A neural classifier enabling high-throughput topological analysis of lymphocytes in tissue sections

Nattkemper TW, Ritter H, Schubert W (2001)
IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE 5(2): 138-149.

Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Zeitschriftenaufsatz | Veröffentlicht | Englisch
Abstract / Bemerkung
A neural cell detection system (NCDS) for the automatic quantitation of fluorescent lymphocytes in tissue sections is presented in this paper. The system acquires visual knowledge from a set of training cell-image patches selected by a user, The trained system evaluates an image in 2 min calculating: the number, the positions, and the phenotypes of the fluorescent cells. For validation, the NCDS learning performance was tested by cross validation on digitized images of tissue sections obtained from inherently different types of tissue: diagnostic tissue sections across the human tonsil and across an inflammatory lymphocyte infiltrate of the human skeletal muscle. The NCDS detection results were compared with detection results from biomedical experts and were visually evaluated by our most experienced biomedical expert. Although the micrographs were noisy and the fluorescent cells varied in shape and size, the NCDS detected a minimum of 95% of the cells. In contrast, the cellular counts based on visual cell recognition of the experts were inconsistent and largely unreproducible for approximately 80% of the lymphocytes present in a visual field. The data indicate that the NCDS is rapid and delivers highly reproducible results and, therefore, enables high-throughput topological screening of lymphocytes in many types of tissue, e.g., as obtained by routine diagnostic biopsy procedures. High-throughput screening with the NCDS provides the platform for the quantitative analysis of the interrelationship between tissue environment, cellular phenotype, and cellular topology.
Erscheinungsjahr
Zeitschriftentitel
IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE
Band
5
Ausgabe
2
Seite(n)
138-149
ISSN
PUB-ID

Zitieren

Nattkemper TW, Ritter H, Schubert W. A neural classifier enabling high-throughput topological analysis of lymphocytes in tissue sections. IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE. 2001;5(2):138-149.
Nattkemper, T. W., Ritter, H., & Schubert, W. (2001). A neural classifier enabling high-throughput topological analysis of lymphocytes in tissue sections. IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, 5(2), 138-149. doi:10.1109/4233.924804
Nattkemper, T. W., Ritter, H., and Schubert, W. (2001). A neural classifier enabling high-throughput topological analysis of lymphocytes in tissue sections. IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE 5, 138-149.
Nattkemper, T.W., Ritter, H., & Schubert, W., 2001. A neural classifier enabling high-throughput topological analysis of lymphocytes in tissue sections. IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, 5(2), p 138-149.
T.W. Nattkemper, H. Ritter, and W. Schubert, “A neural classifier enabling high-throughput topological analysis of lymphocytes in tissue sections”, IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, vol. 5, 2001, pp. 138-149.
Nattkemper, T.W., Ritter, H., Schubert, W.: A neural classifier enabling high-throughput topological analysis of lymphocytes in tissue sections. IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE. 5, 138-149 (2001).
Nattkemper, Tim Wilhelm, Ritter, Helge, and Schubert, Walter. “A neural classifier enabling high-throughput topological analysis of lymphocytes in tissue sections”. IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE 5.2 (2001): 138-149.

20 Zitationen in Europe PMC

Daten bereitgestellt von Europe PubMed Central.

Automatic detection and classification of leukocytes using convolutional neural networks.
Zhao J, Zhang M, Zhou Z, Chu J, Cao F., Med Biol Eng Comput 55(8), 2017
PMID: 27822698
Unbiased estimation of cell number using the automatic optical fractionator.
Mouton PR, Phoulady HA, Goldgof D, Hall LO, Gordon M, Morgan D., J Chem Neuroanat 80(), 2017
PMID: 27988177
Robust normalization protocols for multiplexed fluorescence bioimage analysis.
Ahmed Raza SE, Langenkämper D, Sirinukunwattana K, Epstein D, Nattkemper TW, Rajpoot NM., BioData Min 9(), 2016
PMID: 26949415
Automated segmentation of the melanocytes in skin histopathological images.
Lu C, Mahmood M, Jha N, Mandal M., IEEE J Biomed Health Inform 17(2), 2013
PMID: 22614727
Approaches to automatic parameter fitting in a microscopy image segmentation pipeline: An exploratory parameter space analysis.
Held C, Nattkemper T, Palmisano R, Wittenberg T., J Pathol Inform 4(suppl), 2013
PMID: 23766941
Benchmarking HEp-2 cells classification methods.
Foggia P, Percannella G, Soda P, Vento M., IEEE Trans Med Imaging 32(10), 2013
PMID: 23797238
Automatic recognition of five types of white blood cells in peripheral blood.
Rezatofighi SH, Soltanian-Zadeh H., Comput Med Imaging Graph 35(4), 2011
PMID: 21300521
Spermatogonium image recognition using Zernike moments.
Liyun W, Hefei L, Fuhao Z, Zhengding L, Zhendi W., Comput Methods Programs Biomed 95(1), 2009
PMID: 19268385
Indirect immunofluorescence in autoimmune diseases: assessment of digital images for diagnostic purpose.
Rigon A, Soda P, Zennaro D, Iannello G, Afeltra A., Cytometry B Clin Cytom 72(6), 2007
PMID: 17549740
Quantification of vesicles in differentiating human SH-SY5Y neuroblastoma cells by automated image analysis.
Selinummi J, Sarkanen JR, Niemistö A, Linne ML, Ylikomi T, Yli-Harja O, Jalonen TO., Neurosci Lett 396(2), 2006
PMID: 16356645
Learning lateral interactions for feature binding and sensory segmentation from prototypic basis interactions.
Weng S, Wersing H, Steil JJ, Ritter H., IEEE Trans Neural Netw 17(4), 2006
PMID: 16856650
An automated method for analysis of flow characteristics of circulating particles from in vivo video microscopy.
Eden E, Waisman D, Rudzsky M, Bitterman H, Brod V, Rivlin E., IEEE Trans Med Imaging 24(8), 2005
PMID: 16092333
A new preprocessing approach for cell recognition.
Long X, Cleveland WL, Yao YL., IEEE Trans Inf Technol Biomed 9(3), 2005
PMID: 16167695
On the accurate counting of tumor cells.
Fang B, Hsu W, Lee ML., IEEE Trans Nanobioscience 2(2), 2003
PMID: 15382665
Using proteomics to identify targets and validate leads.
Jain KK., Trends Biotechnol 20(8), 2002
PMID: 12127271

36 References

Daten bereitgestellt von Europe PubMed Central.

cross-validatory choice and assessment of statistical predictions
stone, J Royal Stat Soc 36(), 1974
efficient vector quantization using the wta-rule with activity equalization
heidemann, Neural Process Lett (), 0

heidemann, Ein flexibel einsetzbares Objekterkennungssystem auf der Basis neuronaler Netze (), 1998

AUTHOR UNKNOWN, 0
Immunology of the tonsils.
Perry M, Whyte A., Immunol. Today 19(9), 1998
PMID: 9745205
Computer-aided detection of breast cancer nuclei.
Schnorrenberg F, Pattichis CS, Kyriacou KC, Schizas CN., IEEE Trans Inf Technol Biomed 1(2), 1997
PMID: 11020815
fast contour identification through efficient hough transform and simplified interpretation strategy
gerig, Proc Int l Conf Pattern Recognition 8(), 1986

AUTHOR UNKNOWN, 0
Lymphocyte antigen Leu-19 as a molecular marker of regeneration in human skeletal muscle.
Schubert W, Zimmermann K, Cramer M, Starzinski-Powitz A., Proc. Natl. Acad. Sci. U.S.A. 86(1), 1989
PMID: 2463624
app$+$ t-lymphocytes selectively sorted endomysial tubes in polymyositis displace ncam expressing muscle fibers
schubert, Eur J Cell Biol 58(), 1993

AUTHOR UNKNOWN, 0

AUTHOR UNKNOWN, 0

rao, An active vision architecture based on iconic representations (), 1995
Eigenfaces for recognition.
Turk M, Pentland A., J Cogn Neurosci 3(1), 1991
PMID: 23964806

AUTHOR UNKNOWN, 0
learning with the self-organizing map
ritter, Artificial Neural Networks 1 (), 1991

oja, Kohonen Maps (), 1999
Fundamentals of flow cytometry.
Jaroszeski MJ, Radcliff G., Mol. Biotechnol. 11(1), 1999
PMID: 10367281
Detection of minimal residual disease in acute leukemia by flow cytometry.
Campana D, Coustan-Smith E., Cytometry 38(4), 1999
PMID: 10440852

AUTHOR UNKNOWN, 0
learning internal representations by error propagation
rumelhart, Parallel Distributed Processing Explorations in the Microstructure of Cognition 1 foundations(), 1986
Reactivity of peripheral blood lymphocytes to oxidized low-density lipoprotein: a novel system to estimate atherosclerosis employing the Cellscan.
Zurgil N, Levy Y, Deutsch M, Gilburd B, George J, Harats D, Kaufman M, Shoenfeld Y., Clin Cardiol 22(8), 1999
PMID: 10492842
a circle-detection algorithm simulating wave propagation
hanahara, Mach Vis Appl 3(), 1990
Leucocyte activation markers in clinical practice.
Viedma Contreras JA., Clin. Chem. Lab. Med. 37(6), 1999
PMID: 10475068
Imaging cytometry by multiparameter fluorescence.
Galbraith W, Wagner MC, Chao J, Abaza M, Ernst LA, Nederlof MA, Hartsock RJ, Taylor DL, Waggoner AS., Cytometry 12(7), 1991
PMID: 1782829
Clinically useful information provided by the flow cytometric immunophenotyping of hematological malignancies: current status and future directions.
Orfao A, Schmitz G, Brando B, Ruiz-Arguelles A, Basso G, Braylan R, Rothe G, Lacombe F, Lanza F, Papa S, Lucio P, San Miguel JF., Clin. Chem. 45(10), 1999
PMID: 10508115
combining multiple neural nets for visual feature selection and classification
heidemann, Proceedings of 9th International Conference on Artificial Neural Networks ICANN 99 1(), 1999

AUTHOR UNKNOWN, 0

kohonen, Self-Organization and Associative Memory (), 1989
gtm: the generative topographic mapping
bishop, Neural Comput 10(), 1998

AUTHOR UNKNOWN, 0
two efficient connectionist schemes for structure-preserving dimension reduction
pal, IEEE Transactions on Neural Networks 8(), 1997

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

PMID: 11420992
PubMed | Europe PMC

Suchen in

Google Scholar