Collaboration transparency in the DISCIPLE framework
GROUP '99 Proceedings of the international ACM SIGGROUP conference on Supporting group work
DISCIPLE: a framework for multimodal collaboration in heterogeneous environments
ACM Computing Surveys (CSUR)
Advanced algorithmic approaches to medical image segmentation
Using human perceptual categories for content-based retrieval from a medical image database
Computer Vision and Image Understanding
Retrieval Performance Improvement through Low Rank Corrections
CBAIVL '99 Proceedings of the IEEE Workshop on Content-Based Access of Image and Video Libraries
Real-Time Collaboration in Heterogeneous Computing Environments
ITCC '00 Proceedings of the The International Conference on Information Technology: Coding and Computing (ITCC'00)
Texture based medical image indexing and retrieval: application to cardiac imaging
Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval
Content based radiology image retrieval using a fuzzy rule based scalable composite descriptor
Multimedia Tools and Applications
Evaluation of a Content-Based Retrieval System for Blood Cell Images with Automated Methods
Journal of Medical Systems
| Hi-index | 0.00 |
The prototype of a system to assist the physicians in differentialdiagnosis of lymphoproliferative disorders of bloodcells from digitized specimens is presented. The user selectsthe region of interest (ROI) in the image which is thenanalyzed with a fast, robust color segmenter. Queries ina database of validated cases can be formulated in termsof shape (similarity invariant Fourier descriptors), texture(multiresolution simultaneous autoregressive model), color(L*u*v* space), and area, derived from the delineatedROI. The uncertainty of the segmentation process (obtainedthrough a numerical method) determines the accuracy ofshape description (number of Fourier harmonics). Tenfoldcross-validated classification over a database of 261color 640 \times 480 images was implemented to assess the system performance. The ground truth was obtained throughimmunophenotyping by flow cytometry. To provide a naturalman-machine interface, most input commands are bi-modal:either using the mouse or by voice. A speech synthesizerprovides feedback to the user. All the employed computationalmodules are context independent and thus the samesystem can be used in a large variety of application domains.