Classification of blood cancer images using a convolutional neural networks ensemble

Kaiqiang Ma; Lingling Sun; Yaqi Wang; Junchao Wang

doi:10.1117/12.2539605

14 August 2019 Classification of blood cancer images using a convolutional neural networks ensemble

Kaiqiang Ma, Lingling Sun, Yaqi Wang, Junchao Wang

Proceedings Volume 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019); 1117903 (2019) https://doi.org/10.1117/12.2539605
Event: Eleventh International Conference on Digital Image Processing (ICDIP 2019), 2019, Guangzhou, China

Abstract

This paper presents the method of our submission to the ISBI 2019 Challenge for the task of classification of normal versus malignant cells in B-ALL white blood cancer microscopic images. We aimed to combine convolutional neural networks with several state-of-the-art techniques. Specifically, we fine-tuned pretrained deep learning networks including ResNet and DenseNet for this task. Overfitting is one of the major problems for this challenge. We solve overfitting by using the gradient norm clipping and the cosine annealing learning rate schedule with restarts, which have a significant impact on the performance of our deep neural network. More importantly, adaptive pooling layer is used in our models. With this modification, models are able to adapt to images of any size. An ensemble of deep models achieved a 0.8570 weighted-f1 score on the preliminary test set reported by the test server.

Citation Download Citation

Kaiqiang Ma, Lingling Sun, Yaqi Wang, and Junchao Wang "Classification of blood cancer images using a convolutional neural networks ensemble", Proc. SPIE 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019), 1117903 (14 August 2019); https://doi.org/10.1117/12.2539605

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available