RESUMEN
Background and purpose: The intraprostatic urethra is an organ at risk in prostate cancer radiotherapy, but its segmentation in computed tomography (CT) is challenging. This work sought to: i) propose an automatic pipeline for intraprostatic urethra segmentation in CT, ii) analyze the dose to the urethra, iii) compare the predictions to magnetic resonance (MR) contours. Materials and methods: First, we trained Deep Learning networks to segment the rectum, bladder, prostate, and seminal vesicles. Then, the proposed Deep Learning Urethra Segmentation model was trained with the bladder and prostate distance transforms and 44 labeled CT with visible catheters. The evaluation was performed on 11 datasets, calculating centerline distance (CLD) and percentage of centerline within 3.5 and 5 mm. We applied this method to a dataset of 32 patients treated with intensity-modulated radiation therapy (IMRT) to quantify the urethral dose. Finally, we compared predicted intraprostatic urethra contours to manual delineations in MR for 15 patients without catheter. Results: A mean CLD of 1.6 ± 0.8 mm for the whole urethra and 1.7 ± 1.4, 1.5 ± 0.9, and 1.7 ± 0.9 mm for the top, middle, and bottom thirds were obtained in CT. On average, 94% and 97% of the segmented centerlines were within a 3.5 mm and 5 mm radius, respectively. In IMRT, the urethra received a higher dose than the overall prostate. We also found a slight deviation between the predicted and manual MR delineations. Conclusion: A fully-automatic segmentation pipeline was validated to delineate the intraprostatic urethra in CT images.
RESUMEN
BACKGROUND AND OBJECTIVE: Sacral nerve stimulation (SNS) is a minimally invasive procedure where an electrode lead is implanted through the sacral foramina to stimulate the nerve modulating colonic and urinary functions. One of the most crucial steps in SNS procedures is the placement of the tined lead close to the sacral nerve. However, needle insertion is very challenging for surgeons. Several x-ray projections are required to interpret the needle position correctly. In many cases, multiple punctures are needed, causing an increase in surgical time and patient's discomfort and pain. In this work we propose and evaluate two different navigation systems to guide electrode placement in SNS surgeries designed to reduce surgical time, minimize patient discomfort and improve surgical outcomes. METHODS: We developed, for the first alternative, an open-source navigation software to guide electrode placement by real-time needle tracking with an optical tracking system (OTS). In the second method, we present a smartphone-based AR application that displays virtual guidance elements directly on the affected area, using a 3D printed reference marker placed on the patient. This guidance facilitates needle insertion with a predefined trajectory. Both techniques were evaluated to determine which one obtained better results than the current surgical procedure. To compare the proposals with the clinical method, we developed an x-ray software tool that calculates a digitally reconstructed radiograph, simulating the fluoroscopy acquisitions during the procedure. Twelve physicians (inexperienced and experienced users) performed needle insertions through several specific targets to evaluate the alternative SNS guidance methods on a realistic patient-based phantom. RESULTS: With each navigation solution, we observed that users took less average time to complete each insertion (36.83 s and 44.43 s for the OTS and AR methods, respectively) and needed fewer average punctures to reach the target (1.23 and 1.96 for the OTS and AR methods respectively) than following the standard clinical method (189.28 s and 3.65 punctures). CONCLUSIONS: To conclude, we have shown two navigation alternatives that could improve surgical outcome by significantly reducing needle insertions, surgical time and patient's pain in SNS procedures. We believe that these solutions are feasible to train surgeons and even replace current SNS clinical procedures.
