Name
Abstract | ||
|---|---|---|
Real-time prostate gland localization in trans-rectal ultrasound images is required for automated ultrasound guided prostate biopsy procedures. We propose a new deep learning based approach aimed at localizing several prostate landmarks efficiently and robustly. Our multitask learning approach primarily makes the overall algorithm more contextually aware. In this approach, we not only consider the explicit learning of landmark locations, but also build-in a mechanism to learn the contour of the prostate. This multitask learning is further coupled with an adversarial arm to promote the generation of feasible structures. We have trained this network using similar to 4000 labeled transrectal ultrasound images and tested on an independent set of images with ground truth landmark locations. We have achieved an overall Dice score of 92.6% for the adversarially trained multitask approach, which is significantly better than the Dice score of 88.3% obtained by only learning of landmark locations. The overall mean distance error using the adversarial multitask approach has also improved by 20% while reducing the standard deviation of the error compared to learning landmark locations only. In terms of computational complexity both approaches can process the images in real-time using a standard computer with a CUDA enabled GPU. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1007/978-3-030-00937-3_18 | Lecture Notes in Computer Science |
DocType | Volume | ISSN |
Conference | 11073 | 0302-9743 |
Citations | PageRank | References |
2 | 0.36 | 3 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ahmet Tuysuzoglu | 1 | 21 | 5.24 |
| Jeremy Tan | 2 | 3 | 2.73 |
| Kareem Eissa | 3 | 2 | 0.36 |
| atilla peter kiraly | 4 | 47 | 9.16 |
| Mamadou Diallo | 5 | 36 | 3.58 |
| Ali Kamen | 6 | 208 | 25.52 |