PMID- 37012446
OWN - NLM
STAT- MEDLINE
DCOM- 20230809
LR  - 20230810
IS  - 1618-727X (Electronic)
IS  - 0897-1889 (Print)
IS  - 0897-1889 (Linking)
VI  - 36
IP  - 4
DP  - 2023 Aug
TI  - Influence of Data Augmentation Strategies on the Segmentation of Oral 
      Histological Images Using Fully Convolutional Neural Networks.
PG  - 1608-1623
LID - 10.1007/s10278-023-00814-z [doi]
AB  - Segmentation of tumor regions in H &E-stained slides is an important task for a 
      pathologist while diagnosing different types of cancer, including oral squamous 
      cell carcinoma (OSCC). Histological image segmentation is often constrained by 
      the availability of labeled training data since labeling histological images is a 
      highly skilled, complex, and time-consuming task. Thus, data augmentation 
      strategies become essential to train convolutional neural networks models to 
      overcome the overfitting problem when only a few training samples are available. 
      This paper proposes a new data augmentation strategy, named Random Composition 
      Augmentation (RCAug), to train fully convolutional networks (FCN) to segment OSCC 
      tumor regions in H &E-stained histological images. Given the input image and 
      their corresponding label, a pipeline with a random composition of geometric, 
      distortion, color transfer, and generative image transformations is executed on 
      the fly. Experimental evaluations were performed using an FCN-based method to 
      segment OSCC regions through a set of different data augmentation 
      transformations. By using RCAug, we improved the FCN-based segmentation method 
      from 0.51 to 0.81 of intersection-over-union (IOU) in a whole slide image dataset 
      and from 0.65 to 0.69 of IOU in a tissue microarray images dataset.
CI  - (c) 2023. The Author(s) under exclusive licence to Society for Imaging Informatics 
      in Medicine.
FAU - Dos Santos, Dali F D
AU  - Dos Santos DFD
AUID- ORCID: 0000-0002-0872-0120
AD  - Faculty of Computer Science, Federal University of Uberlandia, Brazil and 
      Institute of Biomedical Science, Federal University of Uberlandia, Uberlandia, 
      Brazil. dalifreire@gmail.com.
FAU - de Faria, Paulo R
AU  - de Faria PR
AD  - Faculty of Computer Science, Federal University of Uberlandia, Brazil and 
      Institute of Biomedical Science, Federal University of Uberlandia, Uberlandia, 
      Brazil.
FAU - Travencolo, Bruno A N
AU  - Travencolo BAN
AD  - Faculty of Computer Science, Federal University of Uberlandia, Brazil and 
      Institute of Biomedical Science, Federal University of Uberlandia, Uberlandia, 
      Brazil.
FAU - do Nascimento, Marcelo Z
AU  - do Nascimento MZ
AD  - Faculty of Computer Science, Federal University of Uberlandia, Brazil and 
      Institute of Biomedical Science, Federal University of Uberlandia, Uberlandia, 
      Brazil.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20230403
PL  - United States
TA  - J Digit Imaging
JT  - Journal of digital imaging
JID - 9100529
SB  - IM
MH  - Humans
MH  - Image Processing, Computer-Assisted/methods
MH  - *Carcinoma, Squamous Cell/diagnostic imaging
MH  - *Mouth Neoplasms/diagnostic imaging
MH  - Neural Networks, Computer
PMC - PMC10406800
OTO - NOTNLM
OT  - Data augmentation
OT  - Fully convolutional neural networks
OT  - H& E-histological image
OT  - Oral tumor segmentation
OT  - Tissue microarray images
OT  - Whole slide images
COIS- The authors declare no competing interests.
EDAT- 2023/04/04 06:00
MHDA- 2023/08/09 06:43
PMCR- 2024/08/01
CRDT- 2023/04/03 23:26
PHST- 2022/04/29 00:00 [received]
PHST- 2023/03/03 00:00 [accepted]
PHST- 2023/03/01 00:00 [revised]
PHST- 2024/08/01 00:00 [pmc-release]
PHST- 2023/08/09 06:43 [medline]
PHST- 2023/04/04 06:00 [pubmed]
PHST- 2023/04/03 23:26 [entrez]
AID - 10.1007/s10278-023-00814-z [pii]
AID - 814 [pii]
AID - 10.1007/s10278-023-00814-z [doi]
PST - ppublish
SO  - J Digit Imaging. 2023 Aug;36(4):1608-1623. doi: 10.1007/s10278-023-00814-z. Epub 
      2023 Apr 3.