Convolutional Neural Networks and Hash Learning for Feature Extraction and of Fast Retrieval of Pulmonary Nodules
Computer Science and Information Systems, Tome 15 (2018) no. 3
Cet article a éte moissonné depuis la source Computer Science and Information Systems website
With a widespread use of digital imaging data in hospitals, the size of medical image repositories is increasing rapidly. This causes difficulty in managing and querying these large databases leading to the need of content based medical image retrieval (CBMIR) systems. A major challenge in CBMIR systems is the “semantic gap” that exists between the low level visual information captured by imaging devices and high level semantic information perceived by the human. Using deep convolution neural network (CNN) to construct the CBMIR system can fully characterize the high level semantic features information for medical image retrieval. The existing network mostly used for the natural images can’t produce a good result directly applied to medical image. This paper used UNet method to preprocessing under the guidance of medical knowledge. Then, multi-scale receiving field convolution module is used to extract features of the segmented images with different sizes. Finally, encoded the features and used a coarse to fine search strategy with an average search accuracy of 0.73.
Keywords:
Content Based Medical Image Retrieval (CBMIR), Convolutional Neural Networks (CNN), Similarity Measure, Deep Learning
@article{CSIS_2018_15_3_a5,
author = {Pinle Qin and Jun Chen and Kai Zhang and Rui Chai},
title = {Convolutional {Neural} {Networks} and {Hash} {Learning} for {Feature} {Extraction} and of {Fast} {Retrieval} of {Pulmonary} {Nodules}},
journal = {Computer Science and Information Systems},
year = {2018},
volume = {15},
number = {3},
url = {http://geodesic.mathdoc.fr/item/CSIS_2018_15_3_a5/}
}
TY - JOUR AU - Pinle Qin AU - Jun Chen AU - Kai Zhang AU - Rui Chai TI - Convolutional Neural Networks and Hash Learning for Feature Extraction and of Fast Retrieval of Pulmonary Nodules JO - Computer Science and Information Systems PY - 2018 VL - 15 IS - 3 UR - http://geodesic.mathdoc.fr/item/CSIS_2018_15_3_a5/ ID - CSIS_2018_15_3_a5 ER -
%0 Journal Article %A Pinle Qin %A Jun Chen %A Kai Zhang %A Rui Chai %T Convolutional Neural Networks and Hash Learning for Feature Extraction and of Fast Retrieval of Pulmonary Nodules %J Computer Science and Information Systems %D 2018 %V 15 %N 3 %U http://geodesic.mathdoc.fr/item/CSIS_2018_15_3_a5/ %F CSIS_2018_15_3_a5
Pinle Qin; Jun Chen; Kai Zhang; Rui Chai. Convolutional Neural Networks and Hash Learning for Feature Extraction and of Fast Retrieval of Pulmonary Nodules. Computer Science and Information Systems, Tome 15 (2018) no. 3. http://geodesic.mathdoc.fr/item/CSIS_2018_15_3_a5/