The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping

Radiology, Journal Year: 2020, Volume and Issue: 295(2), P. 328 - 338

Published: March 10, 2020

The image biomarker standardisation initiative (IBSI) is an independent international collaboration which works towards standardising the extraction of biomarkers from acquired imaging for purpose high-throughput quantitative analysis (radiomics). Lack reproducibility and validation studies considered to be a major challenge field. Part this lies in scantiness consensus-based guidelines definitions process translating into biomarkers. IBSI therefore seeks provide nomenclature definitions, benchmark data sets, values verify processing calculations, as well reporting guidelines, analysis.

Language: Английский

---

Radiomics: from qualitative to quantitative imaging

British Journal of Radiology, Journal Year: 2020, Volume and Issue: 93(1108)

Published: Feb. 26, 2020

Historically, medical imaging has been a qualitative or semi-quantitative modality. It is difficult to quantify what can be seen in an image, and turn it into valuable predictive outcomes. As result of advances both computational hardware machine learning algorithms, computers are making great strides obtaining quantitative information from correlating with Radiomics, its two forms “handcrafted deep,” emerging field that translates images data yield biological enable radiologic phenotypic profiling for diagnosis, theragnosis, decision support, monitoring. Handcrafted radiomics multistage process which features based on shape, pixel intensities, texture extracted radiographs. Within this review, we describe the steps: starting data, how extracted, correlate clinical outcomes, resulting models used make predictions, such as survival, detection classification diagnostics. The application deep learning, second arm radiomics, place workflow discussed, along advantages disadvantages. To better illustrate technologies being used, provide real-world applications oncology, showcasing research well covering limitations future direction.

Language: Английский

---

Radiomics in predicting treatment response in non-small-cell lung cancer: current status, challenges and future perspectives

European Radiology, Journal Year: 2020, Volume and Issue: 31(2), P. 1049 - 1058

Published: Aug. 18, 2020

Abstract Objectives Radiomics is the extraction of quantitative data from medical imaging, which has potential to characterise tumour phenotype. The radiomics approach capacity construct predictive models for treatment response, essential pursuit personalised medicine. In this literature review, we summarise current status and evaluate scientific reporting quality research in prediction response non-small-cell lung cancer (NSCLC). Methods A comprehensive search was conducted using PubMed database. total 178 articles were screened eligibility 14 peer-reviewed included. score (RQS), a radiomics-specific metric emulating TRIPOD guidelines, used assess quality. Results Included studies reported several markers including first-, second- high-order features, such as kurtosis, grey-level uniformity wavelet HLL mean respectively, well PET-based metabolic parameters. Quality assessment demonstrated low median + 2.5 (range − 5 9), mainly reflecting lack reproducibility clinical evaluation. There extensive heterogeneity between due differences patient population, stage, modality, follow-up timescales workflow methodology. Conclusions not yet been translated into use. Efforts towards standardisation collaboration are needed identify reproducible radiomic predictors response. Promising must be externally validated their impact evaluated within pathway before they can implemented decision-making tool facilitate patients with NSCLC. Key Points • included promising cancer; however, there studies. (RQS) 9). Future should focus on implementation standardised features software, together external validation prospective setting.

Language: Английский

---

Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy

European Journal of Hybrid Imaging, Journal Year: 2020, Volume and Issue: 4(1)

Published: Sept. 22, 2020

Abstract This brief review summarizes the major applications of artificial intelligence (AI), in particular deep learning approaches, molecular imaging and radiation therapy research. To this end, five generic fields therapy, including PET instrumentation design, image reconstruction quantification segmentation, denoising (low-dose imaging), dosimetry computer-aided diagnosis, outcome prediction are discussed. sets out to cover briefly fundamental concepts AI followed by a presentation seminal achievements challenges facing their adoption clinical setting.

Language: Английский

---

Deep Learning for Smart Healthcare—A Survey on Brain Tumor Detection from Medical Imaging

Sensors, Journal Year: 2022, Volume and Issue: 22(5), P. 1960 - 1960

Published: March 2, 2022

Advances in technology have been able to affect all aspects of human life. For example, the use medicine has made significant contributions society. In this article, we focus on assistance for one most common and deadly diseases exist, which is brain tumors. Every year, many people die due tumors; based "braintumor" website estimation U.S., about 700,000 primary tumors, 85,000 are added every year. To solve problem, artificial intelligence come aid humans. Magnetic resonance imaging (MRI) method diagnose Additionally, MRI commonly used medical image processing dissimilarity different parts body. study, conducted a comprehensive review existing efforts applying types deep learning methods data determined challenges domain followed by potential future directions. One branches that very successful images CNN. Therefore, survey, various architectures CNN were reviewed with images, especially images.

Language: Английский

---

Artificial intelligence for pre-operative lymph node staging in colorectal cancer: a systematic review and meta-analysis

BMC Cancer, Journal Year: 2021, Volume and Issue: 21(1)

Published: Sept. 26, 2021

Abstract Background Artificial intelligence (AI) is increasingly being used in medical imaging analysis. We aimed to evaluate the diagnostic accuracy of AI models for detection lymph node metastasis on pre-operative staging colorectal cancer. Methods A systematic review was conducted according PRISMA guidelines using a literature search PubMed (MEDLINE), EMBASE, IEEE Xplore and Cochrane Library studies published from January 2010 October 2020. Studies reporting radiomics and/or deep learning cancer by CT/MRI were included. Conference abstracts image segmentation rather than nodal classification excluded. The quality assessed modified questionnaire QUADAS-2 criteria. Characteristics measures each study extracted. Pooling area under receiver operating characteristic curve (AUROC) calculated meta-analysis. Results Seventeen eligible identified inclusion review, which 12 five models. High risk bias found two there significant heterogeneity among papers (73.0%). In rectal cancer, per-patient AUROC 0.808 (0.739–0.876) 0.917 (0.882–0.952) models, respectively. Both performed better radiologists who had an 0.688 (0.603 0.772). Similarly with 0.727 (0.633–0.821) outperformed radiologist 0.676 (0.627–0.725). Conclusion have potential predict more accurately however, are heterogeneous scarce. Trial registration PROSPERO CRD42020218004 .

Language: Английский

---

Joint EANM/SNMMI guideline on radiomics in nuclear medicine

European Journal of Nuclear Medicine and Molecular Imaging, Journal Year: 2022, Volume and Issue: 50(2), P. 352 - 375

Published: Nov. 3, 2022

The purpose of this guideline is to provide comprehensive information on best practices for robust radiomics analyses both hand-crafted and deep learning-based approaches.

Language: Английский

---

Introduction to radiomics for a clinical audience

Clinical Radiology, Journal Year: 2023, Volume and Issue: 78(2), P. 83 - 98

Published: Jan. 11, 2023

Radiomics is a rapidly developing field of research focused on the extraction quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding disease processes and provide clinical decision support. To date, most radiomics has been oncological applications; however, it increasingly being used in raft other diseases. This review gives an overview for audience, including pipeline common pitfalls associated with each stage. Key studies oncology are presented focus both those use analysis alone integrate its multimodal data streams. Importantly, applications outside also presented. Finally, we conclude by offering vision future, how might impact practice as radiologists.

Language: Английский

---

18F-FDG PET/CT radiomic analysis and artificial intelligence to predict pathological complete response after neoadjuvant chemotherapy in breast cancer patients

La radiologia medica, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 28, 2025

Abstract Purpose Build machine learning (ML) models able to predict pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) in breast cancer (BC) patients based on conventional and radiomic signatures extracted from baseline [ 18 F]FDG PET/CT. Material methods Primary tumor the most significant lymph node metastasis were manually segmented PET/CT of 52 newly diagnosed BC patients. Clinical parameters, NAC semiquantitative PET parameters collected. The standard reference considered was surgical pCR (ypT0;ypN0). Eight-hundred-fifty-four features (RFts) both CT datasets, according IBSI; robust RFTs selected. cohort split training (70%) validation (30%) sets. Four ML Models (Clinical Model, Model_T + N) each one with 3 learners (Random Forest (RF), Neural Network Stochastic Gradient Descendent) trained tested using RFts clinical signatures. built considering either primary alone (PET Model_T) or also including N). Results 72 uptakes (52 20 metastasis) at segmented. occurred 44.2% cases. Twelve, 46 141 selected N, respectively. showed better performance than Models. best performances obtained by RF algorithm N (AUC = 0.83;CA 0.74;TP 78%;TN 72%). Conclusion could concur prediction improve management.

Language: Английский

---

Prostate MRI radiomics: A systematic review and radiomic quality score assessment

European Journal of Radiology, Journal Year: 2020, Volume and Issue: 129, P. 109095 - 109095

Published: May 30, 2020

Language: Английский

---