Literature DB >> 34862241

Automatic Evaluation of Histological Prognostic Factors Using Two Consecutive Convolutional Neural Networks on Kidney Samples.

Elise Marechal1,2,3, Adrien Jaugey2,4, Georges Tarris2,5, Michel Paindavoine2,4,6, Jean Seibel1,7, Laurent Martin2,8, Mathilde Funes de la Vega8, Thomas Crepin2,3,7, Didier Ducloux2,3,7, Gilbert Zanetta1, Sophie Felix5, Pierre Henri Bonnot1, Florian Bardet2,9, Luc Cormier2,9, Jean-Michel Rebibou1,2,3, Mathieu Legendre10,2,3.   

Abstract

BACKGROUND AND OBJECTIVES: The prognosis of patients undergoing kidney tumor resection or kidney donation is linked to many histologic criteria. These criteria notably include glomerular density, glomerular volume, vascular luminal stenosis, and severity of interstitial fibrosis/tubular atrophy. Automated measurements through a deep-learning approach could save time and provide more precise data. This work aimed to develop a free tool to automatically obtain kidney histologic prognostic features. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: In total, 241 samples of healthy kidney tissue were split into three independent cohorts. The "Training" cohort (n=65) was used to train two convolutional neural networks: one to detect the cortex and a second to segment the kidney structures. The "Test" cohort (n=50) assessed their performance by comparing manually outlined regions of interest to predicted ones. The "Application" cohort (n=126) compared prognostic histologic data obtained manually or through the algorithm on the basis of the combination of the two convolutional neural networks.
RESULTS: In the Test cohort, the networks isolated the cortex and segmented the elements of interest with good performances (>90% of the cortex, healthy tubules, glomeruli, and even globally sclerotic glomeruli were detected). In the Application cohort, the expected and predicted prognostic data were significantly correlated. The correlation coefficients r were 0.85 for glomerular volume, 0.51 for glomerular density, 0.75 for interstitial fibrosis, 0.71 for tubular atrophy, and 0.73 for vascular intimal thickness, respectively. The algorithm had a good ability to predict significant (>25%) tubular atrophy and interstitial fibrosis level (receiver operator characteristic curve with an area under the curve, 0.92 and 0.91, respectively) or a significant vascular luminal stenosis (>50%) (area under the curve, 0.85).
CONCLUSION: This freely available tool enables the automated segmentation of kidney tissue to obtain prognostic histologic data in a fast, objective, reliable, and reproducible way.
Copyright © 2022 by the American Society of Nephrology.

Entities:  

Keywords:  computer; deep learning; neural networks; prognosis; renal pathology

Mesh:

Year:  2021        PMID: 34862241      PMCID: PMC8823945          DOI: 10.2215/CJN.07830621

Source DB:  PubMed          Journal:  Clin J Am Soc Nephrol        ISSN: 1555-9041            Impact factor:   8.237


  39 in total

1.  Larger nephron size, low nephron number, and nephrosclerosis on biopsy as predictors of kidney function after donating a kidney.

Authors:  Naim Issa; Lisa E Vaughan; Aleksandar Denic; Walter K Kremers; Harini A Chakkera; Walter D Park; Arthur J Matas; Sandra J Taler; Mark D Stegall; Joshua J Augustine; Andrew D Rule
Journal:  Am J Transplant       Date:  2019-02-01       Impact factor: 8.086

2.  Biopsy-based estimation of total nephron number in Japanese living kidney donors.

Authors:  Takaya Sasaki; Nobuo Tsuboi; Go Kanzaki; Kotaro Haruhara; Yusuke Okabayashi; Kentaro Koike; Akimitsu Kobayashi; Izumi Yamamoto; Makoto Ogura; Wendy E Hoy; John F Bertram; Akira Shimizu; Takashi Yokoo
Journal:  Clin Exp Nephrol       Date:  2019-01-12       Impact factor: 2.801

3.  Volume Ratio of Glomerular Tufts to Bowman Capsules and Renal Outcomes in Nephrosclerosis.

Authors:  Kotaro Haruhara; Nobuo Tsuboi; Takaya Sasaki; Hoichi Amano; Mai Tanaka; Kentaro Koike; Go Kanzaki; Yusuke Okabayashi; Yoichi Miyazaki; Makoto Ogura; Takashi Yokoo
Journal:  Am J Hypertens       Date:  2019-01-01       Impact factor: 2.689

Review 4.  Nephron number, glomerular volume, renal disease and hypertension.

Authors:  Wendy E Hoy; John F Bertram; Rebecca Douglas Denton; Monika Zimanyi; Terence Samuel; Michael D Hughson
Journal:  Curr Opin Nephrol Hypertens       Date:  2008-05       Impact factor: 2.894

Review 5.  Machine learning techniques for biomedical image segmentation: An overview of technical aspects and introduction to state-of-art applications.

Authors:  Hyunseok Seo; Masoud Badiei Khuzani; Varun Vasudevan; Charles Huang; Hongyi Ren; Ruoxiu Xiao; Xiao Jia; Lei Xing
Journal:  Med Phys       Date:  2020-06       Impact factor: 4.071

6.  Automated Computational Detection of Interstitial Fibrosis, Tubular Atrophy, and Glomerulosclerosis.

Authors:  Brandon Ginley; Kuang-Yu Jen; Seung Seok Han; Luís Rodrigues; Sanjay Jain; Agnes B Fogo; Jonathan Zuckerman; Vighnesh Walavalkar; Jeffrey C Miecznikowski; Yumeng Wen; Felicia Yen; Donghwan Yun; Kyung Chul Moon; Avi Rosenberg; Chirag Parikh; Pinaki Sarder
Journal:  J Am Soc Nephrol       Date:  2021-02-23       Impact factor: 10.121

Review 7.  Artificial intelligence and machine learning in nephropathology.

Authors:  Jan U Becker; David Mayerich; Meghana Padmanabhan; Jonathan Barratt; Angela Ernst; Peter Boor; Pietro A Cicalese; Chandra Mohan; Hien V Nguyen; Badrinath Roysam
Journal:  Kidney Int       Date:  2020-04-01       Impact factor: 10.612

8.  A Fully Automated System Using A Convolutional Neural Network to Predict Renal Allograft Rejection: Extra-validation with Giga-pixel Immunostained Slides.

Authors:  Young-Gon Kim; Gyuheon Choi; Heounjeong Go; Yongwon Cho; Hyunna Lee; A-Reum Lee; Beomhee Park; Namkug Kim
Journal:  Sci Rep       Date:  2019-03-26       Impact factor: 4.379

Review 9.  Artificial intelligence driven next-generation renal histomorphometry.

Authors:  Briana A Santo; Avi Z Rosenberg; Pinaki Sarder
Journal:  Curr Opin Nephrol Hypertens       Date:  2020-05       Impact factor: 3.416

Review 10.  Deep Learning for Cardiac Image Segmentation: A Review.

Authors:  Chen Chen; Chen Qin; Huaqi Qiu; Giacomo Tarroni; Jinming Duan; Wenjia Bai; Daniel Rueckert
Journal:  Front Cardiovasc Med       Date:  2020-03-05
View more
  2 in total

1.  Automated Computer-Assisted Image Analysis for the Fast Quantification of Kidney Fibrosis.

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

Review 2.  Artificial Intelligence-Assisted Renal Pathology: Advances and Prospects.

Authors:  Yiqin Wang; Qiong Wen; Luhua Jin; Wei Chen
Journal:  J Clin Med       Date:  2022-08-22       Impact factor: 4.964

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.