PMID- 28771497
OWN - NLM
STAT- MEDLINE
DCOM- 20170828
LR  - 20240326
IS  - 1932-6203 (Electronic)
IS  - 1932-6203 (Linking)
VI  - 12
IP  - 8
DP  - 2017
TI  - SiNC: Saliency-injected neural codes for representation and efficient retrieval 
      of medical radiographs.
PG  - e0181707
LID - 10.1371/journal.pone.0181707 [doi]
LID - e0181707
AB  - Medical image collections contain a wealth of information which can assist 
      radiologists and medical experts in diagnosis and disease detection for making 
      well-informed decisions. However, this objective can only be realized if 
      efficient access is provided to semantically relevant cases from the ever-growing 
      medical image repositories. In this paper, we present an efficient method for 
      representing medical images by incorporating visual saliency and deep features 
      obtained from a fine-tuned convolutional neural network (CNN) pre-trained on 
      natural images. Saliency detector is employed to automatically identify regions 
      of interest like tumors, fractures, and calcified spots in images prior to 
      feature extraction. Neuronal activation features termed as neural codes from 
      different CNN layers are comprehensively studied to identify most appropriate 
      features for representing radiographs. This study revealed that neural codes from 
      the last fully connected layer of the fine-tuned CNN are found to be the most 
      suitable for representing medical images. The neural codes extracted from the 
      entire image and salient part of the image are fused to obtain the 
      saliency-injected neural codes (SiNC) descriptor which is used for indexing and 
      retrieval. Finally, locality sensitive hashing techniques are applied on the SiNC 
      descriptor to acquire short binary codes for allowing efficient retrieval in 
      large scale image collections. Comprehensive experimental evaluations on the 
      radiology images dataset reveal that the proposed framework achieves high 
      retrieval accuracy and efficiency for scalable image retrieval applications and 
      compares favorably with existing approaches.
FAU - Ahmad, Jamil
AU  - Ahmad J
AUID- ORCID: 0000-0001-8407-5971
AD  - College of Software and Convergence Technology, Department of Software, Sejong 
      University, Seoul, Republic of Korea.
FAU - Sajjad, Muhammad
AU  - Sajjad M
AD  - Digital Image Processing Lab, Department of Computer Science, Islamia College, 
      Peshawar, Pakistan.
FAU - Mehmood, Irfan
AU  - Mehmood I
AD  - Department of Computer Science and Engineering, Sejong University, Seoul, 
      Republic of Korea.
FAU - Baik, Sung Wook
AU  - Baik SW
AD  - College of Software and Convergence Technology, Department of Software, Sejong 
      University, Seoul, Republic of Korea.
LA  - eng
PT  - Journal Article
DEP - 20170803
PL  - United States
TA  - PLoS One
JT  - PloS one
JID - 101285081
SB  - IM
MH  - Databases, Factual
MH  - Humans
MH  - Image Processing, Computer-Assisted/*methods
MH  - *Neural Networks, Computer
MH  - *Radiography
PMC - PMC5542646
COIS- Competing Interests: The authors have declared that no competing interests exist.
EDAT- 2017/08/05 06:00
MHDA- 2017/08/29 06:00
PMCR- 2017/08/03
CRDT- 2017/08/04 06:00
PHST- 2016/05/23 00:00 [received]
PHST- 2017/07/06 00:00 [accepted]
PHST- 2017/08/04 06:00 [entrez]
PHST- 2017/08/05 06:00 [pubmed]
PHST- 2017/08/29 06:00 [medline]
PHST- 2017/08/03 00:00 [pmc-release]
AID - PONE-D-16-20681 [pii]
AID - 10.1371/journal.pone.0181707 [doi]
PST - epublish
SO  - PLoS One. 2017 Aug 3;12(8):e0181707. doi: 10.1371/journal.pone.0181707. 
      eCollection 2017.