Benabbou Tarik, Sahel Aïcha, Badri Abdelmajid, Mourabit Ilham El
Laboratory of Electronics, Energy, Automatic, and Information Processing, Faculty of Sciences and Techniques, Hassan II University of Casablanca, Mohammedia, Morocco.
Comput Biol Med. 2025 Sep;195:110617. doi: 10.1016/j.compbiomed.2025.110617. Epub 2025 Jun 27.
Deep learning-based semantic segmentation approaches provide an efficient and automated means for cancer diagnosis and monitoring, which is important in clinical applications. However, implementing these approaches outside the experimental environment and using them in real-world applications requires powerful and adequate hardware resources, which are not available in most hospitals, especially in low- and middle-income countries. Consequently, clinical settings will never use most of these algorithms, or at best, their adoption will be relatively limited. To address these issues, some approaches that reduce computational costs were proposed, but they performed poorly and failed to produce satisfactory results. Therefore, finding a method that overcomes these limitations without losing performance is highly challenging. To face this challenge, our study proposes a novel, optimal convolutional neural network-based approach for medical image segmentation that consists of multiple synthesis and analysis paths connected through a series of long skip connections. The design leverages multi-scale convolution, multi-scale feature extraction, downsampling strategies, and feature map fusion methods, all of which have proven effective in enhancing performance. This framework was extensively evaluated against current state-of-the-art architectures on various medical image segmentation tasks, including lung tumors, spleen, and pancreatic tumors. The results of these experiments conclusively demonstrate the efficacy of the proposed approach in outperforming existing state-of-the-art methods across multiple evaluation metrics. This superiority is further enhanced by the framework's ability to minimize the computational complexity and decrease the number of parameters required, resulting in greater segmentation accuracy, faster processing, and better implementation efficiency.
基于深度学习的语义分割方法为癌症诊断和监测提供了一种高效且自动化的手段,这在临床应用中非常重要。然而,在实验环境之外实施这些方法并将其应用于实际应用中,需要强大且充足的硬件资源,而大多数医院,尤其是中低收入国家的医院并不具备这些资源。因此,临床环境将永远不会使用这些算法中的大多数,或者充其量,它们的采用将相对有限。为了解决这些问题,人们提出了一些降低计算成本的方法,但它们表现不佳,未能产生令人满意的结果。因此,找到一种在不损失性能的情况下克服这些限制的方法极具挑战性。为了应对这一挑战,我们的研究提出了一种新颖的、基于最优卷积神经网络的医学图像分割方法,该方法由通过一系列长跳跃连接相连的多个合成和分析路径组成。该设计利用了多尺度卷积、多尺度特征提取、下采样策略和特征图融合方法,所有这些方法在提高性能方面都已被证明是有效的。该框架在各种医学图像分割任务上,包括肺肿瘤、脾脏和胰腺肿瘤,与当前最先进的架构进行了广泛的评估。这些实验结果确凿地证明了所提出的方法在多个评估指标上优于现有最先进方法的有效性。该框架能够最小化计算复杂度并减少所需参数的数量,从而进一步提高了这种优势,实现了更高的分割精度、更快的处理速度和更好的实现效率。