Khouy Mohammed, Jabrane Younes, Ameur Mustapha, Hajjam El Hassani Amir
MSC Laboratory, Cadi Ayyad University, Marrakech 40000, Morocco.
Nanomedicine Imagery & Therapeutics Laboratory, EA4662-Bourgogne-Franche-Comté University, University of Technologie of Belfort Montbéliard, CEDEX, 90010 Belfort, France.
J Pers Med. 2023 Aug 25;13(9):1298. doi: 10.3390/jpm13091298.
Image segmentation is a crucial aspect of clinical decision making in medicine, and as such, it has greatly enhanced the sustainability of medical care. Consequently, biomedical image segmentation has become a prominent research area in the field of computer vision. With the advent of deep learning, many manual design-based methods have been proposed and have shown promising results in achieving state-of-the-art performance in biomedical image segmentation. However, these methods often require significant expert knowledge and have an enormous number of parameters, necessitating substantial computational resources. Thus, this paper proposes a new approach called GA-UNet, which employs genetic algorithms to automatically design a U-shape convolution neural network with good performance while minimizing the complexity of its architecture-based parameters, thereby addressing the above challenges. The proposed GA-UNet is evaluated on three datasets: lung image segmentation, cell nuclei segmentation in microscope images (DSB 2018), and liver image segmentation. Interestingly, our experimental results demonstrate that the proposed method achieves competitive performance with a smaller architecture and fewer parameters than the original U-Net model. It achieves an accuracy of 98.78% for lung image segmentation, 95.96% for cell nuclei segmentation in microscope images (DSB 2018), and 98.58% for liver image segmentation by using merely 0.24%, 0.48%, and 0.67% of the number of parameters in the original U-Net architecture for the lung image segmentation dataset, the DSB 2018 dataset, and the liver image segmentation dataset, respectively. This reduction in complexity makes our proposed approach, GA-UNet, a more viable option for deployment in resource-limited environments or real-world implementations that demand more efficient and faster inference times.
图像分割是医学临床决策的一个关键方面，因此，它极大地提高了医疗保健的可持续性。因此，生物医学图像分割已成为计算机视觉领域一个突出的研究领域。随着深度学习的出现，许多基于手工设计的方法被提出，并在生物医学图像分割中取得了领先性能，显示出了有前景的结果。然而，这些方法通常需要大量的专家知识，并且有大量的参数，需要大量的计算资源。因此，本文提出了一种名为GA-UNet的新方法，该方法采用遗传算法自动设计一个性能良好的U形卷积神经网络，同时最小化其基于架构的参数的复杂性，从而应对上述挑战。所提出的GA-UNet在三个数据集上进行了评估：肺部图像分割、显微镜图像中的细胞核分割（DSB 2018）和肝脏图像分割。有趣的是，我们的实验结果表明，与原始U-Net模型相比，该方法以更小的架构和更少的参数实现了有竞争力的性能。对于肺部图像分割，它的准确率达到了98.78%；对于显微镜图像中的细胞核分割（DSB 2018），准确率为95.96%；对于肝脏图像分割，准确率为98.58%，而在肺部图像分割数据集、DSB 2018数据集和肝脏图像分割数据集上，分别仅使用了原始U-Net架构参数数量的0.24%、0.48%和0.67%。这种复杂性的降低使得我们提出的方法GA-UNet成为在资源有限的环境中部署或在需要更高效、更快推理时间的实际应用中更可行的选择。
