Abstract
Deep learning has shown a great potential in computer aided diagnosis. However, in many applications, large dataset is not available. This makes the training of a sophisticated deep learning neural network (DNN) difficult. In this study, we demonstrated that with transfer learning, we can quickly retrain start-of-the-art DNN models with limited data provided by the prostateX challenge. The training data consists of 330 lesions, only 78 were clinical significant. Efforts were made to balance the data during training. We used ImageNet pre-trained inceptionV3 and Vgg-16 model and obtained AUC of 0.81 and 0.83 respectively on the prostateX test data, good for a 4th place finish. We noticed that models trained for different prostate zone has different sensitivity. Applying scaling factors before merging the result improves the AUC for the final result.
Original language | English |
---|---|
Title of host publication | Medical Imaging 2017 |
Subtitle of host publication | Computer-Aided Diagnosis |
Editors | Nicholas A. Petrick, Samuel G. Armato |
ISBN (Electronic) | 9781510607132 |
DOIs | |
State | Published - 2017 |
Event | Medical Imaging 2017: Computer-Aided Diagnosis - Orlando, United States Duration: Feb 13 2017 → Feb 16 2017 |
Publication series
Name | Progress in Biomedical Optics and Imaging - Proceedings of SPIE |
---|---|
Volume | 10134 |
ISSN (Print) | 1605-7422 |
Conference
Conference | Medical Imaging 2017: Computer-Aided Diagnosis |
---|---|
Country/Territory | United States |
City | Orlando |
Period | 2/13/17 → 2/16/17 |
Bibliographical note
Publisher Copyright:© 2017 SPIE.
Keywords
- Computer aided diagnosis (CADx)
- Convolution neural Network (CNN)
- Deep learning neural network (DNN)
- Multiparameter MRI (mpMRI)
- Prostate cancer
- ProstateX challenge
- Transfer learning
- VGG
ASJC Scopus subject areas
- Electronic, Optical and Magnetic Materials
- Atomic and Molecular Physics, and Optics
- Radiology Nuclear Medicine and imaging
- Biomaterials