An Initial Approach to Segmentation and Analysis of Nerve Cells using Ridge Detection

S. J. Richerson; A. P. Condurache; J. A. Lohmeyer; K. Schultz; P. Ganske

doi:10.1109/SSIAI.2008.4512298

An Initial Approach to Segmentation and Analysis of Nerve Cells using Ridge Detection

S. J. Richerson, A. P. Condurache, J. A. Lohmeyer, K. Schultz, P. Ganske

Abstract

Histological studies of nerve cells are used by researchers to explore many nerve pathologies and treatments. Manual analysis and interpretation of hundreds of nerve fibers typically seen on one image is not possible and therefore, we propose a semi-automated tool based on ridge detection to allow users to segment histological images as they desire. An automatic segmentation is used to first segment the image. Ridges of the cells were enhanced using the first eigenvalue of the Hessian matrix. A hysteresis based ridge segmentation is then used to separate the cells from the background. The completed automatic segmentation is presented to the user. It can be further enhanced to meet the individual needs of the user. The user has the ability to (1) remove any cells in the histological image that are not desired cells or (2) add any cells not initially detected. Once the user-defined segmentation is completed, the final segmented image is used to analyze the properties of each individual cell. The size of each cell as well as a measure of wall thickness is calculated and saved for the user. In images of good contrast, where nerve cells are large and well spaced, the automatic cell detection rates are between 90-95%. In images with poor contrast with small nerve cells tightly packed together, the cell detection rate is 50-75%.

Original language	English
Title of host publication	2008 IEEE Southwest Symposium on Image Analysis and Interpretation
Number of pages	4
Publisher	IEEE
Publication date	01.03.2008
Pages	113-116
Article number	4512298
ISBN (Print)	978-1-4244-2296-8
ISBN (Electronic)	978-1-4244-2297-5
DOIs	https://doi.org/10.1109/SSIAI.2008.4512298
Publication status	Published - 01.03.2008
Event	2008 IEEE Southwest Symposium on Image Analysis and Interpretation - Santa Fe, United States Duration: 24.03.2008 → 26.03.2008 Conference number: 79811

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/SSIAI.2008.4512298

Cite this

Richerson, S. J., Condurache, A. P., Lohmeyer, J. A., Schultz, K., & Ganske, P. (2008). An Initial Approach to Segmentation and Analysis of Nerve Cells using Ridge Detection. In 2008 IEEE Southwest Symposium on Image Analysis and Interpretation (pp. 113-116). Article 4512298 (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation). IEEE. https://doi.org/10.1109/SSIAI.2008.4512298

@inproceedings{9449141fe45f4d75a09b69cc735e5f16,

title = "An Initial Approach to Segmentation and Analysis of Nerve Cells using Ridge Detection",

abstract = "Histological studies of nerve cells are used by researchers to explore many nerve pathologies and treatments. Manual analysis and interpretation of hundreds of nerve fibers typically seen on one image is not possible and therefore, we propose a semi-automated tool based on ridge detection to allow users to segment histological images as they desire. An automatic segmentation is used to first segment the image. Ridges of the cells were enhanced using the first eigenvalue of the Hessian matrix. A hysteresis based ridge segmentation is then used to separate the cells from the background. The completed automatic segmentation is presented to the user. It can be further enhanced to meet the individual needs of the user. The user has the ability to (1) remove any cells in the histological image that are not desired cells or (2) add any cells not initially detected. Once the user-defined segmentation is completed, the final segmented image is used to analyze the properties of each individual cell. The size of each cell as well as a measure of wall thickness is calculated and saved for the user. In images of good contrast, where nerve cells are large and well spaced, the automatic cell detection rates are between 90-95%. In images with poor contrast with small nerve cells tightly packed together, the cell detection rate is 50-75%.",

author = "Richerson, {S. J.} and Condurache, {A. P.} and Lohmeyer, {J. A.} and K. Schultz and P. Ganske",

year = "2008",

month = mar,

day = "1",

doi = "10.1109/SSIAI.2008.4512298",

language = "English",

isbn = "978-1-4244-2296-8",

series = "Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation",

publisher = "IEEE",

pages = "113--116",

booktitle = "2008 IEEE Southwest Symposium on Image Analysis and Interpretation",

note = "2008 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2008 ; Conference date: 24-03-2008 Through 26-03-2008",

}

Richerson, SJ, Condurache, AP, Lohmeyer, JA, Schultz, K & Ganske, P 2008, An Initial Approach to Segmentation and Analysis of Nerve Cells using Ridge Detection. in 2008 IEEE Southwest Symposium on Image Analysis and Interpretation., 4512298, Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation, IEEE, pp. 113-116, 2008 IEEE Southwest Symposium on Image Analysis and Interpretation, Santa Fe, New Mexico, United States, 24.03.08. https://doi.org/10.1109/SSIAI.2008.4512298

An Initial Approach to Segmentation and Analysis of Nerve Cells using Ridge Detection. / Richerson, S. J.; Condurache, A. P.; Lohmeyer, J. A. et al.
2008 IEEE Southwest Symposium on Image Analysis and Interpretation. IEEE, 2008. p. 113-116 4512298 (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - An Initial Approach to Segmentation and Analysis of Nerve Cells using Ridge Detection

AU - Richerson, S. J.

AU - Condurache, A. P.

AU - Lohmeyer, J. A.

AU - Schultz, K.

AU - Ganske, P.

N1 - Conference code: 79811

PY - 2008/3/1

Y1 - 2008/3/1

N2 - Histological studies of nerve cells are used by researchers to explore many nerve pathologies and treatments. Manual analysis and interpretation of hundreds of nerve fibers typically seen on one image is not possible and therefore, we propose a semi-automated tool based on ridge detection to allow users to segment histological images as they desire. An automatic segmentation is used to first segment the image. Ridges of the cells were enhanced using the first eigenvalue of the Hessian matrix. A hysteresis based ridge segmentation is then used to separate the cells from the background. The completed automatic segmentation is presented to the user. It can be further enhanced to meet the individual needs of the user. The user has the ability to (1) remove any cells in the histological image that are not desired cells or (2) add any cells not initially detected. Once the user-defined segmentation is completed, the final segmented image is used to analyze the properties of each individual cell. The size of each cell as well as a measure of wall thickness is calculated and saved for the user. In images of good contrast, where nerve cells are large and well spaced, the automatic cell detection rates are between 90-95%. In images with poor contrast with small nerve cells tightly packed together, the cell detection rate is 50-75%.

AB - Histological studies of nerve cells are used by researchers to explore many nerve pathologies and treatments. Manual analysis and interpretation of hundreds of nerve fibers typically seen on one image is not possible and therefore, we propose a semi-automated tool based on ridge detection to allow users to segment histological images as they desire. An automatic segmentation is used to first segment the image. Ridges of the cells were enhanced using the first eigenvalue of the Hessian matrix. A hysteresis based ridge segmentation is then used to separate the cells from the background. The completed automatic segmentation is presented to the user. It can be further enhanced to meet the individual needs of the user. The user has the ability to (1) remove any cells in the histological image that are not desired cells or (2) add any cells not initially detected. Once the user-defined segmentation is completed, the final segmented image is used to analyze the properties of each individual cell. The size of each cell as well as a measure of wall thickness is calculated and saved for the user. In images of good contrast, where nerve cells are large and well spaced, the automatic cell detection rates are between 90-95%. In images with poor contrast with small nerve cells tightly packed together, the cell detection rate is 50-75%.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-77950850413&origin=inward&txGid=d4eb542c5e6cded77eb9d82cbc42b010

U2 - 10.1109/SSIAI.2008.4512298

DO - 10.1109/SSIAI.2008.4512298

M3 - Conference contribution

SN - 978-1-4244-2296-8

T3 - Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation

SP - 113

EP - 116

BT - 2008 IEEE Southwest Symposium on Image Analysis and Interpretation

PB - IEEE

T2 - 2008 IEEE Southwest Symposium on Image Analysis and Interpretation

Y2 - 24 March 2008 through 26 March 2008

ER -

An Initial Approach to Segmentation and Analysis of Nerve Cells using Ridge Detection

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this