Adapting Fisher Vectors for histopathology image classification

Yang Song; Ju Jia Zou; Hang Chang; Weidong Cai

doi:10.1109/ISBI.2017.7950592

Adapting Fisher Vectors for histopathology image classification

Yang Song
, Ju Jia Zou
, Hang Chang
, Weidong Cai

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

87 Citations (Scopus)

Abstract

Histopathology image classification can provide automated support towards cancer diagnosis. In this paper, we present a transfer learning-based approach for histopathology image classification. We first represent the image feature by Fisher Vector (FV) encoding of local features that are extracted using the Convolutional Neural Network (CNN) model pretrained on ImageNet. Next, to better transfer the pretrained model to the histopathology image dataset, we design a new adaptation layer to further transform the FV descriptors for higher discriminative power and classification accuracy. We used the publicly available BreaKHis image dataset for classifying between benign and malignant breast tumors, and obtained improved performance over the state-of-the-art.

Original language	English
Title of host publication	Proceedings of the 14th IEEE International Symposium on Biomedical Imaging (ISBI 2017): From Nano to Macro, 18-21 April 2017, Melbourne, Australia
Publisher	IEEE
Pages	600-603
Number of pages	4
ISBN (Print)	9781509011711
DOIs	https://doi.org/10.1109/ISBI.2017.7950592
Publication status	Published - 2017
Event	IEEE International Symposium on Biomedical Imaging - Duration: 18 Apr 2017 → …

Publication series

Name
ISSN (Print)	1945-8452

Conference

Conference	IEEE International Symposium on Biomedical Imaging
Period	18/04/17 → …

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

diagnostic imaging
neural networks (computer science)

Access to Document

10.1109/ISBI.2017.7950592

Cite this

@inproceedings{9b319257d7f64efe85a4378db4dfd274,

title = "Adapting Fisher Vectors for histopathology image classification",

abstract = "Histopathology image classification can provide automated support towards cancer diagnosis. In this paper, we present a transfer learning-based approach for histopathology image classification. We first represent the image feature by Fisher Vector (FV) encoding of local features that are extracted using the Convolutional Neural Network (CNN) model pretrained on ImageNet. Next, to better transfer the pretrained model to the histopathology image dataset, we design a new adaptation layer to further transform the FV descriptors for higher discriminative power and classification accuracy. We used the publicly available BreaKHis image dataset for classifying between benign and malignant breast tumors, and obtained improved performance over the state-of-the-art.",

keywords = "diagnostic imaging, neural networks (computer science)",

author = "Yang Song and Zou, \{Ju Jia\} and Hang Chang and Weidong Cai",

year = "2017",

doi = "10.1109/ISBI.2017.7950592",

language = "English",

isbn = "9781509011711",

publisher = "IEEE",

pages = "600--603",

booktitle = "Proceedings of the 14th IEEE International Symposium on Biomedical Imaging (ISBI 2017): From Nano to Macro, 18-21 April 2017, Melbourne, Australia",

note = "IEEE International Symposium on Biomedical Imaging ; Conference date: 18-04-2017",

}

Song, Y, Zou, JJ, Chang, H & Cai, W 2017, Adapting Fisher Vectors for histopathology image classification. in Proceedings of the 14th IEEE International Symposium on Biomedical Imaging (ISBI 2017): From Nano to Macro, 18-21 April 2017, Melbourne, Australia. IEEE, pp. 600-603, IEEE International Symposium on Biomedical Imaging, 18/04/17. https://doi.org/10.1109/ISBI.2017.7950592

Adapting Fisher Vectors for histopathology image classification. / Song, Yang; Zou, Ju Jia; Chang, Hang et al.
Proceedings of the 14th IEEE International Symposium on Biomedical Imaging (ISBI 2017): From Nano to Macro, 18-21 April 2017, Melbourne, Australia. IEEE, 2017. p. 600-603.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Adapting Fisher Vectors for histopathology image classification

AU - Song, Yang

AU - Zou, Ju Jia

AU - Chang, Hang

AU - Cai, Weidong

PY - 2017

Y1 - 2017

N2 - Histopathology image classification can provide automated support towards cancer diagnosis. In this paper, we present a transfer learning-based approach for histopathology image classification. We first represent the image feature by Fisher Vector (FV) encoding of local features that are extracted using the Convolutional Neural Network (CNN) model pretrained on ImageNet. Next, to better transfer the pretrained model to the histopathology image dataset, we design a new adaptation layer to further transform the FV descriptors for higher discriminative power and classification accuracy. We used the publicly available BreaKHis image dataset for classifying between benign and malignant breast tumors, and obtained improved performance over the state-of-the-art.

AB - Histopathology image classification can provide automated support towards cancer diagnosis. In this paper, we present a transfer learning-based approach for histopathology image classification. We first represent the image feature by Fisher Vector (FV) encoding of local features that are extracted using the Convolutional Neural Network (CNN) model pretrained on ImageNet. Next, to better transfer the pretrained model to the histopathology image dataset, we design a new adaptation layer to further transform the FV descriptors for higher discriminative power and classification accuracy. We used the publicly available BreaKHis image dataset for classifying between benign and malignant breast tumors, and obtained improved performance over the state-of-the-art.

KW - diagnostic imaging

KW - neural networks (computer science)

UR - http://handle.westernsydney.edu.au:8081/1959.7/uws:41131

U2 - 10.1109/ISBI.2017.7950592

DO - 10.1109/ISBI.2017.7950592

M3 - Conference Paper

SN - 9781509011711

SP - 600

EP - 603

BT - Proceedings of the 14th IEEE International Symposium on Biomedical Imaging (ISBI 2017): From Nano to Macro, 18-21 April 2017, Melbourne, Australia

PB - IEEE

T2 - IEEE International Symposium on Biomedical Imaging

Y2 - 18 April 2017

ER -

Adapting Fisher Vectors for histopathology image classification

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this