Breast Histopathology with High-Performance Computing and Deep Learning
| Type of publication: | Article |
| Citation: | |
| Journal: | Computer and Informatics |
| Year: | 2020 |
| Month: | December |
| Note: | To be published in the Computer and Informatics Journal |
| Abstract: | The increasing availability of extremely large (in the gigapixel range) digital images of tumor tissue made histopathology a demanding application in terms of computational and storage resources. With images containing billions of pixels, the need for optimizing and adapting histopathology to large-scale data analysis is compelling. This paper presents a modular pipeline with three independent layers for the detection of tumor regions in digital specimens of breast lymph nodes with deep learning models. Our pipeline can be deployed either on local machines or high-performance computing resources with a containerized approach that also makes the software very mobile. The need for expertise in high-performance computing is removed by the self-sufficient structure of Docker containers, whereas a large possibility for customization is left in terms of deep learning models and hyperparameter optimization. We show that by deploying the software layers in different types of infrastructures we can optimize both the data preprocessing and the network training times, further increasing the scalability of the application to datasets of approximatively 43 million images. The code is open source and available on github. |
| Keywords: | |
| Authors | |
| Added by: | [] |
| Access rights: | r: e: (Edit all rights) |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
|
Topics
|
|
|
|
|
