Número de confirmación: 2990397
|
Automated Grading of Prenatal Hydronephrosis Severity from Segmented Kidney Ultrasounds using Deep Learning Mahmud, S(1); Abbas, T(2); Vallasciani, S(2); Chowdhury, MEH(1); Mushtak, A(3); Kabir, S(4); Muthiyal, S(5); Koko, A(5); Altyeb, ABA(6); Alqahtani, A(7); Khandakar, A(1); Islam, SMS(8) (1)Department of Electrical Engineering, Qatar University. Doha, Qatar (2)Division of Urology, Sidra Medicine. Doha, Qatar (3)Clinical Imaging Department, Hamad Medical Corporation. Doha, Qatar (4)Department of Electrical and Electronic Engineering, University of Dhaka. Dhaka, Bangladesh (5)Department of Radiology, Hamad Medical Corporation. Doha, Qatar (6)Department of Urology, Hamad Medical Corporation. Doha, Qatar (7)Department of Biomedical Technology, College of Applied Medical Sciences in Al-Kharj, , Prince Sattam Bin Abdulaziz University. Al-Kharj, Arabia Saudita (8)11Institute for Physical Activity and Nutrition, Deakin University. Melbourne, Australia Background and Motivations: Antenatal or prenatal hydronephrosis (AHN) is a common kidney complication in unborn children. Kidney ultrasound images are one of the most common methods of monitoring AHN, but grading of this condition is highly subjective and clinicians may select inappropriate therapies or surgical interventions as a result. New approaches are required to differentiate subjects who can be managed without surgical intervention from those who require life-saving operations. Methods: An end-to-end deep machine learning framework was developed to sequentially detect ultrasound regions of interest, segment kidneys from US images, and classify AHN severity. We propose the novel Kidney Ultrasound Segmentation Network (KUSNet) for kidney segmentation from ultrasound images, and the Prenatal Hydronephrosis Classification Network (PHCNet) for hydronephrosis severity stratification according to the Society of Fetal Urology (SFU) standards. The ground truth kidney masks were generated by two radiologists with more than five years of working experience while the SFU-based annotations for the AHN severity were done by two senior radiologists and three senior urologists with more than ten years of domain expertise. At each stage, the performance of the proposed models was assessed both quantitatively and qualitatively against state-of-the-art networks in the respective fields. Results: The proposed KUSNet for ultrasound kidney segmentation achieved 97.6% accuracy, 97.4% precision, 97.6% recall or sensitivity, 97.5% f1-score, 95.5% IoU or Jaccard score, and 92.1% Dice score, beating several state-of-the-art networks originally developed for segmenting medical images. On the other hand, the novel PHCNet reached 93.9% accuracy, 93.7% precision, 93.9% recall, 93.8% specificity, and 89.0% f1-score subject-wise when performing multiclass stratification of AHN severity based on the SFU grading system. Conclusion: Artificial intelligence-based tools can reliably classify AHN severity to reduce inter- and intra-observer bias, thereby aiding clinicians in the rapid selection of appropriate treatments and surgeries. Keywords: Prenatal or Antenatal Hydronephrosis (AHN), Renal Ultrasound (US), Deep Machine Learning |
Presentación al Congreso de la Sociedad Iberoamericana de Urología Pediátrica (SIUP)
Forma de presentación: Oral
Financiamiento / conflicto de intereses: No