Frequency-domain information along with LSTM and GRU methods for histopathological breast-image classification

Abdullah-Al Nahid; Mohamad Ali Mehrabi; Yinan Kong

doi:10.1109/ISSPIT.2017.8388678

Frequency-domain information along with LSTM and GRU methods for histopathological breast-image classification

Abdullah-Al Nahid
, Mohamad Ali Mehrabi
, Yinan Kong

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

9 Citations (Scopus)

Abstract

Biomedical image classification has always been a challenging and critical task which has the highest level of importance. The Deep Neural Network (DNN) has been recently introduced for normal image classification and lately introduced for Biomedical image classification with some advanced engineering. In this paper we have classified an image dataset with a DNN utilizing Long Short Term Memory (LSTM) as well as Gated Recurrent Unit (GRU) for breast-image classification. Instead of directly using raw images, we have utilized frequency-domain information for the image classification. Using our model we have obtained 93.01% Accuracy, 94.00% Recall and 94.00% Precision, which is the best available result on this dataset.

Original language	English
Title of host publication	Proceedings of the 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2017), 18 - 20 December 2017, Bilbao, Spain
Publisher	IEEE
Number of pages	6
ISBN (Print)	9781538646625
DOIs	https://doi.org/10.1109/ISSPIT.2017.8388678
Publication status	Published - 2017
Event	IEEE International Symposium on Signal Processing and Information Technology - Duration: 1 Jan 2017 → …

Conference

Conference	IEEE International Symposium on Signal Processing and Information Technology
Period	1/01/17 → …

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

breast
cancer
diagnostic imaging
short-term memory

Access to Document

10.1109/ISSPIT.2017.8388678

Cite this

@inproceedings{d0bdcaee18e64441ab2dff09aa1b6bc1,

title = "Frequency-domain information along with LSTM and GRU methods for histopathological breast-image classification",

abstract = "Biomedical image classification has always been a challenging and critical task which has the highest level of importance. The Deep Neural Network (DNN) has been recently introduced for normal image classification and lately introduced for Biomedical image classification with some advanced engineering. In this paper we have classified an image dataset with a DNN utilizing Long Short Term Memory (LSTM) as well as Gated Recurrent Unit (GRU) for breast-image classification. Instead of directly using raw images, we have utilized frequency-domain information for the image classification. Using our model we have obtained 93.01\% Accuracy, 94.00\% Recall and 94.00\% Precision, which is the best available result on this dataset.",

keywords = "breast, cancer, diagnostic imaging, short-term memory",

author = "Abdullah-Al Nahid and Mehrabi, \{Mohamad Ali\} and Yinan Kong",

year = "2017",

doi = "10.1109/ISSPIT.2017.8388678",

language = "English",

isbn = "9781538646625",

booktitle = "Proceedings of the 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2017), 18 - 20 December 2017, Bilbao, Spain",

publisher = "IEEE",

note = "IEEE International Symposium on Signal Processing and Information Technology ; Conference date: 01-01-2017",

}

Nahid, A-A, Mehrabi, MA & Kong, Y 2017, Frequency-domain information along with LSTM and GRU methods for histopathological breast-image classification. in Proceedings of the 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2017), 18 - 20 December 2017, Bilbao, Spain. IEEE, IEEE International Symposium on Signal Processing and Information Technology, 1/01/17. https://doi.org/10.1109/ISSPIT.2017.8388678

Frequency-domain information along with LSTM and GRU methods for histopathological breast-image classification. / Nahid, Abdullah-Al; Mehrabi, Mohamad Ali; Kong, Yinan.
Proceedings of the 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2017), 18 - 20 December 2017, Bilbao, Spain. IEEE, 2017.

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

TY - GEN

T1 - Frequency-domain information along with LSTM and GRU methods for histopathological breast-image classification

AU - Nahid, Abdullah-Al

AU - Mehrabi, Mohamad Ali

AU - Kong, Yinan

PY - 2017

Y1 - 2017

N2 - Biomedical image classification has always been a challenging and critical task which has the highest level of importance. The Deep Neural Network (DNN) has been recently introduced for normal image classification and lately introduced for Biomedical image classification with some advanced engineering. In this paper we have classified an image dataset with a DNN utilizing Long Short Term Memory (LSTM) as well as Gated Recurrent Unit (GRU) for breast-image classification. Instead of directly using raw images, we have utilized frequency-domain information for the image classification. Using our model we have obtained 93.01% Accuracy, 94.00% Recall and 94.00% Precision, which is the best available result on this dataset.

AB - Biomedical image classification has always been a challenging and critical task which has the highest level of importance. The Deep Neural Network (DNN) has been recently introduced for normal image classification and lately introduced for Biomedical image classification with some advanced engineering. In this paper we have classified an image dataset with a DNN utilizing Long Short Term Memory (LSTM) as well as Gated Recurrent Unit (GRU) for breast-image classification. Instead of directly using raw images, we have utilized frequency-domain information for the image classification. Using our model we have obtained 93.01% Accuracy, 94.00% Recall and 94.00% Precision, which is the best available result on this dataset.

KW - breast

KW - cancer

KW - diagnostic imaging

KW - short-term memory

UR - https://hdl.handle.net/1959.7/uws:59033

U2 - 10.1109/ISSPIT.2017.8388678

DO - 10.1109/ISSPIT.2017.8388678

M3 - Conference Paper

SN - 9781538646625

BT - Proceedings of the 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2017), 18 - 20 December 2017, Bilbao, Spain

PB - IEEE

T2 - IEEE International Symposium on Signal Processing and Information Technology

Y2 - 1 January 2017

ER -

Frequency-domain information along with LSTM and GRU methods for histopathological breast-image classification

Abstract

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this