Evaluating tubulointerstitial compartments in renal biopsy specimens using a deep learning-based approach for classifying normal and abnormal tubules
Ontology highlight
ABSTRACT:
SUBMITTER: Hara S
PROVIDER: S-EPMC9273082 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundEndocytoscopy (ECS) provides a magnification of approximately 450× for real-time observation of lesion nuclei. Using ECS, we aimed to evaluate whether sufficient samples for diagnosis can be obtained during bronchoscopy. We also investigated whether ECS can enable two-class diagnosis of malignant or non-malignant transbronchial biopsy specimens in real-time during bronchoscopy.MethodsThis was a single-facility, prospective, observational, ex vivo study. Forty cases with localized peripheral pulmonary lesions underwent transbronchial biopsy with endobronchial ultrasonography using a guide sheath. Each biopsy specimen was immediately observed and evaluated endocytoscopically after the collection by the bronchoscopic procedure.ResultsThirty-seven cases were enrolled. The diagnostic accuracy achieved by ECS was 91.9% (34/37). The agreement rate between the endocytoscopic evaluation and pathological diagnosis of each specimen (170 specimens) was 65.3% (111/170). The median time required for endocytoscopic evaluation per specimen was 70 s. When we judged a specimen to be malignant a second time on ECS evaluations of five specimens in one case, pathologically malignant specimens were collected in 26 of 27 cases (96.3%).ConclusionsECS with methylene blue staining may aid in the two-class diagnosis of malignant or non-malignant transbronchial biopsy specimens during bronchoscopy. This may reduce the number of tissue biopsies.
| S-EPMC9834692 | biostudies-literature
Project description:ImportanceA 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.ObjectiveTo 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 participantsThis 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 measuresCorrelation 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.ResultsThe 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 relevanceThe 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.
| S-EPMC7818108 | biostudies-literature
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.
| S-EPMC7378872 | biostudies-literature
Project description:BackgroundAutosomal dominant tubulointerstitial kidney disease (ADTKD) is a rare hereditary disease caused by a variety of genetic mutations. Carriers of a mutation in the responsible genes are at risk of reaching end-stage kidney disease typically in middle age. The frequency of this disease is assumed to be underestimated because of a lack of disease-specific signs. Pathological findings obtained from kidney of uromodulin related ADTKD (ADTKD-UMOD) patients are regarded as non-specific and less-informative for its diagnosis. This research was undertaken to evaluate the significance of kidney biopsy in ADTKD-UMOD patients.MethodsThirteen patients from 10 families with nine identified uromodulin (UMOD) gene mutations who underwent kidney biopsy in the past were studied. Their kidney tissues were stained with anti-UMOD antibody in addition to conventional methods such as PAS staining. When positive, the numbers of tubules with visible UMOD protein accumulations were calculated based on the total numbers of UMOD expressing tubules. Pathological findings such as tubulointerstitial fibrosis, atrophy, inflammation and glomerulosclerosis were also evaluated and analyzed.ResultsInterstitial fibrosis and tubular atrophy were present in all 13 patients. Most atrophic tubules with thickening and lamellation of tubular basement membranes showed negative UMOD staining. In all but two patients with C94F mutations, massive accumulation of UMOD proteins was observed in the renal endoplasmic reticulum. UMOD accumulations were also detectable by PAS staining as polymorphic unstructured materials in the 11 patients at frequencies of 2.6-53.4%. 80.4% of the UMOD accumulations were surrounded by halos. The detection rate of UMOD accumulations positively correlated with eGFR. Glomerulosclerosis was detected in 11/13 patients, with a frequency of 20.0 to 61.1%, while no cystic dilatations of glomeruli were detected.ConclusionsMassively accumulated UMOD proteins in ADTKD-UMOD kidneys are detectable not only by immunostaining using anti-UMOD antibody but also by conventional methods such as PAS staining, although their detection is not easy. These findings can provide important clues to the diagnosis of ADTKD-UMOD. Kidney biopsy in ADTKD-UMOD may be more informative than assumed previously.
| S-EPMC7784305 | biostudies-literature
Project description:BackgroundHysteroscopy is a commonly used technique for diagnosing endometrial lesions. It is essential to develop an objective model to aid clinicians in lesion diagnosis, as each type of lesion has a distinct treatment, and judgments of hysteroscopists are relatively subjective. This study constructs a convolutional neural network model that can automatically classify endometrial lesions using hysteroscopic images as input.MethodsAll histopathologically confirmed endometrial lesion images were obtained from the Shengjing Hospital of China Medical University, including endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyps, and submucous myomas. The study included 1851 images from 454 patients. After the images were preprocessed (histogram equalization, addition of noise, rotations, and flips), a training set of 6478 images was input into a tuned VGGNet-16 model; 250 images were used as the test set to evaluate the model's performance. Thereafter, we compared the model's results with the diagnosis of gynecologists.ResultsThe overall accuracy of the VGGNet-16 model in classifying endometrial lesions is 80.8%. Its sensitivity to endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyp, and submucous myoma is 84.0%, 68.0%, 78.0%, 94.0%, and 80.0%, respectively; for these diagnoses, the model's specificity is 92.5%, 95.5%, 96.5%, 95.0%, and 96.5%, respectively. When classifying lesions as benign or as premalignant/malignant, the VGGNet-16 model's accuracy, sensitivity, and specificity are 90.8%, 83.0%, and 96.0%, respectively. The diagnostic performance of the VGGNet-16 model is slightly better than that of the three gynecologists in both classification tasks. With the aid of the model, the overall accuracy of the diagnosis of endometrial lesions by gynecologists can be improved.ConclusionsThe VGGNet-16 model performs well in classifying endometrial lesions from hysteroscopic images and can provide objective diagnostic evidence for hysteroscopists.
| S-EPMC7788977 | biostudies-literature
Project description:Melanoma is the least common form of skin cancer, but accounts for the most deaths. Dermatopathologists face difficult diganostic determinations with a subset of ambiguous melanoma cases. Copy number variation in melanoma can serve as an additional biomarker to distinguish melanoma from benign melanocytic lesions.
2016-04-22 | GSE68476 | GEO
Project description:ImportanceA breast pathology diagnosis provides the basis for clinical treatment and management decisions; however, its accuracy is inadequately understood.ObjectivesTo quantify the magnitude of diagnostic disagreement among pathologists compared with a consensus panel reference diagnosis and to evaluate associated patient and pathologist characteristics.Design, setting, and participantsStudy of pathologists who interpret breast biopsies in clinical practices in 8 US states.ExposuresParticipants independently interpreted slides between November 2011 and May 2014 from test sets of 60 breast biopsies (240 total cases, 1 slide per case), including 23 cases of invasive breast cancer, 73 ductal carcinoma in situ (DCIS), 72 with atypical hyperplasia (atypia), and 72 benign cases without atypia. Participants were blinded to the interpretations of other study pathologists and consensus panel members. Among the 3 consensus panel members, unanimous agreement of their independent diagnoses was 75%, and concordance with the consensus-derived reference diagnoses was 90.3%.Main outcomes and measuresThe proportions of diagnoses overinterpreted and underinterpreted relative to the consensus-derived reference diagnoses were assessed.ResultsSixty-five percent of invited, responding pathologists were eligible and consented to participate. Of these, 91% (N = 115) completed the study, providing 6900 individual case diagnoses. Compared with the consensus-derived reference diagnosis, the overall concordance rate of diagnostic interpretations of participating pathologists was 75.3% (95% CI, 73.4%-77.0%; 5194 of 6900 interpretations). Among invasive carcinoma cases (663 interpretations), 96% (95% CI, 94%-97%) were concordant, and 4% (95% CI, 3%-6%) were underinterpreted; among DCIS cases (2097 interpretations), 84% (95% CI, 82%-86%) were concordant, 3% (95% CI, 2%-4%) were overinterpreted, and 13% (95% CI, 12%-15%) were underinterpreted; among atypia cases (2070 interpretations), 48% (95% CI, 44%-52%) were concordant, 17% (95% CI, 15%-21%) were overinterpreted, and 35% (95% CI, 31%-39%) were underinterpreted; and among benign cases without atypia (2070 interpretations), 87% (95% CI, 85%-89%) were concordant and 13% (95% CI, 11%-15%) were overinterpreted. Disagreement with the reference diagnosis was statistically significantly higher among biopsies from women with higher (n = 122) vs lower (n = 118) breast density on prior mammograms (overall concordance rate, 73% [95% CI, 71%-75%] for higher vs 77% [95% CI, 75%-80%] for lower, P < .001), and among pathologists who interpreted lower weekly case volumes (P < .001) or worked in smaller practices (P = .034) or nonacademic settings (P = .007).Conclusions and relevanceIn this study of pathologists, in which diagnostic interpretation was based on a single breast biopsy slide, overall agreement between the individual pathologists' interpretations and the expert consensus-derived reference diagnoses was 75.3%, with the highest level of concordance for invasive carcinoma and lower levels of concordance for DCIS and atypia. Further research is needed to understand the relationship of these findings with patient management.
| S-EPMC4516388 | biostudies-literature
Project description:AimsTo investigate the relationship between the progression of anaemia and renal pathological findings in patients with diabetic nephropathy.MethodsA total of 223 patients with diabetes underwent renal biopsy from 1985 to 2010 and were confirmed to have pure diabetic nephropathy according to the recent classification, of whom 113 (baseline haemoglobin ≥ 11 g/dl) were enrolled in the study. Linear regression analysis was used to estimate the changes in haemoglobin levels during the follow-up period.ResultsIn a multivariate model adjusted for clinical and histopathological variables, higher interstitial fibrosis and tubular atrophy scores were more strongly associated with a decrease in haemoglobin levels than were lower scores. Compared with an interstitial fibrosis and tubular atrophy score of 0, the standardized coefficients for interstitial fibrosis and tubular atrophy scores of 1, 2 and 3 were 0.20 (95% CI -0.31 to 0.93), 0.34 (95% CI -0.22 to 1.34) and 0.47 (95% CI 0.07 to 1.96), respectively, whereas a higher glomerular class, a higher vascular lesion score and the presence of exudative lesions were not strongly correlated with the decrease in haemoglobin.ConclusionsTubulointerstitial lesions that are more advanced are significantly associated with the progression of anaemia in patients with diabetic nephropathy after adjustment for numerous covariates. This finding suggests that tubulointerstitial lesions may be a useful prognostic indicator for anaemia in patients with diabetic nephropathy, and that decreased erythropoietin production attributable to the progression of tubulointerstitial lesions is a major cause of anaemia in these patients.
| S-EPMC4407915 | biostudies-literature
Project description:BackgroundRenal tubules and interstitium are vulnerable to injury and play a central role in the progression of various chronic kidney diseases (CKDs). However, high quality epidemiologic study on the profiles of biopsy-proven tubulointerstitial lesions (TILs) is extremely limited.MethodsWe conducted a retrospective renal biopsy series including 62,569 native biopsies at 1,211 hospitals across China from 2015 to 2017. The TILs, including the shedding of tube epithelial, renal tubular atrophy, renal interstitial fibrosis, edema and inflammatory infiltration, were identified from the pathological report. We analyzed the severity and chronicity of TILs stratified by gender, age groups, biopsy indications, and concurrent glomerular diseases. We also examined the correlation between TIL and glomerulosclerosis.ResultsOf 56,880 patients with biopsy-proven glomerular disease, 79.5% had TILs. Renal interstitial inflammatory infiltration was the most common type of TIL (77.7%), followed by renal tubular atrophy (56.0%) and renal interstitial fibrosis (32.8%). Severe and chronic TILs were more common in adults than in children. The three glomerular diseases with the highest proportion of moderate-to-severe and chronic TIL were diabetic nephropathy, immunoglobulin A (IgA) nephropathy and focal segmental glomerulosclerosis. The severity of TILs was moderately correlated with glomerulosclerosis score (r=0.51). Moderate-to-severe and chronic TIL were more common in southern China. After adjusting for age, sex, hospital level, region, biopsy indication and type of concurrent glomerular diseases, adults with renal arteriole injury had a six-fold higher risk of moderate-to-severe TIL [odds ratio (OR), 7.12; 95% confidence interval (CI), 6.42 to 7.91] and a three-fold higher risk of chronic TIL (OR, 4.58; 95% CI, 4.37 to 4.79).ConclusionsTILs were common in patients with biopsy-proven glomerular disease. The type and severity of TILs varied with age, region and concurrent glomerular diseases. Renal arteriole injury and glomerulosclerosis was associated with a significantly increased risk of TIL.
| S-EPMC7575977 | biostudies-literature
Project description:BackgroundAutomated text classification has many important applications in the clinical setting; however, obtaining labelled data for training machine learning and deep learning models is often difficult and expensive. Active learning techniques may mitigate this challenge by reducing the amount of labelled data required to effectively train a model. In this study, we analyze the effectiveness of 11 active learning algorithms on classifying subsite and histology from cancer pathology reports using a Convolutional Neural Network as the text classification model.ResultsWe compare the performance of each active learning strategy using two differently sized datasets and two different classification tasks. Our results show that on all tasks and dataset sizes, all active learning strategies except diversity-sampling strategies outperformed random sampling, i.e., no active learning. On our large dataset (15K initial labelled samples, adding 15K additional labelled samples each iteration of active learning), there was no clear winner between the different active learning strategies. On our small dataset (1K initial labelled samples, adding 1K additional labelled samples each iteration of active learning), marginal and ratio uncertainty sampling performed better than all other active learning techniques. We found that compared to random sampling, active learning strongly helps performance on rare classes by focusing on underrepresented classes.ConclusionsActive learning can save annotation cost by helping human annotators efficiently and intelligently select which samples to label. Our results show that a dataset constructed using effective active learning techniques requires less than half the amount of labelled data to achieve the same performance as a dataset constructed using random sampling.
| S-EPMC7941989 | biostudies-literature