1
|
Nishino T, Takahashi K, Ono S, Mimaki M. Pathological Factors Affecting the R2* Values of the Kidney in Blood Oxygenation Level-dependent MR Imaging: A Retrospective Study. Magn Reson Med Sci 2024; 23:153-160. [PMID: 36754388 PMCID: PMC11024711 DOI: 10.2463/mrms.mp.2022-0140] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2022] [Accepted: 01/07/2023] [Indexed: 02/08/2023] Open
Abstract
PURPOSE Despite the usefulness of blood oxygenation level-dependent (BOLD) MRI in assessing glomerulonephritis activity, its relationship with histological findings remains unclear. Because glomerulonephritis presents multiple complex injury patterns, analysis of each pattern is essential. We aimed to elucidate the relationship between the histological findings of the kidney and BOLD MRI findings in mesangial proliferative glomerulonephritis. METHODS Children under 16 years of age diagnosed with mesangial proliferative glomerulonephritis by kidney biopsy at our university hospital between January 2013 and September 2022 were included in this study. Cortical and medullary spin relaxation rate (R2*) values were measured using BOLD MRI at 3T within two weeks before and after the kidney biopsy. The R2* values, including the fluctuations with low-dose oxygen administration, were retrospectively examined in relation to the cortical (mesangial proliferation, endothelial cell proliferation, crescent, sclerosis, and fibrosis) and medullary findings (fibrosis). RESULTS Sixteen times kidney biopsies were performed for glomerulonephritis during the study period, and one patient was excluded because of comorbidities; the remaining 14 patients included six boys with a mean age of 11.9 ± 3.5 years at the BOLD examination. None of the patients had medullary fibrosis. Among the kidney tissue parameters, only sclerosis showed a significant correlation with R2* values: medulla with R2* values under atmospheric pressure (r = 0.53, P < 0.05) and cortex with the rate of change in R2* values with low-dose oxygen administration (r = -0.57, P < 0.03). In the multiple regression analysis, only sclerosis was an independent contributor to the change in R2* values with oxygen administration in the cortex (regression coefficient -0.109, P < 0.05). CONCLUSION Since the R2* values reflect histological changes in the kidney, BOLD MRI may facilitate the evaluation of mesangial proliferative glomerulonephritis, potentially reducing the patient burden.
Collapse
Affiliation(s)
- Tomohiko Nishino
- Department of Pediatrics, Teikyo University School of Medicine, Tokyo, Japan
| | - Kazuhiro Takahashi
- Department of Pediatrics, Teikyo University School of Medicine, Tokyo, Japan
| | - Sayaka Ono
- Department of Pediatrics, Teikyo University School of Medicine, Tokyo, Japan
| | - Masakazu Mimaki
- Department of Pediatrics, Teikyo University School of Medicine, Tokyo, Japan
| |
Collapse
|
2
|
Fenton KA, Pedersen HL. Advanced methods and novel biomarkers in autoimmune diseases ‑ a review of the recent years progress in systemic lupus erythematosus. Front Med (Lausanne) 2023; 10:1183535. [PMID: 37425332 PMCID: PMC10326284 DOI: 10.3389/fmed.2023.1183535] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/10/2023] [Accepted: 06/01/2023] [Indexed: 07/11/2023] Open
Abstract
There are several autoimmune and rheumatic diseases affecting different organs of the human body. Multiple sclerosis (MS) mainly affects brain, rheumatoid arthritis (RA) mainly affects joints, Type 1 diabetes (T1D) mainly affects pancreas, Sjogren's syndrome (SS) mainly affects salivary glands, while systemic lupus erythematosus (SLE) affects almost every organ of the body. Autoimmune diseases are characterized by production of autoantibodies, activation of immune cells, increased expression of pro-inflammatory cytokines, and activation of type I interferons. Despite improvements in treatments and diagnostic tools, the time it takes for the patients to be diagnosed is too long, and the main treatment for these diseases is still non-specific anti-inflammatory drugs. Thus, there is an urgent need for better biomarkers, as well as tailored, personalized treatment. This review focus on SLE and the organs affected in this disease. We have used the results from various rheumatic and autoimmune diseases and the organs involved with an aim to identify advanced methods and possible biomarkers to be utilized in the diagnosis of SLE, disease monitoring, and response to treatment.
Collapse
Affiliation(s)
- Kristin Andreassen Fenton
- UiT The Arctic University of Norway, Tromsø, Norway
- Centre of Clinical Research and Education, University Hospital of North Norway, Tromsø, Norway
| | - Hege Lynum Pedersen
- UiT The Arctic University of Norway, Tromsø, Norway
- Centre of Clinical Research and Education, University Hospital of North Norway, Tromsø, Norway
| |
Collapse
|
3
|
Wang DC, Xu WD, Wang SN, Wang X, Leng W, Fu L, Liu XY, Qin Z, Huang AF. Lupus nephritis or not? A simple and clinically friendly machine learning pipeline to help diagnosis of lupus nephritis. Inflamm Res 2023:10.1007/s00011-023-01755-7. [PMID: 37300586 DOI: 10.1007/s00011-023-01755-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2023] [Revised: 05/17/2023] [Accepted: 05/30/2023] [Indexed: 06/12/2023] Open
Abstract
OBJECTIVE Diagnosis of lupus nephritis (LN) is a complex process, which usually requires renal biopsy. We aim to establish a machine learning pipeline to help diagnosis of LN. METHODS A cohort of 681 systemic lupus erythematosus (SLE) patients without LN and 786 SLE patients with LN was established, and a total of 95 clinical, laboratory data and 17 meteorological indicators were collected. After tenfold cross-validation, the patients were divided into training set and test set. The features selected by collective feature selection method of mutual information (MI) and multisurf were used to construct the models of logistic regression, decision tree, random forest, naive Bayes, support vector machine (SVM), light gradient boosting (LGB), extreme gradient boosting (XGB), and artificial neural network (ANN), the models were compared and verified in post-analysis. RESULTS Collective feature selection method screens out antistreptolysin (ASO), retinol binding protein (RBP), lupus anticoagulant 1 (LA1), LA2, proteinuria and other features, and the hyperparameter optimized XGB (ROC: AUC = 0.995; PRC: AUC = 1.000, APS = 1.000; balance accuracy: 0.990) has the best performance, followed by LGB (ROC: AUC = 0.992; PRC: AUC = 0.997, APS = 0.977; balance accuracy: 0.957). The worst performance is naive Bayes model (ROC: AUC = 0.799; PRC: AUC = 0.822, APS = 0.823; balance accuracy: 0.693). In the composite feature importance bar plots, ASO, RF, Up/Ucr, and other features play important roles in LN. CONCLUSION We developed and validated a new and simple machine learning pathway for diagnosis of LN, especially the XGB model based on ASO, LA1, LA2, proteinuria, and other features screened out by collective feature selection.
Collapse
Affiliation(s)
- Da-Cheng Wang
- Department of Evidence-Based Medicine, Southwest Medical University, 1 Xianglin Road, Luzhou, Sichuan, China
| | - Wang-Dong Xu
- Department of Evidence-Based Medicine, Southwest Medical University, 1 Xianglin Road, Luzhou, Sichuan, China
| | - Shen-Nan Wang
- Luzhou Meteorological Bureau, 3 Songshan Road, Luzhou, Sichuan, China
| | - Xiang Wang
- Luzhou Meteorological Bureau, 3 Songshan Road, Luzhou, Sichuan, China
| | - Wei Leng
- Luzhou Meteorological Bureau, 3 Songshan Road, Luzhou, Sichuan, China
| | - Lu Fu
- Laboratory Animal Center, Southwest Medical University, 1 Xianglin Road, Luzhou, Sichuan, China
| | - Xiao-Yan Liu
- Department of Evidence-Based Medicine, Southwest Medical University, 1 Xianglin Road, Luzhou, Sichuan, China
| | - Zhen Qin
- Department of Rheumatology and Immunology, Affiliated Hospital of Southwest Medical University, 25 Taiping Road, Luzhou, Sichuan, China
| | - An-Fang Huang
- Department of Rheumatology and Immunology, Affiliated Hospital of Southwest Medical University, 25 Taiping Road, Luzhou, Sichuan, China.
| |
Collapse
|
4
|
Zhao D, Wang W, Tang T, Zhang YY, Yu C. Current progress in artificial intelligence-assisted medical image analysis for chronic kidney disease: A literature review. Comput Struct Biotechnol J 2023; 21:3315-3326. [PMID: 37333860 PMCID: PMC10275698 DOI: 10.1016/j.csbj.2023.05.029] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2022] [Revised: 05/28/2023] [Accepted: 05/28/2023] [Indexed: 06/20/2023] Open
Abstract
Chronic kidney disease (CKD) causes irreversible damage to kidney structure and function. Arising from various etiologies, risk factors for CKD include hypertension and diabetes. With a progressively increasing global prevalence, CKD is an important public health problem worldwide. Medical imaging has become an important diagnostic tool for CKD through the non-invasive identification of macroscopic renal structural abnormalities. Artificial intelligence (AI)-assisted medical imaging techniques aid clinicians in the analysis of characteristics that cannot be easily discriminated by the naked eye, providing valuable information for the identification and management of CKD. Recent studies have demonstrated the effectiveness of AI-assisted medical image analysis as a clinical support tool using radiomics- and deep learning-based AI algorithms for improving the early detection, pathological assessment, and prognostic evaluation of various forms of CKD, including autosomal dominant polycystic kidney disease. Herein, we provide an overview of the potential roles of AI-assisted medical image analysis for the diagnosis and management of CKD.
Collapse
Affiliation(s)
- Dan Zhao
- Department of Nephrology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| | - Wei Wang
- Department of Radiology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| | - Tian Tang
- Department of Nephrology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| | - Ying-Ying Zhang
- Department of Nephrology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| | - Chen Yu
- Department of Nephrology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| |
Collapse
|
5
|
Artificial Intelligence-Assisted Renal Pathology: Advances and Prospects. J Clin Med 2022; 11:jcm11164918. [PMID: 36013157 PMCID: PMC9410196 DOI: 10.3390/jcm11164918] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2022] [Revised: 07/30/2022] [Accepted: 08/11/2022] [Indexed: 11/17/2022] Open
Abstract
Digital imaging and advanced microscopy play a pivotal role in the diagnosis of kidney diseases. In recent years, great achievements have been made in digital imaging, providing novel approaches for precise quantitative assessments of nephropathology and relieving burdens of renal pathologists. Developing novel methods of artificial intelligence (AI)-assisted technology through multidisciplinary interaction among computer engineers, renal specialists, and nephropathologists could prove beneficial for renal pathology diagnoses. An increasing number of publications has demonstrated the rapid growth of AI-based technology in nephrology. In this review, we offer an overview of AI-assisted renal pathology, including AI concepts and the workflow of processing digital image data, focusing on the impressive advances of AI application in disease-specific backgrounds. In particular, this review describes the applied computer vision algorithms for the segmentation of kidney structures, diagnosis of specific pathological changes, and prognosis prediction based on images. Lastly, we discuss challenges and prospects to provide an objective view of this topic.
Collapse
|
6
|
Detection of renal hypoxia configuration in patients with lupus nephritis: a primary study using blood oxygen level-dependent MR imaging. Abdom Radiol (NY) 2021; 46:2032-2044. [PMID: 33079255 DOI: 10.1007/s00261-020-02794-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2020] [Revised: 09/15/2020] [Accepted: 09/27/2020] [Indexed: 10/23/2022]
Abstract
BACKGROUND Renal microstructure and function are closely associated with oxygenation homeostasis. Analyzing renal blood oxygen level‒dependent (BOLD) magnetic resonance imaging (MRI) examination results will provide information on the biological status of the kidneys. The current study was performed to explore the hypoxia mode of the entire renal parenchyma in patients with lupus nephritis (LN). METHODS A total of 23 adult patients with LN and 18 healthy volunteers were recruited. R2* values were acquired using BOLD MRI analysis. The narrow rectangular region of interest was used to explore the hypoxia configuration in entire depths of renal parenchyma. Acquired sequential R2* data were fitted using four categories of mathematic functions. The tendency of R2* data in both patients with LN and healthy volunteers was also compared using repeated-measures analysis of variance. RESULTS R2* data from the superficial cortex to deep medulla displayed two patterns called a sharp uptrend style and a flat uptrend style. After sequential R2* data were fitted individually with the use of four mathematic formulas, the multiple-compartment Gaussian function showed the highest goodness of fit. Compared with two categories of R2* value styles, the R2* tendency of entire parenchyma in patients with LN was different from that in healthy volunteers. CONCLUSIONS Deep renal medullary oxygenation was not always overtly lower than oxygenation in the superficial renal cortical zone. The manifestation of renal parenchyma oxygenation could be described using a Gaussian function model. Deoxygenation tolerance was damaged in patients with LN.
Collapse
|
7
|
Alnazer I, Bourdon P, Urruty T, Falou O, Khalil M, Shahin A, Fernandez-Maloigne C. Recent advances in medical image processing for the evaluation of chronic kidney disease. Med Image Anal 2021; 69:101960. [PMID: 33517241 DOI: 10.1016/j.media.2021.101960] [Citation(s) in RCA: 30] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2020] [Revised: 11/18/2020] [Accepted: 12/31/2020] [Indexed: 12/31/2022]
Abstract
Assessment of renal function and structure accurately remains essential in the diagnosis and prognosis of Chronic Kidney Disease (CKD). Advanced imaging, including Magnetic Resonance Imaging (MRI), Ultrasound Elastography (UE), Computed Tomography (CT) and scintigraphy (PET, SPECT) offers the opportunity to non-invasively retrieve structural, functional and molecular information that could detect changes in renal tissue properties and functionality. Currently, the ability of artificial intelligence to turn conventional medical imaging into a full-automated diagnostic tool is widely investigated. In addition to the qualitative analysis performed on renal medical imaging, texture analysis was integrated with machine learning techniques as a quantification of renal tissue heterogeneity, providing a promising complementary tool in renal function decline prediction. Interestingly, deep learning holds the ability to be a novel approach of renal function diagnosis. This paper proposes a survey that covers both qualitative and quantitative analysis applied to novel medical imaging techniques to monitor the decline of renal function. First, we summarize the use of different medical imaging modalities to monitor CKD and then, we show the ability of Artificial Intelligence (AI) to guide renal function evaluation from segmentation to disease prediction, discussing how texture analysis and machine learning techniques have emerged in recent clinical researches in order to improve renal dysfunction monitoring and prediction. The paper gives a summary about the role of AI in renal segmentation.
Collapse
Affiliation(s)
- Israa Alnazer
- XLIM-ICONES, UMR CNRS 7252, Université de Poitiers, France; Laboratoire commune CNRS/SIEMENS I3M, Poitiers, France; AZM Center for Research in Biotechnology and its Applications, EDST, Lebanese University, Beirut, Lebanon.
| | - Pascal Bourdon
- XLIM-ICONES, UMR CNRS 7252, Université de Poitiers, France; Laboratoire commune CNRS/SIEMENS I3M, Poitiers, France
| | - Thierry Urruty
- XLIM-ICONES, UMR CNRS 7252, Université de Poitiers, France; Laboratoire commune CNRS/SIEMENS I3M, Poitiers, France
| | - Omar Falou
- AZM Center for Research in Biotechnology and its Applications, EDST, Lebanese University, Beirut, Lebanon; American University of Culture and Education, Koura, Lebanon; Lebanese University, Faculty of Science, Tripoli, Lebanon
| | - Mohamad Khalil
- AZM Center for Research in Biotechnology and its Applications, EDST, Lebanese University, Beirut, Lebanon
| | - Ahmad Shahin
- AZM Center for Research in Biotechnology and its Applications, EDST, Lebanese University, Beirut, Lebanon
| | - Christine Fernandez-Maloigne
- XLIM-ICONES, UMR CNRS 7252, Université de Poitiers, France; Laboratoire commune CNRS/SIEMENS I3M, Poitiers, France
| |
Collapse
|
8
|
Abstract
PURPOSE OF REVIEW The management of lupus nephritis remains unsatisfactory due to insufficiently effective treatment regimens and the dearth of reliable predictors of disease onset or progression to guide individualized therapeutic decisions. This review summarizes new findings related to lupus nephritis over the last 18 months and discusses clinical needs that should be considered to advance trials of mechanism-based therapeutic strategies. RECENT FINDINGS Collaborative teams are addressing how to improve disease definitions and are developing predictive models for disease onset, disease response and risk of flare in individual patients. More attention is being paid to clinical trial design. Advanced technologic approaches are allowing the analysis of small amounts of human tissue and urine in unprecedented detail so as to discover new pathogenic mechanisms and identify disease biomarkers. Novel therapies continue to be tested in disease models and include new strategies to protect renal tissue from cell damage and fibrosis. SUMMARY The collaborative efforts of patients, clinical and translational researchers, the pharmaceutical industry and funding sources are needed to advance therapies for lupus nephritis. Specialized clinical centers can then deliver optimal and more personalized patient care that will improve patient outcomes.
Collapse
|
9
|
Wolfson J, Venkatasubramaniam A. Branching Out: Use of Decision Trees in Epidemiology. CURR EPIDEMIOL REP 2018. [DOI: 10.1007/s40471-018-0163-y] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/31/2022]
|