Combining prostate cancer region predictions from MALDI spectra processing and texture analysis

Jiang Li, Ayyappa Vadlamudi, Shao Hui Chuang, Xiaoyan Sun, Bo Sun, Frederic D. McKenzie, Lisa Cazares, Julius Nyalwidhe, Dean Troyer, O. John Semmes

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We present a three-step method to predict Prostate cancer (PCa) regions on biopsy tissue samples based on high confidence, low resolution PCa regions marked by a pathologist. First, we apply a texture analysis technique on a high magnification optical image to predict PCa regions on an adjacent tissue slice. Second, we design a prediction model for the same purpose using matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) tissue imaging data from the adjacent slice. Finally, we fuse those two results to obtain the PCa regions that will assist MALDI imaging biomarker identification. Experiment results show that the texture analysis based prediction is sensitive (sen. 87.45%) but not specific (spe. 75%), and the prediction based on the MALDI spectra data is specific (spe. 100%) but less sensitive (sen. 50.98%). By combining those two results, a much better prediction for PCa regions on the adjacent slice can be achieved (sen. 80.39%, spe. 93.09%).

Original languageEnglish (US)
Title of host publication10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010
Pages73-78
Number of pages6
DOIs
StatePublished - Sep 6 2010
Event10th IEEE International Conference on Bioinformatics and Bioengineering, BIBE-2010 - Philadelphia, PA, United States
Duration: May 31 2010Jun 3 2010

Publication series

Name10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010

Other

Other10th IEEE International Conference on Bioinformatics and Bioengineering, BIBE-2010
CountryUnited States
CityPhiladelphia, PA
Period5/31/106/3/10

Fingerprint

Matrix-Assisted Laser Desorption-Ionization Mass Spectrometry
Prostatic Neoplasms
Textures
Tissue
Processing
Imaging techniques
Biopsy
Biomarkers
Electric fuses
Ionization
Mass spectrometry
Desorption
Lasers
Experiments

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Health Informatics

Cite this

Li, J., Vadlamudi, A., Chuang, S. H., Sun, X., Sun, B., McKenzie, F. D., ... Semmes, O. J. (2010). Combining prostate cancer region predictions from MALDI spectra processing and texture analysis. In 10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010 (pp. 73-78). [5521709] (10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010). https://doi.org/10.1109/BIBE.2010.20
Li, Jiang ; Vadlamudi, Ayyappa ; Chuang, Shao Hui ; Sun, Xiaoyan ; Sun, Bo ; McKenzie, Frederic D. ; Cazares, Lisa ; Nyalwidhe, Julius ; Troyer, Dean ; Semmes, O. John. / Combining prostate cancer region predictions from MALDI spectra processing and texture analysis. 10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010. 2010. pp. 73-78 (10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010).
@inproceedings{684005a1519143fb814f44130aaabf93,
title = "Combining prostate cancer region predictions from MALDI spectra processing and texture analysis",
abstract = "We present a three-step method to predict Prostate cancer (PCa) regions on biopsy tissue samples based on high confidence, low resolution PCa regions marked by a pathologist. First, we apply a texture analysis technique on a high magnification optical image to predict PCa regions on an adjacent tissue slice. Second, we design a prediction model for the same purpose using matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) tissue imaging data from the adjacent slice. Finally, we fuse those two results to obtain the PCa regions that will assist MALDI imaging biomarker identification. Experiment results show that the texture analysis based prediction is sensitive (sen. 87.45{\%}) but not specific (spe. 75{\%}), and the prediction based on the MALDI spectra data is specific (spe. 100{\%}) but less sensitive (sen. 50.98{\%}). By combining those two results, a much better prediction for PCa regions on the adjacent slice can be achieved (sen. 80.39{\%}, spe. 93.09{\%}).",
author = "Jiang Li and Ayyappa Vadlamudi and Chuang, {Shao Hui} and Xiaoyan Sun and Bo Sun and McKenzie, {Frederic D.} and Lisa Cazares and Julius Nyalwidhe and Dean Troyer and Semmes, {O. John}",
year = "2010",
month = "9",
day = "6",
doi = "10.1109/BIBE.2010.20",
language = "English (US)",
isbn = "9780769540832",
series = "10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010",
pages = "73--78",
booktitle = "10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010",

}

Li, J, Vadlamudi, A, Chuang, SH, Sun, X, Sun, B, McKenzie, FD, Cazares, L, Nyalwidhe, J, Troyer, D & Semmes, OJ 2010, Combining prostate cancer region predictions from MALDI spectra processing and texture analysis. in 10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010., 5521709, 10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010, pp. 73-78, 10th IEEE International Conference on Bioinformatics and Bioengineering, BIBE-2010, Philadelphia, PA, United States, 5/31/10. https://doi.org/10.1109/BIBE.2010.20

Combining prostate cancer region predictions from MALDI spectra processing and texture analysis. / Li, Jiang; Vadlamudi, Ayyappa; Chuang, Shao Hui; Sun, Xiaoyan; Sun, Bo; McKenzie, Frederic D.; Cazares, Lisa; Nyalwidhe, Julius; Troyer, Dean; Semmes, O. John.

10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010. 2010. p. 73-78 5521709 (10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Combining prostate cancer region predictions from MALDI spectra processing and texture analysis

AU - Li, Jiang

AU - Vadlamudi, Ayyappa

AU - Chuang, Shao Hui

AU - Sun, Xiaoyan

AU - Sun, Bo

AU - McKenzie, Frederic D.

AU - Cazares, Lisa

AU - Nyalwidhe, Julius

AU - Troyer, Dean

AU - Semmes, O. John

PY - 2010/9/6

Y1 - 2010/9/6

N2 - We present a three-step method to predict Prostate cancer (PCa) regions on biopsy tissue samples based on high confidence, low resolution PCa regions marked by a pathologist. First, we apply a texture analysis technique on a high magnification optical image to predict PCa regions on an adjacent tissue slice. Second, we design a prediction model for the same purpose using matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) tissue imaging data from the adjacent slice. Finally, we fuse those two results to obtain the PCa regions that will assist MALDI imaging biomarker identification. Experiment results show that the texture analysis based prediction is sensitive (sen. 87.45%) but not specific (spe. 75%), and the prediction based on the MALDI spectra data is specific (spe. 100%) but less sensitive (sen. 50.98%). By combining those two results, a much better prediction for PCa regions on the adjacent slice can be achieved (sen. 80.39%, spe. 93.09%).

AB - We present a three-step method to predict Prostate cancer (PCa) regions on biopsy tissue samples based on high confidence, low resolution PCa regions marked by a pathologist. First, we apply a texture analysis technique on a high magnification optical image to predict PCa regions on an adjacent tissue slice. Second, we design a prediction model for the same purpose using matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) tissue imaging data from the adjacent slice. Finally, we fuse those two results to obtain the PCa regions that will assist MALDI imaging biomarker identification. Experiment results show that the texture analysis based prediction is sensitive (sen. 87.45%) but not specific (spe. 75%), and the prediction based on the MALDI spectra data is specific (spe. 100%) but less sensitive (sen. 50.98%). By combining those two results, a much better prediction for PCa regions on the adjacent slice can be achieved (sen. 80.39%, spe. 93.09%).

UR - http://www.scopus.com/inward/record.url?scp=77956168214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956168214&partnerID=8YFLogxK

U2 - 10.1109/BIBE.2010.20

DO - 10.1109/BIBE.2010.20

M3 - Conference contribution

AN - SCOPUS:77956168214

SN - 9780769540832

T3 - 10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010

SP - 73

EP - 78

BT - 10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010

ER -

Li J, Vadlamudi A, Chuang SH, Sun X, Sun B, McKenzie FD et al. Combining prostate cancer region predictions from MALDI spectra processing and texture analysis. In 10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010. 2010. p. 73-78. 5521709. (10th IEEE International Conference on Bioinformatics and Bioengineering 2010, BIBE 2010). https://doi.org/10.1109/BIBE.2010.20