Development and Validation of a Deep Learning Model to Quantify Interstitial Fibrosis and Tubular Atrophy From Kidney Ultrasonography Images

Athavale, Ambarish M.; Hart, Peter D.; Itteera, M.; Cimbaluk, David; Patel, Tushar M.; Alabkaa, Anas; Arruda, José A.L.; Singh, Ashok; Rosenberg, Avi; Kulkarni, Hemant

doi:10.1001/jamanetworkopen.2021.11176

Cited by 13 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ability of ultrasound-based prediction of kidney interstitial fibrosis and tubular atrophy using a deep learning framework was also demonstrated in a diagnostic evaluation of 6,135 images in a study by Athavale et al, and the accuracy at the patient level was approximately 90% (35).…”

Section: Ckdmentioning

confidence: 85%

“…Early and noninvasive detection is crucial to preventing or delaying the progression of CKD. In this systematic review, 12 studies were identified in this section, of which 10 referred to CKD and related diseases classification or screening (31)(32)(33)(34)(35)(36)(37)(38)(39)48) and two referred to complications after allograft renal transplantation (8,40). Iqbal et al showed that texture feature obtained from the cortex region in ultrasound images was more significant than those obtained from the entire kidney or renal medulla in distinguishing between normal and CKD patients (48).…”

Section: Ckdmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence-aided ultrasound in renal diseases: a systematic review

Liang¹,

Du²,

Chen³

2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: The development of artificial intelligence (AI) techniques has provided a novel strategy for improving the performance of renal ultrasound. To reflect the development of AI methods in renal ultrasound, we aimed to clarify and analyze the state of AI-aided ultrasound research in renal diseases.Methods: PRISMA 2020 guidelines have been used to guide all processes and results. AI-aided renal ultrasound studies (for both image segmentation and disease diagnosis) published up to June 2022 were screened through the databases of PubMed and Web of Science. Accuracy/Dice similarity coefficient (DICE), the area under the curve (AUC), sensitivity/specificity, and other indications were applied as evaluation parameters. The PROBAST was used to assess the risk of bias in the studies screened.Results: Of 364 articles, 38 studies were analyzed, and could be divided into AI-aided diagnosis or prediction related studies (28/38) and image segmentation related studies (10/38). The output of these 28 studies involved differential diagnosis of local lesions, disease grading of, automatic diagnosis, and diseases prediction. The median values of accuracy and AUC were 0.88 and 0.96, respectively. Overall, 86% of the AI-aided diagnosis or prediction models were classified as high risk. An unclear source of data, inadequate sample size, inappropriate analysis methods, and lack of rigorous external validation were found to be the most frequent and critical risk factors in AI-aided renal ultrasound studies.Conclusions: AI is a potential technique in the ultrasound diagnosis of different types of renal diseases, but the reliability and availability need to be strengthened. The use of AI-aided ultrasound in chronic kidney disease and quantitative hydronephrosis diagnosis will be a promising possibility. The size and quality of sample data, rigorous external validation, and adherence to guidelines and standards should be considered in further studies.

show abstract

Section: Ckdmentioning

confidence: 85%

Section: Ckdmentioning

confidence: 99%

Artificial intelligence-aided ultrasound in renal diseases: a systematic review

Liang¹,

Du²,

Chen³

2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

show abstract

“…Nowadays, there are an increasing number of tools to generate the segmentation of the entire WSIs [ 20 ], such as HALO software [ 21 ] and the PyTorch platform [ 22 , 23 ]. However, they require either GPU-based hardware or programming skills for researchers, which limits the promotion and application.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning-Based Model Significantly Improves Diagnostic Performance for Assessing Renal Histopathology in Lupus Glomerulonephritis

et al. 2022

View full text Add to dashboard Cite

Background: Assessment of glomerular lesions and structures plays an essential role in understanding the pathological diagnosis of glomerulonephritis and prognostic evaluation of many kidney diseases. Renal pathophysiological assessment requires novel high-throughput tools to conduct quantitative, unbiased, and reproducible analyses representing a central readout. Deep learning may be an effective tool for glomerulonephritis pathological analysis. Methods: We developed a murine renal pathological system (MRPS) model to objectify the pathological evaluation via the deep learning method on whole-slide image (WSI) segmentation and feature extraction. A convolutional neural network model was used for accurate segmentation of glomeruli and glomerular cells of periodic acid-Schiff-stained kidney tissue from healthy and lupus nephritis mice. To achieve a quantitative evaluation, we subsequently filtered five independent predictors as image biomarkers from all features and developed a formula for the scoring model. Results: Perimeter, shape factor, minimum internal diameter, minimum caliper diameter, and number of objects were identified as independent predictors and were included in the establishment of the MRPS. The MRPS showed a positive correlation with renal score (r = 0.480, p < 0.001) and obtained great diagnostic performance in discriminating different score bands (Obuchowski index, 0.842 [95% confidence interval: 0.759, 0.925]), with an area under the curve of 0.78–0.98, sensitivity of 58–93%, specificity of 72–100%, and accuracy of 74–94%. Conclusion: Our MRPS for quantitative assessment of renal WSIs from MRL/lpr lupus nephritis mice enables accurate histopathological analyses with high reproducibility, which may serve as a useful tool for glomerulonephritis diagnosis and prognosis evaluation.

show abstract

“…Results of routine histological analyses of renal biopsy tissues, such as light microscopic findings of formalin fixed paraffin embedded tissue sections, immunofluorescence staining for IgG, IgA, IgM, C1q, and C3c on fresh frozen tissue sections, and electron microscopic findings were collected from the patients’ medical charts in our hospital. Regarding the light microscopic findings, in addition to the usual evaluation items such as glomerular global sclerosis rate and crescent formation rate, we also evaluated the interstitial fibrosis and tubular atrophy (IFTA) score as the chronic histological change using the previously reported grading scale of 1–4 [ 16 ].…”

Section: Methodsmentioning

confidence: 99%

Circulating immune-complexes and complement activation through the classical pathway in myeloperoxidase-ANCA-associated glomerulonephritis

et al. 2022

View full text Add to dashboard Cite

Background Anti-neutrophil cytoplasmic antibody (ANCA)-associated glomerulonephritis (AAGN) is the fulminant glomerular diseases with poor renal prognosis. Activation of the complement system has recently been reported in the pathogenesis of AAGN, but it remains to be clarified as to which complement pathway is mainly involved. Methods 20 patients with myeloperoxidase (MPO)-AAGN were retrospectively evaluated. Using serum samples, circulating immune-complexes (CICs) were assessed by the monoclonal rheumatoid factor assay, and C5a and C5b-9 were assessed by ELISA. Complement activation through the classical pathway was further evaluated by the WIESLAB® Complement System Classical Pathway kit. The affinities of ANCAs were evaluated by a competitive inhibition method using ELISA, and were classified into the high, and low-affinity group. Deposition of complement components, such as C3, C5, C4d, C5b-9, factor Bb, mannan-binding lectin serine peptidase (MASP)-1, MASP-2, and mannose/mannan-binding lectin (MBL), in frozen renal sections were analyzed by immunofluorescence staining. Results CICs were found to be positive in 65% of the patients. All CIC-positive patients belonged to the high-affinity group. Furthermore, serum C5a and C5b-9 were significantly increased in MPO-AAGN patients, and these levels positively correlated with CIC levels. A significant negative correlation was also found between levels of WIESLAB® classical pathway kit and CICs. By immunofluorescence staining, glomerular deposition of C4d, C5, and C5b-9 were observed in similar distributions in MPO-AAGN patients, whereas the deposition of MASP-1, MASP-2, MBL, and factor Bb were minimal. Conclusions These results suggest the involvement of immune-complex induced complement activation through the classical pathway in the pathogenesis of MPO-AAGN.

show abstract

Development and Validation of a Deep Learning Model to Quantify Interstitial Fibrosis and Tubular Atrophy From Kidney Ultrasonography Images

Cited by 13 publications

References 28 publications

Artificial intelligence-aided ultrasound in renal diseases: a systematic review

Artificial intelligence-aided ultrasound in renal diseases: a systematic review

Deep Learning-Based Model Significantly Improves Diagnostic Performance for Assessing Renal Histopathology in Lupus Glomerulonephritis

Circulating immune-complexes and complement activation through the classical pathway in myeloperoxidase-ANCA-associated glomerulonephritis

Contact Info

Product

Resources

About