Department of Electrical Engineering, Tel-Aviv University, Ramat-Aviv, Israel.
Diagnostic Imaging Institute, Sheba Medical Center, Affiliated with Sackler School of Medicine, Tel Aviv University, Tel-Aviv, Israel.
Int J Comput Assist Radiol Surg. 2018 Jul;13(7):957-966. doi: 10.1007/s11548-018-1726-6. Epub 2018 Mar 15.
Simple renal cysts are a common benign finding in abdominal CT scans. However, since they may evolve in time, simple cysts need to be reported. With an ever-growing number of slices per CT scan, cysts are easily overlooked by the overloaded radiologist. In this paper, we address the detection of simple renal cysts as an incidental finding in a real clinical setting.
We propose a fully automatic framework for renal cyst detection, supported by a robust segmentation of the kidneys performed by a fully convolutional neural network. A combined 3D distance map of the kidneys and surrounding fluids provides initial candidates for cysts. Eventually, a second convolutional neural network classifies the candidates as cysts or non-cyst objects.
Performance was evaluated on 52 abdominal CT scans selected at random in a real radiological workflow and containing over 70 cysts annotated by an experienced radiologist. Setting the minimal cyst diameter to 10 mm, the algorithm detected 59/70 cysts (true-positive rate = 84.3%) while producing an average of 1.6 false-positive per case.
The obtained results suggest the proposed framework is a promising approach for the automatic detection of renal cysts as incidental findings of abdominal CT scans.
单纯性肾囊肿是腹部 CT 扫描中常见的良性发现。然而，由于它们可能随时间演变，因此需要报告单纯性囊肿。随着 CT 扫描每片的切片数量不断增加，超负荷工作的放射科医生很容易忽略囊肿。在本文中，我们针对在真实临床环境中作为偶然发现的单纯性肾囊肿检测问题提出了一种完全自动化的框架。
我们提出了一种完全自动的肾囊肿检测框架，该框架得到了由全卷积神经网络执行的稳健肾脏分割的支持。肾脏和周围液体的联合 3D 距离图为囊肿提供了初始候选对象。最终，第二个卷积神经网络将候选对象分类为囊肿或非囊肿对象。
在真实放射工作流程中随机选择的 52 例腹部 CT 扫描上进行了性能评估，这些扫描包含了一位有经验的放射科医生标注的超过 70 个囊肿。将最小囊肿直径设置为 10mm 时，该算法检测到了 70 个囊肿中的 59 个（真阳性率为 84.3%），平均每个病例产生 1.6 个假阳性。
所得结果表明，所提出的框架是一种有前途的方法，可用于自动检测腹部 CT 扫描中作为偶然发现的肾囊肿。
