An Interactive Java Statistical Image Segmentation System: GemIdent
Supervised learning can be used to segment/identify regions of interest in images usingboth color and morphological information. A novel object identication algorithm wasdeveloped in Java to locate immune and cancer cells in images of immunohistochemically-stained lymph node tissue from a recent stu...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Foundation for Open Access Statistics
2009-06-01
|
| Series: | Journal of Statistical Software |
| Subjects: | |
| Online Access: | http://www.jstatsoft.org/v30/i10/paper |
| _version_ | 1818615440873619456 |
|---|---|
| author | Susan Holmes Adam Kapelner Peter P. Lee |
| author_facet | Susan Holmes Adam Kapelner Peter P. Lee |
| author_sort | Susan Holmes |
| collection | DOAJ |
| description | Supervised learning can be used to segment/identify regions of interest in images usingboth color and morphological information. A novel object identication algorithm wasdeveloped in Java to locate immune and cancer cells in images of immunohistochemically-stained lymph node tissue from a recent study published by Kohrt et al. (2005). Thealgorithms are also showing promise in other domains. The success of the method de-pends heavily on the use of color, the relative homogeneity of object appearance and oninteractivity. As is often the case in segmentation, an algorithm specically tailored tothe application works better than using broader methods that work passably well on anyproblem. Our main innovation is the interactive feature extraction from color images. Wealso enable the user to improve the classication with an interactive visualization system.This is then coupled with the statistical learning algorithms and intensive feedback fromthe user over many classication-correction iterations, resulting in a highly accurate anduser-friendly solution. The system ultimately provides the locations of every cell recog-nized in the entire tissue in a text le tailored to be easily imported into R (Ihaka andGentleman 1996; R Development Core Team 2009) for further statistical analyses. Thisdata is invaluable in the study of spatial and multidimensional relationships between cellpopulations and tumor structure. This system is available at http://www.GemIdent.com/together with three demonstration videos and a manual. |
| first_indexed | 2024-12-16T16:33:57Z |
| format | Article |
| id | doaj.art-f666b6560e024257b0aa742d2b0f7de3 |
| institution | Directory Open Access Journal |
| issn | 1548-7660 |
| language | English |
| last_indexed | 2024-12-16T16:33:57Z |
| publishDate | 2009-06-01 |
| publisher | Foundation for Open Access Statistics |
| record_format | Article |
| series | Journal of Statistical Software |
| spelling | doaj.art-f666b6560e024257b0aa742d2b0f7de32022-12-21T22:24:31ZengFoundation for Open Access StatisticsJournal of Statistical Software1548-76602009-06-013010An Interactive Java Statistical Image Segmentation System: GemIdentSusan HolmesAdam KapelnerPeter P. LeeSupervised learning can be used to segment/identify regions of interest in images usingboth color and morphological information. A novel object identication algorithm wasdeveloped in Java to locate immune and cancer cells in images of immunohistochemically-stained lymph node tissue from a recent study published by Kohrt et al. (2005). Thealgorithms are also showing promise in other domains. The success of the method de-pends heavily on the use of color, the relative homogeneity of object appearance and oninteractivity. As is often the case in segmentation, an algorithm specically tailored tothe application works better than using broader methods that work passably well on anyproblem. Our main innovation is the interactive feature extraction from color images. Wealso enable the user to improve the classication with an interactive visualization system.This is then coupled with the statistical learning algorithms and intensive feedback fromthe user over many classication-correction iterations, resulting in a highly accurate anduser-friendly solution. The system ultimately provides the locations of every cell recog-nized in the entire tissue in a text le tailored to be easily imported into R (Ihaka andGentleman 1996; R Development Core Team 2009) for further statistical analyses. Thisdata is invaluable in the study of spatial and multidimensional relationships between cellpopulations and tumor structure. This system is available at http://www.GemIdent.com/together with three demonstration videos and a manual.http://www.jstatsoft.org/v30/i10/paperinteractive boostingcell recognitionimage segmentationJava |
| spellingShingle | Susan Holmes Adam Kapelner Peter P. Lee An Interactive Java Statistical Image Segmentation System: GemIdent Journal of Statistical Software interactive boosting cell recognition image segmentation Java |
| title | An Interactive Java Statistical Image Segmentation System: GemIdent |
| title_full | An Interactive Java Statistical Image Segmentation System: GemIdent |
| title_fullStr | An Interactive Java Statistical Image Segmentation System: GemIdent |
| title_full_unstemmed | An Interactive Java Statistical Image Segmentation System: GemIdent |
| title_short | An Interactive Java Statistical Image Segmentation System: GemIdent |
| title_sort | interactive java statistical image segmentation system gemident |
| topic | interactive boosting cell recognition image segmentation Java |
| url | http://www.jstatsoft.org/v30/i10/paper |
| work_keys_str_mv | AT susanholmes aninteractivejavastatisticalimagesegmentationsystemgemident AT adamkapelner aninteractivejavastatisticalimagesegmentationsystemgemident AT peterplee aninteractivejavastatisticalimagesegmentationsystemgemident AT susanholmes interactivejavastatisticalimagesegmentationsystemgemident AT adamkapelner interactivejavastatisticalimagesegmentationsystemgemident AT peterplee interactivejavastatisticalimagesegmentationsystemgemident |