Automated quantification of steatosis: agreement with stereological point counting
Abstract Background Steatosis is routinely assessed histologically in clinical practice and research. Automated image analysis can reduce the effort of quantifying steatosis. Since reproducibility is essential for practical use, we have evaluated different analysis methods in terms of their agreemen...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2017-11-01
|
| Series: | Diagnostic Pathology |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13000-017-0671-y |
| _version_ | 1819155868464185344 |
|---|---|
| author | André Homeyer Patrik Nasr Christiane Engel Stergios Kechagias Peter Lundberg Mattias Ekstedt Henning Kost Nick Weiss Tim Palmer Horst Karl Hahn Darren Treanor Claes Lundström |
| author_facet | André Homeyer Patrik Nasr Christiane Engel Stergios Kechagias Peter Lundberg Mattias Ekstedt Henning Kost Nick Weiss Tim Palmer Horst Karl Hahn Darren Treanor Claes Lundström |
| author_sort | André Homeyer |
| collection | DOAJ |
| description | Abstract Background Steatosis is routinely assessed histologically in clinical practice and research. Automated image analysis can reduce the effort of quantifying steatosis. Since reproducibility is essential for practical use, we have evaluated different analysis methods in terms of their agreement with stereological point counting (SPC) performed by a hepatologist. Methods The evaluation was based on a large and representative data set of 970 histological images from human patients with different liver diseases. Three of the evaluated methods were built on previously published approaches. One method incorporated a new approach to improve the robustness to image variability. Results The new method showed the strongest agreement with the expert. At 20× resolution, it reproduced steatosis area fractions with a mean absolute error of 0.011 for absent or mild steatosis and 0.036 for moderate or severe steatosis. At 10× resolution, it was more accurate than and twice as fast as all other methods at 20× resolution. When compared with SPC performed by two additional human observers, its error was substantially lower than one and only slightly above the other observer. Conclusions The results suggest that the new method can be a suitable automated replacement for SPC. Before further improvements can be verified, it is necessary to thoroughly assess the variability of SPC between human observers. |
| first_indexed | 2024-12-22T15:43:49Z |
| format | Article |
| id | doaj.art-48c031e72778412b8c262afebf33acce |
| institution | Directory Open Access Journal |
| issn | 1746-1596 |
| language | English |
| last_indexed | 2024-12-22T15:43:49Z |
| publishDate | 2017-11-01 |
| publisher | BMC |
| record_format | Article |
| series | Diagnostic Pathology |
| spelling | doaj.art-48c031e72778412b8c262afebf33acce2022-12-21T18:21:03ZengBMCDiagnostic Pathology1746-15962017-11-0112111010.1186/s13000-017-0671-yAutomated quantification of steatosis: agreement with stereological point countingAndré Homeyer0Patrik Nasr1Christiane Engel2Stergios Kechagias3Peter Lundberg4Mattias Ekstedt5Henning Kost6Nick Weiss7Tim Palmer8Horst Karl Hahn9Darren Treanor10Claes Lundström11Fraunhofer MEVISDepartment of Medical and Health Sciences, Linköping UniversityFraunhofer MEVISDepartment of Medical and Health Sciences, Linköping UniversityDepartment of Medical and Health Sciences, Linköping UniversityDepartment of Medical and Health Sciences, Linköping UniversityFraunhofer MEVISFraunhofer MEVISInstitute of Cancer and Pathology, University of LeedsFraunhofer MEVISCenter for Medical Image Science and Visualization, Linköping UniversityCenter for Medical Image Science and Visualization, Linköping UniversityAbstract Background Steatosis is routinely assessed histologically in clinical practice and research. Automated image analysis can reduce the effort of quantifying steatosis. Since reproducibility is essential for practical use, we have evaluated different analysis methods in terms of their agreement with stereological point counting (SPC) performed by a hepatologist. Methods The evaluation was based on a large and representative data set of 970 histological images from human patients with different liver diseases. Three of the evaluated methods were built on previously published approaches. One method incorporated a new approach to improve the robustness to image variability. Results The new method showed the strongest agreement with the expert. At 20× resolution, it reproduced steatosis area fractions with a mean absolute error of 0.011 for absent or mild steatosis and 0.036 for moderate or severe steatosis. At 10× resolution, it was more accurate than and twice as fast as all other methods at 20× resolution. When compared with SPC performed by two additional human observers, its error was substantially lower than one and only slightly above the other observer. Conclusions The results suggest that the new method can be a suitable automated replacement for SPC. Before further improvements can be verified, it is necessary to thoroughly assess the variability of SPC between human observers.http://link.springer.com/article/10.1186/s13000-017-0671-ySteatosisHistologyStereologyStereological point countingAutomated image analysisAgreement |
| spellingShingle | André Homeyer Patrik Nasr Christiane Engel Stergios Kechagias Peter Lundberg Mattias Ekstedt Henning Kost Nick Weiss Tim Palmer Horst Karl Hahn Darren Treanor Claes Lundström Automated quantification of steatosis: agreement with stereological point counting Diagnostic Pathology Steatosis Histology Stereology Stereological point counting Automated image analysis Agreement |
| title | Automated quantification of steatosis: agreement with stereological point counting |
| title_full | Automated quantification of steatosis: agreement with stereological point counting |
| title_fullStr | Automated quantification of steatosis: agreement with stereological point counting |
| title_full_unstemmed | Automated quantification of steatosis: agreement with stereological point counting |
| title_short | Automated quantification of steatosis: agreement with stereological point counting |
| title_sort | automated quantification of steatosis agreement with stereological point counting |
| topic | Steatosis Histology Stereology Stereological point counting Automated image analysis Agreement |
| url | http://link.springer.com/article/10.1186/s13000-017-0671-y |
| work_keys_str_mv | AT andrehomeyer automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT patriknasr automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT christianeengel automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT stergioskechagias automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT peterlundberg automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT mattiasekstedt automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT henningkost automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT nickweiss automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT timpalmer automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT horstkarlhahn automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT darrentreanor automatedquantificationofsteatosisagreementwithstereologicalpointcounting AT claeslundstrom automatedquantificationofsteatosisagreementwithstereologicalpointcounting |