This website requires JavaScript.

Kidney and Kidney Tumour Segmentation in CT Images

Qi Ming HowHoi Leong Lee
Dec 2022
摘要
Automatic segmentation of kidney and kidney tumour in Computed Tomography(CT) images is essential, as it uses less time as compared to the current goldstandard of manual segmentation. However, many hospitals are still reliant onmanual study and segmentation of CT images by medical practitioners because ofits higher accuracy. Thus, this study focuses on the development of an approachfor automatic kidney and kidney tumour segmentation in contrast-enhanced CTimages. A method based on Convolutional Neural Network (CNN) was proposed,where a 3D U-Net segmentation model was developed and trained to delineate thekidney and kidney tumour from CT scans. Each CT image was pre-processed beforeinputting to the CNN, and the effect of down-sampled and patch-wise inputimages on the model performance was analysed. The proposed method was evaluatedon the publicly available 2021 Kidney and Kidney Tumour Segmentation Challenge(KiTS21) dataset. The method with the best performing model recorded an averagetraining Dice score of 0.6129, with the kidney and kidney tumour Dice scores of0.7923 and 0.4344, respectively. For testing, the model obtained a kidney Dicescore of 0.8034, and a kidney tumour Dice score of 0.4713, with an average Dicescore of 0.6374.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答