The reading of components of diabetic retinopathy: an evolutionary approach for filtering normal digital fundus imaging in screening and population based studies.
In any diabetic retinopathy screening program, about two-thirds of patients have no retinopathy. However, on average, it takes a human expert about one and a half times longer to decide an image is normal than to recognize an abnormal case with obvious features. In this work, we present an automated...
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Public Library of Science (PLoS)
2013
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/9bfe811c86c8480e9b16cd2eb91c61d4 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:9bfe811c86c8480e9b16cd2eb91c61d4 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:9bfe811c86c8480e9b16cd2eb91c61d42021-11-18T07:39:17ZThe reading of components of diabetic retinopathy: an evolutionary approach for filtering normal digital fundus imaging in screening and population based studies.1932-620310.1371/journal.pone.0066730https://doaj.org/article/9bfe811c86c8480e9b16cd2eb91c61d42013-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/23840865/pdf/?tool=EBIhttps://doaj.org/toc/1932-6203In any diabetic retinopathy screening program, about two-thirds of patients have no retinopathy. However, on average, it takes a human expert about one and a half times longer to decide an image is normal than to recognize an abnormal case with obvious features. In this work, we present an automated system for filtering out normal cases to facilitate a more effective use of grading time. The key aim with any such tool is to achieve high sensitivity and specificity to ensure patients' safety and service efficiency. There are many challenges to overcome, given the variation of images and characteristics to identify. The system combines computed evidence obtained from various processing stages, including segmentation of candidate regions, classification and contextual analysis through Hidden Markov Models. Furthermore, evolutionary algorithms are employed to optimize the Hidden Markov Models, feature selection and heterogeneous ensemble classifiers. In order to evaluate its capability of identifying normal images across diverse populations, a population-oriented study was undertaken comparing the software's output to grading by humans. In addition, population based studies collect large numbers of images on subjects expected to have no abnormality. These studies expect timely and cost-effective grading. Altogether 9954 previously unseen images taken from various populations were tested. All test images were masked so the automated system had not been exposed to them before. This system was trained using image subregions taken from about 400 sample images. Sensitivities of 92.2% and specificities of 90.4% were achieved varying between populations and population clusters. Of all images the automated system decided to be normal, 98.2% were true normal when compared to the manual grading results. These results demonstrate scalability and strong potential of such an integrated computational intelligence system as an effective tool to assist a grading service.Hongying Lilian TangJonathan GohTunde PetoBingo Wing-Kuen LingLutfiah Ismail Al TurkYin HuSu WangGeorge Michael SalehPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 8, Iss 7, p e66730 (2013) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Hongying Lilian Tang Jonathan Goh Tunde Peto Bingo Wing-Kuen Ling Lutfiah Ismail Al Turk Yin Hu Su Wang George Michael Saleh The reading of components of diabetic retinopathy: an evolutionary approach for filtering normal digital fundus imaging in screening and population based studies. |
| description |
In any diabetic retinopathy screening program, about two-thirds of patients have no retinopathy. However, on average, it takes a human expert about one and a half times longer to decide an image is normal than to recognize an abnormal case with obvious features. In this work, we present an automated system for filtering out normal cases to facilitate a more effective use of grading time. The key aim with any such tool is to achieve high sensitivity and specificity to ensure patients' safety and service efficiency. There are many challenges to overcome, given the variation of images and characteristics to identify. The system combines computed evidence obtained from various processing stages, including segmentation of candidate regions, classification and contextual analysis through Hidden Markov Models. Furthermore, evolutionary algorithms are employed to optimize the Hidden Markov Models, feature selection and heterogeneous ensemble classifiers. In order to evaluate its capability of identifying normal images across diverse populations, a population-oriented study was undertaken comparing the software's output to grading by humans. In addition, population based studies collect large numbers of images on subjects expected to have no abnormality. These studies expect timely and cost-effective grading. Altogether 9954 previously unseen images taken from various populations were tested. All test images were masked so the automated system had not been exposed to them before. This system was trained using image subregions taken from about 400 sample images. Sensitivities of 92.2% and specificities of 90.4% were achieved varying between populations and population clusters. Of all images the automated system decided to be normal, 98.2% were true normal when compared to the manual grading results. These results demonstrate scalability and strong potential of such an integrated computational intelligence system as an effective tool to assist a grading service. |
| format |
article |
| author |
Hongying Lilian Tang Jonathan Goh Tunde Peto Bingo Wing-Kuen Ling Lutfiah Ismail Al Turk Yin Hu Su Wang George Michael Saleh |
| author_facet |
Hongying Lilian Tang Jonathan Goh Tunde Peto Bingo Wing-Kuen Ling Lutfiah Ismail Al Turk Yin Hu Su Wang George Michael Saleh |
| author_sort |
Hongying Lilian Tang |
| title |
The reading of components of diabetic retinopathy: an evolutionary approach for filtering normal digital fundus imaging in screening and population based studies. |
| title_short |
The reading of components of diabetic retinopathy: an evolutionary approach for filtering normal digital fundus imaging in screening and population based studies. |
| title_full |
The reading of components of diabetic retinopathy: an evolutionary approach for filtering normal digital fundus imaging in screening and population based studies. |
| title_fullStr |
The reading of components of diabetic retinopathy: an evolutionary approach for filtering normal digital fundus imaging in screening and population based studies. |
| title_full_unstemmed |
The reading of components of diabetic retinopathy: an evolutionary approach for filtering normal digital fundus imaging in screening and population based studies. |
| title_sort |
reading of components of diabetic retinopathy: an evolutionary approach for filtering normal digital fundus imaging in screening and population based studies. |
| publisher |
Public Library of Science (PLoS) |
| publishDate |
2013 |
| url |
https://doaj.org/article/9bfe811c86c8480e9b16cd2eb91c61d4 |
| work_keys_str_mv |
AT hongyingliliantang thereadingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT jonathangoh thereadingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT tundepeto thereadingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT bingowingkuenling thereadingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT lutfiahismailalturk thereadingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT yinhu thereadingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT suwang thereadingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT georgemichaelsaleh thereadingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT hongyingliliantang readingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT jonathangoh readingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT tundepeto readingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT bingowingkuenling readingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT lutfiahismailalturk readingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT yinhu readingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT suwang readingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies AT georgemichaelsaleh readingofcomponentsofdiabeticretinopathyanevolutionaryapproachforfilteringnormaldigitalfundusimaginginscreeningandpopulationbasedstudies |
| _version_ |
1718423178356719616 |