[论文解读] 3D Medical Image Segmentation based on multi-scale MPU-Net

Zeqiu. Yu, Shuo Han+1 more|arXiv (Cornell University)|Jul 11, 2023

Advanced Neural Network Applications被引用 8

一句话总结

论文介绍了 MPU-Net，一种用于患者体积 CT 图像的三维肿瘤分割模型，采用多尺度模块和受 Transformer 启发的注意力机制，在 LiTS 2017 上进行评估，分割指标表现出色。

ABSTRACT

The high cure rate of cancer is inextricably linked to physicians' accuracy in diagnosis and treatment, therefore a model that can accomplish high-precision tumor segmentation has become a necessity in many applications of the medical industry. It can effectively lower the rate of misdiagnosis while considerably lessening the burden on clinicians. However, fully automated target organ segmentation is problematic due to the irregular stereo structure of 3D volume organs. As a basic model for this class of real applications, U-Net excels. It can learn certain global and local features, but still lacks the capacity to grasp spatial long-range relationships and contextual information at multiple scales. This paper proposes a tumor segmentation model MPU-Net for patient volume CT images, which is inspired by Transformer with a global attention mechanism. By combining image serialization with the Position Attention Module, the model attempts to comprehend deeper contextual dependencies and accomplish precise positioning. Each layer of the decoder is also equipped with a multi-scale module and a cross-attention mechanism. The capability of feature extraction and integration at different levels has been enhanced, and the hybrid loss function developed in this study can better exploit high-resolution characteristic information. Moreover, the suggested architecture is tested and evaluated on the Liver Tumor Segmentation Challenge 2017 (LiTS 2017) dataset. Compared with the benchmark model U-Net, MPU-Net shows excellent segmentation results. The dice, accuracy, precision, specificity, IOU, and MCC metrics for the best model segmentation results are 92.17%, 99.08%, 91.91%, 99.52%, 85.91%, and 91.74%, respectively. Outstanding indicators in various aspects illustrate the exceptional performance of this framework in automatic medical image segmentation.

研究动机与目标

• 推动高精度自动肿瘤分割以降低误诊率和临床工作量。
• 提出 MPU-Net，以在 3D 医学图像中捕获全局上下文和多尺度信息。
• 在多尺度解码器中结合位置感知注意力和跨注意力，以改善定位和分割。
• 开发混合损失函数，在训练中利用高分辨率信息以提高分割质量。

提出的方法

• 采用受 Transformer 启发的全局注意力机制，结合图像序列化和 Position Attention Module（位置注意力模块）。
• 为每个解码器层配备多尺度模块和跨注意力机制，以增强跨尺度的特征融合。
• 使用旨在在训练中利用高分辨率特征信息的混合损失函数。
• 在 Liver Tumor Segmentation Challenge 2017（LiTS 2017）数据集上评估模型。
• 将 MPU-Net 与 U-Net 基线进行对比，以证明性能提升。

实验结果

研究问题

• RQ1 MPU-Net 是否能在 LiTS 2017 CT 肿瘤数据上达到比 U-Net 更高的分割精度？
• RQ2 将图像序列化与 Position Attention Module 相结合是否能改善 3D CT 分割中的上下文理解与定位？
• RQ3 多尺度解码器模块和跨注意力机制是否增强跨尺度的特征融合，从而实现更好的分割？
• RQ4 混合损失函数是否能提高对高分辨率信息在 3D 医学图像分割中的利用？

主要发现

• MPU-Net 在 LiTS 2017 上的分割性能优于 U-Net。
• 最佳模型指标包括 Dice 92.17%、Accuracy 99.08%、Precision 91.91%、Specificity 99.52%、IOU 85.91%、MCC 91.74%。
• 该架构通过多尺度和跨注意力机制提升了在不同层次的特征提取与整合。
• 混合损失函数在分割中有效利用了高分辨率特征信息。