School of Computer Science & Engineering, Shri Mata Vaishno Devi University, Kakryal, Katra-182320, Jammu & Kashmir, India.
Ir J Med Sci. 2023 Jun;192(3):1401-1409. doi: 10.1007/s11845-022-03113-8. Epub 2022 Aug 5.
The precise segmentation of the kidneys in computed tomography (CT) images is vital in urology for diagnosis, treatment, and surgical planning. Medical experts can get assistance through segmentation, as it provides information about kidney malformations in terms of shape and size. Manual segmentation is slow, tedious, and not reproducible. An automatic computer-aided system is a solution to this problem. This paper presents an automated kidney segmentation technique based on active contour and deep learning.
In this work, 210 CTs from the KiTS 19 repository were used. The used dataset was divided into a train set (168 CTs), test set (21 CTs), and validation set (21 CTs). The suggested technique has broadly four phases: (1) extraction of kidney regions using active contours, (2) preprocessing, (3) kidney segmentation using 3D U-Net, and (4) reconstruction of the segmented CT images.
The proposed segmentation method has received the Dice score of 97.62%, Jaccard index of 95.74%, average sensitivity of 98.28%, specificity of 99.95%, and accuracy of 99.93% over the validation dataset.
The proposed method can efficiently solve the problem of tumorous kidney segmentation in CT images by using active contour and deep learning. The active contour was used to select kidney regions and 3D-UNet was used for precisely segmenting the tumorous kidney.
在泌尿科中，计算机断层扫描（CT）图像中肾脏的精确分割对于诊断、治疗和手术规划至关重要。医学专家可以通过分割获得帮助，因为它可以提供有关肾脏形状和大小的畸形信息。手动分割既缓慢又繁琐，且不可重复。自动计算机辅助系统是解决此问题的一种方法。本文提出了一种基于主动轮廓和深度学习的自动肾脏分割技术。
本研究使用了来自 KiTS19 数据库的 210 个 CT。所使用的数据集分为训练集（168 个 CT）、测试集（21 个 CT）和验证集（21 个 CT）。该技术主要包括四个阶段：（1）使用主动轮廓提取肾脏区域；（2）预处理；（3）使用 3D-U-Net 进行肾脏分割；（4）重建分割后的 CT 图像。
在验证数据集上，所提出的分割方法的 Dice 得分为 97.62%，Jaccard 指数为 95.74%，平均灵敏度为 98.28%，特异性为 99.95%，准确性为 99.93%。
该方法通过使用主动轮廓和深度学习，可以有效地解决 CT 图像中肿瘤性肾脏的分割问题。使用主动轮廓选择肾脏区域，使用 3D-U-Net 精确分割肿瘤性肾脏。
