en-usIn this collection, JASN Editors are pleased to present a series of innovative studies that utilize artificial intelligence and machine learning approaches to study questions of importance for nephrology and renal research. The range of problems being tackled with these techniques is quite broad, from quantitative microscopic image analysis, to diagnostic characterization, to reading radiological images, to improving clinical prediction algorithms. <p></p><p> </p><p></p> <b> Related Information: </b><p></p><p></p> <li><a href="https://www.kidneynews.org/view/journals/kidney-news/13/2/article-p1_1.xml?rskey=mKon1m&amp;result=1?WT.mc_id=CC">Machine Learning Technique Identifies and Classifies CKD Subtypes</a> (ASN <i>Kidney News</i>)</li>Thu, 25 Apr 2024 08:20:46 GMThttp://cct.highwire.org/feeds/asn/machine-learning.rss10.1681/ASN.2021030404Tue, 07 Dec 2021 07:24:09 GMT-08:00Automated Segmentation of Kidney Cortex and Medulla in CT Images: A Multisite Evaluation StudyKorfiatis, PanagiotisDenic, AleksandarEdwards, Marie E.Gregory, Adriana V.Wright, Darryl E.Mullan, AidanAugustine, JoshuaRule, Andrew D.Kline, Timothy L.2021-12-07T07:24:09-08:00doi:10.1681/ASN.2021030404hwp:resource-id:jnephrol;33/2/420American Society of NephrologyCopyright © 2022 by the American Society of NephrologyJournal of the American Society of Nephrologykidney cortex, kidney medulla, kidney volume, deep learning, segmentation, computed tomography, machine learning collectionClinical ResearchClinical Researchresearch-article20222022-02-01February 202210.1681/ASN.20210304041046-66731533-34502021-12-07T07:24:09-08:002022-02Journal of the American Society of NephrologyClinical Research33242043010.1681/ASN.2021040538Tue, 11 Jan 2022 09:52:05 GMT-08:00Using Machine Learning to Identify Metabolomic Signatures of Pediatric Chronic Kidney Disease EtiologyLee, Arthur M.Hu, JianXu, YunwenAbraham, Alison G.Xiao, RuiCoresh, JosefRebholz, CaseyChen, JingshaRhee, Eugene P.Feldman, Harold I.Ramachandran, Vasan S.Kimmel, Paul L.Warady, Bradley A.Furth, Susan L.Denburg, Michelle R.,2022-01-11T09:52:05-08:00doi:10.1681/ASN.2021040538hwp:resource-id:jnephrol;33/2/375American Society of NephrologyCopyright © 2022 by the American Society of NephrologyJournal of the American Society of Nephrologymetabolomics, pediatric nephrology, chronic kidney disease, machine learning, machine learning collectionClinical ResearchClinical Researchresearch-article20222022-02-01February 202210.1681/ASN.20210405381046-66731533-34502022-01-11T09:52:05-08:002022-02Journal of the American Society of NephrologyClinical Research33237538610.1681/ASN.2020050652Tue, 23 Feb 2021 10:57:49 GMT-08:00Automated Computational Detection of Interstitial Fibrosis, Tubular Atrophy, and GlomerulosclerosisGinley, BrandonJen, Kuang-YuHan, Seung SeokRodrigues, LuísJain, SanjayFogo, Agnes B.Zuckerman, JonathanWalavalkar, VighneshMiecznikowski, Jeffrey C.Wen, YumengYen, FeliciaYun, DonghwanMoon, Kyung ChulRosenberg, AviParikh, ChiragSarder, Pinaki2021-02-23T10:57:49-08:00doi:10.1681/ASN.2020050652hwp:resource-id:jnephrol;32/4/837American Society of NephrologyCopyright © 2021 by the American Society of NephrologyJournal of the American Society of Nephrologyinterstitial fibrosis, tubular atrophy, glomerulosclerosis, prognostication, convolutional neural network, whole slide segmentation, diabetes, transplant, eGFR, machine learningBasic ResearchBasic Researchresearch-article20212021-04-01April 202110.1681/ASN.20200506521046-66731533-34502021-02-23T10:57:49-08:002021-04Journal of the American Society of NephrologyBasic Research324483776785076810.1681/ASN.2020050597Thu, 05 Nov 2020 08:49:17 GMT-08:00Deep Learning–Based Segmentation and Quantification in Experimental Kidney HistopathologyBouteldja, NassimKlinkhammer, Barbara M.Bülow, Roman D.Droste, PatrickOtten, Simon W.Freifrau von Stillfried, SaskiaMoellmann, JuliaSheehan, Susan M.Korstanje, RonMenzel, SylviaBankhead, PeterMietsch, MatthiasDrummer, CharisLehrke, MichaelKramann, RafaelFloege, JürgenBoor, PeterMerhof, Dorit2020-11-05T08:49:17-08:00doi:10.1681/ASN.2020050597hwp:resource-id:jnephrol;32/1/52American Society of NephrologyCopyright © 2021 by the American Society of NephrologyJournal of the American Society of Nephrologydigital pathology, segmentation, histopathology, animal model, machine learning collectionBasic ResearchBasic Researchresearch-article20212021-01-01January 202110.1681/ASN.20200505971046-66731533-34502020-11-05T08:49:17-08:002021-01Journal of the American Society of NephrologyBasic Research321526810.1681/ASN.2018121259Thu, 05 Sep 2019 06:03:14 GMT-07:00Computational Segmentation and Classification of Diabetic GlomerulosclerosisGinley, BrandonLutnick, BrendonJen, Kuang-YuFogo, Agnes B.Jain, SanjayRosenberg, AviWalavalkar, VighneshWilding, GregoryTomaszewski, John E.Yacoub, RabiRossi, Giovanni MariaSarder, Pinaki2019-09-05T06:03:14-07:00doi:10.1681/ASN.2018121259hwp:resource-id:jnephrol;30/10/1953American Society of NephrologyCopyright © 2019 by the American Society of NephrologyJournal of the American Society of NephrologyComputational renal pathology, diabetic nephropathy, glomerulus, Tervaert's classification, Digital pathology, Image analysis, machine learningClinical ResearchClinical Researchresearch-article20192019-10-01October 201910.1681/ASN.20181212591046-66731533-34502019-09-05T06:03:14-07:002019-10Journal of the American Society of NephrologyClinical Research3010101019531780196819671781197910.1681/ASN.2018090902Wed, 03 Jul 2019 08:02:01 GMT-07:00Automatic Measurement of Kidney and Liver Volumes from MR Images of Patients Affected by Autosomal Dominant Polycystic Kidney Diseasevan Gastel, Maatje D.A.Edwards, Marie E.Torres, Vicente E.Erickson, Bradley J.Gansevoort, Ron T.Kline, Timothy L.2019-07-03T08:02:01-07:00doi:10.1681/ASN.2018090902hwp:resource-id:jnephrol;30/8/1514American Society of NephrologyCopyright © 2019 by the American Society of NephrologyJournal of the American Society of Nephrologydeep learning, liver volume, magnetic resonance imaging, polycystic kidney disease, segmentation, total kidney volume, machine learning collectionClinical ResearchClinical Researchresearch-article20192019-08-01August 201910.1681/ASN.20180909021046-66731533-34502019-07-03T08:02:01-07:002019-08Journal of the American Society of NephrologyClinical Research3081514152210.1681/ASN.2018060629Tue, 02 Oct 2018 07:26:26 GMT-07:00Translational Methods in Nephrology: Individual Treatment Effect ModelingWilson, F. PerryParikh, Chirag R.2018-10-02T07:26:26-07:00doi:10.1681/ASN.2018060629hwp:resource-id:jnephrol;29/11/2615American Society of NephrologyCopyright © 2018 by the American Society of NephrologyJournal of the American Society of Nephrologyoutcomes, uplift, personalized medicine, marketing, randomized controlled trials, machine-learning, machine learning collectionUp Front MattersPerspectivesUp Front MattersPerspectivesresearch-article20182018-11-01November 201810.1681/ASN.20180606291046-66731533-34502018-10-02T07:26:26-07:002018-11Journal of the American Society of NephrologyUp Front Matters29112615261810.1681/ASN.2018050566Tue, 19 Jun 2018 07:48:15 GMT-07:00AI: What Have You Done for Us Lately?Torres, RichardOlson, Eben2018-06-19T07:48:15-07:00doi:10.1681/ASN.2018050566hwp:resource-id:jnephrol;29/8/2031American Society of NephrologyCopyright © 2018 by the American Society of NephrologyJournal of the American Society of Nephrologyglomerulus, renal morphology, pathology, machine learning collectionUp Front MattersEditorialsUp Front MattersEditorialseditorial20182018-08-01August 201810.1681/ASN.20180505661046-66731533-34502018-06-19T07:48:15-07:002018-08Journal of the American Society of NephrologyUp Front Matters29882031208120322088Background Histologic examination of fixed renal tissue is widely used to assess morphology and the progression of disease. Commonly reported metrics include glomerular number and injury. However, characterization of renal histology is a time-consuming and user-dependent process. To accelerate and improve the process, we have developed a glomerular localization pipeline for trichrome-stained kidney sections using a machine learning image classification algorithm. Methods We prepared 4-μm slices of kidneys from rats of various genetic backgrounds that were subjected to different experimental protocols and mounted the slices on glass slides. All sections used in this analysis were trichrome stained and imaged in bright field at a minimum resolution of 0.92 μm per pixel. The training and test datasets for the algorithm comprised 74 and 13 whole renal sections, respectively, totaling over 28,000 glomeruli manually localized. Additionally, because this localizer will be ultimately used for automated assessment of glomerular injury, we assessed bias of the localizer for preferentially identifying healthy or damaged glomeruli. Results Localizer performance achieved an average precision and recall of 96.94% and 96.79%, respectively, on whole kidney sections without evidence of bias for or against glomerular injury or the need for manual preprocessing. Conclusions This study presents a novel and robust application of convolutional neural nets for the localization of glomeruli in healthy and damaged trichrome-stained whole-renal section mounts and lays the groundwork for automated glomerular injury scoring.10.1681/ASN.2017111210Tue, 19 Jun 2018 07:48:15 GMT-07:00Region-Based Convolutional Neural Nets for Localization of Glomeruli in Trichrome-Stained Whole Kidney SectionsBackground Histologic examination of fixed renal tissue is widely used to assess morphology and the progression of disease. Commonly reported metrics include glomerular number and injury. However, characterization of renal histology is a time-consuming and user-dependent process. To accelerate and improve the process, we have developed a glomerular localization pipeline for trichrome-stained kidney sections using a machine learning image classification algorithm. Methods We prepared 4-μm slices of kidneys from rats of various genetic backgrounds that were subjected to different experimental protocols and mounted the slices on glass slides. All sections used in this analysis were trichrome stained and imaged in bright field at a minimum resolution of 0.92 μm per pixel. The training and test datasets for the algorithm comprised 74 and 13 whole renal sections, respectively, totaling over 28,000 glomeruli manually localized. Additionally, because this localizer will be ultimately used for automated assessment of glomerular injury, we assessed bias of the localizer for preferentially identifying healthy or damaged glomeruli. Results Localizer performance achieved an average precision and recall of 96.94% and 96.79%, respectively, on whole kidney sections without evidence of bias for or against glomerular injury or the need for manual preprocessing. Conclusions This study presents a novel and robust application of convolutional neural nets for the localization of glomeruli in healthy and damaged trichrome-stained whole-renal section mounts and lays the groundwork for automated glomerular injury scoring.Bukowy, John D.Dayton, AlexCloutier, DustinManis, Anna D.Staruschenko, AlexanderLombard, Julian H.Solberg Woods, Leah C.Beard, Daniel A.Cowley, Allen W.2018-06-19T07:48:15-07:00doi:10.1681/ASN.2017111210hwp:resource-id:jnephrol;29/8/2081American Society of NephrologyCopyright © 2018 by the American Society of NephrologyJournal of the American Society of Nephrologyrenal injury, renal morphology, Renal pathology, kidney disease, glomerular disease, glomerulus, machine learning collectionBasic ResearchBasic Researchresearch-article20182018-08-01August 201810.1681/ASN.20171112101046-66731533-34502018-06-19T07:48:15-07:002018-08Journal of the American Society of NephrologyBasic Research29882081203120882032