Chanon Chantaduly1, Hayden R Troutt2, Karla A Perez Reyes2, Jonathan E Zuckerman3, Peter D Chang1, Wei Ling Lau2. 1. Department of Radiological Sciences and Center for Artificial Intelligence in Diagnostic Medicine, University of California Irvine, Orange, California. 2. Division of Nephrology, Department of Medicine, University of California Irvine, Orange, California. 3. Department of Pathology and Laboratory Medicine, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, California.
Abstract
Background: The goal of the Artificial Intelligence in Renal Scarring (AIRS) study is to develop machine learning tools for noninvasive quantification of kidney fibrosis from imaging scans. Methods: We conducted a retrospective analysis of patients who had one or more abdominal computed tomography (CT) scans within 6 months of a kidney biopsy. The final cohort encompassed 152 CT scans from 92 patients, which included images of 300 native kidneys and 76 transplant kidneys. Two different convolutional neural networks (slice-level and voxel-level classifiers) were tested to differentiate severe versus mild/moderate kidney fibrosis (≥50% versus <50%). Interstitial fibrosis and tubular atrophy scores from kidney biopsy reports were used as ground-truth. Results: The two machine learning models demonstrated similar positive predictive value (0.886 versus 0.935) and accuracy (0.831 versus 0.879). Conclusions: In summary, machine learning algorithms are a promising noninvasive diagnostic tool to quantify kidney fibrosis from CT scans. The clinical utility of these prediction tools, in terms of avoiding renal biopsy and associated bleeding risks in patients with severe fibrosis, remains to be validated in prospective clinical trials.
Background: The goal of the Artificial Intelligence in Renal Scarring (AIRS) study is to develop machine learning tools for noninvasive quantification of kidney fibrosis from imaging scans. Methods: We conducted a retrospective analysis of patients who had one or more abdominal computed tomography (CT) scans within 6 months of a kidney biopsy. The final cohort encompassed 152 CT scans from 92 patients, which included images of 300 native kidneys and 76 transplant kidneys. Two different convolutional neural networks (slice-level and voxel-level classifiers) were tested to differentiate severe versus mild/moderate kidney fibrosis (≥50% versus <50%). Interstitial fibrosis and tubular atrophy scores from kidney biopsy reports were used as ground-truth. Results: The two machine learning models demonstrated similar positive predictive value (0.886 versus 0.935) and accuracy (0.831 versus 0.879). Conclusions: In summary, machine learning algorithms are a promising noninvasive diagnostic tool to quantify kidney fibrosis from CT scans. The clinical utility of these prediction tools, in terms of avoiding renal biopsy and associated bleeding risks in patients with severe fibrosis, remains to be validated in prospective clinical trials.
Authors: Emilio D Poggio; Robyn L McClelland; Kristina N Blank; Spencer Hansen; Shweta Bansal; Andrew S Bomback; Pietro A Canetta; Pascale Khairallah; Krzysztof Kiryluk; Stewart H Lecker; Gearoid M McMahon; Paul M Palevsky; Samir Parikh; Sylvia E Rosas; Katherine Tuttle; Miguel A Vazquez; Anitha Vijayan; Brad H Rovin Journal: Clin J Am Soc Nephrol Date: 2020-10-15 Impact factor: 8.237
Authors: Charumathi Sabanayagam; Dejiang Xu; Daniel S W Ting; Simon Nusinovici; Riswana Banu; Haslina Hamzah; Cynthia Lim; Yih-Chung Tham; Carol Y Cheung; E Shyong Tai; Ya Xing Wang; Jost B Jonas; Ching-Yu Cheng; Mong Li Lee; Wynne Hsu; Tien Y Wong Journal: Lancet Digit Health Date: 2020-05-12
Authors: P D Chang; E Kuoy; J Grinband; B D Weinberg; M Thompson; R Homo; J Chen; H Abcede; M Shafie; L Sugrue; C G Filippi; M-Y Su; W Yu; C Hess; D Chow Journal: AJNR Am J Neuroradiol Date: 2018-07-26 Impact factor: 3.825
Authors: Kanishka Sharma; Christian Rupprecht; Anna Caroli; Maria Carolina Aparicio; Andrea Remuzzi; Maximilian Baust; Nassir Navab Journal: Sci Rep Date: 2017-05-17 Impact factor: 4.379
Authors: Esteban Andrés Sánchez-Jaramillo; Luz Elena Gasca-Lozano; José María Vera-Cruz; Luis Daniel Hernández-Ortega; Adriana María Salazar-Montes Journal: Biology (Basel) Date: 2022-08-17