1
40
3
-
Text
A resource consisting primarily of words for reading. Examples include books, letters, dissertations, poems, newspapers, articles, archives of mailing lists. Note that facsimiles or images of texts are still of the genre Text.
URL Address
<a href="http://doi.org/10.1186/s12880-019-0308-6" target="_blank" rel="noreferrer noopener">http://doi.org/10.1186/s12880-019-0308-6</a>
Rights
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).
Pages
12-12
Volume
19
Search for Full-text
Locate full-text within NEOMED Library's e-journal collections
<p>Users with a NEOMED Library login can search for full-text journal articles at the following url: <a href="https://libraryguides.neomed.edu/home">https://libraryguides.neomed.edu/home</a></p>
NEOMED College
NEOMED College of Medicine
NEOMED Department
NEOMED Student Publications
Dublin Core
The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/.
Title
A name given to the resource
Comparing radiomic classifiers and classifier ensembles for detection of peripheral zone prostate tumors on T2-weighted MRI: a multi-site study
Publisher
An entity responsible for making the resource available
Bmc Medical Imaging
Date
A point or period of time associated with an event in the lifecycle of the resource
2019
2019-02
Subject
The topic of the resource
adenocarcinoma; benign; cancer; Classifiers; Comparison; features; machine-learning-methods; MRI; Nuclear Medicine & Medical Imaging; Prostate cancer; Radiology; Radiomics; texture analysis
Creator
An entity primarily responsible for making the resource
Viswanath S E; Chirra P V; Yim M C; Rofsky N M; Purysko A S; Rosen M A; Bloch B N; Madabhushi A
Description
An account of the resource
BackgroundFor most computer-aided diagnosis (CAD) problems involving prostate cancer detection via medical imaging data, the choice of classifier has been largely ad hoc, or been motivated by classifier comparison studies that have involved large synthetic datasets. More significantly, it is currently unknown how classifier choices and trends generalize across multiple institutions, due to heterogeneous acquisition and intensity characteristics (especially when considering MR imaging data). In this work, we empirically evaluate and compare a number of different classifiers and classifier ensembles in a multi-site setting, for voxel-wise detection of prostate cancer (PCa) using radiomic texture features derived from high-resolution in vivo T2-weighted (T2w) MRI.MethodsTwelve different supervised classifier schemes: Quadratic Discriminant Analysis (QDA), Support Vector Machines (SVMs), naive Bayes, Decision Trees (DTs), and their ensemble variants (bagging, boosting), were compared in terms of classification accuracy as well as execution time. Our study utilized 85 prostate cancer T2w MRI datasets acquired from across 3 different institutions (1 for discovery, 2 for independent validation), from patients who later underwent radical prostatectomy. Surrogate ground truth for disease extent on MRI was established by expert annotation of pre-operative MRI through spatial correlation with corresponding ex vivo whole-mount histology sections. Classifier accuracy in detecting PCa extent on MRI on a per-voxel basis was evaluated via area under the ROC curve.ResultsThe boosted DT classifier yielded the highest cross-validated AUC (= 0.744) for detecting PCa in the discovery cohort. However, in independent validation, the boosted QDA classifier was identified as the most accurate and robust for voxel-wise detection of PCa extent (AUCs of 0.735, 0.683, 0.768 across the 3 sites). The next most accurate and robust classifier was the single QDA classifier, which also enjoyed the advantage of significantly lower computation times compared to any of the other methods.ConclusionsOur results therefore suggest that simpler classifiers (such as QDA and its ensemble variants) may be more robust, accurate, and efficient for prostate cancer CAD problems, especially in the context of multi-site validation.
Identifier
An unambiguous reference to the resource within a given context
<a href="http://doi.org/10.1186/s12880-019-0308-6" target="_blank" rel="noreferrer noopener">10.1186/s12880-019-0308-6</a>
Format
The file format, physical medium, or dimensions of the resource
Journal Article
2019
Adenocarcinoma
benign
Bloch B N
BMC medical imaging
Cancer
Chirra P V
Classifiers
Comparison
features
Journal Article
machine-learning-methods
Madabhushi A
MRI
NEOMED College of Medicine Student
NEOMED Student Publications
Nuclear Medicine & Medical Imaging
Prostate cancer
Purysko A S
Radiology
radiomics
Rofsky N M
Rosen M A
texture analysis
Viswanath S E
Yim M C
-
Text
A resource consisting primarily of words for reading. Examples include books, letters, dissertations, poems, newspapers, articles, archives of mailing lists. Note that facsimiles or images of texts are still of the genre Text.
URL Address
<a href="http://doi.org/10.1117/12.2293992" target="_blank" rel="noreferrer noopener">http://doi.org/10.1117/12.2293992</a>
Rights
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).
Volume
10575
Search for Full-text
Locate full-text within NEOMED Library's e-journal collections
<p>Users with a NEOMED Library login can search for full-text journal articles at the following url: <a href="https://libraryguides.neomed.edu/home">https://libraryguides.neomed.edu/home</a></p>
Dublin Core
The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/.
Title
A name given to the resource
Empirical Evaluation of Cross-Site Reproducibility in Radiomic Features for Characterizing Prostate MRI
Publisher
An entity responsible for making the resource available
Medical Imaging 2018: Computer-Aided Diagnosis
Date
A point or period of time associated with an event in the lifecycle of the resource
2018
2018
Subject
The topic of the resource
mri; Stability; prostate; feature analysis; multi-site; radiomics; reproducibility; variance
Creator
An entity primarily responsible for making the resource
Chirra P; Leo P; Yim M; Bloch B N; Rastinehad A R; Purysko A; Rosen M; Madabhushi A; Viswanath S
Description
An account of the resource
The recent advent of radiomics has enabled the development of prognostic and predictive tools which use routine imaging, but a key question that still remains is how reproducible these features may be across multiple sites and scanners. This is especially relevant in the context of MRI data, where signal intensity values lack tissue specific, quantitative meaning, as well as being dependent on acquisition parameters (magnetic field strength, image resolution, type of receiver coil). In this paper we present the first empirical study of the reproducibility of 5 different radiomic feature families in a multi-site setting; specifically, for characterizing prostate MRI appearance. Our cohort comprised 147 patient T2w MRI datasets from 4 different sites, all of which were first pre-processed to correct acquisition-related for artifacts such as bias field, differing voxel resolutions, as well as intensity drift (non-standardness). 406 3D voxel wise radiomic features were extracted and evaluated in a cross-site setting to determine how reproducible they were within a relatively homogeneous non-tumor tissue region; using 2 different measures of reproducibility: Multivariate Coefficient of Variation and Instability Score. Our results demonstrated that Haralick features were most reproducible between all 4 sites. By comparison, Laws features were among the least reproducible between sites, as well as performing highly variably across their entire parameter space. Similarly, the Gabor feature family demonstrated good cross-site reproducibility, but for certain parameter combinations alone. These trends indicate that despite extensive pre-processing, only a subset of radiomic features and associated parameters may be reproducible enough for use within radiomics-based machine learning classifier schemes.
Identifier
An unambiguous reference to the resource within a given context
<a href="http://doi.org/10.1117/12.2293992" target="_blank" rel="noreferrer noopener">10.1117/12.2293992</a>
Format
The file format, physical medium, or dimensions of the resource
Book Chapter
2018
Bloch B N
Book Chapter
Chirra P
feature analysis
Leo P
Madabhushi A
Medical Imaging 2018: Computer-Aided Diagnosis
MRI
multi-site
Prostate
Purysko A
radiomics
Rastinehad A R
reproducibility
Rosen M
Stability
variance
Viswanath S
Yim M
-
Text
A resource consisting primarily of words for reading. Examples include books, letters, dissertations, poems, newspapers, articles, archives of mailing lists. Note that facsimiles or images of texts are still of the genre Text.
URL Address
<a href="http://doi.org/10.1117/1.JMI.6.2.024502" target="_blank" rel="noreferrer noopener">http://doi.org/10.1117/1.JMI.6.2.024502</a>
Rights
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).
Pages
024502-024502
Issue
2
Volume
6
Search for Full-text
Locate full-text within NEOMED Library's e-journal collections
<p>Users with a NEOMED Library login can search for full-text journal articles at the following url: <a href="https://libraryguides.neomed.edu/home">https://libraryguides.neomed.edu/home</a></p>
Dublin Core
The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/.
Title
A name given to the resource
Multisite evaluation of radiomic feature reproducibility and discriminability for identifying peripheral zone prostate tumors on MRI
Publisher
An entity responsible for making the resource available
Journal of Medical Imaging (Bellingham, Wash.)
Date
A point or period of time associated with an event in the lifecycle of the resource
2019
2019-04
Subject
The topic of the resource
discriminability; feature analysis; magnetic resonance imaging; multisite; prostate; radiomics; reproducibility; stability
Creator
An entity primarily responsible for making the resource
Chirra Prathyush; Leo Patrick; Yim Michael; Bloch B Nicolas; Rastinehad Ardeshir R; Purysko Andrei; Rosen Mark; Madabhushi Anant; Viswanath Satish E
Description
An account of the resource
Recent advances in the field of radiomics have enabled the development of a number of prognostic and predictive imaging-based tools for a variety of diseases. However, wider clinical adoption of these tools is contingent on their generalizability across multiple sites and scanners. This may be particularly relevant in the context of radiomic features derived from T1- or T2-weighted magnetic resonance images (MRIs), where signal intensity values are known to lack tissue-specific meaning and vary based on differing acquisition protocols between institutions. We present the first empirical study of benchmarking five different radiomic feature families in terms of both reproducibility and discriminability in a multisite setting, specifically, for identifying prostate tumors in the peripheral zone on MRI. Our cohort comprised 147 patient T2-weighted MRI datasets from four different sites, all of which are first preprocessed to correct for acquisition-related artifacts such as bias field, differing voxel resolutions, and intensity drift (nonstandardness). About 406 three-dimensional voxel-wise radiomic features from five different families (gray, Haralick, gradient, Laws, and Gabor) were evaluated in a cross-site setting to determine (a) how reproducible they are within a relatively homogeneous nontumor tissue region and (b) how well they could discriminate tumor regions from nontumor regions. Our results demonstrate that a majority of the popular Haralick features are reproducible in over 99% of all cross-site comparisons, as well as achieve excellent cross-site discriminability (classification accuracy of ≈ 0.8 ). By contrast, a majority of Laws features are highly variable across sites (reproducible in < 75 % of all cross-site comparisons) as well as resulting in low cross-site classifier accuracies ( < 0.6 ), likely due to a large number of noisy filter responses that can be extracted. These trends suggest that only a subset of radiomic features and associated parameters may be both reproducible and discriminable enough for use within machine learning classifier schemes.
Identifier
An unambiguous reference to the resource within a given context
<a href="http://doi.org/10.1117/1.JMI.6.2.024502" target="_blank" rel="noreferrer noopener">10.1117/1.JMI.6.2.024502</a>
2019
Bloch B Nicolas
Chirra Prathyush
discriminability
feature analysis
Journal of Medical Imaging (Bellingham
Journal of Medical Imaging (Bellingham, Wash.)
Leo Patrick
Madabhushi Anant
Magnetic Resonance Imaging
multisite
NEOMED College of Medicine Student
NEOMED Student Publications
Prostate
Purysko Andrei
radiomics
Rastinehad Ardeshir R
reproducibility
Rosen Mark
September 2019 Update
Stability
Viswanath Satish E
Wash.)
Yim Michael