Abstract
Shock wave lithotripsy (SWL) is a noninvasive and safe treatment for small renal stones. In unsuccessful cases, retreatment procedures are needed after SWL. According to the previous studies, patient and stone descriptors are good predictors of SWL success. Some stone and kidney descriptors are measured from renal Non-Contrast Computed Tomography (NCCT) images. It is a tedious, time-consuming and error-prone process with large inter-user variability when performed manually. In this study, novel features are proposed automatically extracted from NCCT images to describe morphology and location of renal stones and kidneys to predict retreatments after SWL. The proposed features can distinguish between different kidney and stone morphologies and locations while being less sensitive to image segmentation errors. These features are added to other stone and patient features to predict retreatment within 3 months after SWL. The experimental results show that using the proposed stone features extracted from NCCT images can improve the accuracy of predicting retreatment.
TopBackground
Shock wave lithotripsy (SWL) is the treatment of choice for renal stones smaller than 2 cm in the renal pelvic and upper or middle pole calyces (Tiselius et al.,2001), whereas percutaneous nephrolithotomy (PCNL) is recommended for large or complex stones (Skolarikos, Alivizatos, & Delarosette, 2005). SWL has been introduced by Chaussy et al. (Chaussy, Brendel, & Schmiedt, 1980) as a noninvasive and safe therapy for small renal stones(Lee et al., 2015).
Goktas et al. have shown that SWL is very successful in pediatric patients for lower calyceal stones (Goktas et al., 2011). They have evaluated SWL for adults and children. For this purpose, stone free rate and the need for auxiliary procedures after the first SWL treatment have been considered. The results showed that the stone free rate after the first SWL for children was 66.6% and they have concluded that SWL is very successful for children.
In some cases, larger fragments remain after renal stone primary treatment and retreatment procedures are needed. Retreatment is a subsequent intervention for the disease condition. If SWL treats the stones successfully, there is no need for retreatment and the stone is completely fragmented. Therefore, retreatment rate and/or stone-free rate after the primary renal stone treatment show how the stone treatment is successful (G.V. et al., 2003; Pareek, Armenakas, Panagopoulos, Bruno, & Fracchia, 2005).
Retreatment rate can be estimated via Kidney, Ureter and Bladder X-ray (KUB radiography), and NCCT images. In this study, two class labels are considered as positive (if the patient has retreatment rate within three months after SWL) and negative (otherwise).
Key Terms in this Chapter
Renal Stone Descriptors: Features describing the renal stone position, shape and size.
Image Slices: 2D images captured by CT scan from a soft tissue.
Data Preprocessing: Preparing and cleaning the data records.
Kidney Descriptors: Features describing the position, shape and size of the kidneys.
Non-Contrast CT Images: One type of imaging recommended for detecting and characterizing the renal stones.
Classification: Deciding which data record belongs to each class.
Shockwave Lithotripsy: A non-invasive treatment procedure for small renal stones.