Share Email Print
cover

Proceedings Paper • new

Can ImageNet feature maps be applied to small histopathological datasets for the classification of breast cancer metastatic tissue in whole slide images?
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The scarcity of large histopathological datasets can be problematic for Deep Learning in medical imaging and digital pathology. However, transfer Learning has been shown to be promising for the effective training of classifiers on smaller datasets. ImageNet is a popular dataset that is commonly used for transfer learning in various domains. The features extracted from the ImageNet dataset are generalizable and can be applied to alternative tasks and datasets. Deep Learning typically requires a vast amount of data for training, however, in our study we interrogated two datasets with patches extracted from only 30 whole slide images (WSIs) and 60 WSIs respectively. As a consequence, we decided to extract features and feed them into separate classifier models such as a fully connected softmax layer, Support Vector Machines (SVM) and Logistic Regression. This study demonstrated that for the small dataset, the best pretrained feature extractor was DenseNet201, whereas the best model for training was a fully connected softmax layer with a reported accuracy of 88.20% and an average f1-score of 0.881. For the larger dataset size, the best feature extractor was InceptionResNetV2 where the highest accuracy and f1-score of 90.60% and 0.908 was produced when classified using a fully connected softmax layer. All models, apart from ResNet50 demonstrated an improvement in performance when pretraining using ImageNet for bottleneck feature extraction.

Paper Details

Date Published: 18 March 2019
PDF: 10 pages
Proc. SPIE 10956, Medical Imaging 2019: Digital Pathology, 109560V (18 March 2019); doi: 10.1117/12.2512853
Show Author Affiliations
T. Rai, Ctr. for Vision, Speech and Signal Processing, Univ. of Surrey (United Kingdom)
A. Morisi, Univ. of Surrey (United Kingdom)
B. Bacci, Univ. of Surrey (United Kingdom)
N. J. Bacon , Fitzpatrick Referrals Oncology and Soft Tissue (United Kingdom)
S. A. Thomas, National Physical Lab. (United Kingdom)
R. M. La Ragione, Univ. of Surrey (United Kingdom)
M. Bober, Ctr. for Vision, Speech and Signal Processing, Univ. of Surrey (United Kingdom)
K. Wells, Ctr. for Vision, Speech and Signal Processing, Univ. of Surrey (United Kingdom)


Published in SPIE Proceedings Vol. 10956:
Medical Imaging 2019: Digital Pathology
John E. Tomaszewski; Aaron D. Ward, Editor(s)

© SPIE. Terms of Use
Back to Top