TY - GEN
T1 - Lightweight Encoder-Decoder Architecture for Foot Ulcer Segmentation
AU - Ali, Shahzad
AU - Mahmood, Arif
AU - Jung, Soon Ki
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - Continuous monitoring of foot ulcer healing is needed to ensure the efficacy of a given treatment and to avoid any possibility of deterioration. Foot ulcer segmentation is an essential step in wound diagnosis. We developed a model that is similar in spirit to the well-established encoder-decoder and residual convolution neural networks. Our model includes a residual connection along with a channel and spatial attention integrated within each convolution block. A simple patch-based approach for model training, test time augmentations, and majority voting on the obtained predictions resulted in superior performance. Our model did not leverage any readily available backbone architecture, pre-training on a similar external dataset, or any of the transfer learning techniques. The total number of network parameters being around 5 million made it a significantly lightweight model as compared with the available state-of-the-art models used for the foot ulcer segmentation task. Our experiments presented results at the patch-level and image-level. Applied on publicly available Foot Ulcer Segmentation (FUSeg) Challenge dataset from MICCAI 2021, our model achieved state-of-the-art image-level performance of 88.22% in terms of Dice similarity score and ranked second in the official challenge leaderboard. We also showed an extremely simple solution that could be compared against the more advanced architectures.
AB - Continuous monitoring of foot ulcer healing is needed to ensure the efficacy of a given treatment and to avoid any possibility of deterioration. Foot ulcer segmentation is an essential step in wound diagnosis. We developed a model that is similar in spirit to the well-established encoder-decoder and residual convolution neural networks. Our model includes a residual connection along with a channel and spatial attention integrated within each convolution block. A simple patch-based approach for model training, test time augmentations, and majority voting on the obtained predictions resulted in superior performance. Our model did not leverage any readily available backbone architecture, pre-training on a similar external dataset, or any of the transfer learning techniques. The total number of network parameters being around 5 million made it a significantly lightweight model as compared with the available state-of-the-art models used for the foot ulcer segmentation task. Our experiments presented results at the patch-level and image-level. Applied on publicly available Foot Ulcer Segmentation (FUSeg) Challenge dataset from MICCAI 2021, our model achieved state-of-the-art image-level performance of 88.22% in terms of Dice similarity score and ranked second in the official challenge leaderboard. We also showed an extremely simple solution that could be compared against the more advanced architectures.
KW - Attention mechanism
KW - Encoder-decoder architecture
KW - Foot ulcer segmentation
KW - Medical image segmentation
UR - http://www.scopus.com/inward/record.url?scp=85131130848&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-06381-7_17
DO - 10.1007/978-3-031-06381-7_17
M3 - Conference contribution
AN - SCOPUS:85131130848
SN - 9783031063800
T3 - Communications in Computer and Information Science
SP - 242
EP - 253
BT - Frontiers of Computer Vision - 28th International Workshop, IW-FCV 2022, Revised Selected Papers
A2 - Sumi, Kazuhiko
A2 - Na, In Seop
A2 - Kaneko, Naoshi
PB - Springer Science and Business Media Deutschland GmbH
T2 - 28th International Workshop on Frontiers of Computer Vision, IW-FCV 2022
Y2 - 21 February 2022 through 22 February 2022
ER -