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

---

Eleven grand challenges in single-cell data science

Genome biology, Journal Year: 2020, Volume and Issue: 21(1)

Published: Feb. 7, 2020

Abstract The recent boom in microfluidics and combinatorial indexing strategies, combined with low sequencing costs, has empowered single-cell technology. Thousands—or even millions—of cells analyzed a single experiment amount to data revolution biology pose unique science problems. Here, we outline eleven challenges that will be central bringing this emerging field of forward. For each challenge, highlight motivating research questions, review prior work, formulate open This compendium is for established researchers, newcomers, students alike, highlighting interesting rewarding problems the coming years.

Language: Английский

---

The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges

Theranostics, Journal Year: 2019, Volume and Issue: 9(5), P. 1303 - 1322

Published: Jan. 1, 2019

Medical imaging can assess the tumor and its environment in their entirety, which makes it suitable for monitoring temporal spatial characteristics of tumor.Progress computational methods, especially artificial intelligence medical image process analysis, has converted these images into quantitative minable data associated with clinical events oncology management.This concept was first described as radiomics 2012.Since then, computer scientists, radiologists, oncologists have gravitated towards this new tool exploited advanced methodologies to mine information behind images.On basis a great quantity radiographic novel technologies, researchers developed validated radiomic models that may improve accuracy diagnoses therapy response assessments.Here, we review recent methodological developments radiomics, including acquisition, segmentation, feature extraction, modelling, well rapidly developing deep learning technology.Moreover, outline main applications diagnosis, treatment planning evaluations field aim personalized medicine.Finally, discuss challenges scope applicability methods.

Language: Английский

---

Repeatability and Reproducibility of Radiomic Features: A Systematic Review

International Journal of Radiation Oncology*Biology*Physics, Journal Year: 2018, Volume and Issue: 102(4), P. 1143 - 1158

Published: June 5, 2018

An ever-growing number of predictive models used to inform clinical decision making have included quantitative, computer-extracted imaging biomarkers, or "radiomic features." Broadly generalizable validity radiomics-assisted may be impeded by concerns about reproducibility. We offer a qualitative synthesis 41 studies that specifically investigated the repeatability and reproducibility radiomic features, derived from systematic review published peer-reviewed literature.The PubMed electronic database was searched using combinations broad Haynes Ingui filters along with set text words specific cancer, radiomics (including texture analyses), reproducibility, repeatability. This has been reported in compliance Preferred Reporting Items for Systematic Reviews Meta-Analyses guidelines. From each full-text article, information extracted regarding cancer type, class feature examined, reporting quality key processing steps, statistical metric segregate stable features.Among 624 unique records, articles were subjected review. The primarily addressed non-small cell lung oropharyngeal cancer. Only 7 detail every methodologic aspect related image acquisition, preprocessing, extraction. features are sensitive at various degrees details such as acquisition settings, reconstruction algorithm, digital software extract features. First-order overall more reproducible than shape metrics textural Entropy consistently one most first-order There no emergent consensus either features; however, coarseness contrast appeared among least reproducible.Investigations currently limited small types. could improved extraction software, manipulation (preprocessing), cutoff value distinguish

Language: Английский

---

Beyond imaging: The promise of radiomics

Physica Medica, Journal Year: 2017, Volume and Issue: 38, P. 122 - 139

Published: June 1, 2017

Language: Английский

---

Radiomics in Oncology: A Practical Guide

Radiographics, Journal Year: 2021, Volume and Issue: 41(6), P. 1717 - 1732

Published: Oct. 1, 2021

Radiomics refers to the extraction of mineable data from medical imaging and has been applied within oncology improve diagnosis, prognostication, clinical decision support, with goal delivering precision medicine. The authors provide a practical approach for successfully implementing radiomic workflow planning conceptualization through manuscript writing. Applications in typically are either classification tasks that involve computing probability sample belonging category, such as benign versus malignant, or prediction events time-to-event analysis, overall survival. is multidisciplinary, involving radiologists scientists, follows stepwise process tumor segmentation, image preprocessing, feature extraction, model development, validation. Images curated processed before which can be performed on tumors, subregions, peritumoral zones. Extracted features describe distribution signal intensities spatial relationship pixels region interest. To performance reduce overfitting, redundant nonreproducible removed. Validation essential estimate new iteratively samples dataset (cross-validation) separate hold-out by using internal external data. A variety noncommercial commercial software applications used. Guidelines artificial intelligence checklists useful when writing up studies. Although interest field continues grow, should familiar potential pitfalls ensure meaningful conclusions drawn. Online supplemental material available this article. Published under CC BY 4.0 license.

Language: Английский

---

Influence of gray level discretization on radiomic feature stability for different CT scanners, tube currents and slice thicknesses: a comprehensive phantom study

Acta Oncologica, Journal Year: 2017, Volume and Issue: 56(11), P. 1544 - 1553

Published: Sept. 8, 2017

Background: Radiomic analyses of CT images provide prognostic information that can potentially be used for personalized treatment. However, heterogeneity acquisition- and reconstruction protocols influences robustness radiomic analyses. The aim this study was to investigate the influence different CT-scanners, slice thicknesses, exposures gray-level discretization on feature values their stability.Material methods: A texture phantom with ten inserts scanned nine CT-scanners varying tube currents. Scans were reconstructed 1.5 mm or 3 thickness. Image pre-processing comprised in bin widths ranging from 5 50 HU resampling methods (i.e., linear, cubic nearest neighbor interpolation 1 × mm3 voxels) investigated. Subsequently, 114 textural features extracted a 2.1 cm3 sphere center each insert. thickness, exposure width Feature stability assessed by calculating concordance correlation coefficient (CCC) test-retest setting combinations scanners, currents thicknesses.Results: Bin influenced values, but only had marginal effect total number stable (CCC > 0.85) when comparing thicknesses exposures. Most affected could reduced CT-images before extraction. Statistics 'energy' most dependent No clear between observed.Conclusions: CT-scanner, thickness whereas no observed. Optimization improve value performed without compromising stability. Resampling prior extraction decreases variability features.

Language: Английский

---

Voxel size and gray level normalization of CT radiomic features in lung cancer

Scientific Reports, Journal Year: 2018, Volume and Issue: 8(1)

Published: July 6, 2018

Abstract Radiomic features are potential imaging biomarkers for therapy response assessment in oncology. However, the robustness of with respect to parameters is not well established. Previously identified were found be intrinsically dependent on voxel size and number gray levels (GLs) a recent texture phantom investigation. Here, we validate GL in-phantom normalizations lung tumors. Eighteen patients non-small cell cancer varying tumor volumes analyzed. To compare patient data, scans acquired eight different scanners. Twenty four previously extracted from The Spearman rank (r s ) interclass correlation coefficient (ICC) used as metrics. Eight out 10 showed high > 0.9) low < 0.5) correlations voxels before after normalizations, respectively. Likewise, unstable (ICC 0.6) highly stable 0.8) We conclude that derived study also apply This highlights importance utility investigating radiomic CT phantoms.

Language: Английский

---

The role of deep learning and radiomic feature extraction in cancer-specific predictive modelling: a review

Translational Cancer Research, Journal Year: 2018, Volume and Issue: 7(3), P. 803 - 816

Published: June 1, 2018

This paper reviews objective methods for prognostic modelling of cancer tumours located within radiology images, a process known as radiomics.Radiomics is novel feature transformation method detecting clinically relevant features from radiological imaging data that are difficult the human eye to perceive.To facilitate detection machine learning and deep increasingly investigated with aim improving patient diagnosis, treatment options outcomes.A review works in expanding field radiomics survival prediction provided.Research outside which define techniques may be future use improve extraction analysis also reviewed.Radiomics rapidly advancing clinical image vast potential supporting decision making involved diagnosis cancer.The realisation this goal more effective requires significant individual integrated expertise domain experts medicine, biology computer science allow advances vision applied effectively.Deep combined has advance significantly years come, provided mechanisms sharing or distributed established increase availability across all tumour types.

Language: Английский

---

Influence of inter-observer delineation variability on radiomics stability in different tumor sites

Acta Oncologica, Journal Year: 2018, Volume and Issue: 57(8), P. 1070 - 1074

Published: March 7, 2018

Background: Radiomics is a promising methodology for quantitative analysis and description of radiological images using advanced mathematics statistics. Tumor delineation, which still often done manually, an essential step in radiomics, however, inter-observer variability well-known uncertainty radiation oncology. This study investigated the impact (IOV) manual tumor delineation on reliability radiomic features (RF).Methods: Three different types (head neck squamous cell carcinoma (HNSCC), malignant pleural mesothelioma (MPM) non-small lung cancer (NSCLC)) were included. For each site, eleven individual tumors contoured CT scans by three experienced oncologists. Dice coefficients (DC) calculated quantification variability. RF with in-house developed software implementation, comprises 1404 features: shape (n = 18), histogram 17), texture 137) wavelet 1232). The IOV was studied intraclass correlation coefficient (ICC). An ICC >0.8 indicates good reproducibility. stable RF, average linkage hierarchical clustering performed to identify classes uncorrelated features.Results: Median DC high NSCLC (0.86, range 0.57–0.90) HNSCC (0.72, 0.21–0.89), whereas it low MPM (0.26, 0–0.9) indicating substantial IOV. Stability rate correlated depended showing stability (90% total parameters), acceptable (59% parameters) (36% parameters). Shape showed weakest across all types. Hierarchical revealed 14 groups 6 both MPM.Conclusion: Inter-observer has relevant influence radiomics strongly influenced type. leads reduced number suitable imaging features.

Language: Английский

---