Abstract
Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.
Original language | English |
---|---|
Title of host publication | 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) |
Editors | Simon Warfield, Arrate Munoz-Barrutia |
Place of Publication | Piscataway NJ USA |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 256-260 |
Number of pages | 5 |
ISBN (Electronic) | 9781509011728 |
ISBN (Print) | 9781509011735 |
DOIs | |
Publication status | Published - 15 Jun 2017 |
Externally published | Yes |
Event | IEEE International Symposium on Biomedical Imaging (ISBI) 2017 - Melbourne Convention and Exhibition Centre, Melbourne, Australia Duration: 18 Apr 2017 → 21 Apr 2017 Conference number: 14th http://biomedicalimaging.org/2017/ |
Conference
Conference | IEEE International Symposium on Biomedical Imaging (ISBI) 2017 |
---|---|
Abbreviated title | ISBI 2017 |
Country | Australia |
City | Melbourne |
Period | 18/04/17 → 21/04/17 |
Other | ISBI is a joint initiative from the IEEE Signal Processing Society (SPS) and the IEEE Engineering in Medicine and Biology Society (EMBS). The 2017 meeting will include tutorials, and a scientific program composed of plenary talks, invited special sessions, challenges, as well as oral and poster presentations of peer-reviewed papers. |
Internet address |
Keywords
- Convolutional neural network
- Fusion
- Multi-layer net architectures
- Skin lesion segmentation
Cite this
}
Investigating deep side layers for skin lesion segmentation. / Bozorgtabar, Behzad; Ge, Zongyuan; Chakravorty, Rajib; Abedini, Mani; Demyanov, Sergey; Garnavi, Rahil.
2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). ed. / Simon Warfield; Arrate Munoz-Barrutia. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 256-260 7950514.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - Investigating deep side layers for skin lesion segmentation
AU - Bozorgtabar, Behzad
AU - Ge, Zongyuan
AU - Chakravorty, Rajib
AU - Abedini, Mani
AU - Demyanov, Sergey
AU - Garnavi, Rahil
PY - 2017/6/15
Y1 - 2017/6/15
N2 - Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.
AB - Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.
KW - Convolutional neural network
KW - Fusion
KW - Multi-layer net architectures
KW - Skin lesion segmentation
UR - http://www.scopus.com/inward/record.url?scp=85023181428&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2017.7950514
DO - 10.1109/ISBI.2017.7950514
M3 - Conference Paper
SN - 9781509011735
SP - 256
EP - 260
BT - 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
A2 - Warfield, Simon
A2 - Munoz-Barrutia, Arrate
PB - IEEE, Institute of Electrical and Electronics Engineers
CY - Piscataway NJ USA
ER -