RESUMO
Background: Pediatric perianal fistula is a common disorder. It is more difficult to detect the fistula tract and internal opening (IO) in children than in adults. This study aimed to evaluate the clinical diagnostic value of transcutaneous perianal ultrasound for children with perianal fistula. Methods: A retrospective review was conducted by analysing the preoperative transcutaneous perianal ultrasound and intraoperative exploration results of 203 consecutive patients who were <3 years old and diagnosed with perianal fistula. Analyses were conducted to evaluate the accuracy and consistency of utilizing the transcutaneous perianal ultrasound in the diagnosis of the complexity and location of the IO of perianal fistulas. Results: Compared with intraoperative exploration, the preoperative transcutaneous perianal ultrasonography has almost perfect agreement (Kappa = 0.881, P < 0.001) in the diagnosis of fistula tract complexity and IO with a sensitivity of 92% and a specificity of 97%. In addition, both intraoperative exploration and transcutaneous perianal ultrasound diagnosis showed high consistency in the identification of the IO of perianal fistulas (Quadrant I Kappa = 0.831, Quadrant II Kappa = 0.773, Quadrant III Kappa = 0.735, Quadrant IV Kappa = 0.802, all P < 0.01). The IOs were mainly distributed in Quadrants IV and II in both simple and complex fistulas. Conclusions: Transcutaneous perianal ultrasound, as a non-invasive and simple imaging technique, showed high accuracy in the diagnosis and identification of the fistula classification and IO location. It could be considered a first-line diagnostic instrument for evaluating perianal fistulas among children.
RESUMO
Cerebrospinal fluid (CSF) hypovolemia is the core of spontaneous intracranial hypotension (SIH). More than 1000 magnetic resonance myelography (MRM) images are required to evaluate each subject. An effective spinal CSF quantification method is needed. In this study, we proposed a cascade artificial intelligence (AI) model to automatically segment spinal CSF. From January 2014 to December 2019, patients with SIH and 12 healthy volunteers (HVs) were recruited. We evaluated the performance of AI models which combined object detection (YOLO v3) and semantic segmentation (U-net or U-net++). The network of performance was evaluated using intersection over union (IoU). The best AI model was used to quantify spinal CSF in patients. We obtained 25,603 slices of MRM images from 13 patients and 12 HVs. We divided the images into training, validation, and test datasets with a ratio of 4:1:5. The IoU of Cascade YOLO v3 plus U-net++ (0.9374) was the highest. Applying YOLO v3 plus U-net++ to another 13 SIH patients showed a significant decrease in the volume of spinal CSF measured (59.32 ± 10.94 mL) at disease onset compared to during their recovery stage (70.61 ± 15.31 mL). The cascade AI model provided a satisfactory performance with regard to the fully automatic segmentation of spinal CSF from MRM images. The spinal CSF volume obtained through its measurements could reflect a patient's clinical status.