Chen Chih-I, Lu Nan-Han, Huang Yung-Hui, Liu Kuo-Ying, Hsu Shih-Yen, Matsushima Akari, Wang Yi-Ming, Chen Tai-Been
Division of Colon and Rectal Surgery, Department of Surgery, E-DA Hospital, Kaohsiung City, Taiwan.
Division of General Medicine Surgery, Department of Surgery, E-DA Hospital, Kaohsiung City, Taiwan.
J Xray Sci Technol. 2022;30(5):953-966. doi: 10.3233/XST-221194.
Dividing liver organs or lesions depicting on computed tomography (CT) images could be applied to help tumor staging and treatment. However, most existing image segmentation technologies use manual or semi-automatic analysis, making the analysis process costly and time-consuming.
This research aims to develop and apply a deep learning network architecture to segment liver tumors automatically after fine tuning parameters.
The medical imaging is obtained from the International Symposium on Biomedical Imaging (ISBI), which includes 3D abdominal CT scans of 131 patients diagnosed with liver tumors. From these CT scans, there are 7,190 2D CT images along with the labeled binary images. The labeled binary images are regarded as gold standard for evaluation of the segmented results by FCN (Fully Convolutional Network). The backbones of FCN are extracted from Xception, InceptionresNetv2, MobileNetv2, ResNet18, ResNet50 in this study. Meanwhile, the parameters including optimizers (SGDM and ADAM), size of epoch, and size of batch are investigated. CT images are randomly divided into training and testing sets using a ratio of 9:1. Several evaluation indices including Global Accuracy, Mean Accuracy, Mean IoU (Intersection over Union), Weighted IoU and Mean BF Score are applied to evaluate tumor segmentation results in the testing images.
The Global Accuracy, Mean Accuracy, Mean IoU, Weighted IoU, and Mean BF Scores are 0.999, 0.969, 0.954, 0.998, 0.962 using ResNet50 in FCN with optimizer SGDM, batch size 12, and epoch 9. It is important to fine tuning the parameters in FCN model. Top 20 FNC models enable to achieve higher tumor segmentation accuracy with Mean IoU over 0.900. The occurred frequency of InceptionresNetv2, MobileNetv2, ResNet18, ResNet50, and Xception are 9, 6, 3, 5, and 2 times. Therefore, the InceptionresNetv2 has higher performance than others.
This study develop and test an automated liver tumor segmentation model based on FCN. Study results demonstrate that many deep learning models including InceptionresNetv2, MobileNetv2, ResNet18, ResNet50, and Xception have high potential to segment liver tumors from CT images with accuracy exceeding 90%. However, it is still difficult to accurately segment tiny and small size tumors by FCN models.
对计算机断层扫描（CT）图像上显示的肝脏器官或病变进行分割，可用于辅助肿瘤分期和治疗。然而，现有的大多数图像分割技术采用手动或半自动分析，使得分析过程成本高且耗时。
本研究旨在开发并应用一种深度学习网络架构，在微调参数后自动分割肝脏肿瘤。
医学影像数据来自生物医学成像国际研讨会（ISBI），其中包括131例被诊断为肝脏肿瘤患者的3D腹部CT扫描图像。从这些CT扫描图像中，获取了7190张二维CT图像以及带标注的二值图像。带标注的二值图像被视为通过全卷积网络（FCN）评估分割结果的金标准。本研究中FCN的主干网络分别从Xception、InceptionresNetv2、MobileNetv2、ResNet18、ResNet50中提取。同时，对优化器（SGDM和ADAM）、轮次大小和批次大小等参数进行了研究。CT图像按9:1的比例随机分为训练集和测试集。应用包括全局准确率、平均准确率、平均交并比（IoU）、加权IoU和平均BF分数等多个评估指标，对测试图像中的肿瘤分割结果进行评估。
在FCN中使用ResNet50，优化器为SGDM，批次大小为12，轮次为9时，全局准确率、平均准确率、平均IoU、加权IoU和平均BF分数分别为0.999、0.969、0.954、0.998、0.962。在FCN模型中微调参数很重要。排名前20的FCN模型能够实现更高的肿瘤分割准确率，平均IoU超过0.900。InceptionresNetv2、MobileNetv2、ResNet18、ResNet50和Xception出现的次数分别为9次、6次、3次、5次和2次。因此，InceptionresNetv2具有比其他模型更高的性能。
本研究开发并测试了一种基于FCN的肝脏肿瘤自动分割模型。研究结果表明，包括InceptionresNetv2、MobileNetv2、ResNet18、ResNet50和Xception在内的许多深度学习模型，在从CT图像中分割肝脏肿瘤方面具有很高的潜力，准确率超过90%。然而，使用FCN模型仍难以准确分割微小尺寸的肿瘤。
