PathMiner: a web-based tool for computer-assisted diagnostics in pathology

Authors:
Lin Yang;Oncel Tuzel;Wenjin Chen;Peter Meer;Gratian Salaru;Lauri A. Goodell;David J. Foran
Affiliations:
Department of Electrical and Computer Engineering, Rutgers University, Piscataway and The Cancer Institute of New Jersey, New Brunswick, NJ;Mitsubishi Electric Research Laboratories, Cambridge, MA and Department of Computer Science, Rutgers University, Piscataway, NJ;Center for Biomedical Imaging and Informatics, University of Medicine and Dentistry of New Jersey, Piscataway, NJ;Department of Electrical and Computer Engineering, Rutgers University, Piscataway, NJ;Department of Pathology and Laboratory Medicine, Robert Wood Johnson Medical School, University of Medicine and Dentistry of New Jersey, New Brunswick, NJ;Department of Pathology and Laboratory Medicine, Robert Wood Johnson Medical School, University of Medicine and Dentistry of New Jersey and Immunohistochemistry Core Research Laboratory, The Cance ...;Center for Biomedical Imaging and Informatics, Robert Wood Johnson Medical School, University of Medicine and Dentistry of New Jersey, Piscataway and The Cancer Institute of New Jersey, New Brunsw ...
Venue:
IEEE Transactions on Information Technology in Biomedicine
Year:
2009

Citing 18
Cited 0

Efficient and effective querying by image content

Journal of Intelligent Information Systems - Special issue: advances in visual information management systems
Pyramid-based texture analysis/synthesis

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Support-Vector Networks

Machine Learning
Photobook: content-based manipulation of image databases

International Journal of Computer Vision
Computational Aspects of Pathology Image Classification and Retrieval

The Journal of Supercomputing - Special issue on supercomputing in medicine
Parallel marker-based image segmentation with watershed transformation

Journal of Parallel and Distributed Computing
Image-guided decision support system for pathology

Machine Vision and Applications
IRM: integrated region matching for image retrieval

MULTIMEDIA '00 Proceedings of the eighth ACM international conference on Multimedia
Content-based retrieval of breast cancer biopsy slides

Technology and Health Care
Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying

IEEE Transactions on Pattern Analysis and Machine Intelligence
Classifying Images of Materials: Achieving Viewpoint and Illumination Independence

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Recognizing Surfaces Using Three-Dimensional Textons

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
3D Texture Recognition Using Bidirectional Feature Histograms

International Journal of Computer Vision
Classification of hematologic malignancies using texton signatures

Pattern Analysis & Applications
High throughput analysis of breast cancer specimens on the grid

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Unsupervised segmentation based on robust estimation and color active contour models

IEEE Transactions on Information Technology in Biomedicine
Snakes, shapes, and gradient vector flow

IEEE Transactions on Image Processing
A comparison of methods for multiclass support vector machines

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Large-scale, multisite collaboration has become indispensable for a wide range of research and clinical activities that rely on the capacity of individuals to dynamically acquire, share, and assess images and correlated data. In this paper, we report the development of a Web-based system, PathMiner, for interactive telemedicine, intelligent archiving, and automated decision support in pathology. The PathMiner system supports network-based submission of queries and can automatically locate and retrieve digitized pathology specimens along with correlated molecular studies of cases from "ground-truth" databases that exhibit spectral and spatial profiles consistent with a given query image. The statistically most probable diagnosis is provided to the individual who is seeking decision support. To test the system under real-case scenarios, a pipeline infrastructure was developed and a network-based test laboratory was established at strategic sites at the University of Medicine and Dentistry of New Jersey--Robert Wood Johnson Medical School, Robert Wood Johnson University Hospital, theUniversity ofPennsylvania School of Medicine, Hospital of the University of Pennsylvania, The Cancer Institute of New Jersey, and Rutgers University. The average five-class classification accuracy of the system was 93.18% based on a tenfold cross validation on a close dataset containing 3691 imaged specimens. We also conducted prospective performance studies with the Path-Miner system in real applications in which the specimens exhibited large variations in staining characters compared with the training data. The average five-class classification accuracy in this open-set experiment was 87.22%. We also provide the comparative results with the previous literature and the PathMiner system shows superior performance.