Using deep learning to detect patients at risk for prostate cancer despite benign biopsies.
Ontology highlight
ABSTRACT:
SUBMITTER: Liu B
PROVIDER: S-EPMC9272383 | biostudies-literature | 2022 Jul
REPOSITORIES: biostudies-literature
Publications
Using deep learning to detect patients at risk for prostate cancer despite benign biopsies.
Liu Bojing B Wang Yinxi Y Weitz Philippe P Lindberg Johan J Hartman Johan J Wang Wanzhong W Egevad Lars L Grönberg Henrik H Eklund Martin M Rantalainen Mattias M
iScience 20220623 7
Routine transrectal ultrasound-guided systematic prostate biopsy only samples a small volume of the prostate and tumors between biopsy cores can be missed, leading to low sensitivity to detect clinically relevant prostate cancers (PCa). Deep learning may enable detection of PCa despite benign biopsies. We included 14,354 hematoxylin-eosin stained benign prostate biopsies from 1,508 men in two groups: men without established PCa diagnosis and men with at least one core biopsy diagnosed with PCa. ...[more]
Similar Datasets
Project description:BackgroundTelomere shortening is linked to aging and may be associated with increased risk for cancer. Most cancer studies have used telomere length in leukocytes rather than in the target tissue of cancer origin.MethodsA case-control study of 524 case-control pairs with a benign prostate biopsy nested within a historical cohort of 10,478 men was conducted to determine whether premalignant prostate telomere length (assessed using a modified qRT-PCR) is associated with prostate cancer risk.ResultsTelomere lengths in benign prostate biopsies of cases versus controls were similar (1.46 ± 0.38 vs. 1.45 ± 0.42; P = 0.49). African American (AA) men had significantly shorter telomeres compared with White men (1.51 ± 0.38 vs. 1.63 ± 0.39; P < 0.0001). In race-stratified analyses, increasing telomere length was more strongly associated with prostate cancer risk in White men, wherein those with telomere length in the highest quartile had 1.9-fold greater adjusted risk of prostate cancer compared with men with prostate telomere lengths in the lowest quartile [OR = 1.90; 95% confidence interval (CI) = 1.08-3.36]. Men in the highest telomere length quartile also had a greater risk of aggressive prostate cancer compared with men with telomere lengths in the lowest quartile (OR = 2.78; 95% CI = 1.25-6.19).ConclusionsWhite men have longer telomeres in benign prostate tissue compared with AA men, and those with the longest telomeres may be at increased risk for prostate cancer, particularly the more aggressive form of the disease.ImpactRace-specific telomere length measures may be an early biomarker of aggressive prostate cancer.
| S-EPMC9081233 | biostudies-literature
Project description:ObjectivesRisk calculators (RCs) improve patient selection for prostate biopsy with clinical/demographic information, recently with prostate MRI using the prostate imaging reporting and data system (PI-RADS). Fully-automated deep learning (DL) analyzes MRI data independently, and has been shown to be on par with clinical radiologists, but has yet to be incorporated into RCs. The goal of this study is to re-assess the diagnostic quality of RCs, the impact of replacing PI-RADS with DL predictions, and potential performance gains by adding DL besides PI-RADS.Material and methodsOne thousand six hundred twenty-seven consecutive examinations from 2014 to 2021 were included in this retrospective single-center study, including 517 exams withheld for RC testing. Board-certified radiologists assessed PI-RADS during clinical routine, then systematic and MRI/Ultrasound-fusion biopsies provided histopathological ground truth for significant prostate cancer (sPC). nnUNet-based DL ensembles were trained on biparametric MRI predicting the presence of sPC lesions (UNet-probability) and a PI-RADS-analogous five-point scale (UNet-Likert). Previously published RCs were validated as is; with PI-RADS substituted by UNet-Likert (UNet-Likert-substituted RC); and with both UNet-probability and PI-RADS (UNet-probability-extended RC). Together with a newly fitted RC using clinical data, PI-RADS and UNet-probability, existing RCs were compared by receiver-operating characteristics, calibration, and decision-curve analysis.ResultsDiagnostic performance remained stable for UNet-Likert-substituted RCs. DL contained complementary diagnostic information to PI-RADS. The newly-fitted RC spared 49% [252/517] of biopsies while maintaining the negative predictive value (94%), compared to PI-RADS ≥ 4 cut-off which spared 37% [190/517] (p < 0.001).ConclusionsIncorporating DL as an independent diagnostic marker for RCs can improve patient stratification before biopsy, as there is complementary information in DL features and clinical PI-RADS assessment.Clinical relevance statementFor patients with positive prostate screening results, a comprehensive diagnostic workup, including prostate MRI, DL analysis, and individual classification using nomograms can identify patients with minimal prostate cancer risk, as they benefit less from the more invasive biopsy procedure.Key pointsThe current MRI-based nomograms result in many negative prostate biopsies. The addition of DL to nomograms with clinical data and PI-RADS improves patient stratification before biopsy. Fully automatic DL can be substituted for PI-RADS without sacrificing the quality of nomogram predictions. Prostate nomograms show cancer detection ability comparable to previous validation studies while being suitable for the addition of DL analysis.
| S-EPMC11557625 | biostudies-literature
Project description:Artificial intelligence as a screening tool for eyelid lesions will be helpful for early diagnosis of eyelid malignancies and proper decision-making. This study aimed to evaluate the performance of a deep learning model in differentiating eyelid lesions using clinical eyelid photographs in comparison with human ophthalmologists. We included 4954 photographs from 928 patients in this retrospective cross-sectional study. Images were classified into three categories: malignant lesion, benign lesion, and no lesion. Two pre-trained convolutional neural network (CNN) models, DenseNet-161 and EfficientNetV2-M architectures, were fine-tuned to classify images into three or two (malignant versus benign) categories. For a ternary classification, the mean diagnostic accuracies of the CNNs were 82.1% and 83.0% using DenseNet-161 and EfficientNetV2-M, respectively, which were inferior to those of the nine clinicians (87.0-89.5%). For the binary classification, the mean accuracies were 87.5% and 92.5% using DenseNet-161 and EfficientNetV2-M models, which was similar to that of the clinicians (85.8-90.0%). The mean AUC of the two CNN models was 0.908 and 0.950, respectively. Gradient-weighted class activation map successfully highlighted the eyelid tumors on clinical photographs. Deep learning models showed a promising performance in discriminating malignant versus benign eyelid lesions on clinical photographs, reaching the level of human observers.
| S-EPMC10011394 | biostudies-literature
Project description:Tumor biopsy is one of the most widely used materials in cancer diagnoses and molecular studies, where the purity of the biopsies (i.e., proportion of cells that are cancerous) is crucial for both applications. However, conventional approaches for tumor biopsy purity evaluation require experienced pathologists and/or various materials/experiments therefore were time-consuming and error prone. Rapid, easy-to-perform and cost-effective methods are thus still of demand. Recent studies had demonstrated that molecular signatures were informative to this task. Previously, we had developed GeneCT, a deep learning-based cancerous status and tissue-of-origin classifier for pan-tumor/tissue biopsies. In the current work, we applied GeneCT on datasets collected from various groups, where the experimental protocols and cancer types differed from each other. We found that GeneCT showed high accuracies on most datasets; for samples with unexpected results, in-depth investigations suggested that they might suffer from imperfect purity. In silico mixture experiments further showed that GeneCT classification was highly indicative in predicting the purity of the tumor biopsies. Considering that transcriptome profiling is a common and inexpensive experiment in molecular cancer studies, our deep learning-based GeneCT could thus serve as a valuable tool for rapid, preliminary tumor biopsy purity assessment.
| S-EPMC7352054 | biostudies-literature
Project description:Histopathologic grading of prostate cancer using Gleason patterns (GPs) is subject to a large inter-observer variability, which may result in suboptimal treatment of patients. With the introduction of digitization and whole-slide images of prostate biopsies, computer-aided grading becomes feasible. Computer-aided grading has the potential to improve histopathological grading and treatment selection for prostate cancer. Automated detection of GPs and determination of the grade groups (GG) using a convolutional neural network. In total, 96 prostate biopsies from 38 patients are annotated on pixel-level. Automated detection of GP 3 and GP ≥ 4 in digitized prostate biopsies is performed by re-training the Inception-v3 convolutional neural network (CNN). The outcome of the CNN is subsequently converted into probability maps of GP ≥ 3 and GP ≥ 4, and the GG of the whole biopsy is obtained according to these probability maps. Differentiation between non-atypical and malignant (GP ≥ 3) areas resulted in an accuracy of 92% with a sensitivity and specificity of 90 and 93%, respectively. The differentiation between GP ≥ 4 and GP ≤ 3 was accurate for 90%, with a sensitivity and specificity of 77 and 94%, respectively. Concordance of our automated GG determination method with a genitourinary pathologist was obtained in 65% (κ = 0.70), indicating substantial agreement. A CNN allows for accurate differentiation between non-atypical and malignant areas as defined by GPs, leading to a substantial agreement with the pathologist in defining the GG.
| S-EPMC6611751 | biostudies-literature
Project description:Background: Radiotherapy is an effective treatment of intermediate/high-risk locally advanced prostate cancer, however,>30% of patients relapse within 5 years. Clinicopathological parameters currently fail to identify patients prone to systemic relapse and those whom treatment intensification may be beneficial. The purpose of this study was to independently validate prognostics assays in a cohort of diagnostic biopsies from patients treated with radical radiotherapy and androgen deprivation therapy. Patients and methods: Independent clinical validation in a cohort of diagnostic biopsies from patients treated with radical radiotherapy and androgen deprivation therapy. Multivariable Cox proportional hazard regression analysis was used to assess assay performance in predicting biochemical failure-free survival (BFFS) and metastasis free survival (MFS). Results: Gene expression analysis was carried out in 248 patients from the independent validation cohort and the Metastatic Assay applied. Ten-year MFS was 72% for Metastatic Assay positive patients and 94% for Metastatic Assay negative patients [HR 3.21 (1.35–7.67); P=0.003]. On multivariable analysis the Metastatic Assay remained predictive for development of distant metastases [HR 2.71 (1.11–6.63); P=0.030]. The assay retained independent prognostic performance for MFS when assessed with the Cancer of the Prostate Assessment Score (CAPRA) [HR 3.23 (1.22–8.59); P=0.019] whilst CAPRA itself was not significant [HR 1.88, (0.52–6.77); P=0.332]. Conclusions: The Metastatic Assay demonstrated significant prognostic performance in patients treated with radical radiotherapy both alone and independent of standard clinical and pathological variables. The Metastatic Assay could have clinical utility when deciding upon treatment intensification in high-risk patients.
2018-07-12 | GSE116918 | GEO
Project description:More than 1 million women per year in the United States with benign breast biopsies are known to be at elevated risk for breast cancer (BC), with risk stratified on histologic categories of epithelial proliferation. Here we assessed women who had serial benign biopsies over time and how changes in the histologic classification affected BC risk. In the Mayo Clinic Benign Breast Disease Cohort of 13 466 women, 1414 women had multiple metachronous benign biopsies (10.5%). Both initial and subsequent biopsies were assessed histologically. BC risk for clinical and prognostic factors was assessed using subdistribution models to account for competing risks, and logistic regression/Wilcoxon/chi-square tests to assess covariates. All statistical tests were two-sided. Breast cancer risk for women with serial biopsies, stratified by histologic category in the later biopsies, was similar to women with a single biopsy. We found that changes in histological category between initial and subsequent biopsy statistically significantly impacted BC risk. Women with nonproliferative initial findings and subsequent proliferative findings had an increased risk (hazard ratio [HR] = 1.77, 95% confidence interval [CI] = 1.06 to 2.94, P = .03) compared with no change. Among women with proliferative disease without atypia at initial biopsy, risk decreased if later biopsy regressed to nonproliferative (HR = 0.49, 95% CI = 0.25 to 0.98) and increased if later biopsy showed progression to atypical hyperplasia (HR = 1.49, 95% CI = 0.73 to 3.05) compared with no change ( P = .04). We found that breast cancer risk increases in women with progressive epithelial proliferation over time and decreases in women whose biopsies show less proliferation. This finding has important implications for effective clinical management of the 100 000 women per year who have multiple benign breast biopsies.
| S-EPMC5412118 | biostudies-literature
Project description:Morphologic examination of tissue biopsies is essential for histopathological diagnosis. However, accurate and scalable cellular quantification in human samples remains challenging. Here, we present a deep learning-based approach for antigen-specific cellular morphometrics in human kidney biopsies, which combines indirect immunofluorescence imaging with U-Net-based architectures for image-to-image translation and dual segmentation tasks, achieving human-level accuracy. In the kidney, podocyte loss represents a hallmark of glomerular injury and can be estimated in diagnostic biopsies. Thus, we profiled over 27,000 podocytes from 110 human samples, including patients with antineutrophil cytoplasmic antibody-associated glomerulonephritis (ANCA-GN), an immune-mediated disease with aggressive glomerular damage and irreversible loss of kidney function. We identified previously unknown morphometric signatures of podocyte depletion in patients with ANCA-GN, which allowed patient classification and, in combination with routine clinical tools, showed potential for risk stratification. Our approach enables robust and scalable molecular morphometric analysis of human tissues, yielding deeper biological insights into the human kidney pathophysiology.
| S-EPMC8119189 | biostudies-literature
Project description:PurposeTo characterize associations of microcalcifications (calcs) with benign breast disease lesion subtypes and assess whether tissue calcs affect risks of ductal carcinoma in situ (DCIS) and invasive breast cancer (IBC).MethodsWe analyzed detailed histopathologic data for 4,819 BBD biopsies from a single institution cohort (2002-2013) followed for DCIS or IBC for a median of 7.4 years for cases (N = 338) and 11.2 years for controls. Natural language processing was used to identify biopsies containing calcs based on pathology reports. Univariable and multivariable regression models were applied to assess associations with BBD lesion type and age-adjusted Cox proportional hazard regressions were performed to model risk of IBC or DCIS stratified by the presence or absence of calcs.ResultsCalcs were identified in 2063 (42.8%) biopsies. Calcs were associated with older age at BBD diagnosis (56.2 versus 49.0 years; P < 0.001). Overall, the risk of developing IBC or DCIS did not differ significantly between patients with calcs (HR 1.13, 95% CI 0.90, 1.41) as compared to patients without calcs. Stratification by BBD severity or subtype, age at BBD biopsy, outcomes of IBC versus DCIS, and mammography technique (screen-film versus full-field digital mammography) did not significantly alter association between calcs and risk.ConclusionOur analysis of calcs in BBD biopsies did not find a significant association between calcs and risk of breast cancer.
| S-EPMC11574978 | biostudies-literature
Project description:Gleason grading, a risk stratification method for prostate cancer, is subjective and dependent on experience and expertise of the reporting pathologist. Deep Learning (DL) systems have shown promise in enhancing the objectivity and efficiency of Gleason grading. However, DL networks exhibit domain shift and reduced performance on Whole Slide Images (WSI) from a source other than training data. We propose a DL approach for segmenting and grading epithelial tissue using a novel training methodology that learns domain agnostic features. In this retrospective study, we analyzed WSI from three cohorts of prostate cancer patients. 3741 core needle biopsies (CNBs) received from two centers were used for training. The κquad (quadratic-weighted kappa) and AUC were measured for grade group comparison and core-level detection accuracy, respectively. Accuracy of 89.4% and κquad of 0.92 on the internal test set of 425 CNB WSI and accuracy of 85.3% and κquad of 0.96 on an external set of 1201 images, was observed. The system showed an accuracy of 83.1% and κquad of 0.93 on 1303 WSI from the third institution (blind evaluation). Our DL system, used as an assistive tool for CNB review, can potentially improve the consistency and accuracy of grading, resulting in better patient outcomes.
| S-EPMC8888647 | biostudies-literature