Automated segmentation of the injured kidney due to abdominal trauma

• Published in: Journal of medical systems Vol. 44; no. 1; pp. 5 - 8
• Main Authors: Tulum, Gokalp, Teomete, Uygar, Cuce, Ferhat, Ergin, Tuncer, Koksal, Murathan, Dandin, Ozgur, Osman, Onur
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2020; Springer Nature B.V
• Subjects: Abdomen; Abdominal Injuries - diagnostic imaging; Acute Kidney Injury - diagnostic imaging; Algorithms; Automation; Computed tomography; Extravasation; Female; Health Informatics; Health Sciences; Hematoma; Histograms; Hough transformation; Humans; Image & Signal Processing; Imaging, Three-Dimensional - methods; Injuries; Kidneys; Male; Medicine; Medicine & Public Health; Parenchyma; Radiographic Image Interpretation, Computer-Assisted - methods; Segmentation; Sensitivity; Statistics for Life Sciences; Tomography, X-Ray Computed - methods; Trauma; Urine; Abdominal trauma; Solid organ injuries; Injured kidney; Automated segmentation
• ISSN: 0148-5598; 1573-689X
• DOI: 10.1007/s10916-019-1476-1

The objective of this study is to propose and validate a computer-aided segmentation system which performs the automated segmentation of injured kidney in the presence of contusion, peri-, intra-, sub-capsular hematoma, laceration, active extravasation and urine leak due to abdominal trauma. In the present study, total multi-phase CT scans of thirty-seven cases were used; seventeen of them for the development of the method and twenty of them for the validation of the method. The proposed algorithm contains three steps: determination of the kidney mask using Circular Hough Transform, segmentation of the renal parenchyma of the kidney applying the symmetry property to the histogram, and estimation of the kidney volume. The results of the proposed method were compared using various metrics. The kidney quantification led to 92.3 ± 4.2% Dice coefficient, 92.8 ± 7.4%/92.3 ± 5.1% precision/sensitivity, 1.4 ± 0.6 mm/2.0 ± 1.0 mm average surface distance/root-mean-squared error for intact and 87.3 ± 8.4% Dice coefficient, 84.3 ± 13.8%/92.2 ± 3.8% precision/sensitivity and 2.4 ± 2.2 mm/4.0 ± 4.2 mm average surface distance/root-mean-squared error for injured kidneys. The segmentation of the injured kidney was satisfactorily performed in all cases. This method may lead to the automated detection of renal lesions due to abdominal trauma and estimate the intraperitoneal blood amount, which is vital for trauma patients.