Radiomics: the process and the challenges

Kumar, Virendra; Gu, Yi; Basu, Shibani; Berglund, Anders; Eschrich, Steven; Schabath, Matthew B.; Forster, Kenneth; Aerts, Hugo J.W.L.; Dekker, André; Fenstermacher, David; Goldgof, Dmitry B.; Hall, Lawrence O.; Lambin, Philippe; Balagurunathan, Yoganand; Gatenby, Robert A.; Gillies, Robert J.

doi:10.1016/j.mri.2012.06.010

Cited by 1,709 publications

(1,263 citation statements)

References 80 publications

Supporting

Mentioning

1,238

Contrasting

Unclassified

Order By: Relevance

“…In a recent study, Kumar et al defined radiomics as45 “the extraction and analysis of large amounts of advanced high throughput of imaging features with high throughput from medical images obtained with computed tomography, positron emission tomography or magnetic resonance imaging. Importantly, these data are designed to be extracted from standard‐of‐care images, leading to a considerable potential subject pool”.…”

Section: Methodsmentioning

confidence: 99%

Reproducibility of F18‐FDG PET radiomic features for different cervical tumor segmentation methods, gray‐level discretization, and reconstruction algorithms

Altazi

Zhang

Fernandez

et al. 2017

J Applied Clin Med Phys

View full text Add to dashboard Cite

Site‐specific investigations of the role of radiomics in cancer diagnosis and therapy are emerging. We evaluated the reproducibility of radiomic features extracted from 18Flourine–fluorodeoxyglucose (18F‐FDG) PET images for three parameters: manual versus computer‐aided segmentation methods, gray‐level discretization, and PET image reconstruction algorithms. Our cohort consisted of pretreatment PET/CT scans from 88 cervical cancer patients. Two board‐certified radiation oncologists manually segmented the metabolic tumor volume (MTV1 and MTV2) for each patient. For comparison, we used a graphical‐based method to generate semiautomated segmented volumes (GBSV). To address any perturbations in radiomic feature values, we down‐sampled the tumor volumes into three gray‐levels: 32, 64, and 128 from the original gray‐level of 256. Finally, we analyzed the effect on radiomic features on PET images of eight patients due to four PET 3D‐reconstruction algorithms: maximum likelihood‐ordered subset expectation maximization (OSEM) iterative reconstruction (IR) method, fourier rebinning‐ML‐OSEM (FOREIR), FORE‐filtered back projection (FOREFBP), and 3D‐Reprojection (3DRP) analytical method. We extracted 79 features from all segmentation method, gray‐levels of down‐sampled volumes, and PET reconstruction algorithms. The features were extracted using gray‐level co‐occurrence matrices (GLCM), gray‐level size zone matrices (GLSZM), gray‐level run‐length matrices (GLRLM), neighborhood gray‐tone difference matrices (NGTDM), shape‐based features (SF), and intensity histogram features (IHF). We computed the Dice coefficient between each MTV and GBSV to measure segmentation accuracy. Coefficient values close to one indicate high agreement, and values close to zero indicate low agreement. We evaluated the effect on radiomic features by calculating the mean percentage differences (d¯) between feature values measured from each pair of parameter elements (i.e. segmentation methods: MTV1‐MTV2, MTV1‐GBSV, MTV2‐GBSV; gray‐levels: 64‐32, 64‐128, and 64‐256; reconstruction algorithms: OSEM‐FORE‐OSEM, OSEM‐FOREFBP, and OSEM‐3DRP). We used false|normald¯false| as a measure of radiomic feature reproducibility level, where any feature scored false|normald¯false| ±SD ≤ |25|% ± 35% was considered reproducible. We used Bland–Altman analysis to evaluate the mean, standard deviation (SD), and upper/lower reproducibility limits (U/LRL) for radiomic features in response to variation in each testing parameter. Furthermore, we proposed U/LRL as a method to classify the level of reproducibility: High— ±1% ≤ U/LRL ≤ ±30%; Intermediate— ±30% < U/LRL ≤ ±45%; Low— ±45 < U/LRL ≤ ±50%. We considered any feature below the low level as nonreproducible (NR). Finally, we calculated the interclass correlation coefficient (ICC) to evaluate the reliability of radiomic feature measurements for each parameter. The segmented volumes of 65 patients (81.3%) scored Dice coefficient >0.75 for all three volumes. The result outcomes revealed a tendency of higher radiomic fe...

show abstract

Section: Methodsmentioning

confidence: 99%

Reproducibility of F18‐FDG PET radiomic features for different cervical tumor segmentation methods, gray‐level discretization, and reconstruction algorithms

Altazi

Zhang

Fernandez

et al. 2017

J Applied Clin Med Phys

View full text Add to dashboard Cite

show abstract

“…With such a variety of spatial metrics available, there is no consensus as to the most suitable metric for assessing geometric accuracy 18 , 24 . As both the geometric and dosimetric accuracy are important for treatment planning and evaluation, it can be argued that suitable spatial metrics are those that provide results related to dosimetric accuracy (25) .…”

Section: Introductionmentioning

confidence: 99%

The suitability of common metrics for assessing parotid and larynx autosegmentation accuracy

Beasley

McWilliam

Aitkenhead

et al. 2016

J Applied Clin Med Phys

View full text Add to dashboard Cite

Contouring structures in the head and neck is time‐consuming, and automatic segmentation is an important part of an adaptive radiotherapy workflow. Geometric accuracy of automatic segmentation algorithms has been widely reported, but there is no consensus as to which metrics provide clinically meaningful results. This study investigated whether geometric accuracy (as quantified by several commonly used metrics) was associated with dosimetric differences for the parotid and larynx, comparing automatically generated contours against manually drawn ground truth contours. This enabled the suitability of different commonly used metrics to be assessed for measuring automatic segmentation accuracy of the parotid and larynx. Parotid and larynx structures for 10 head and neck patients were outlined by five clinicians to create ground truth structures. An automatic segmentation algorithm was used to create automatically generated normal structures, which were then used to create volumetric‐modulated arc therapy plans. The mean doses to the automatically generated structures were compared with those of the corresponding ground truth structures, and the relative difference in mean dose was calculated for each structure. It was found that this difference did not correlate with the geometric accuracy provided by several metrics, notably the Dice similarity coefficient, which is a commonly used measure of spatial overlap. Surface‐based metrics provided stronger correlation and are, therefore, more suitable for assessing automatic segmentation of the parotid and larynx.PACS number(s): 87.57.nm, 87.55.D, 87.55.Qr

show abstract

“…Imaging used for followup, date of followup, date of local recurrence -if any -date and location of metastasis (M+) -if any -and biopsy confirmation for local recurrence and/or M+ are recorded. The third and most detailed level, the research level, includes clinical and imaging information used for advanced research projects such as radiomics [32]. Concomitant medication, preexisting general and rectal quality of life (QoL; EORTC QoL questionnaire [QLQ]-C30, EORTC QLQ-C29 and EQ-5D-5L) and tumor features including tumor markers are recorded.…”

Section: Standardized Data Collection and Ontologymentioning

confidence: 99%

VATE: VAlidation of high TEchnology based on large database analysis by learning machine

Meldolesi

Soest²,

Alitto

et al. 2014

Colorectal Cancer

Self Cite

View full text Add to dashboard Cite

SummaryThe interaction between implementation of new technologies and different outcomes can allow a broad range of researches to be expanded. The purpose of this paper is to introduce the VAlidation of high TEchnology based on large database analysis by learning machine (VATE) project that aims to combine new technologies with outcomes related to rectal cancer in terms of tumor control and normal tissue sparing. Using automated computer bots and the knowledge for screening data it is possible to identify the factors that can mostly influence those outcomes. Population-based observational studies resulting from the linkage of different datasets will be conducted in order to develop predictive models that allow physicians to share decision with patients into a wider concept of tailored treatment. KeywordSOver the past decade, remarkable advances in cancer care with the adoption of newest diagnostic and treatment technologies has created new challenges [1].The use and role of medical imaging technologies in clinical oncology has greatly expanded from a primarily diagnostic tool to award a central role in the context of individualized medicine. Multiple imaging features involving descriptors of intensity distribution, spatial relationships between the various intensity levels, texture heterogeneity patterns, descriptors of shape and the relations of the tumor with the surrounding tissues have been analyzed for their relationship with treatment outcomes or Practice points• Progress in individualized medicine has created new challenges.• New technology implementation.• Necessity to develop systems that allow shared decision making by the physicians and the patients and chose a tailored treatment.• Standardization of the data collection -ontology.• Sharing data: Semantic Web and Resource Description Framework.• Statistical analysis.• Privacy protection of individual patients.• Development of predictive models based on individual patients features which complement existing consensus or guidelines.For reprint orders, please contact: reprints@futuremedicine.com

show abstract

Radiomics: the process and the challenges

Cited by 1,709 publications

References 80 publications

Reproducibility of F18‐FDG PET radiomic features for different cervical tumor segmentation methods, gray‐level discretization, and reconstruction algorithms

Reproducibility of F18‐FDG PET radiomic features for different cervical tumor segmentation methods, gray‐level discretization, and reconstruction algorithms

The suitability of common metrics for assessing parotid and larynx autosegmentation accuracy

VATE: VAlidation of high TEchnology based on large database analysis by learning machine

Contact Info

Product

Resources

About