改进U-Net结构，提升乳腺超声图像肿瘤分割精度
Modifying the U-Net's Encoder-Decoder Architecture for Segmentation of Tumors in Breast Ultrasound Images
- 融合ResNet与MultiResUNet构建新编码器解码器结构
- 在BUSI数据集上达98.4%全局准确率和90.3%AUC
- 仅888万参数，适合医疗影像轻量化部署
图像分割是图像处理中最重要的步骤之一，能根据像素特征将数字图像划分为不同区域。乳腺超声图像分割广泛用于癌症识别，有助于通过医学影像实现早期诊断。然而，由于存在斑点噪声、信噪比低和强度不均等超声伪影，准确分割医学图像仍具挑战性。本文提出一种基于U-Net的新型神经网络，通过结合残差网络（ResNet）与多分辨率U-Net（MultiResUNet），引入新型协同块（Co-Block），有效保留高低层特征。所提网络在公开的乳腺超声图像（BUSI）数据集上进行评估，该数据集包含780张图像，分为正常、良性与恶性三类。实验表明，本方法在分割精度上优于现有先进深度学习模型。仅使用888万参数的CResU-Net，在BUSI数据集上获得82.88%的骰子相似系数（DSC）、77.5%的交并比（IoU）、90.3%的曲线下面积（AUC）和98.4%的全局准确率（ACC）。
原文摘要 · Abstract (English)
Segmentation is one of the most significant steps in image processing. Segmenting an image is a technique that makes it possible to separate a digital image into various areas based on the different characteristics of pixels in the image. In particular, segmentation of breast ultrasound images is widely used for cancer identification. As a result of image segmentation, it is possible to make early diagnoses of a diseases via medical images in a very effective way. Due to various ultrasound artifacts and noises, including speckle noise, low signal-to-noise ratio, and intensity heterogeneity, the process of accurately segmenting medical images, such as ultrasound images, is still a challenging task. In this paper, we present a new method to improve the accuracy and effectiveness of breast ultrasound image segmentation. More precisely, we propose a Neural Network (NN) based on U-Net and an encoder-decoder architecture. By taking U-Net as the basis, both encoder and decoder parts are developed by combining U-Net with other Deep Neural Networks (Res-Net and MultiResUNet) and introducing a new approach and block (Co-Block), which preserve as much as possible the low-level and the high-level features. Designed network is evaluated using the Breast Ultrasound Images (BUSI) Dataset. It consists of 780 images and the images are categorized into three classes, which are normal, benign, and malignant. According to our extensive evaluations on a public breast ultrasound dataset, designed network segments the breast lesions more accurately than other state-of-the-art deep learning methods. With only 8.88M parameters, our network (CResU-Net) obtained 82.88%, 77.5%, 90.3%, and 98.4% in terms of Dice similarity coefficients (DSC), Intersection over Union (IoU), Area under curve (AUC), and global accuracy (ACC), respectively, on BUSI dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。