| 1. |
- Arvidsson, Ida, et al.
(författare)
-
Generalization of prostate cancer classification for multiple sites using deep learning
- 2018
-
Ingår i: 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. - 9781538636367 ; 2018-April, s. 191-194
-
Konferensbidrag (refereegranskat)abstract
- Deep learning has the potential to drastically increase the accuracy and efficiency of prostate cancer diagnosis, which would be of uttermost use. Today the diagnosis is determined manually from H&E stained specimens using a light microscope. In this paper several different approaches based on convolutional neural networks for prostate cancer classification are presented and compared, using three different datasets with different origins. The issue that algorithms trained on a certain site might not generalize to other sites, due to for example inevitable stain variations, is highlighted. Two different techniques to overcome this complication are compared; by training the networks using color augmentation and by using digital stain separation. Furthermore, the potential of using an autoencoder to get a more efficient downsampling is investigated, which turned out to be the method giving the best generalization. We achieve accuracies of 95% for classification of benign versus malignant tissue and 81% for Gleason grading for data from the same site as the training data. The corresponding accuracies for images from other sites are in average 88% and 52% respectively.
|
|
| 2. |
|
|
| 3. |
- del Aguila Pla, Pol, 1990-, et al.
(författare)
-
Cell detection on image-based immunoassays
- 2018
-
Ingår i: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). - : IEEE. - 9781538636367 - 9781538636374 - 9781538636350 ; , s. 431-435
-
Konferensbidrag (refereegranskat)abstract
- Cell detection and counting in the image-based ELISPOT and Fluorospot immunoassays is considered a bottleneck.The task has remained hard to automatize, and biomedical researchers often have to rely on results that are not accurate.Previously proposed solutions are heuristic, and data-based solutions are subject to a lack of objective ground truth data. In this paper, we analyze a partial differential equations model for ELISPOT, Fluorospot, and assays of similar design. This leads us to a mathematical observation model forthe images generated by these assays. We use this model to motivate a methodology for cell detection. Finally, we provide a real-data example that suggests that this cell detection methodology and a human expert perform comparably.
|
|
| 4. |
|
|
