049

Title:

Classification of Histopathology Images with Random Depthwise Convolutional Neural Networks

Discipline: CS

Presenter:

Yanan Yang

Abstract:

The classification of whole slide images plays an important role in understanding and diagnosing cancer. Pathologists typically have to work through numerous pathology images that can be in the order of hundreds or thousands which takes time and is prone to manual error. Here we investigate an automated method based on a random depthwise convolutional neural network (RDCNN). In previous work this network has shown to achieve high accuracies for image similarity. We conjecture that for pathology images similarity may play an important role in accurate classification of the images. We evaluate RDCNN against trained deep convolutional neural networks VGG16 and ResNet50 on four pathology image datasets. We find RDCNN to give the average highest accuracy across the four datasets. On two datasets RDCNN is significantly higher in accuracy and comparable in the others. This suggests that for whole side image data a network with random weights can better capture similarity and thus classification.

Author(s):

Yanan Yang, Usman Roshan, Frank Shih

Funding Acknowledgements:

The author(s) received no financial support for the research, authorship, and/or publication of this article.