Dataset Information

Development and Validation of a Deep Learning Model to Quantify Glomerulosclerosis in Kidney Biopsy Specimens.

ABSTRACT:

Importance

A chronic shortage of donor kidneys is compounded by a high discard rate, and this rate is directly associated with biopsy specimen evaluation, which shows poor reproducibility among pathologists. A deep learning algorithm for measuring percent global glomerulosclerosis (an important predictor of outcome) on images of kidney biopsy specimens could enable pathologists to more reproducibly and accurately quantify percent global glomerulosclerosis, potentially saving organs that would have been discarded.

Objective

To compare the performances of pathologists with a deep learning model on quantification of percent global glomerulosclerosis in whole-slide images of donor kidney biopsy specimens, and to determine the potential benefit of a deep learning model on organ discard rates.

Design, setting, and participants

This prognostic study used whole-slide images acquired from 98 hematoxylin-eosin-stained frozen and 51 permanent donor biopsy specimen sections retrieved from 83 kidneys. Serial annotation by 3 board-certified pathologists served as ground truth for model training and for evaluation. Images of kidney biopsy specimens were obtained from the Washington University database (retrieved between June 2015 and June 2017). Cases were selected randomly from a database of more than 1000 cases to include biopsy specimens representing an equitable distribution within 0% to 5%, 6% to 10%, 11% to 15%, 16% to 20%, and more than 20% global glomerulosclerosis.

Main outcomes and measures

Correlation coefficient (r) and root-mean-square error (RMSE) with respect to annotations were computed for cross-validated model predictions and on-call pathologists' estimates of percent global glomerulosclerosis when using individual and pooled slide results. Data were analyzed from March 2018 to August 2020.

Results

The cross-validated model results of section images retrieved from 83 donor kidneys showed higher correlation with annotations (r?=?0.916; 95% CI, 0.886-0.939) than on-call pathologists (r?=?0.884; 95% CI, 0.825-0.923) that was enhanced when pooling glomeruli counts from multiple levels (r?=?0.933; 95% CI, 0.898-0.956). Model prediction error for single levels (RMSE, 5.631; 95% CI, 4.735-6.517) was 14% lower than on-call pathologists (RMSE, 6.523; 95% CI, 5.191-7.783), improving to 22% with multiple levels (RMSE, 5.094; 95% CI, 3.972-6.301). The model decreased the likelihood of unnecessary organ discard by 37% compared with pathologists.

Conclusions and relevance

The findings of this prognostic study suggest that this deep learning model provided a scalable and robust method to quantify percent global glomerulosclerosis in whole-slide images of donor kidneys. The model performance improved by analyzing multiple levels of a section, surpassing the capacity of pathologists in the time-sensitive setting of examining donor biopsy specimens. The results indicate the potential of a deep learning model to prevent erroneous donor organ discard.

SUBMITTER: Marsh JN

PROVIDER: S-EPMC7818108 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and Validation of a Deep Learning Model to Quantify Glomerulosclerosis in Kidney Biopsy Specimens.

Marsh Jon N JN Liu Ta-Chiang TC Wilson Parker C PC Swamidass S Joshua SJ Gaut Joseph P JP

JAMA network open 20210104 1

<h4>Importance</h4>A chronic shortage of donor kidneys is compounded by a high discard rate, and this rate is directly associated with biopsy specimen evaluation, which shows poor reproducibility among pathologists. A deep learning algorithm for measuring percent global glomerulosclerosis (an important predictor of outcome) on images of kidney biopsy specimens could enable pathologists to more reproducibly and accurately quantify percent global glomerulosclerosis, potentially saving organs that ...[more]

PMID: 33471115

Similar Datasets

Project description:ImportanceInterstitial fibrosis and tubular atrophy (IFTA) is a strong indicator of decline in kidney function and is measured using histopathological assessment of kidney biopsy core. At present, a noninvasive test to assess IFTA is not available.ObjectiveTo develop and validate a deep learning (DL) algorithm to quantify IFTA from kidney ultrasonography images.Design, setting, and participantsThis was a single-center diagnostic study of consecutive patients who underwent native kidney biopsy at John H. Stroger Jr. Hospital of Cook County, Chicago, Illinois, between January 1, 2014, and December 31, 2018. A DL algorithm was trained, validated, and tested to classify IFTA from kidney ultrasonography images. Of 6135 Crimmins-filtered ultrasonography images, 5523 were used for training (5122 images) and validation (401 images), and 612 were used to test the accuracy of the DL system. Kidney segmentation was performed using the UNet architecture, and classification was performed using a convolution neural network-based feature extractor and extreme gradient boosting. IFTA scored by a nephropathologist on trichrome stained kidney biopsy slide was used as the reference standard. IFTA was divided into 4 grades (grade 1, 0%-24%; grade 2, 25%-49%; grade 3, 50%-74%; and grade 4, 75%-100%). Data analysis was performed from December 2019 to May 2020.Main outcomes and measuresPrediction of IFTA grade was measured using the metrics precision, recall, accuracy, and F1 score.ResultsThis study included 352 patients (mean [SD] age 47.43 [14.37] years), of whom 193 (54.82%) were women. There were 159 patients with IFTA grade 1 (2701 ultrasonography images), 74 patients with IFTA grade 2 (1239 ultrasonography images), 41 patients with IFTA grade 3 (701 ultrasonography images), and 78 patients with IFTA grade 4 (1494 ultrasonography images). Kidney ultrasonography images were segmented with 91% accuracy. In the independent test set, the point estimates for performance matrices showed precision of 0.8927 (95% CI, 0.8682-0.9172), recall of 0.8037 (95% CI, 0.7722-0.8352), accuracy of 0.8675 (95% CI, 0.8406-0.8944), and an F1 score of 0.8389 (95% CI, 0.8098-0.8680) at the image level. Corresponding estimates at the patient level were precision of 0.9003 (95% CI, 0.8644-0.9362), recall of 0.8421 (95% CI, 0.7984-0.8858), accuracy of 0.8955 (95% CI, 0.8589-0.9321), and an F1 score of 0.8639 (95% CI, 0.8228-0.9049). Accuracy at the patient level was highest for IFTA grade 1 and IFTA grade 4. The accuracy (approximately 90%) remained high irrespective of the timing of ultrasonography studies and the biopsy diagnosis. The predictive performance of the DL system did not show significant improvement when combined with baseline clinical characteristics.Conclusions and relevanceThese findings suggest that a DL algorithm can accurately and independently predict IFTA from kidney ultrasonography images.

Project description:ImportanceFor prostate cancer, Gleason grading of the biopsy specimen plays a pivotal role in determining case management. However, Gleason grading is associated with substantial interobserver variability, resulting in a need for decision support tools to improve the reproducibility of Gleason grading in routine clinical practice.ObjectiveTo evaluate the ability of a deep learning system (DLS) to grade diagnostic prostate biopsy specimens.Design, setting, and participantsThe DLS was evaluated using 752 deidentified digitized images of formalin-fixed paraffin-embedded prostate needle core biopsy specimens obtained from 3 institutions in the United States, including 1 institution not used for DLS development. To obtain the Gleason grade group (GG), each specimen was first reviewed by 2 expert urologic subspecialists from a multi-institutional panel of 6 individuals (years of experience: mean, 25 years; range, 18-34 years). A third subspecialist reviewed discordant cases to arrive at a majority opinion. To reduce diagnostic uncertainty, all subspecialists had access to an immunohistochemical-stained section and 3 histologic sections for every biopsied specimen. Their review was conducted from December 2018 to June 2019.Main outcomes and measuresThe frequency of the exact agreement of the DLS with the majority opinion of the subspecialists in categorizing each tumor-containing specimen as 1 of 5 categories: nontumor, GG1, GG2, GG3, or GG4-5. For comparison, the rate of agreement of 19 general pathologists' opinions with the subspecialists' majority opinions was also evaluated.ResultsFor grading tumor-containing biopsy specimens in the validation set (n = 498), the rate of agreement with subspecialists was significantly higher for the DLS (71.7%; 95% CI, 67.9%-75.3%) than for general pathologists (58.0%; 95% CI, 54.5%-61.4%) (P < .001). In subanalyses of biopsy specimens from an external validation set (n = 322), the Gleason grading performance of the DLS remained similar. For distinguishing nontumor from tumor-containing biopsy specimens (n = 752), the rate of agreement with subspecialists was 94.3% (95% CI, 92.4%-95.9%) for the DLS and similar at 94.7% (95% CI, 92.8%-96.3%) for general pathologists (P = .58).Conclusions and relevanceIn this study, the DLS showed higher proficiency than general pathologists at Gleason grading prostate needle core biopsy specimens and generalized to an independent institution. Future research is necessary to evaluate the potential utility of using the DLS as a decision support tool in clinical workflows and to improve the quality of prostate cancer grading for therapy decisions.

Project description:BackgroundMedication errors account for a large proportion of all medical errors. In most homes, patients take a variety of medications for a long period. However, medication errors frequently occur because patients often throw away the containers of their medications.ObjectiveWe proposed a deep learning-based system for reducing medication errors by accurately identifying prescription pills. Given the pill images, our system located the pills in the respective pill databases in South Korea and the United States.MethodsWe organized the system into a pill recognition step and pill retrieval step, and we applied deep learning models to train not only images of the pill but also imprinted characters. In the pill recognition step, there are 3 modules that recognize the 3 features of pills and their imprints separately and correct the recognized imprint to fit the actual data. We adopted image classification and text detection models for the feature and imprint recognition modules, respectively. In the imprint correction module, we introduced a language model for the first time in the pill identification system and proposed a novel coordinate encoding technique for effective correction in the language model. We identified pills using similarity scores of pill characteristics with those in the database.ResultsWe collected the open pill database from South Korea and the United States in May 2022. We used a total of 24,404 pill images in our experiments. The experimental results show that the predicted top-1 candidates achieve accuracy levels of 85.6% (South Korea) and 74.5% (United States) for the types of pills not trained on 2 different databases (South Korea and the United States). Furthermore, the predicted top-1 candidate accuracy of our system was 78% with consumer-granted images, which was achieved by training only 1 image per pill. The results demonstrate that our system could identify and retrieve new pills without additional model updates. Finally, we confirmed through an ablation study that the language model that we emphasized significantly improves the pill identification ability of the system.ConclusionsOur study proposes the possibility of reducing medical errors by showing that the introduction of artificial intelligence can identify numerous pills with high precision in real time. Our study suggests that the proposed system can reduce patients' misuse of medications and help medical staff focus on higher-level tasks by simplifying time-consuming lower-level tasks such as pill identification.

Project description:Importance:There is a lack of studies exploring the performance of a deep learning survival neural network in non-small cell lung cancer (NSCLC). Objectives:To compare the performances of DeepSurv, a deep learning survival neural network with a tumor, node, and metastasis staging system in the prediction of survival and test the reliability of individual treatment recommendations provided by the deep learning survival neural network. Design, Setting, and Participants:In this population-based cohort study, a deep learning-based algorithm was developed and validated using consecutive cases of newly diagnosed stages I to IV NSCLC between January 2010 and December 2015 in a Surveillance, Epidemiology, and End Results database. A total of 127 features, including patient characteristics, tumor stage, and treatment strategies, were assessed for analysis. The algorithm was externally validated on an independent test cohort, comprising 1182 patients with stage I to III NSCLC diagnosed between January 2009 and December 2013 in Shanghai Pulmonary Hospital. Analysis began January 2018 and ended June 2019. Main Outcomes and Measures:The deep learning survival neural network model was compared with the tumor, node, and metastasis staging system for lung cancer-specific survival. The C statistic was used to assess the performance of models. A user-friendly interface was provided to facilitate the survival predictions and treatment recommendations of the deep learning survival neural network model. Results:Of 17 322 patients with NSCLC included in the study, 13 361 (77.1%) were white and the median (interquartile range) age was 68 (61-74) years. The majority of tumors were stage I disease (10 273 [59.3%]) and adenocarcinoma (11 985 [69.2%]). The median (interquartile range) follow-up time was 24 (10-43) months. There were 3119 patients who had lung cancer-related death during the follow-up period. The deep learning survival neural network model showed more promising results in the prediction of lung cancer-specific survival than the tumor, node, and metastasis stage on the test data set (C statistic = 0.739 vs 0.706). The population who received the recommended treatments had superior survival rates than those who received treatments not recommended (hazard ratio, 2.99; 95% CI, 2.49-3.59; P < .001), which was verified by propensity score-matched groups. The deep learning survival neural network model visualization was realized by a user-friendly graphic interface. Conclusions and Relevance:The deep learning survival neural network model shows potential benefits in prognostic evaluation and treatment recommendation with respect to lung cancer-specific survival. This novel analytical approach may provide reliable individual survival information and treatment recommendations.

Project description:Renal pathology is essential for diagnosing and assessing the severity and prognosis of kidney diseases. Deep learning-based approaches have developed rapidly and have been applied in renal pathology. However, methods for the automated classification of normal and abnormal renal tubules remain scarce. Using a deep learning-based method, we aimed to classify normal and abnormal renal tubules, thereby assisting renal pathologists in the evaluation of renal biopsy specimens. Consequently, we developed a U-Net-based segmentation model using randomly selected regions obtained from 21 renal biopsy specimens. Further, we verified its performance in multiclass segmentation by calculating the Dice coefficients (DCs). We used 15 cases of tubulointerstitial nephritis to assess its applicability in aiding routine diagnoses conducted by renal pathologists and calculated the agreement ratio between diagnoses conducted by two renal pathologists and the time taken for evaluation. We also determined whether such diagnoses were improved when the output of segmentation was considered. The glomeruli and interstitium had the highest DCs, whereas the normal and abnormal renal tubules had intermediate DCs. Following the detailed evaluation of the tubulointerstitial compartments, the proximal, distal, atrophied, and degenerated tubules had intermediate DCs, whereas the arteries and inflamed tubules had low DCs. The annotation and output areas involving normal and abnormal tubules were strongly correlated in each class. The pathological concordance for the glomerular count, t, ct, and ci scores of the Banff classification of renal allograft pathology remained high with or without the segmented images. However, in terms of time consumption, the quantitative assessment of tubulitis, tubular atrophy, degenerated tubules, and the interstitium was improved significantly when renal pathologists considered the segmentation output. Deep learning algorithms can assist renal pathologists in the classification of normal and abnormal tubules in renal biopsy specimens, thereby facilitating the enhancement of renal pathology and ensuring appropriate clinical decisions.

Project description:BackgroundRetinal vascular diseases, including diabetic macular edema (DME), neovascular age-related macular degeneration (nAMD), myopic choroidal neovascularization (mCNV), and branch and central retinal vein occlusion (BRVO/CRVO), are considered vision-threatening eye diseases. However, accurate diagnosis depends on multimodal imaging and the expertise of retinal ophthalmologists.ObjectiveThe aim of this study was to develop a deep learning model to detect treatment-requiring retinal vascular diseases using multimodal imaging.MethodsThis retrospective study enrolled participants with multimodal ophthalmic imaging data from 3 hospitals in Taiwan from 2013 to 2019. Eye-related images were used, including those obtained through retinal fundus photography, optical coherence tomography (OCT), and fluorescein angiography with or without indocyanine green angiography (FA/ICGA). A deep learning model was constructed for detecting DME, nAMD, mCNV, BRVO, and CRVO and identifying treatment-requiring diseases. Model performance was evaluated and is presented as the area under the curve (AUC) for each receiver operating characteristic curve.ResultsA total of 2992 eyes of 2185 patients were studied, with 239, 1209, 1008, 211, 189, and 136 eyes in the control, DME, nAMD, mCNV, BRVO, and CRVO groups, respectively. Among them, 1898 eyes required treatment. The eyes were divided into training, validation, and testing groups in a 5:1:1 ratio. In total, 5117 retinal fundus photos, 9316 OCT images, and 20,922 FA/ICGA images were used. The AUCs for detecting mCNV, DME, nAMD, BRVO, and CRVO were 0.996, 0.995, 0.990, 0.959, and 0.988, respectively. The AUC for detecting treatment-requiring diseases was 0.969. From the heat maps, we observed that the model could identify retinal vascular diseases.ConclusionsOur study developed a deep learning model to detect retinal diseases using multimodal ophthalmic imaging. Furthermore, the model demonstrated good performance in detecting treatment-requiring retinal diseases.

Dataset Information

Development and Validation of a Deep Learning Model to Quantify Glomerulosclerosis in Kidney Biopsy Specimens.

Importance

Objective

Design, setting, and participants

Main outcomes and measures

Results

Conclusions and relevance

Publications

Development and Validation of a Deep Learning Model to Quantify Glomerulosclerosis in Kidney Biopsy Specimens.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets