article

Real time decision support system for diagnosis of rare cancers, trained in parallel, on a graphics processing unit

Authors:

Konstantinos Sidiropoulos,

Dimitrios Glotsos,

Spiros Kostopoulos,

Panagiota Ravazoula,

Ioannis Kalatzis,

Dionisis Cavouras,

John StonhamAuthors Info & Claims

Computers in Biology and Medicine, Volume 42, Issue 4

Pages 376 - 386

https://doi.org/10.1016/j.compbiomed.2011.12.004

Published: 01 April 2012 Publication History

Abstract

In the present study a new strategy is introduced for designing and developing of an efficient dynamic Decision Support System (DSS) for supporting rare cancers decision making. The proposed DSS operates on a Graphics Processing Unit (GPU) and it is capable of adjusting its design in real time based on user-defined clinical questions in contrast to standard CPU implementations that are limited by processing and memory constrains. The core of the proposed DSS was a Probabilistic Neural Network classifier and was evaluated on 140 rare brain cancer cases, regarding its ability to predict tumors' malignancy, using a panel of 20 morphological and textural features Generalization was estimated using an external 10-fold cross-validation. The proposed GPU-based DSS achieved significantly higher training speed, outperforming the CPU-based system by a factor that ranged from 267 to 288 times. System design was optimized using a combination of 4 textural and morphological features with 78.6% overall accuracy, whereas system generalization was 73.8%+/-3.2%. By exploiting the inherently parallel architecture of a consumer level GPU, the proposed approach enables real time, optimal design of a DSS for any user-defined clinical question for improving diagnostic assessments, prognostic relevance and concordance rates for rare cancers in clinical practice.

References

[1]

Fletcher, C., Diagnostic Histopathology of Tumors. 1995. Churchill Livingstone, Edinburgh, New York.

[2]

Ramsay, A.D., Errors by locums. Histopathology departments already audit diagnostic errors. Br. Med. J. v313. 117

[3]

Diagnostic errors in surgical pathology uncovered by a review of malpractice claims. Part III. breast biopsies. Int. J. Surg. Pathol. v8. 335-337.

[4]

Cowie, F., Treatment of rare cancers: gastrointestinal stromal tumours. Br. J. Hosp. Med. v67. 361-364.

[5]

Gonzalez, J. and Gilbert, M.R., Treatment of astrocytomas. Curr. Opin. Neurobiol. v18. 632-638.

[6]

Rare anal canal cancers in the U.S. veteran: patterns of disease and results of treatment. Am. Surg. v61. 495-500.

[7]

DiSario, J.A., Colorectal cancers of rare histologic types compared with adenocarcinomas. Dis. Colon Rectum. v38. 1227

[8]

Dixon, A., Rare skin cancers in general practice. Aust. Fam. Physician. v36. 141-143.

[9]

Joannides, T., Rare cancers. Clin. Oncol. v13. 235

[10]

Belkacemi, Y., Zouhair, A., Ozsahin, M., Azria, D. and Mirimanoff, R.O., {Prognostic factors and management of rare cancers}. Cancer/Radiothér. v10. 323-329.

[11]

Kutikova, L., Bowman, L. and Chang, S., Utilization and cost of health care services associated with primary malignant brain tumors in the United States. J. Neuro-oncol. v81. 61-65.

[12]

Prayson, R.A., Agamanolis, D.P. and Cohen, M.L., Interobserver reproducibility among neuropathologists and surgical pathologists in fibrillary astrocytoma grading. J. Neurol. Sci. v175. 33-39.

[13]

Coons, W., Jhonson, P., Sceithauer, B., Yates, A. and Pearl, D., Improving diagnostic accuracy and interobserver concordance in the classification and grading of Primary Gliomas. Cancer. v79. 1381-1393.

[14]

Belacel, N. and Boulassel, M., Multicriteria fuzzy assignment method: a useful tool to assist medical diagnosis. Artif. Intell. Med. v21. 201-207.

[15]

Decaestecker, C., Camby, I. and Nagy, N., Improving morphology-based malignancy grading schemes in astrocytic tumors by means of computer-assisted techniques. Brain Pathol. v8. 29-38.

[16]

Li, Guo-Zheng, Jie, Yang, Chen-Zhou, Ye and Dao-Ying, Geng, Degree prediction of malignancy in brain glioma using support vector machines. Comput. Biol. Med. v36. 313-325.

Digital Library

[17]

Nafe, R., Schlote, W. and Schneider, B., Histomorphometry of tumour cell nuclei in astrocytomas using shape analysis, densitometry and topometric analysis. Neuropathol. Appl. Neurobiol. v31. 34-44.

[18]

Grading of diffusely infiltrating astrocytomas by quantitative histopathology, cell proliferation and image cytometric DNA analysis. Comparison of 133 tumours in the context of the WHO 1979 and WHO 1993 grading schemes, Neuropathology and Applied Neurobiology. v26. 319-331.

[19]

Scarpelli, M., Montironi, R., Thompson, D. and Bartels, P., Computer-Assisted Discrimination of Glioblastomas. Anal. Quant. Cytol. Histopathol. v19. 369-375.

[20]

eTumour, {http://www.ist-world.org/ProjectDetails.aspx?ProjectId=ec81f1ded2ff4c82a6573cc77f2a3c79}.

[21]

DISHEART, {http://www.ist-world.org/ProjectDetails.aspx?ProjectId=2916094e804346ecbffc9d9a45fe9cf8}.

[22]

EUROPATH, {http://telescan.nki.nl/action/europath.htm}.

[23]

E-SCOPE, {http://cordis.europa.eu/fetch?CALLER=PROJ_ICT&ACTION=D&CAT=PROJ&RCN=71240}.

[24]

TUBAFROST, {http://www.tubafrost.org/}.

[25]

Rousseau, A., Mokhtari, K. and Duyckaerts, C., The 2007 WHO classification of tumors of the central nervous system - what has changed?. Curr. Opin. Neurobiol. v21. 720-727.

[26]

Paolo G. Casali, Do rare cancers deserve specific strategies for cancer research?, The Lancet Oncology 11 506-507.

[27]

Glotsos, D., Spyridonos, P. and Cavouras, D., Automated segmentation of routinely hematoxylin-eosin-stained microscopic images by combining support vector machine clustering and active contour models. Anal. Quant. Cytol. Histol. v26. 331-340.

[28]

Specht, D.F., Probabilistic. Neural Net. v3. 109-118.

[29]

Lachenbruch, P.A., An almost unbiased method of obtaining confidence intervals for the probability of misclassification in discriminant analysis. Biometrics. v23. 639-645.

[30]

Fellow, J., Duin, R. and Mao, J., Statistical pattern recognition: a review. IEEE Trans. Pattern Anal. Mach. Intell. v22. 4-37.

[31]

Dorin Comaniciu, Bogdan Georgescu, Peter Meer, Wenjin Chen, David Foran, Decision Support system for multiuser remote microscopy; in: Telepathology 12th IEEE Symposium on Computer-Based Medical Systems (CBMS '99), 18-20 June 1999, IEEE Computer Society, Stamford, CT, USA.

[32]

Logeswaran, R., Cholangiocarcinoma--an automated preliminary detection system using MLP. J. Med. Syst. v33. 413-421.

Digital Library

[33]

Spyridonos, P., Cavouras, D., Ravazoula, P. and Nikiforidis, G., A computer-based diagnostic and prognostic system for assessing urinary bladder tumour grade and predicting cancer recurrence. Med. Inf. Internet Med. v27. 111-122.

[34]

Xu, F. and Mueller, K., Real-time 3D computed tomographic reconstruction using commodity graphics hardware. Phys. Med. Biol. v52. 3405-3419.

[35]

Kyoung-Su, Oh. and Jung, Keechul, GPU implementation of neural networks. Pattern Recognit. v37. 1311-1314.

[36]

Julius. Ohmer, Maire, Frederic. and Brown, Ross., Implementation of Kernel Methods on the GPU digital imaging computing: techniques and applications (DICTA 2005) 2005.

[37]

Vincent Garcia, Eric Debreuve, Ross Brown, Fast k nearest neighbor search using GPU, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 24-26 June 2008, IEEE Computer Society, Anchorage, Alaska, USA

[38]

Shams, R., Sadeghi, P., Kennedy, R. and Hartley, R., Parallel computation of mutual information on the GPU with application to real-time registration of 3D medical images. Comput. Meth. Prog. Bio.

[39]

Lapeer, R.J., Shah, S.K. and Rowland, R.S., An optimised radial basis function algorithm for fast non-rigid registration of medical images. Comput. Biol. Med. v40. 1-7.

[40]

Ruiz, A., Sertel, O. and Ujaldon, M., Stroma classification for neuroblastoma on graphics processors. Int.J.Data Mining Bioinf. v3. 280-298.

Digital Library

[41]

Ambroise, C. and McLachlan, G.J., Selection bias in gene extraction on the basis of microarray gene-expression data. Proceedings of the National Academy of Sciences of the United States of America. v99. 6562-6566.

[42]

Kechman, V., . Learn. Soft Comput. 121-184.

Cited By

Theodosi AOuzounis SKostopoulos SGlotsos DKalatzis ITzelepi VRavazoula PAsvestas PCavouras DSakellaropoulos G(2021)Design of a hybrid deep learning system for discriminating between low- and high-grade colorectal cancer lesions, using microscopy images of IHC stained for AIB1 expression biopsy materialMachine Vision and Applications10.1007/s00138-021-01184-832:3Online publication date: 1-May-2021
https://dl.acm.org/doi/10.1007/s00138-021-01184-8
Jabez Christopher JKhanna Nehemiah HKannan A(2015)A clinical decision support system for diagnosis of Allergic Rhinitis based on intradermal skin testsComputers in Biology and Medicine10.1016/j.compbiomed.2015.07.01965:C(76-84)Online publication date: 1-Oct-2015
https://dl.acm.org/doi/10.1016/j.compbiomed.2015.07.019

Real time decision support system for diagnosis of rare cancers, trained in parallel, on a graphics processing unit
1. Applied computing
  1. Life and medical sciences
  2. Operations research
2. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
    2. Machine learning approaches

Recommendations

Graphics processing unit accelerated phase field dislocation dynamics

High-performance computing implementation of phase field dislocation dynamics is developed.The implementation is based on OpenACC and compute unified device architecture FFT library.Interaction and motion of dislocations through a bi-phase CuNi ...
Algorithmic performance studies on graphics processing units

We report on our experience with integrating and using graphics processing units (GPUs) as fast parallel floating-point co-processors to accelerate two fundamental computational scientific kernels on the GPU: sparse direct factorization and nonlinear ...
Massively parallel computation of linear recurrence equations with graphics processing units
SAMOS '18: Proceedings of the 18th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation

Graphics processing units (GPUs) show very high performance when executing many parallel programs; however their use in solving linear recurrence equations is considered difficult because of the sequential nature of the problem. Previously developed ...

Comments

Information & Contributors

Information

Published In

Copyright © Elsevier Ltd © 2011.

Publisher

Pergamon Press, Inc.

United States

Publication History

Published: 01 April 2012

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 04 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Theodosi AOuzounis SKostopoulos SGlotsos DKalatzis ITzelepi VRavazoula PAsvestas PCavouras DSakellaropoulos G(2021)Design of a hybrid deep learning system for discriminating between low- and high-grade colorectal cancer lesions, using microscopy images of IHC stained for AIB1 expression biopsy materialMachine Vision and Applications10.1007/s00138-021-01184-832:3Online publication date: 1-May-2021
https://dl.acm.org/doi/10.1007/s00138-021-01184-8
Jabez Christopher JKhanna Nehemiah HKannan A(2015)A clinical decision support system for diagnosis of Allergic Rhinitis based on intradermal skin testsComputers in Biology and Medicine10.1016/j.compbiomed.2015.07.01965:C(76-84)Online publication date: 1-Oct-2015
https://dl.acm.org/doi/10.1016/j.compbiomed.2015.07.019

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents