Abstract | ||
---|---|---|
Prostate cancer is the most common and second most deadly form of cancer in men in the United States. The classification of prostate cancers based on Gleason grading using histological images is important in risk assessment and treatment planning for patients. Here, we demonstrate a new region-based convolutional neural network (R-CNN) framework for multitask prediction using a Epithelial Network Head and a Grading Network Head. Compared to a single task model, our multi-task model can provide complementary contextual information, which contributes to better performance. Our model achieved stateof-the-art performance in epithelial cells detection and Gleason grading tasks simultaneously. Using five-fold cross-validation, our model achieved an epithelial cells detection accuracy of 99.07with an average AUC of 0.998. As for Gleason grading, our model obtained a mean intersection over union of 79.56an overall pixel accuracy of 89.40%. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TMI.2018.2875868 | IEEE transactions on medical imaging |
Keywords | Field | DocType |
Feature extraction,Image segmentation,Biomedical imaging,Glands,Prostate cancer,Solid modeling | Computer vision,Grading (education),Medical imaging,Convolutional neural network,Radiation treatment planning,Image segmentation,Artificial intelligence,Prostate cancer,Prostate,Radiology,Mathematics,Cancer | Journal |
Volume | Issue | ISSN |
38 | 4 | 1558-254X |
Citations | PageRank | References |
3 | 0.43 | 0 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenyuan Li | 1 | 6 | 4.22 |
Jiayun Li | 2 | 10 | 4.65 |
Karthik Sarma | 3 | 11 | 2.98 |
King Chung Ho | 4 | 7 | 2.21 |
Shiwen Shen | 5 | 34 | 4.42 |
Beatrice S. Knudsen | 6 | 4 | 1.13 |
Arkadiusz Gertych | 7 | 88 | 4.95 |
Corey Arnold | 8 | 41 | 12.22 |