Radiomics: the bridge between medical imaging and personalized medicine

Nature Reviews Clinical Oncology, Journal Year: 2017, Volume and Issue: 14(12), P. 749 - 762

Published: Oct. 4, 2017

Language: Английский

---

Artificial intelligence in healthcare: past, present and future

Stroke and Vascular Neurology, Journal Year: 2017, Volume and Issue: 2(4), P. 230 - 243

Published: June 21, 2017

Artificial intelligence (AI) aims to mimic human cognitive functions. It is bringing a paradigm shift healthcare, powered by increasing availability of healthcare data and rapid progress analytics techniques. We survey the current status AI applications in discuss its future. can be applied various types (structured unstructured). Popular techniques include machine learning methods for structured data, such as classical support vector neural network, modern deep learning, well natural language processing unstructured data. Major disease areas that use tools cancer, neurology cardiology. then review more details stroke, three major early detection diagnosis, treatment, outcome prediction prognosis evaluation. conclude with discussion about pioneer systems, IBM Watson, hurdles real-life deployment AI.

Language: Английский

---

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

---

Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features

Scientific Data, Journal Year: 2017, Volume and Issue: 4(1)

Published: Sept. 5, 2017

Abstract Gliomas belong to a group of central nervous system tumors, and consist various sub-regions. Gold standard labeling these sub-regions in radiographic imaging is essential for both clinical computational studies, including radiomic radiogenomic analyses. Towards this end, we release segmentation labels features all pre-operative multimodal magnetic resonance (MRI) ( n =243) the multi-institutional glioma collections The Cancer Genome Atlas (TCGA), publicly available Imaging Archive (TCIA). Pre-operative scans were identified glioblastoma (TCGA-GBM, =135) low-grade-glioma (TCGA-LGG, =108) via radiological assessment. sub-region produced by an automated state-of-the-art method manually revised expert board-certified neuroradiologist. An extensive panel was extracted based on manually-revised labels. This set should enable i) direct utilization TCGA/TCIA towards repeatable, reproducible comparative quantitative studies leading new predictive, prognostic, diagnostic assessments, as well ii) performance evaluation computer-aided methods, comparison our method.

Language: Английский

---

Nasopharyngeal carcinoma

The Lancet, Journal Year: 2019, Volume and Issue: 394(10192), P. 64 - 80

Published: June 7, 2019

Language: Английский

---

Development and Validation of a Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer

Journal of Clinical Oncology, Journal Year: 2016, Volume and Issue: 34(18), P. 2157 - 2164

Published: May 3, 2016

To develop and validate a radiomics nomogram for preoperative prediction of lymph node (LN) metastasis in patients with colorectal cancer (CRC).The model was developed primary cohort that consisted 326 clinicopathologically confirmed CRC, data gathered from January 2007 to April 2010. Radiomic features were extracted portal venous-phase computed tomography (CT) CRC. Lasso regression used dimension reduction, feature selection, signature building. Multivariable logistic analysis the predicting model, we incorporated signature, CT-reported LN status, independent clinicopathologic risk factors, this presented nomogram. The performance assessed respect its calibration, discrimination, clinical usefulness. Internal validation assessed. An contained 200 consecutive May 2010 December 2011.The which 24 selected features, significantly associated status (P < .001 both cohorts). Predictors individualized included carcinoembryonic antigen level. Addition histologic grade failed show incremental prognostic value. showed good C-index 0.736 (C-index, 0.759 0.766 through internal validation), calibration. Application still gave discrimination 0.778 [95% CI, 0.769 0.787]) Decision curve demonstrated clinically useful.This study presents incorporates can be conveniently facilitate

Language: Английский

---

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography

Nature Medicine, Journal Year: 2019, Volume and Issue: 25(6), P. 954 - 961

Published: May 20, 2019

Language: Английский

---

Artificial intelligence in cancer imaging: Clinical challenges and applications

CA A Cancer Journal for Clinicians, Journal Year: 2019, Volume and Issue: 69(2), P. 127 - 157

Published: Feb. 5, 2019

Abstract Judgement, as one of the core tenets medicine, relies upon integration multilayered data with nuanced decision making. Cancer offers a unique context for medical decisions given not only its variegated forms evolution disease but also need to take into account individual condition patients, their ability receive treatment, and responses treatment. Challenges remain in accurate detection, characterization, monitoring cancers despite improved technologies. Radiographic assessment most commonly visual evaluations, interpretations which may be augmented by advanced computational analyses. In particular, artificial intelligence (AI) promises make great strides qualitative interpretation cancer imaging expert clinicians, including volumetric delineation tumors over time, extrapolation tumor genotype biological course from radiographic phenotype, prediction clinical outcome, impact treatment on adjacent organs. AI automate processes initial images shift workflow management whether or administer an intervention, subsequent observation yet envisioned paradigm. Here, authors review current state applied describe advances 4 types (lung, brain, breast, prostate) illustrate how common problems are being addressed. Although studies evaluating applications oncology date have been vigorously validated reproducibility generalizability, results do highlight increasingly concerted efforts pushing technology use future directions care.

Language: Английский

---

Introduction to Radiomics

Journal of Nuclear Medicine, Journal Year: 2020, Volume and Issue: 61(4), P. 488 - 495

Published: Feb. 14, 2020

Radiomics is a rapidly evolving field of research concerned with the extraction quantitative metrics—the so-called radiomic features—within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity shape may, alone or in combination demographic, histologic, genomic, proteomic data, be used for clinical problem solving. The goal this continuing education article to provide an introduction field, covering basic radiomics workflow: feature calculation selection, dimensionality reduction, data processing. Potential applications nuclear medicine that include PET radiomics-based prediction treatment response survival will discussed. Current limitations radiomics, sensitivity acquisition parameter variations, common pitfalls also covered.

Language: Английский

---

Imaging biomarker roadmap for cancer studies

Nature Reviews Clinical Oncology, Journal Year: 2016, Volume and Issue: 14(3), P. 169 - 186

Published: Oct. 11, 2016

Imaging biomarkers (IBs) are used extensively in drug development and cancer research, but important differences exist between IBs biospecimen-derived biomarkers. A tailored 'roadmap' is required for the of new to be either clinical research or decision-making healthcare. In this Consensus statement, a group experts assembled by CRUK EORTC present 14 key recommendations accelerating translation IBs. integral routine management patients with cancer. daily oncology include TNM stage, objective response left ventricular ejection fraction. Other CT, MRI, PET ultrasonography development. New need established as useful tools testing hypotheses trials studies, use healthcare, crossing 'translational gaps' through validation qualification. Important and, therefore, requires 'roadmap'. Recognizing need, Cancer Research UK (CRUK) European Organisation Treatment (EORTC) review, debate summarize challenges IB This consensus has produced IBs, which highlight role parallel (rather than sequential) tracks technical (assay) validation, biological/clinical assessment cost-effectiveness; standardization accreditation systems; continually revisit precision; an alternative framework IBs; essential requirements multicentre studies qualify use.

Language: Английский

---