patients. Methods. A total of sixty-three patients locally advanced who underwent three-dimensional conformal radiation therapy (3D-CRT) were included this study. Radiomics extracted from the rectum walls pretreatment CT MR-T2W-weighted images. Feature selection was performed various methods, including Least Absolute Shrinkage Selection Operator (Lasso), Minimum Redundancy Maximum Relevance (MRMR), Chi-square (Chi2), Analysis Variance (ANOVA), Recursive Elimination (RFE), SelectPercentile. Predictive modeling carried out machine learning algorithms, such as K-nearest neighbor (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Gradient Boosting (XGB), Linear Discriminant (LDA). The impact Laplacian Gaussian (LoG) filter investigated sigma values ranging 0.5 2. Model performance evaluated terms area under receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, specificity. Results. 479 extracted, 59 selected. pre-MRI T2W model exhibited highest predictive an AUC: 91.0/96.57%, accuracy: 90.38/96.92%, precision: 90.0/97.14%, sensitivity: 93.33/96.50%, specificity: 88.09/97.14%. These results achieved both original image LoG (sigma = 0.5–1.5) based on LDA/DT-RF classifiers for proctitis cystitis, respectively. Furthermore, data, 90.71/96.0%, 90.0/96.92%, 88.14/97.14%, 93.0/96.0%, 88.09/97.14% acquired. XGB/DT-XGB cystitis 2)/LoG 0.5–2), MRMR/RFE-Chi2 feature methods demonstrated best model. MRMR/MRMR-Lasso yielded CT. Conclusion. MR images can effectively radiation-induced cystitis. found that LDA, DT, RF, XGB classifiers, combined MRMR, RFE, Chi2, Lasso along filter, offer strong performance. With inclusion a larger training dataset, these models be valuable tools personalized radiotherapy decision-making.

Language: Английский

Citations

9
The Evolving Role of Novel Imaging techniques for Radiotherapy Planning DOI
David J. Noble,

R. Ramaesh,

Morag Brothwell

et al.

Clinical Oncology, Journal Year: 2024, Volume and Issue: 36(8), P. 514 - 526

Published: June 11, 2024

Language: Английский

Citations

3
Personalized Medicine Through Quantum Computing DOI
Muskan Sharma, Yash Mahajan, Abdullah Alzahrani

et al.

Advances in bioinformatics and biomedical engineering book series, Journal Year: 2023, Volume and Issue: unknown, P. 147 - 166

Published: Dec. 29, 2023

This chapter explores the transformative intersection of quantum computing and healthcare, particularly in realm personalized medicine. The amalgamation healthcare has ushered a new era where unique genetic profile individuals can be leveraged to craft highly tailored medical treatments. Traditional methods often fall short managing immense complexity data, necessitating paradigm shift. Quantum computing, with its unprecedented computational capabilities, especially machine learning, emerges as revolutionary technology decipher intricate patterns streamline development treatment approaches. delineates objectives medicine, emphasizing pivotal role enhancing efficacy, minimizing adverse effects, tailoring preventive strategies, facilitating drug discovery, harnessing advantages.

Language: Английский

Citations

2
“Under the hood”: artificial intelligence in personalized radiotherapy DOI Creative Commons
Chiara Gianoli, Elisabetta De Bernardi, Katia Parodi

et al.

BJR|Open, Journal Year: 2023, Volume and Issue: 6(1)

Published: Dec. 12, 2023

Abstract This review presents and discusses the ways in which artificial intelligence (AI) tools currently intervene, or could potentially intervene future, to enhance diverse tasks involved radiotherapy workflow. The framework is presented on 2 different levels for personalization of treatment, distinct methodologies. first level clinically well-established anatomy-based workflow, known as adaptive radiation therapy. second referred biology-driven explored research literature recently appearing some preliminary clinical trials personalized treatments. A 2-fold role AI defined according these levels. In streamline improve terms time variability reductions compared conventional workflow instead fully relies AI, introduces decision-making opening uncharted frontiers that were past deemed challenging explore. These methodologies are radiomics dosiomics, handling imaging dosimetric information, multiomics, when complemented by biological parameters (ie, biomarkers). explicitly highlights incorporated into practice still research, with aim presenting AI’s growing radiotherapy.

Language: Английский

Citations

1