Garbaz Anass, Oukdach Yassine, Charfi Said, El Ansari Mohamed, Koutti Lahcen, Salihoun Mouna
Laboratory of Computer Systems and Vision, Faculty of Science, Ibn Zohr University, Agadir, 80000, Morocco.
Laboratory of Computer Systems and Vision, Faculty of Science, Ibn Zohr University, Agadir, 80000, Morocco.
Methods. 2024 Dec;232:52-64. doi: 10.1016/j.ymeth.2024.10.010. Epub 2024 Oct 29.
Medical image segmentation is crucial for accurate diagnosis and treatment in medical image analysis. Among the various methods employed, fully convolutional networks (FCNs) have emerged as a prominent approach for segmenting medical images. Notably, the U-Net architecture and its variants have gained widespread adoption in this domain. This paper introduces MLFA-UNet, an innovative architectural framework aimed at advancing medical image segmentation. MLFA-UNet adopts a U-shaped architecture and integrates two pivotal modules: multi-level feature assembly (MLFA) and multi-scale information attention (MSIA), complemented by a pixel-vanishing (PV) attention mechanism. These modules synergistically contribute to the segmentation process enhancement, fostering both robustness and segmentation precision. MLFA operates within both the network encoder and decoder, facilitating the extraction of local information crucial for accurately segmenting lesions. Furthermore, the bottleneck MSIA module serves to replace stacking modules, thereby expanding the receptive field and augmenting feature diversity, fortified by the PV attention mechanism. These integrated mechanisms work together to boost segmentation performance by effectively capturing both detailed local features and a broader range of contextual information, enhancing both accuracy and resilience in identifying lesions. To assess the versatility of the network, we conducted evaluations of MFLA-UNet across a range of medical image segmentation datasets, encompassing diverse imaging modalities such as wireless capsule endoscopy (WCE), colonoscopy, and dermoscopic images. Our results consistently demonstrate that MFLA-UNet outperforms state-of-the-art algorithms, achieving dice coefficients of 91.42%, 82.43%, 90.8%, and 88.68% for the MICCAI 2017 (Red Lesion), ISIC 2017, PH2, and CVC-ClinicalDB datasets, respectively.
医学图像分割对于医学图像分析中的准确诊断和治疗至关重要。在采用的各种方法中，全卷积网络（FCN）已成为分割医学图像的一种突出方法。值得注意的是，U-Net架构及其变体在该领域已得到广泛应用。本文介绍了MLFA-UNet，这是一种旨在推进医学图像分割的创新架构框架。MLFA-UNet采用U形架构，并集成了两个关键模块：多级特征组装（MLFA）和多尺度信息注意力（MSIA），并辅以像素消失（PV）注意力机制。这些模块协同作用，有助于增强分割过程，提高鲁棒性和分割精度。MLFA在网络编码器和解码器中均起作用，有助于提取对准确分割病变至关重要的局部信息。此外，瓶颈MSIA模块用于替代堆叠模块，从而扩大感受野并增加特征多样性，并由PV注意力机制强化。这些集成机制共同作用，通过有效捕获详细的局部特征和更广泛的上下文信息来提高分割性能，增强识别病变的准确性和弹性。为了评估该网络的通用性，我们在一系列医学图像分割数据集上对MFLA-UNet进行了评估，这些数据集涵盖了多种成像模态，如无线胶囊内窥镜检查（WCE）、结肠镜检查和皮肤镜图像。我们的结果一致表明，MFLA-UNet优于现有算法，在MICCAI 2017（红色病变）、ISIC 2017、PH2和CVC-ClinicalDB数据集上分别实现了91.42%、82.43%、90.8%和88.68%的骰子系数。
