Abstract
Automation of HEp-2 cell pattern classification would drastically improve the accuracy and throughput of diagnostic services for many auto-immune diseases, but it has proven difficult to reach a sufficient level of precision. Correct diagnosis relies on a subtle assessment of texture type in microscopic images of indirect immunofluorescence (IIF), which so far has eluded reliable replication through automated measurements. We introduce a combination of spectral analysis and multi-scale digital filtering to extract the most discriminative variables from the cell images. We also apply multistage classification techniques to make optimal use of the limited labelled data set. Overall error rate of 1.6% is achieved in recognition of 6 different cell patterns, which drops to 0.5% if only positive samples are considered.
Original language | English |
---|---|
Title of host publication | Pattern Recognition (ICPR), 2012 21st International Conference on |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 3750-3753 |
Number of pages | 4 |
Publication status | Published - 14 Feb 2013 |
Event | 21st International Conference on Pattern Recognition - Tsukuba, Japan Duration: 11 Nov 2012 → 15 Nov 2012 |
Conference
Conference | 21st International Conference on Pattern Recognition |
---|---|
Country/Territory | Japan |
City | Tsukuba |
Period | 11/11/12 → 15/11/12 |
Keywords
- vectors
- error analysis
- shape
- diseases
- noise
- pattern recognition
- accuracy