Use of Mechanical Turk as a MapReduce Framework for Macular OCT Segmentation
Purpose. To evaluate the feasibility of using Mechanical Turk as a massively parallel platform to perform manual segmentations of macular spectral domain optical coherence tomography (SD-OCT) images using a MapReduce framework. Methods. A macular SD-OCT volume of 61 slice images was map-distributed...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2016-01-01
|
| Series: | Journal of Ophthalmology |
| Online Access: | http://dx.doi.org/10.1155/2016/6571547 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832549411786326016 |
|---|---|
| author | Aaron Y. Lee Cecilia S. Lee Pearse A. Keane Adnan Tufail |
| author_facet | Aaron Y. Lee Cecilia S. Lee Pearse A. Keane Adnan Tufail |
| author_sort | Aaron Y. Lee |
| collection | DOAJ |
| description | Purpose. To evaluate the feasibility of using Mechanical Turk as a massively parallel platform to perform manual segmentations of macular spectral domain optical coherence tomography (SD-OCT) images using a MapReduce framework. Methods. A macular SD-OCT volume of 61 slice images was map-distributed to Amazon Mechanical Turk. Each Human Intelligence Task was set to $0.01 and required the user to draw five lines to outline the sublayers of the retinal OCT image after being shown example images. Each image was submitted twice for segmentation, and interrater reliability was calculated. The interface was created using custom HTML5 and JavaScript code, and data analysis was performed using R. An automated pipeline was developed to handle the map and reduce steps of the framework. Results. More than 93,500 data points were collected using this framework for the 61 images submitted. Pearson’s correlation of interrater reliability was 0.995 (p<0.0001) and coefficient of determination was 0.991. The cost of segmenting the macular volume was $1.21. A total of 22 individual Mechanical Turk users provided segmentations, each completing an average of 5.5 HITs. Each HIT was completed in an average of 4.43 minutes. Conclusions. Amazon Mechanical Turk provides a cost-effective, scalable, high-availability infrastructure for manual segmentation of OCT images. |
| format | Article |
| id | doaj-art-ef69ad25a40644a588b0ff442eaefe23 |
| institution | Kabale University |
| issn | 2090-004X 2090-0058 |
| language | English |
| publishDate | 2016-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Ophthalmology |
| spelling | doaj-art-ef69ad25a40644a588b0ff442eaefe232025-02-03T06:11:24ZengWileyJournal of Ophthalmology2090-004X2090-00582016-01-01201610.1155/2016/65715476571547Use of Mechanical Turk as a MapReduce Framework for Macular OCT SegmentationAaron Y. Lee0Cecilia S. Lee1Pearse A. Keane2Adnan Tufail3Department of Ophthalmology, University of Washington, Seattle, WA 98104, USADepartment of Ophthalmology, University of Washington, Seattle, WA 98104, USAMedical Retina Service, Moorfields Eye Hospital NHS Foundation Trust, London EC1V 2PD, UKMedical Retina Service, Moorfields Eye Hospital NHS Foundation Trust, London EC1V 2PD, UKPurpose. To evaluate the feasibility of using Mechanical Turk as a massively parallel platform to perform manual segmentations of macular spectral domain optical coherence tomography (SD-OCT) images using a MapReduce framework. Methods. A macular SD-OCT volume of 61 slice images was map-distributed to Amazon Mechanical Turk. Each Human Intelligence Task was set to $0.01 and required the user to draw five lines to outline the sublayers of the retinal OCT image after being shown example images. Each image was submitted twice for segmentation, and interrater reliability was calculated. The interface was created using custom HTML5 and JavaScript code, and data analysis was performed using R. An automated pipeline was developed to handle the map and reduce steps of the framework. Results. More than 93,500 data points were collected using this framework for the 61 images submitted. Pearson’s correlation of interrater reliability was 0.995 (p<0.0001) and coefficient of determination was 0.991. The cost of segmenting the macular volume was $1.21. A total of 22 individual Mechanical Turk users provided segmentations, each completing an average of 5.5 HITs. Each HIT was completed in an average of 4.43 minutes. Conclusions. Amazon Mechanical Turk provides a cost-effective, scalable, high-availability infrastructure for manual segmentation of OCT images.http://dx.doi.org/10.1155/2016/6571547 |
| spellingShingle | Aaron Y. Lee Cecilia S. Lee Pearse A. Keane Adnan Tufail Use of Mechanical Turk as a MapReduce Framework for Macular OCT Segmentation Journal of Ophthalmology |
| title | Use of Mechanical Turk as a MapReduce Framework for Macular OCT Segmentation |
| title_full | Use of Mechanical Turk as a MapReduce Framework for Macular OCT Segmentation |
| title_fullStr | Use of Mechanical Turk as a MapReduce Framework for Macular OCT Segmentation |
| title_full_unstemmed | Use of Mechanical Turk as a MapReduce Framework for Macular OCT Segmentation |
| title_short | Use of Mechanical Turk as a MapReduce Framework for Macular OCT Segmentation |
| title_sort | use of mechanical turk as a mapreduce framework for macular oct segmentation |
| url | http://dx.doi.org/10.1155/2016/6571547 |
| work_keys_str_mv | AT aaronylee useofmechanicalturkasamapreduceframeworkformacularoctsegmentation AT ceciliaslee useofmechanicalturkasamapreduceframeworkformacularoctsegmentation AT pearseakeane useofmechanicalturkasamapreduceframeworkformacularoctsegmentation AT adnantufail useofmechanicalturkasamapreduceframeworkformacularoctsegmentation |