Radiomics: Difference between revisions
m Replace magic links with templates per local RfC and MediaWiki RfC |
No edit summary |
||
| Line 3: | Line 3: | ||
}} |
}} |
||
'''Radiomics''' is a field of medical study that aims to extract large amount of quantitative features from medical images using data-characterisation algorithms.<ref name=":1">{{ |
'''Radiomics''' is a field of medical study that aims to extract large amount of quantitative features from medical images using data-characterisation algorithms.<ref name=":1">{{cite journal |doi=10.1016/j.ejca.2011.11.036 }}</ref><ref>{{cite journal |doi=10.1016/j.mri.2012.06.010 }}</ref><ref name=":3">{{cite journal |doi=10.1148/radiol.2015151169 }}</ref><ref>{{cite journal |doi=10.1080/23808993.2016.1164013 }}</ref> These features, termed radiomic features, have the potential to uncover disease characteristics that fail to be appreciated by the naked eye.<ref>{{cite web|last1=yip|title=Associations between radiologist-defined semantic and automatically computed radiomic features in non-small cell lung cancer}}</ref> The hypothesis of radiomics is that the distinctive imaging features between disease forms may be useful for predicting prognosis and therapeutic response for various conditions, thus providing valuable information for personalised therapy.<ref name=":1"/><ref name=":1"/><ref>{{cite journal |doi=10.1007/s00259-012-2247-0 }}</ref><ref>{{cite journal |doi=10.1007/s40336-014-0064-0 }}</ref> Radiomics emerged from the medical field of oncology<ref name=":3" /> and is the most advanced in applications within that field. However, the technique can be applied to any medical study where a disease or a condition can be tomographically imaged. |
||
== Process<ref>{{cite journal |doi=10.1016/j.mri.2012.06.010 }}</ref> == |
|||
== Process<ref>{{Cite journal|last=Kumar|first=Virendra|last2=Gu|first2=Yuhua|last3=Basu|first3=Satrajit|last4=Berglund|first4=Anders|last5=Eschrich|first5=Steven A.|last6=Schabath|first6=Matthew B.|last7=Forster|first7=Kenneth|last8=Aerts|first8=Hugo J.W.L.|last9=Dekker|first9=Andre|date=November 2012|title=QIN "Radiomics: The Process and the Challenges"|journal=Magnetic resonance imaging|volume=30|issue=9|pages=1234–1248|doi=10.1016/j.mri.2012.06.010|issn=0730-725X|pmc=3563280|pmid=22898692}}</ref> == |
|||
=== Image Acquisition === |
=== Image Acquisition === |
||
| Line 42: | Line 42: | ||
==Features== |
==Features== |
||
Radiomic features can be divided into five groups: size and shape based–features, descriptors of the image intensity histogram, descriptors of the relationships between image voxels (e.g. [[Co-occurrence matrix|gray-level co-occurrence matrix]] (GLCM), run length matrix (RLM), [[Gray level size zone matrix|size zone matrix]] (SZM), and neighborhood gray tone difference matrix (NGTDM) derived textures, [[Image texture|textures]] extracted from filtered images, and fractal features. The mathematical definitions of these features are independent of imaging modality and can be found in the literature.<ref>{{ |
Radiomic features can be divided into five groups: size and shape based–features, descriptors of the image intensity histogram, descriptors of the relationships between image voxels (e.g. [[Co-occurrence matrix|gray-level co-occurrence matrix]] (GLCM), run length matrix (RLM), [[Gray level size zone matrix|size zone matrix]] (SZM), and neighborhood gray tone difference matrix (NGTDM) derived textures, [[Image texture|textures]] extracted from filtered images, and fractal features. The mathematical definitions of these features are independent of imaging modality and can be found in the literature.<ref>{{cite journal |doi=10.1016/S0146-664X(75)80008-6 }}</ref><ref>{{cite journal |doi=10.1109/TPAMI.1984.4767591 }}</ref><ref>{{cite journal |doi=10.1109/21.44046 }}</ref><ref>{{cite journal |doi=10.1109/TBME.2013.2284600 }}</ref> |
||
A detailed description of texture features for radiomics can be found in Depeursinge et al. (2017).<ref>{{ |
A detailed description of texture features for radiomics can be found in Depeursinge et al. (2017).<ref>{{cite journal |doi=10.1016/B978-0-12-812133-7.00008-9 }}</ref> |
||
=== Prediction of clinical outcomes === |
=== Prediction of clinical outcomes === |
||
Aerts et al. (2014)<ref name=":1"/> performed the first large-scale radiomic study that included three lung and two head-and-neck cancer cohorts, consisting of over 1000 patients. They assessed the prognostic values of over 400 textural and shape- and intensity-based features extracted from the [[CT scan|computed tomography]] (CT) images acquired before any treatment. Tumor volumes were defined either by expert radiation oncologists or using semiautomatic segmentation methods.<ref>{{ |
Aerts et al. (2014)<ref name=":1"/> performed the first large-scale radiomic study that included three lung and two head-and-neck cancer cohorts, consisting of over 1000 patients. They assessed the prognostic values of over 400 textural and shape- and intensity-based features extracted from the [[CT scan|computed tomography]] (CT) images acquired before any treatment. Tumor volumes were defined either by expert radiation oncologists or using semiautomatic segmentation methods.<ref>{{cite journal |doi=10.1016/j.patcog.2012.10.005 }}</ref><ref>{{cite journal |doi=10.1038/srep03529 }}</ref> Their results identified a subset of radiomic features that may be useful for predicting patient survival and describing intratumoural heterogeneity. They also confirmed that the prognostic ability of these radiomics features may be transferred from lung to head-and-neck cancer. However, Parmar et al. (2015)<ref>{{cite journal |doi=10.1038/srep11044 }}</ref> demonstrated that prognostic value of some radiomic features may be cancer type dependent. Particularly, they observed that not every radiomic feature that significantly predicted the survival of [[lung cancer]] patients could also predict the survival of [[Head and neck cancer|head-and-neck cancer]] patients and vice versa. |
||
Several studies have also shown radiomic features are better at predicting treatment response than conventional measures, such as tumor volume and diameter, and the maximum radiotracer uptake on [[positron emission tomography]] (PET) imaging.<ref>{{cite journal |doi=10.2967/jnumed.110.082404 }}</ref><ref>{{cite journal |doi=10.2967/jnumed.114.144055 }}</ref><ref>{{cite journal |doi=10.2967/jnumed.115.163766 }}</ref><ref>{{cite journal |doi=10.3389/fonc.2016.00072 }}</ref><ref>{{cite journal |doi=10.1016/j.ijrobp.2013.09.037 }}</ref><ref>{{cite journal |doi=10.1007/s00259-014-2933-1 }}</ref><ref>{{cite journal |doi=10.2967/jnumed.112.107375 }}</ref> Using this technique an algorythm has been developped, after initial training based on intra tumor lymphocyte density, to predict the probability of tumor response to immunotherapy, providing a demonstration of the clinical potential of radiomics as a powerful to for personnalized therapy in the emerging field of immunooncology.<ref>{{cite journal |doi=10.1016/S1470-2045(18)30413-3 }}</ref> |
|||
Several studies have also shown radiomic features are better at predicting treatment response than conventional measures, such as tumor volume and diameter, and the maximum radiotracer uptake on [[positron emission tomography]] (PET) imaging.<ref>{{Cite journal|last=Tixier|first=Florent|last2=Rest|first2=Catherine Cheze Le|last3=Hatt|first3=Mathieu|last4=Albarghach|first4=Nidal|last5=Pradier|first5=Olivier|last6=Metges|first6=Jean-Philippe|last7=Corcos|first7=Laurent|last8=Visvikis|first8=Dimitris|date=2011-03-01|title=Intratumor Heterogeneity Characterized by Textural Features on Baseline 18F-FDG PET Images Predicts Response to Concomitant Radiochemotherapy in Esophageal Cancer|url=http://jnm.snmjournals.org/content/52/3/369|journal=Journal of Nuclear Medicine|volume=52|issue=3|pages=369–378|doi=10.2967/jnumed.110.082404|issn=0161-5505|pmc=3789272|pmid=21321270}}</ref><ref>{{Cite journal|last=Hatt|first=Mathieu|last2=Majdoub|first2=Mohamed|last3=Vallières|first3=Martin|last4=Tixier|first4=Florent|last5=Rest|first5=Catherine Cheze Le|last6=Groheux|first6=David|last7=Hindié|first7=Elif|last8=Martineau|first8=Antoine|last9=Pradier|first9=Olivier|date=2015-01-01|title=18F-FDG PET Uptake Characterization Through Texture Analysis: Investigating the Complementary Nature of Heterogeneity and Functional Tumor Volume in a Multi–Cancer Site Patient Cohort|url=http://jnm.snmjournals.org/content/56/1/38|journal=Journal of Nuclear Medicine|volume=56|issue=1|pages=38–44|doi=10.2967/jnumed.114.144055|issn=0161-5505|pmid=25500829}}</ref><ref>{{Cite journal|last=Rossum|first=Peter S. N. van|last2=Fried|first2=David V.|last3=Zhang|first3=Lifei|last4=Hofstetter|first4=Wayne L.|last5=Vulpen|first5=Marco van|last6=Meijer|first6=Gert J.|last7=Court|first7=Laurence E.|last8=Lin|first8=Steven H.|date=2016-01-21|title=The incremental value of subjective and quantitative assessment of 18F-FDG PET for the prediction of pathologic complete response to preoperative chemoradiotherapy in esophageal cancer.|url=http://jnm.snmjournals.org/content/early/2016/01/20/jnumed.115.163766|journal=Journal of Nuclear Medicine|pages=jnumed.115.163766|doi=10.2967/jnumed.115.163766|issn=0161-5505|pmid=26795288|volume=57}}</ref><ref>{{Cite journal|last=Yip|first=Stephen S. F.|last2=Coroller|first2=Thibaud P.|last3=Sanford|first3=Nina N.|last4=Mamon|first4=Harvey|last5=Aerts|first5=Hugo J. W. L.|last6=Berbeco|first6=Ross I.|date=2016-01-01|title=Relationship between the Temporal Changes in Positron-Emission-Tomography-Imaging-Based Textural Features and Pathologic Response and Survival in Esophageal Cancer Patients|url=http://journal.frontiersin.org/Article/10.3389/fonc.2016.00072/abstract|journal=Radiation Oncology|pages=72|doi=10.3389/fonc.2016.00072|pmc=4810033|pmid=27066454|volume=6}}</ref><ref>{{Cite journal|last=Zhang|first=Hao|last2=Tan|first2=Shan|last3=Chen|first3=Wengen|last4=Kligerman|first4=Seth|last5=Kim|first5=Grace|last6=D'Souza|first6=Warren D.|last7=Suntharalingam|first7=Mohan|last8=Lu|first8=Wei|title=Modeling Pathologic Response of Esophageal Cancer to Chemoradiation Therapy Using Spatial-Temporal 18F-FDG PET Features, Clinical Parameters, and Demographics|url=http://linkinghub.elsevier.com/retrieve/pii/S0360301613031453|journal=International Journal of Radiation Oncology*Biology*Physics|volume=88|issue=1|pages=195–203|doi=10.1016/j.ijrobp.2013.09.037|pmc=3875172|pmid=24189128}}</ref><ref>{{Cite journal|last=Cheng|first=Nai-Ming|last2=Fang|first2=Yu-Hua Dean|last3=Lee|first3=Li-yu|last4=Chang|first4=Joseph Tung-Chieh|last5=Tsan|first5=Din-Li|last6=Ng|first6=Shu-Hang|last7=Wang|first7=Hung-Ming|last8=Liao|first8=Chun-Ta|last9=Yang|first9=Lan-Yan|date=2014-10-23|title=Zone-size nonuniformity of 18F-FDG PET regional textural features predicts survival in patients with oropharyngeal cancer|url=https://link.springer.com/article/10.1007/s00259-014-2933-1|journal=European Journal of Nuclear Medicine and Molecular Imaging|volume=42|issue=3|pages=419–428|doi=10.1007/s00259-014-2933-1|issn=1619-7070}}</ref><ref>{{Cite journal|last=Cook|first=Gary J. R.|last2=Yip|first2=Connie|last3=Siddique|first3=Muhammad|last4=Goh|first4=Vicky|last5=Chicklore|first5=Sugama|last6=Roy|first6=Arunabha|last7=Marsden|first7=Paul|last8=Ahmad|first8=Shahreen|last9=Landau|first9=David|date=2013-01-01|title=Are Pretreatment 18F-FDG PET Tumor Textural Features in Non–Small Cell Lung Cancer Associated with Response and Survival After Chemoradiotherapy?|url=http://jnm.snmjournals.org/content/54/1/19|journal=Journal of Nuclear Medicine|volume=54|issue=1|pages=19–26|doi=10.2967/jnumed.112.107375|issn=0161-5505|pmid=23204495}}</ref> Using this technique an algorythm has been developped, after initial training based on intra tumor lymphocyte density, to predict the probability of tumor response to immunotherapy, providing a demonstration of the clinical potential of radiomics as a powerful to for personnalized therapy in the emerging field of immunooncology <ref>Sun R, Limkin EJ, Vakalopoulou M, Dercle L, Champiat S, Han SR, Verlingue L,Brandao D, Lancia A, Ammari S, Hollebecque A, Scoazec JY, Marabelle A, Massard C,Soria JC, Robert C, Paragios N, Deutsch E, Ferté C. A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1immunotherapy: an imaging biomarker, retrospective multicohort study. Lancet Oncol. 2018 Aug 14. pii: S1470-2045(18)30413-3. doi:10.1016/S1470-2045(18)30413-3. [Epub ahead of print] PubMed {{PMID|30120041}}.</ref> |
|||
=== Prediction risk of distant metastasis === |
=== Prediction risk of distant metastasis === |
||
Metastatic potential of tumors may also be predicted by radiomic features.<ref name=":2">{{ |
Metastatic potential of tumors may also be predicted by radiomic features.<ref name=":2">{{cite journal |doi=10.1016/j.radonc.2015.02.015 }}</ref><ref>{{cite journal |doi=10.1088/0031-9155/60/14/5471 }}</ref> For example, thirty-five CT-based radiomic features were identified to be predictive of distant [[metastasis]] of lung cancer in a study by Coroller et al. in 2015.<ref name=":2" /> They thus concluded that radiomic features can be useful to identify patients with high risk of developing distant metastasis, guiding physicians to select the effective treatment for individual patients. |
||
=== Assessment of cancer genetics === |
=== Assessment of cancer genetics === |
||
[[Lung cancer|Lung tumor]] biological mechanisms were found{{by whom|date=April 2016}} to demonstrate distinct and complex imaging patterns.<ref name=":1"/> In particular, Aerts et al. (2014)<ref name=":1"/> showed that radiomic features were associated with biological gene sets, such as cell cycle phase, DNA recombination, regulation of immune system process, etc. Moreover, various mutations of glioblastoma (GBM), such as 1p/19q deletion, MGMT methylation, TP53, EGFR, and NF1, have been shown to be significantly predicted by magnetic resonance imaging (MRI) volumetric measures, including tumor volume, necrosis volume, and contrast enhancing volume.<ref>{{ |
[[Lung cancer|Lung tumor]] biological mechanisms were found{{by whom|date=April 2016}} to demonstrate distinct and complex imaging patterns.<ref name=":1"/> In particular, Aerts et al. (2014)<ref name=":1"/> showed that radiomic features were associated with biological gene sets, such as cell cycle phase, DNA recombination, regulation of immune system process, etc. Moreover, various mutations of glioblastoma (GBM), such as 1p/19q deletion, MGMT methylation, TP53, EGFR, and NF1, have been shown to be significantly predicted by magnetic resonance imaging (MRI) volumetric measures, including tumor volume, necrosis volume, and contrast enhancing volume.<ref>{{cite journal |doi=10.1158/1078-0432.CCR-07-1964 }}</ref><ref>{{cite journal |doi=10.1016/j.neuroimage.2009.09.049 }}</ref><ref>{{cite journal |doi=10.1007/s00234-015-1576-7 }}</ref> |
||
===Image Guided Radiotherapy=== |
===Image Guided Radiotherapy=== |
||
Radiomics offers the advantage to be non invasive and can therefore be repeated propsectively for a given patient more easily than invasive tumor biopsies. It has been suggeste that radiomics could be a mean to monitor tumor dynamic changes along the course of radiotherapy and to define sub volumes at risk for which dose escalation could be beneficial |
Radiomics offers the advantage to be non invasive and can therefore be repeated propsectively for a given patient more easily than invasive tumor biopsies. It has been suggeste that radiomics could be a mean to monitor tumor dynamic changes along the course of radiotherapy and to define sub volumes at risk for which dose escalation could be beneficial.<ref>{{cite journal |doi=10.1016/j.ijrobp.2016.03.038 }}</ref> |
||
===Prediction of physiological events=== |
===Prediction of physiological events=== |
||
Radiomics can also be used to identify challenging physiological events such as brain activity, which is usually studied with imaging techniques such as functional MRI "fMRI". FMRI raw images can undergo radiomic analysis to generate imaging features that can be later correlated with meaningful brain activity.<ref> |
Radiomics can also be used to identify challenging physiological events such as brain activity, which is usually studied with imaging techniques such as functional MRI "fMRI". FMRI raw images can undergo radiomic analysis to generate imaging features that can be later correlated with meaningful brain activity.<ref>{{cite journal |pmid=27151623 }}</ref> |
||
==See also== |
==See also== |
||
Revision as of 11:36, 16 September 2018
 | This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these template messages)
|
Radiomics is a field of medical study that aims to extract large amount of quantitative features from medical images using data-characterisation algorithms.[1][2][3][4] These features, termed radiomic features, have the potential to uncover disease characteristics that fail to be appreciated by the naked eye.[5] The hypothesis of radiomics is that the distinctive imaging features between disease forms may be useful for predicting prognosis and therapeutic response for various conditions, thus providing valuable information for personalised therapy.[1][1][6][7] Radiomics emerged from the medical field of oncology[3] and is the most advanced in applications within that field. However, the technique can be applied to any medical study where a disease or a condition can be tomographically imaged.
Process[8]
Image Acquisition
The underlying image data that is used to characterize tumors is provided by medical scanning technology. Instead of taking a picture like a camera, the scans produce raw volumes of data which must be further processed to be usable in medical investigations. To get actual images that are interpretable, a reconstruction tool must be used.
There are a variety of reconstruction algorithms, so consideration must be taken to determine the most suitable one for each case, as the resultant images will differ. This influences the quality and usability of the images, which in turn determines how easily an abnormal finding can be detected and how well it can be characterized.
The reconstructed images are saved in a large database. A public database to which all clinics have access enables broadly collaborative and cumulative work in which all can benefit from growing amounts of data, ideally enabling a more precise workflow.
Image Segmentation
After the images have been saved in the database, they have to be reduced to the essential parts, in this case the tumors, which are called “volumes of interest”.
Because of the large image data that needs to be processed, it would be too much work to perform the segmentation manually for every single image if a radiomics database with lots of data is created. Instead of manual segmentation, an automated process has to be used. A possible solution are automatic and semiautomatic segmentation algorithms. Before it can be applied on a big scale an algorithm must score as high as possible in the following four tasks:
- First, it must be reproducible, which means that when it is used on the same data the outcome will not change.
- Another important factor is the consistency. The algorithm does solve the problem at hand and performs the task rather than doing something that is not important. In this case, it is necessary that the algorithm can detect the diseased part in all different scans.
- The algorithm also needs to be accurate. It is very important that the algorithm detects the diseased part in the most precise way possible. Only with accurate data, accurate results can be achieved.
- A minor but still important point is the time efficiency. The results should be generated as fast as possible so that the whole process of radiomics can also be accelerated. A minor point means in this case that, if it is in a certain frame, it is not as important as the others.
Features Extraction and Qualification
After the segmentation, many features of the tumor may be computed. They stretch from volume, shape, surface to density and intensity as well as texture, tumor location, relations with the surrounding tissues and a lot of others.
Due to its massive variety, the data needs to be qualified as well, so that we can eliminate redundant information. Hundreds of different features need to be evaluated and so we need feature selection algorithms to accelerate this process.
Analysis
After the selection of features that are important for our task it is crucial to analyze the chosen data. Before the actual analysis, the clinical and molecular (sometimes even the genetic) data needs to be integrated because it has a big impact on what can be deducted from the analysis. There are different methods to finally analyze the data. First, the different features are compared to one another to find out whether they have any information in common and to reveal what it means when they all occur at the same time.
Another way is Supervised or Unsupervised Analysis. Supervised Analysis uses an outcome variable to be able to create prediction models. Unsupervised Analysis summarizes the information we have and can be represented graphically. So that the conclusion of our results is clearly visible.
Database
Creation
Several steps are necessary to create an integrated radiomics database. The data needs to be exported from the clinics. This is already a very challenging step because the patient information is very sensitive. At the same time the exported data must not lose any of its integrity when compressed so that the database only incorporates data of the same quality. The integration of clinical and molecular data is important as well and a large image storage location is needed.
Use
The goal of radiomics is to be able to use this database for new patients. This means that we need algorithms that run new input data through the database which return a result with information about what the course of the patients’ disease might look like. For example, how fast the tumor will grow or how good the chances are that the patient survives for a certain time, whether distant metastases are possible and where. This determines how the further treatment (like surgery, chemotherapy, radiotherapy or targeted drugs etc.) and the best solution which maximizes survival or improvement is selected. The algorithm has to recognize correlations between the images and the features, so that it is possible to extrapolate from the data base material to the input data.
Features
Radiomic features can be divided into five groups: size and shape based–features, descriptors of the image intensity histogram, descriptors of the relationships between image voxels (e.g. gray-level co-occurrence matrix (GLCM), run length matrix (RLM), size zone matrix (SZM), and neighborhood gray tone difference matrix (NGTDM) derived textures, textures extracted from filtered images, and fractal features. The mathematical definitions of these features are independent of imaging modality and can be found in the literature.[9][10][11][12] A detailed description of texture features for radiomics can be found in Depeursinge et al. (2017).[13]
Prediction of clinical outcomes
Aerts et al. (2014)[1] performed the first large-scale radiomic study that included three lung and two head-and-neck cancer cohorts, consisting of over 1000 patients. They assessed the prognostic values of over 400 textural and shape- and intensity-based features extracted from the computed tomography (CT) images acquired before any treatment. Tumor volumes were defined either by expert radiation oncologists or using semiautomatic segmentation methods.[14][15] Their results identified a subset of radiomic features that may be useful for predicting patient survival and describing intratumoural heterogeneity. They also confirmed that the prognostic ability of these radiomics features may be transferred from lung to head-and-neck cancer. However, Parmar et al. (2015)[16] demonstrated that prognostic value of some radiomic features may be cancer type dependent. Particularly, they observed that not every radiomic feature that significantly predicted the survival of lung cancer patients could also predict the survival of head-and-neck cancer patients and vice versa.
Several studies have also shown radiomic features are better at predicting treatment response than conventional measures, such as tumor volume and diameter, and the maximum radiotracer uptake on positron emission tomography (PET) imaging.[17][18][19][20][21][22][23] Using this technique an algorythm has been developped, after initial training based on intra tumor lymphocyte density, to predict the probability of tumor response to immunotherapy, providing a demonstration of the clinical potential of radiomics as a powerful to for personnalized therapy in the emerging field of immunooncology.[24]
Prediction risk of distant metastasis
Metastatic potential of tumors may also be predicted by radiomic features.[25][26] For example, thirty-five CT-based radiomic features were identified to be predictive of distant metastasis of lung cancer in a study by Coroller et al. in 2015.[25] They thus concluded that radiomic features can be useful to identify patients with high risk of developing distant metastasis, guiding physicians to select the effective treatment for individual patients.
Assessment of cancer genetics
Lung tumor biological mechanisms were found[by whom?] to demonstrate distinct and complex imaging patterns.[1] In particular, Aerts et al. (2014)[1] showed that radiomic features were associated with biological gene sets, such as cell cycle phase, DNA recombination, regulation of immune system process, etc. Moreover, various mutations of glioblastoma (GBM), such as 1p/19q deletion, MGMT methylation, TP53, EGFR, and NF1, have been shown to be significantly predicted by magnetic resonance imaging (MRI) volumetric measures, including tumor volume, necrosis volume, and contrast enhancing volume.[27][28][29]
Image Guided Radiotherapy
Radiomics offers the advantage to be non invasive and can therefore be repeated propsectively for a given patient more easily than invasive tumor biopsies. It has been suggeste that radiomics could be a mean to monitor tumor dynamic changes along the course of radiotherapy and to define sub volumes at risk for which dose escalation could be beneficial.[30]
Prediction of physiological events
Radiomics can also be used to identify challenging physiological events such as brain activity, which is usually studied with imaging techniques such as functional MRI "fMRI". FMRI raw images can undergo radiomic analysis to generate imaging features that can be later correlated with meaningful brain activity.[31]
See also
References
- ^ a b c d e f . doi:10.1016/j.ejca.2011.11.036.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1016/j.mri.2012.06.010.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ a b . doi:10.1148/radiol.2015151169.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1080/23808993.2016.1164013.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ yip. "Associations between radiologist-defined semantic and automatically computed radiomic features in non-small cell lung cancer".
{{cite web}}: Missing or empty|url=(help) - ^ . doi:10.1007/s00259-012-2247-0.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1007/s40336-014-0064-0.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1016/j.mri.2012.06.010.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1016/S0146-664X(75)80008-6.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1109/TPAMI.1984.4767591.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1109/21.44046.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1109/TBME.2013.2284600.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1016/B978-0-12-812133-7.00008-9.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1016/j.patcog.2012.10.005.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1038/srep03529.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1038/srep11044.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.2967/jnumed.110.082404.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.2967/jnumed.114.144055.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.2967/jnumed.115.163766.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.3389/fonc.2016.00072.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help)CS1 maint: unflagged free DOI (link) - ^ . doi:10.1016/j.ijrobp.2013.09.037.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1007/s00259-014-2933-1.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.2967/jnumed.112.107375.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1016/S1470-2045(18)30413-3.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ a b . doi:10.1016/j.radonc.2015.02.015.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1088/0031-9155/60/14/5471.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1158/1078-0432.CCR-07-1964.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1016/j.neuroimage.2009.09.049.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1007/s00234-015-1576-7.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . doi:10.1016/j.ijrobp.2016.03.038.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help) - ^ . PMID 27151623.
{{cite journal}}: Cite journal requires|journal=(help); Missing or empty|title=(help)