M-CSAFN: Multi-Color Space Adaptive Fusion Network for Automated Port-Wine Stains Segmentation

Mu, Jinrong; Lin, Yucong; Meng, Xianqi; Fan, Jingfan; Ai, Danni; Chen, Defu; Qiu, Haixia; Yang, Jian; Gu, Ying

doi:10.1109/jbhi.2023.3247479

Cited by 4 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…R. Azad [13] and colleagues proposed TransCeption, which utilizes converters and U-shaped network architectures to enhance feature fusion by redesigning modules and introducing multi-scale feature extraction. J. Mu [14] and colleagues proposed M-CSAFN, which uses a multi-color space adaptive fusion network for PWS segmentation, focusing on the internal differences caused by color heterogeneity. D. Dai [15] and colleagues proposed Ms RED, which uses a multi-scale residual coding fusion module and a decoding fusion module to adaptively fuse multi-scale features and introduces multi-resolution and multi-channel feature fusion modules to enhance feature expression.…”

Section: Introductionmentioning

confidence: 99%

DTONet a Lightweight Model for Melanoma Segmentation

Hao,

Wang,

Chen

et al. 2024

Bioengineering

View full text Add to dashboard Cite

With the further development of neural networks, automatic segmentation techniques for melanoma are becoming increasingly mature, especially under the conditions of abundant hardware resources. This allows for the accuracy of segmentation to be improved by increasing the complexity and computational capacity of the model. However, a new problem arises when it comes to actual applications, as there may not be the high-end hardware available, especially in hospitals and among the general public, who may have limited computing resources. In response to this situation, this paper proposes a lightweight deep learning network that can achieve high segmentation accuracy with minimal resource consumption. We introduce a network called DTONet (double-tailed octave network), which was specifically designed for this purpose. Its computational parameter count is only 30,859, which is 1/256th of the mainstream UNet model. Despite its reduced complexity, DTONet demonstrates superior performance in terms of accuracy, with an IOU improvement over other similar models. To validate the generalization capability of this model, we conducted tests on the PH2 dataset, and the results still outperformed existing models. Therefore, the proposed DTONet network exhibits excellent generalization ability and is sufficiently outstanding.

show abstract

Section: Introductionmentioning

confidence: 99%