scholarly journals Quality control stress test for deep learning-based diagnostic model in digital pathology

2021 ◽  
Author(s):  
Birgid Schömig-Markiefka ◽  
Alexey Pryalukhin ◽  
Wolfgang Hulla ◽  
Andrey Bychkov ◽  
Junya Fukuoka ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cancer Detection ◽  
Stress Testing ◽  
Computational Analysis ◽  
Stress Test ◽  
Digital Pathology ◽  
Model Performance ◽  
Diagnostic Model ◽  
Model Accuracy ◽  
Diagnostic Models

AbstractDigital pathology provides a possibility for computational analysis of histological slides and automatization of routine pathological tasks. Histological slides are very heterogeneous concerning staining, sections’ thickness, and artifacts arising during tissue processing, cutting, staining, and digitization. In this study, we digitally reproduce major types of artifacts. Using six datasets from four different institutions digitized by different scanner systems, we systematically explore artifacts’ influence on the accuracy of the pre-trained, validated, deep learning-based model for prostate cancer detection in histological slides. We provide evidence that any histological artifact dependent on severity can lead to a substantial loss in model performance. Strategies for the prevention of diagnostic model accuracy losses in the context of artifacts are warranted. Stress-testing of diagnostic models using synthetically generated artifacts might be an essential step during clinical validation of deep learning-based algorithms.

scholarly journals Adversarial Attack Vulnerability of Deep Learning Models for Oncologic Images

2021 ◽  
Author(s):  
Marina Z. Joel ◽  
Sachin Umrao ◽  
Enoch Chang ◽  
Rachel Choi ◽  
Daniel Yang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Model Performance ◽  
Predictive Ability ◽  
Model Accuracy ◽  
Image Domain ◽  
Attack Model ◽  
Highly Sensitive ◽  
Adversarial Training ◽  
Adversarial Attack ◽  
Magnetic Resonance Imaging Mri

AbstractBackgroundDeep learning (DL) models have shown promise to automate the classification of medical images used for cancer detection. Unfortunately, recent studies have found that DL models are vulnerable to adversarial attacks, which manipulate images with small pixel-level perturbations designed to cause models to misclassify images. There is a need for better understanding of how adversarial attacks impact the predictive ability of DL models in the medical image domain.MethodsWe examined adversarial attacks on DL classification models separately trained on three medical imaging modalities commonly used in oncology: computed tomography (CT), mammography, and magnetic resonance imaging (MRI). We investigated how iterative adversarial training could be employed to increase model robustness against three first-order attack methods.ResultsOn unmodified images, we achieved classification accuracies of 75.4% for CT, 76.4% accuracy for mammogram, and 93.6% for MRI. Under adversarial attack, model accuracy showed a maximum absolute decrease of 49.8% for CT, 52.9% for mammogram, 87.3% for MRI. Adversarial training caused model accuracy on adversarial images to increase by up to 42.9% for CT, 35.7% for mammogram, and 73.2% for MRI.ConclusionOur results indicated that DL models for oncologic images are highly sensitive to adversarial attacks, as visually imperceptible degrees of perturbation are sufficient to deceive the model the majority of the time. Adversarial training mitigated the effect of adversarial attacks on model performance but was less successful against stronger attacks. Our findings provide a useful basis for designing more robust and accurate medical DL models as well as techniques to defend models from adversarial attack.

scholarly journals Deep Learning Based Syndrome Diagnosis of Chronic Gastritis

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Guo-Ping Liu ◽  
Jian-Jun Yan ◽  
Yi-Qin Wang ◽  
Wu Zheng ◽  
Tao Zhong ◽  
...  
Keyword(s):  
Deep Learning ◽  
Clinical Practice ◽  
Chronic Gastritis ◽  
Diagnostic Model ◽  
Nonlinear Relationship ◽  
Cognitive Perspective ◽  
Multilabel Learning ◽  
Diagnostic Models ◽  
Syndrome Diagnosis ◽  
The Brain

In Traditional Chinese Medicine (TCM), most of the algorithms used to solve problems of syndrome diagnosis are superficial structure algorithms and not considering the cognitive perspective from the brain. However, in clinical practice, there is complex and nonlinear relationship between symptoms (signs) and syndrome. So we employed deep leaning and multilabel learning to construct the syndrome diagnostic model for chronic gastritis (CG) in TCM. The results showed that deep learning could improve the accuracy of syndrome recognition. Moreover, the studies will provide a reference for constructing syndrome diagnostic models and guide clinical practice.

scholarly journals xDEEP-MSI: Explainable Bias-Rejecting Microsatellite Instability Deep Learning System in Colorectal Cancer

Biomolecules ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 1786
Author(s):  
Aurelia Bustos ◽  
Artemio Payá ◽  
Andrés Torrubia ◽  
Rodrigo Jover ◽  
Xavier Llor ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Deep Learning ◽  
Microsatellite Instability ◽  
Digital Pathology ◽  
Model Performance ◽  
Tissue Microarrays ◽  
Learning System ◽  
Batch Effects ◽  
Patient Level ◽  
The Impact

The prediction of microsatellite instability (MSI) using deep learning (DL) techniques could have significant benefits, including reducing cost and increasing MSI testing of colorectal cancer (CRC) patients. Nonetheless, batch effects or systematic biases are not well characterized in digital histology models and lead to overoptimistic estimates of model performance. Methods to not only palliate but to directly abrogate biases are needed. We present a multiple bias rejecting DL system based on adversarial networks for the prediction of MSI in CRC from tissue microarrays (TMAs), trained and validated in 1788 patients from EPICOLON and HGUA. The system consists of an end-to-end image preprocessing module that tile samples at multiple magnifications and a tissue classification module linked to the bias-rejecting MSI predictor. We detected three biases associated with the learned representations of a baseline model: the project of origin of samples, the patient’s spot and the TMA glass where each spot was placed. The system was trained to directly avoid learning the batch effects of those variables. The learned features from the bias-ablated model achieved maximum discriminative power with respect to the task and minimal statistical mean dependence with the biases. The impact of different magnifications, types of tissues and the model performance at tile vs patient level is analyzed. The AUC at tile level, and including all three selected tissues (tumor epithelium, mucin and lymphocytic regions) and 4 magnifications, was 0.87 ± 0.03 and increased to 0.9 ± 0.03 at patient level. To the best of our knowledge, this is the first work that incorporates a multiple bias ablation technique at the DL architecture in digital pathology, and the first using TMAs for the MSI prediction task.

Stress-testing Russian Banking System: Will Banks Need Government Assistance Again?

2010 ◽  
pp. 61-81 ◽  
Author(s):  
O. Solntsev ◽  
A. Pestova ◽  
M. Mamonov
Keyword(s):  
Stress Testing ◽  
Banking Sector ◽  
Stress Test ◽  
Banking System ◽  
Government Assistance ◽  
Methodological Issues ◽  
Loan Portfolio ◽  
Macroeconomic Indicators ◽  
Remote Stress ◽  
Capital Injections

The article analyzes factors that affect growth of the share of non-performing loans in the loan portfolio of Russian banks and proposes approaches for this share forecasting on the basis of dynamics of macroeconomic indicators. It also deals with methodological issues of remote stress-test of lending agencies. Using the results of conducted stress-test of Russian banks the authors assess their perspective capital needs in 2010 and estimate the share of government assistance in capital injections. Furthermore, the authors define the scale of vulnerable banks groups in the Russian banking sector.

ERROR LOCALIZATION DIAGNOSTIC MODEL OPTIMIZATION IN DIGITAL STATE MACHINES NETWORKS

2019 ◽  
Author(s):  
Irina Bystrova ◽  
E. Danil'chuk ◽  
Boris Podkopaev
Keyword(s):  
Single Component ◽  
Diagnostic Model ◽  
State Machines ◽  
Model Optimization ◽  
Error Localization ◽  
Diagnostic Models

The problem of constructing a diagnostic model for a network S consisting of a number of digital automata is considered, provided that the diagnostic models of all network components are known. It is assumed that these models are given by systems of logical equations, and the errors to be detected are localized in any but a single component of the network.

An Information-theoretical Model for Breast Cancer Detection

2008 ◽  
Vol 47 (04) ◽  
pp. 322-327 ◽  
Author(s):  
D. Blokh ◽  
N. Zurgil ◽  
I. Stambler ◽  
E. Afrimzon ◽  
Y. Shafran ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cancer Detection ◽  
Hamming Distance ◽  
Formal Model ◽  
Methodological Approach ◽  
Breast Cancer Detection ◽  
Receptor Expression ◽  
Diagnostic Model ◽  
Model Parameters ◽  
Two Stages

Summary Objectives: Formal diagnostic modeling is an important line of modern biological and medical research. The construction of a formal diagnostic model consists of two stages: first, the estimation of correlation between model parameters and the disease under consideration; and second, the construction of a diagnostic decision rule using these correlation estimates. A serious drawback of current diagnostic models is the absence of a unified mathematical methodological approach to implementing these two stages. The absence of aunified approach makesthe theoretical/biomedical substantiation of diagnostic rules difficult and reduces the efficacyofactual diagnostic model application. Methods: The present study constructs a formal model for breast cancer detection. The diagnostic model is based on information theory. Normalized mutual information is chosen as the measure of relevance between parameters and the patterns studied. The “nearest neighbor” rule is utilized for diagnosis, while the distance between elements is the weighted Hamming distance. The model concomitantly employs cellular fluorescence polarization as the quantitative input parameter and cell receptor expression as qualitative parameters. Results: Twenty-four healthy individuals and 34 patients (not including the subjects analyzed for the model construction) were tested by the model. Twenty-three healthy subjects and 34 patients were correctly diagnosed. Conclusions: The proposed diagnostic model is an open one,i.e.it can accommodate new additional parameters, which may increase its effectiveness.

scholarly journals Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Young-Gon Kim ◽  
Sungchul Kim ◽  
Cristina Eunbee Cho ◽  
In Hye Song ◽  
Hee Jin Lee ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Frozen Section ◽  
Medical Center ◽  
External Validation ◽  
Model Performance ◽  
Classification Model ◽  
Training Dataset

AbstractFast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.

scholarly journals Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Christian Crouzet ◽  
Gwangjin Jeong ◽  
Rachel H. Chae ◽  
Krystal T. LoPresti ◽  
Cody E. Dunn ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prussian Blue ◽  
Processing Speed ◽  
Digital Pathology ◽  
Ground Truth ◽  
Individual Variability ◽  
Rgb Images ◽  
Cerebral Microhemorrhages ◽  
Phasor Analysis ◽  
Better Than

AbstractCerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

scholarly journals A deep-learning method using computed tomography scout images for estimating patient body weight

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shota Ichikawa ◽  
Misaki Hamada ◽  
Hiroyuki Sugimori
Keyword(s):  
Computed Tomography ◽  
Body Weight ◽  
Deep Learning ◽  
Contrast Medium ◽  
Model Performance ◽  
Ct Scanning ◽  
Drug Dosing ◽  
Body Weights ◽  
Dose Management ◽  
Medium Dose

AbstractBody weight is an indispensable parameter for determination of contrast medium dose, appropriate drug dosing, or management of radiation dose. However, we cannot always determine the accurate patient body weight at the time of computed tomography (CT) scanning, especially in emergency care. Time-efficient methods to estimate body weight with high accuracy before diagnostic CT scans currently do not exist. In this study, on the basis of 1831 chest and 519 abdominal CT scout images with the corresponding body weights, we developed and evaluated deep-learning models capable of automatically predicting body weight from CT scout images. In the model performance assessment, there were strong correlations between the actual and predicted body weights in both chest (ρ = 0.947, p < 0.001) and abdominal datasets (ρ = 0.869, p < 0.001). The mean absolute errors were 2.75 kg and 4.77 kg for the chest and abdominal datasets, respectively. Our proposed method with deep learning is useful for estimating body weights from CT scout images with clinically acceptable accuracy and potentially could be useful for determining the contrast medium dose and CT dose management in adult patients with unknown body weight.

Sign in / Sign up

Export Citation Format

Share Document