Preprocessing of Heteroscedastic Medical Images
Tissue intensity distributions in medical images can have varying degrees of statistical dispersion, which is referred to as heteroscedasticity. This can influence image contrast and gradients, but can also negatively affect the performance of general-purpose distance metrics. Numerous methods to pr...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8354895/ |
| _version_ | 1818331812826447872 |
|---|---|
| author | Philip Joris Wim Develter Wim Van De Voorde Paul Suetens Frederik Maes Dirk Vandermeulen Peter Claes |
| author_facet | Philip Joris Wim Develter Wim Van De Voorde Paul Suetens Frederik Maes Dirk Vandermeulen Peter Claes |
| author_sort | Philip Joris |
| collection | DOAJ |
| description | Tissue intensity distributions in medical images can have varying degrees of statistical dispersion, which is referred to as heteroscedasticity. This can influence image contrast and gradients, but can also negatively affect the performance of general-purpose distance metrics. Numerous methods to preprocess heteroscedastic images have already been proposed, though most are application-specific and rely on either manual input or certain heuristics. We therefore propose a more general and data-driven approach that relies on the notion of intensity variance around each specific intensity value, simply referred to as intensityspecific variances. First, we introduce a method for estimating these variances from an image (or a collection of images) directly, which is followed by an illustration of how they can be used to define intensity-specific distance measures. Next, we evaluate the proposed concepts through various applications using both homoand heteroscedastic CT and MR images. Finally, we present results from both qualitative and quantitative analyses that confirm the working of the proposed approaches, and support the presented concepts as valid and effective tools for (pre)processing heteroscedastic medical images. |
| first_indexed | 2024-12-13T13:25:48Z |
| format | Article |
| id | doaj.art-e9450b4d06b24da3b8f2c303c5724f54 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T13:25:48Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e9450b4d06b24da3b8f2c303c5724f542022-12-21T23:44:19ZengIEEEIEEE Access2169-35362018-01-016260472605810.1109/ACCESS.2018.28332868354895Preprocessing of Heteroscedastic Medical ImagesPhilip Joris0https://orcid.org/0000-0001-6848-1259Wim Develter1Wim Van De Voorde2Paul Suetens3Frederik Maes4Dirk Vandermeulen5Peter Claes6Department ESAT-PSI, Medical Imaging Research Center, KU Leuven, Leuven, BelgiumDepartment of Forensic Medicine, University Hospitals UZ Leuven, Leuven, BelgiumDepartment of Forensic Medicine, University Hospitals UZ Leuven, Leuven, BelgiumDepartment ESAT-PSI, Medical Imaging Research Center, KU Leuven, Leuven, BelgiumDepartment ESAT-PSI, Medical Imaging Research Center, KU Leuven, Leuven, BelgiumDepartment ESAT-PSI, Medical Imaging Research Center, KU Leuven, Leuven, BelgiumDepartment ESAT-PSI, Medical Imaging Research Center, KU Leuven, Leuven, BelgiumTissue intensity distributions in medical images can have varying degrees of statistical dispersion, which is referred to as heteroscedasticity. This can influence image contrast and gradients, but can also negatively affect the performance of general-purpose distance metrics. Numerous methods to preprocess heteroscedastic images have already been proposed, though most are application-specific and rely on either manual input or certain heuristics. We therefore propose a more general and data-driven approach that relies on the notion of intensity variance around each specific intensity value, simply referred to as intensityspecific variances. First, we introduce a method for estimating these variances from an image (or a collection of images) directly, which is followed by an illustration of how they can be used to define intensity-specific distance measures. Next, we evaluate the proposed concepts through various applications using both homoand heteroscedastic CT and MR images. Finally, we present results from both qualitative and quantitative analyses that confirm the working of the proposed approaches, and support the presented concepts as valid and effective tools for (pre)processing heteroscedastic medical images.https://ieeexplore.ieee.org/document/8354895/Heteroscedasticheteroscedasticityimage contrastimage enhancementintensity-specific distributions |
| spellingShingle | Philip Joris Wim Develter Wim Van De Voorde Paul Suetens Frederik Maes Dirk Vandermeulen Peter Claes Preprocessing of Heteroscedastic Medical Images IEEE Access Heteroscedastic heteroscedasticity image contrast image enhancement intensity-specific distributions |
| title | Preprocessing of Heteroscedastic Medical Images |
| title_full | Preprocessing of Heteroscedastic Medical Images |
| title_fullStr | Preprocessing of Heteroscedastic Medical Images |
| title_full_unstemmed | Preprocessing of Heteroscedastic Medical Images |
| title_short | Preprocessing of Heteroscedastic Medical Images |
| title_sort | preprocessing of heteroscedastic medical images |
| topic | Heteroscedastic heteroscedasticity image contrast image enhancement intensity-specific distributions |
| url | https://ieeexplore.ieee.org/document/8354895/ |
| work_keys_str_mv | AT philipjoris preprocessingofheteroscedasticmedicalimages AT wimdevelter preprocessingofheteroscedasticmedicalimages AT wimvandevoorde preprocessingofheteroscedasticmedicalimages AT paulsuetens preprocessingofheteroscedasticmedicalimages AT frederikmaes preprocessingofheteroscedasticmedicalimages AT dirkvandermeulen preprocessingofheteroscedasticmedicalimages AT peterclaes preprocessingofheteroscedasticmedicalimages |