Alexander K. Seewald

Dr. Alexander K. Seewald

orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 October 2007 in Intelligent Data Analysis: An International Journal
Verified
Journal Article
Closed access
PDF file
ASAlexander K. Seewald
Alexander K. Seewald
We describe an in-depth analysis of spam-filtering performance of a simple Naive Bayes learner and two extended variants. A set of seven mailboxes comprising about 65,000 mails from seven different users, as well as a representative snapshot of 25,00

7 August 2009 in Computers & Security
Verified
Journal Article
Closed access
ASAlexander K. Seewald
Alexander K. Seewald
WGWilfried N. Gansterer
Wilfried N. Gansterer

19 July 2010 in PLOS ONE
Verified
Journal Article
Open access
PDF file
ASAlexander K. Seewald
Alexander K. Seewald
JCJames Cypser
James Cypser
AMAlexander Mendenhall
Alexander Mendenhall
TJThomas Johnson
Thomas Johnson
Isogenic populations of animals still show a surprisingly large amount of phenotypic variation between individuals. Using a GFP reporter that has been shown to predict longevity and resistance to stress in isogenic populations of the nematode Caenorhabditis elegans, we examined residual variation in expression of this GFP reporter. We found that when we separated the populations into brightest 3% and dimmest 3% we also saw variation in relative expression patterns that distinguished the bright and dim worms. Using a novel image processing method which is capable of directly analyzing worm images, we found that bright worms (after normalization to remove variation between bright and dim worms) had expression patterns that correlated with other bright worms but that dim worms fell into two distinct expression patterns. We have analysed a small set of worms with confocal microscopy to validate these findings, and found that the activity loci in these clusters are caused by extremely bright intestine cells. We also found that the vast majority of the fluorescent signal for all worms came from intestinal cells as well, which may indicate that the activity of intestinal cells is responsible for the observed patterns. Phenotypic variation in C. elegans is still not well understood but our proposed novel method to analyze complex expression patterns offers a way to enable a better understanding.

31 August 2007 in Advances in Data Analysis and Classification
Verified
Journal Article
Closed access
PDF file
ASAlexander K. Seewald
Alexander K. Seewald
FKFlorian Kleedorfer
Florian Kleedorfer

26 February 2010 in Applied Artificial Intelligence
Verified
Journal Article
Closed access
ASAlexander K. Seewald
Alexander K. Seewald
Here we present a constrained object recognition task that has been robustly solved largely with simple machine learning methods, using a small corpus of about 100 images taken under a variety of lighting conditions. The task was to analyze images from a hand-held mobile phone camera showing an endgame position for the Japanese board game Go. The presented system would already be sufficient to reconstruct the full Go game record from a video record of the game and thus is complementary to Seewald ( 2003 Seewald , A. K. 2003 . The Intelligent Go Board project. http://alex.seewald.at/IGO (accessed March 2003) . [Google Scholar] ), which focuses on solving the same task using different sensors. The presented system is robust to a variety of lighting conditions, works with cheap low-quality cameras, and is resistant to changes in board or camera position without the need for any manual calibration.

11 February 2013 in Cytometry Part A
Verified
Journal Article
Open access
PDF file
AHAndreas Heindl
Andreas Heindl
ASAlexander K. Seewald
Alexander K. Seewald
TTTheresia Thalhammer
Theresia Thalhammer
GBGiovanna Bises
Giovanna Bises
MSMartin Schepelmann
Martin Schepelmann
Isabella EllingerIsabella Ellinger
Isabella Ellinger
Automated microscopic image analysis of immunofluorescence‐stained targets on tissue sections is challenged by autofluorescent elements such as erythrocytes, which might interfere with target segmentation and quantification. Therefore, we developed an automated system (Automated REcognition of Tissue‐associated Erythrocytes;ARETE) for in silico exclusion of erythrocytes. To detect erythrocytes in transmission images, a cascade of boosted decision trees of Haar‐like features was trained on 8,640/4,000 areas (15 × 15 pixels) with/without erythrocytes from images of placental sections (4 µm). Ground truth data were generated on 28 transmission images. At least two human experts labelled the area covered by erythrocytes. For validation, output masks of human experts andARETEwere compared pixel‐wise against a mask obtained from majority voting of human experts. F1 score, specificity, and Cohen's κ coefficients were calculated. To study the influence of erythrocyte‐derived autofluorescence, we investigated the expression levels of a protein (receptor for advanced glycated end products; RAGE) in placenta and number of Ki‐67‐positive/cytokeratin 8‐positive epithelial cells in colon sections.ARETEexhibited high sensitivity (99.87%) and specificity (99.81%) on a training‐subset and processed transmission images (1,392 × 1,024 pixels) within 4 sec.ARETEand human expert's F1‐scores were 0.55 versus 0.76, specificities 0.85 versus 0.92 and Cohen's κ coefficients 0.41 versus 0.68. A ranking of Cohen's κ coefficient by the scale of Fleiss certified “good agreement” betweenARETEand the human experts. ApplyingARETE, we demonstrated 4–14% false‐positive RAGE‐expression in placenta, and 18% falsely detected proliferative epithelial cells in colon, caused by erythrocyte‐autofluorescence.ARETEis a fast system for in silico reduction of erythrocytes, which improves automated image analysis in research and diagnostic pathology. © 2013 International Society for Advancement of Cytometry.