Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

BI-RADS classification of breat cancer: a new pre-processing pipeline for deep models training

Abstract: 

One of the main difficulties in the use of deep learning strategies in medical contexts is the training set size. While these methods need large annotated training sets, this data is costly to obtain in medical contexts and suffers from intra and iter-subject variability.

In the present work, two new pre-processing techniques are introduced to improve a classifier performance. First, data augmentation based on co-registration is suggested. Then, multi-scale enhancement based on Difference of Gaussians is proposed.

Results are accessed in a public mammogram database, the InBreast, in the context of an ordinal problem, the BI-RADS classification. Moreover, a pre-trained Convolutional Neural Network with the AlexNet architecture was used as a base classifier.

The multi-class classification experiments show that the proposed pipeline with the Difference of Gaussians and the data augmentation technique outperforms using the original dataset only and using the original dataset augmented by mirroring the images.

up
0 users have voted:

Paper Details

Authors:
Inês Domingues, Pedro H. Abreu, João Santos
Submitted On:
4 October 2018 - 12:24pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Inês Domingues
Paper Code:
ICIP18001
Document Year:
2018
Cite

Document Files

Poster_A0.pdf

(65)

Keywords

Subscribe

[1] Inês Domingues, Pedro H. Abreu, João Santos, "BI-RADS classification of breat cancer: a new pre-processing pipeline for deep models training", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3452. Accessed: Aug. 19, 2019.
@article{3452-18,
url = {http://sigport.org/3452},
author = {Inês Domingues; Pedro H. Abreu; João Santos },
publisher = {IEEE SigPort},
title = {BI-RADS classification of breat cancer: a new pre-processing pipeline for deep models training},
year = {2018} }
TY - EJOUR
T1 - BI-RADS classification of breat cancer: a new pre-processing pipeline for deep models training
AU - Inês Domingues; Pedro H. Abreu; João Santos
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3452
ER -
Inês Domingues, Pedro H. Abreu, João Santos. (2018). BI-RADS classification of breat cancer: a new pre-processing pipeline for deep models training. IEEE SigPort. http://sigport.org/3452
Inês Domingues, Pedro H. Abreu, João Santos, 2018. BI-RADS classification of breat cancer: a new pre-processing pipeline for deep models training. Available at: http://sigport.org/3452.
Inês Domingues, Pedro H. Abreu, João Santos. (2018). "BI-RADS classification of breat cancer: a new pre-processing pipeline for deep models training." Web.
1. Inês Domingues, Pedro H. Abreu, João Santos. BI-RADS classification of breat cancer: a new pre-processing pipeline for deep models training [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3452