Related references
Note: Only part of the references are listed.
Article
Oncology
Ilyass Moummad et al.
Summary: Due to long waiting times for MRI, algorithms such as resampling and denoising models are developed to speed up image acquisition time. However, the impact of these algorithms on radiomics has been poorly studied. This study aimed to develop resampling and denoising DL models and evaluate their impact on radiomics. The findings showed that DL models were able to reconstruct low resolution and noised MRI images quickly into high quality images, restoring radiomic features.
Article
Oncology
Jose Marcio Luna et al.
Summary: Personalized therapy for NSCLC relies on invasive biopsies. This study explores the potential of using predictive models that integrate radiomic features extracted from CT images and clinical predictors to predict the survival of NSCLC patients. The results suggest that radiomic biomarkers derived through feature harmonization significantly improve the prediction of overall survival.
Article
Multidisciplinary Sciences
Marta Luksza et al.
Summary: This study provides evidence that the human immune system naturally edits neoantigens in cancer, leading to the dominance of less immunogenic clones. The research also presents a model to predict how immune pressure affects the evolution of cancer cell populations.
Article
Oncology
Parisa Forouzannezhad et al.
Summary: In this study, the utility of a multitask machine learning radiomics framework for survival outcome prediction in patients with non-small cell lung cancer (NSCLC) was evaluated. The study found that multitask learning of FDG-PET radiomics achieved higher survival prediction than other modalities and clinical benchmarks. The results highlight the potential importance of multitask learning radiomics in personalized cancer treatment strategies.
Review
Oncology
Stella Logotheti et al.
Summary: Cancer follows Darwinian selection, especially during metastasis. Tumors often co-opt developmental and tissue-homeostasis programs as a strategy to increase their fitness. The TP73 gene, a sibling of TP53, regulates various processes in embryonic development, tissue homeostasis, and cancer. The different isoforms of TP73 may work together to activate specific programs that help in overcoming the barriers of metastasis. Understanding the critical isoform patterns of TP73 in tumor evolution could provide strategies for the prevention and therapy of cancer metastasis.
CANCER AND METASTASIS REVIEWS
(2022)
Review
Oncology
Ionut-Gabriel Funingana et al.
Summary: This review aims to identify the challenges and opportunities for discovering new imaging-based biomarkers in single-site solid tumors, focusing on segmentation, validation, and data sharing strategies.
Article
Medical Informatics
Christos P. Kotanidis et al.
Summary: This study aimed to develop an AI-assisted image analysis platform that quantifies cytokine-driven vascular inflammation from routine CT angiograms and validate its prognostic value in COVID-19. The results showed that this novel radiotranscriptomic platform could predict in-hospital mortality in COVID-19 patients and provide insights for targeted therapy.
LANCET DIGITAL HEALTH
(2022)
Review
Oncology
Nader El-Sayes et al.
Summary: Tumor heterogeneity remains a major obstacle in successful cancer treatment, arising from changes in the tumor microenvironment and leading to the presence of different malignant subpopulations within a single tumor mass. Therapeutic interventions can increase selective pressure towards resistant subpopulations, often causing relapse in previously responsive patients. Strategies such as multi-therapy regimens are being employed to combat intrinsic resistance mechanisms, especially in the field of cancer immunotherapy, where antigen escape and immunosuppression are common forms of acquired resistance.
Article
Oncology
Tariq Mahmood et al.
Summary: This study proposes a radiomics approach based on advanced machine learning algorithms for diagnosing pathological microcalcifications in mammogram images, providing radiologists with a valuable decision support system. An adaptive enhancement method based on the contourlet transform is used to enhance microcalcifications and suppress background and noise effectively, improving physicians' work efficiency in diagnosing breast microcalcifications.
Article
Oncology
Michelle Hershman et al.
Summary: The study focuses on the impact of different levels of training and clinical experience on interobserver variability in manual segmentation of non-small cell lung cancer (NSCLC). It concludes that accurate radiomic feature extraction for NSCLC can be achieved using segmenters of different levels of training and clinical experience, potentially allowing flexibility in producing robust prognostic imaging biomarkers for clinical translation.
Article
Medicine, General & Internal
Eleftherios Trivizakis et al.
Summary: Radiogenomic and radiotranscriptomic studies can provide a holistic decision support system for treatment evaluation and care planning by integrating genomics, transcriptomics, radiomics, and clinical parameters. Using data-driven machine learning models, the fusion analysis of deep features and transcriptomics in non-small cell lung carcinoma shows potential for higher sensitivity and AUC compared to baseline models.
Article
Oncology
Liyuan Fan et al.
Review
Oncology
Sanjna Nilesh Nerurkar et al.
Article
Oncology
S. Trebeschi et al.
ANNALS OF ONCOLOGY
(2019)
Article
Biochemical Research Methods
Francisco Romero-Ferrero et al.
Article
Computer Science, Artificial Intelligence
Afshin Dehghan et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Article
Radiology, Nuclear Medicine & Medical Imaging
Robert J. Gillies et al.