scholarly journals Generative Adversarial Domain Adaptation for Nucleus Quantification in Images of Tissue Immunohistochemically Stained for Ki-67

2020 ◽  
pp. 666-679 ◽  
Author(s):  
Xuhong Zhang ◽  
Toby C. Cornish ◽  
Lin Yang ◽  
Tellen D. Bennett ◽  
Debashis Ghosh ◽  
...  
Keyword(s):  
Deep Learning ◽  
Domain Adaptation ◽  
Training Data ◽  
Data Sets ◽  
Learning Models ◽  
Convolutional Network ◽  
Ki 67 ◽  
Data Set ◽  
Target Data ◽  
Real Target

PURPOSE We focus on the problem of scarcity of annotated training data for nucleus recognition in Ki-67 immunohistochemistry (IHC)–stained pancreatic neuroendocrine tumor (NET) images. We hypothesize that deep learning–based domain adaptation is helpful for nucleus recognition when image annotations are unavailable in target data sets. METHODS We considered 2 different institutional pancreatic NET data sets: one (ie, source) containing 38 cases with 114 annotated images and the other (ie, target) containing 72 cases with 20 annotated images. The gold standards were manually annotated by 1 pathologist. We developed a novel deep learning–based domain adaptation framework to count different types of nuclei (ie, immunopositive tumor, immunonegative tumor, nontumor nuclei). We compared the proposed method with several recent fully supervised deep learning models, such as fully convolutional network-8s (FCN-8s), U-Net, fully convolutional regression network (FCRN) A, FCRNB, and fully residual convolutional network (FRCN). We also evaluated the proposed method by learning with a mixture of converted source images and real target annotations. RESULTS Our method achieved an F1 score of 81.3% and 62.3% for nucleus detection and classification in the target data set, respectively. Our method outperformed FCN-8s (53.6% and 43.6% for nucleus detection and classification, respectively), U-Net (61.1% and 47.6%), FCRNA (63.4% and 55.8%), and FCRNB (68.2% and 60.6%) in terms of F1 score and was competitive with FRCN (81.7% and 70.7%). In addition, learning with a mixture of converted source images and only a small set of real target labels could further boost the performance. CONCLUSION This study demonstrates that deep learning–based domain adaptation is helpful for nucleus recognition in Ki-67 IHC stained images when target data annotations are not available. It would improve the applicability of deep learning models designed for downstream supervised learning tasks on different data sets.

scholarly journals Wheel Hub Defects Image Recognition Base on Zero-Shot Learning

2021 ◽  
Vol 11 (4) ◽  
pp. 1529
Author(s):  
Xiaohong Sun ◽  
Jinan Gu ◽  
Meimei Wang ◽  
Yanhua Meng ◽  
Huichao Shi
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Large Scale ◽  
Domain Adaptation ◽  
Data Sets ◽  
Human Beings ◽  
Data Set ◽  
Defect Image ◽  
Product Surface ◽  
Projection Domain

In the wheel hub industry, the quality control of the product surface determines the subsequent processing, which can be realized through the hub defect image recognition based on deep learning. Although the existing methods based on deep learning have reached the level of human beings, they rely on large-scale training sets, however, these models are completely unable to cope with the situation without samples. Therefore, in this paper, a generalized zero-shot learning framework for hub defect image recognition was built. First, a reverse mapping strategy was adopted to reduce the hubness problem, then a domain adaptation measure was employed to alleviate the projection domain shift problem, and finally, a scaling calibration strategy was used to avoid the recognition preference of seen defects. The proposed model was validated using two data sets, VOC2007 and the self-built hub defect data set, and the results showed that the method performed better than the current popular methods.

How to tag non-standard language: Normalisation versus domain adaptation for Slovene historical and user-generated texts

2019 ◽  
Vol 25 (5) ◽  
pp. 651-674 ◽  
Author(s):  
Katja Zupan ◽  
Nikola Ljubešić ◽  
Tomaž Erjavec
Keyword(s):  
Domain Adaptation ◽  
Training Data ◽  
Data Sets ◽  
Standard Language ◽  
Data Set ◽  
Standard Data ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Versus Domain ◽  
Pos Tagger

AbstractPart-of-speech (PoS) tagging of non-standard language with models developed for standard language is known to suffer from a significant decrease in accuracy. Two methods are typically used to improve it: word normalisation, which decreases the out-of-vocabulary rate of the PoS tagger, and domain adaptation where the tagger is made aware of the non-standard language variation, either through supervision via non-standard data being added to the tagger’s training set, or via distributional information calculated from raw texts. This paper investigates the two approaches, normalisation and domain adaptation, on carefully constructed data sets encompassing historical and user-generated Slovene texts, in particular focusing on the amount of labour necessary to produce the manually annotated data sets for each approach and comparing the resulting PoS accuracy. We give quantitative as well as qualitative analyses of the tagger performance in various settings, showing that on our data set closed and open class words exhibit significantly different behaviours, and that even small inconsistencies in the PoS tags in the data have an impact on the accuracy. We also show that to improve tagging accuracy, it is best to concentrate on obtaining manually annotated normalisation training data for short annotation campaigns, while manually producing in-domain training sets for PoS tagging is better when a more substantial annotation campaign can be undertaken. Finally, unsupervised adaptation via Brown clustering is similarly useful regardless of the size of the training data available, but improvements tend to be bigger when adaptation is performed via in-domain tagging data.

A method for adequate selection of training data sets to reconstruct seismic field data using a convolutional U-Net

Geophysics ◽  
2021 ◽  
pp. 1-103
Author(s):  
Jiho Park ◽  
Jihun Choi ◽  
Soon Jee Seol ◽  
Joongmoo Byun ◽  
Young Kim
Keyword(s):  
Data Analysis ◽  
Seismic Data ◽  
Field Data ◽  
Training Data ◽  
Data Reconstruction ◽  
Data Sets ◽  
Training Set ◽  
Data Set ◽  
Seismic Data Reconstruction ◽  
Target Data

Deep learning (DL) methods are recently introduced for seismic signal processing. Using DL methods, many researchers have adopted these novel techniques in an attempt to construct a DL model for seismic data reconstruction. The performance of DL-based methods depends heavily on what is learned from the training data. We focus on constructing the DL model that well reflect the features of target data sets. The main goal is to integrate DL with an intuitive data analysis approach that compares similar patterns prior to the DL training stage. We have developed a two-sequential method consisting of two stage: (i) analyzing training and target data sets simultaneously for determining target-informed training set and (ii) training the DL model with this training data set to effectively interpolate the seismic data. Here, we introduce the convolutional autoencoder t-distributed stochastic neighbor embedding (CAE t-SNE) analysis that can provide the insight into the results of interpolation through the analysis of both the training and target data sets prior to DL model training. The proposed method were tested with synthetic and field data. Dense seismic gathers (e.g. common-shot gathers; CSGs) were used as a labeled training data set, and relatively sparse seismic gather (e.g. common-receiver gathers; CRGs) were reconstructed in both cases. The reconstructed results and SNRs demonstrated that the training data can be efficiently selected using CAE t-SNE analysis and the spatial aliasing of CRGs was successfully alleviated by the trained DL model with this training data, which contain target features. These results imply that the data analysis for selecting target-informed training set is very important for successful DL interpolation. Additionally, the proposed analysis method can also be applied to investigate the similarities between training and target data sets for another DL-based seismic data reconstruction tasks.

scholarly journals COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Mohd Zulfaezal Che Azemin ◽  
Radhiana Hassan ◽  
Mohd Izzuddin Mohd Tamrin ◽  
Mohd Adli Md Ali
Keyword(s):  
Deep Learning ◽  
Network Architecture ◽  
Clinical Findings ◽  
Training Data ◽  
Receiver Operating Curve ◽  
Data Sets ◽  
Data Set ◽  
X Ray ◽  
Chest X Ray ◽  
Sensitivity Specificity

The key component in deep learning research is the availability of training data sets. With a limited number of publicly available COVID-19 chest X-ray images, the generalization and robustness of deep learning models to detect COVID-19 cases developed based on these images are questionable. We aimed to use thousands of readily available chest radiograph images with clinical findings associated with COVID-19 as a training data set, mutually exclusive from the images with confirmed COVID-19 cases, which will be used as the testing data set. We used a deep learning model based on the ResNet-101 convolutional neural network architecture, which was pretrained to recognize objects from a million of images and then retrained to detect abnormality in chest X-ray images. The performance of the model in terms of area under the receiver operating curve, sensitivity, specificity, and accuracy was 0.82, 77.3%, 71.8%, and 71.9%, respectively. The strength of this study lies in the use of labels that have a strong clinical association with COVID-19 cases and the use of mutually exclusive publicly available data for training, validation, and testing.

scholarly journals Using self-supervised feature learning to improve the use of pulse oximeter signals to predict paediatric hospitalization

2021 ◽  
Vol 6 ◽  
pp. 248
Author(s):  
Paul Mwaniki ◽  
Timothy Kamanu ◽  
Samuel Akech ◽  
Dustin Dunsmuir ◽  
J. Mark Ansermino ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Deep Learning ◽  
Pulse Oximeter ◽  
Regression Models ◽  
Data Sets ◽  
Learning Models ◽  
Data Set ◽  
Logistic Regression Models ◽  
End To End

Background: The success of many machine learning applications depends on knowledge about the relationship between the input data and the task of interest (output), hindering the application of machine learning to novel tasks. End-to-end deep learning, which does not require intermediate feature engineering, has been recommended to overcome this challenge but end-to-end deep learning models require large labelled training data sets often unavailable in many medical applications. In this study, we trained machine learning models to predict paediatric hospitalization given raw photoplethysmography (PPG) signals obtained from a pulse oximeter. We trained self-supervised learning (SSL) for automatic feature extraction from PPG signals and assessed the utility of SSL in initializing end-to-end deep learning models trained on a small labelled data set with the aim of predicting paediatric hospitalization.Methods: We compared logistic regression models fitted using features extracted using SSL with end-to-end deep learning models initialized either randomly or using weights from the SSL model. We also compared the performance of SSL models trained on labelled data alone (n=1,031) with SSL trained using both labelled and unlabelled signals (n=7,578). Results: The SSL model trained on both labelled and unlabelled PPG signals produced features that were more predictive of hospitalization compared to the SSL model trained on labelled PPG only (AUC of logistic regression model: 0.78 vs 0.74). The end-to-end deep learning model had an AUC of 0.80 when initialized using the SSL model trained on all PPG signals, 0.77 when initialized using SSL trained on labelled data only, and 0.73 when initialized randomly. Conclusions: This study shows that SSL can improve the classification of PPG signals by either extracting features required by logistic regression models or initializing end-to-end deep learning models. Furthermore, SSL can leverage larger unlabelled data sets to improve performance of models fitted using small labelled data sets.

A Surrogate Data-Based Approach for Validating Deep Learning Model Used in Healthcare

2020 ◽  
pp. 132-146
Author(s):  
Meenakshi Srivastava
Keyword(s):  
Deep Learning ◽  
Predictive Modelling ◽  
Surrogate Data ◽  
Learning Model ◽  
Training Data ◽  
Data Sets ◽  
Data Set ◽  
Huge Data ◽  
Small Data Sets ◽  
Deep Learning Model

IoT-based communication between medical devices has encouraged the healthcare industry to use automated systems which provide effective insight from the massive amount of gathered data. AI and machine learning have played a major role in the design of such systems. Accuracy and validation are considered, since copious training data is required in a neural network (NN)-based deep learning model. This is hardly feasible in medical research, because the size of data sets is constrained by complexity and high cost experiments. The availability of limited sample data validation of NN remains a concern. The prediction of outcomes on a NN trained on a smaller data set cannot guarantee performance and exhibits unstable behaviors. Surrogate data-based validation of NN can be viewed as a solution. In the current chapter, the classification of breast tissue data by a NN model has been detailed. In the absence of a huge data set, a surrogate data-based validation approach has been applied. The discussed study can be applied for predictive modelling for applications described by small data sets.

scholarly journals Evaluation of automated cephalometric analysis based on the latest deep learning method

2021 ◽  
Author(s):  
Hye-Won Hwang ◽  
Jun-Ho Moon ◽  
Min-Gyu Kim ◽  
Richard E. Donatelli ◽  
Shin-Jae Lee
Keyword(s):  
Deep Learning ◽  
Test Data ◽  
Training Data ◽  
Superior Performance ◽  
Cephalometric Analysis ◽  
Data Sets ◽  
Learning Method ◽  
Test Results ◽  
Classification Rate ◽  
Data Set

ABSTRACT Objectives To compare an automated cephalometric analysis based on the latest deep learning method of automatically identifying cephalometric landmarks (AI) with previously published AI according to the test style of the worldwide AI challenges at the International Symposium on Biomedical Imaging conferences held by the Institute of Electrical and Electronics Engineers (IEEE ISBI). Materials and Methods This latest AI was developed by using a total of 1983 cephalograms as training data. In the training procedures, a modification of a contemporary deep learning method, YOLO version 3 algorithm, was applied. Test data consisted of 200 cephalograms. To follow the same test style of the AI challenges at IEEE ISBI, a human examiner manually identified the IEEE ISBI-designated 19 cephalometric landmarks, both in training and test data sets, which were used as references for comparison. Then, the latest AI and another human examiner independently detected the same landmarks in the test data set. The test results were compared by the measures that appeared at IEEE ISBI: the success detection rate (SDR) and the success classification rates (SCR). Results SDR of the latest AI in the 2-mm range was 75.5% and SCR was 81.5%. These were greater than any other previous AIs. Compared to the human examiners, AI showed a superior success classification rate in some cephalometric analysis measures. Conclusions This latest AI seems to have superior performance compared to previous AI methods. It also seems to demonstrate cephalometric analysis comparable to human examiners.

Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

2019 ◽  
Vol 9 (1) ◽  
pp. 16-31
Author(s):  
Kyungkoo Jun
Keyword(s):  
Fourier Transform ◽  
Deep Learning ◽  
Short Term Memory ◽  
Window Size ◽  
Sensor Data ◽  
Data Sets ◽  
Data Set ◽  
Proposed Model ◽  
Testing Data ◽  
Labeling Scheme

Background & Objective: This paper proposes a Fourier transform inspired method to classify human activities from time series sensor data. Methods: Our method begins by decomposing 1D input signal into 2D patterns, which is motivated by the Fourier conversion. The decomposition is helped by Long Short-Term Memory (LSTM) which captures the temporal dependency from the signal and then produces encoded sequences. The sequences, once arranged into the 2D array, can represent the fingerprints of the signals. The benefit of such transformation is that we can exploit the recent advances of the deep learning models for the image classification such as Convolutional Neural Network (CNN). Results: The proposed model, as a result, is the combination of LSTM and CNN. We evaluate the model over two data sets. For the first data set, which is more standardized than the other, our model outperforms previous works or at least equal. In the case of the second data set, we devise the schemes to generate training and testing data by changing the parameters of the window size, the sliding size, and the labeling scheme. Conclusion: The evaluation results show that the accuracy is over 95% for some cases. We also analyze the effect of the parameters on the performance.

scholarly journals Investigating the impact of pre-processing techniques and pre-trained word embeddings in detecting Arabic health information on social media

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Yahya Albalawi ◽  
Jim Buckley ◽  
Nikola S. Nikolov
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Comprehensive Evaluation ◽  
Classification Problem ◽  
Data Sets ◽  
Word Embeddings ◽  
Data Set ◽  
Lower Accuracy ◽  
Health Related ◽  
The Impact

AbstractThis paper presents a comprehensive evaluation of data pre-processing and word embedding techniques in the context of Arabic document classification in the domain of health-related communication on social media. We evaluate 26 text pre-processings applied to Arabic tweets within the process of training a classifier to identify health-related tweets. For this task we use the (traditional) machine learning classifiers KNN, SVM, Multinomial NB and Logistic Regression. Furthermore, we report experimental results with the deep learning architectures BLSTM and CNN for the same text classification problem. Since word embeddings are more typically used as the input layer in deep networks, in the deep learning experiments we evaluate several state-of-the-art pre-trained word embeddings with the same text pre-processing applied. To achieve these goals, we use two data sets: one for both training and testing, and another for testing the generality of our models only. Our results point to the conclusion that only four out of the 26 pre-processings improve the classification accuracy significantly. For the first data set of Arabic tweets, we found that Mazajak CBOW pre-trained word embeddings as the input to a BLSTM deep network led to the most accurate classifier with F1 score of 89.7%. For the second data set, Mazajak Skip-Gram pre-trained word embeddings as the input to BLSTM led to the most accurate model with F1 score of 75.2% and accuracy of 90.7% compared to F1 score of 90.8% achieved by Mazajak CBOW for the same architecture but with lower accuracy of 70.89%. Our results also show that the performance of the best of the traditional classifier we trained is comparable to the deep learning methods on the first dataset, but significantly worse on the second dataset.

scholarly journals Domain randomization-enhanced deep learning models for bird detection

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xin Mao ◽  
Jun Kang Chow ◽  
Pin Siang Tan ◽  
Kuan-fu Liu ◽  
Jimmy Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Continuous Monitoring ◽  
Bird Species ◽  
Training Data ◽  
Learning Models ◽  
Fine Grained ◽  
Bird Detection ◽  
Relationship Of ◽  
The Relationship

AbstractAutomatic bird detection in ornithological analyses is limited by the accuracy of existing models, due to the lack of training data and the difficulties in extracting the fine-grained features required to distinguish bird species. Here we apply the domain randomization strategy to enhance the accuracy of the deep learning models in bird detection. Trained with virtual birds of sufficient variations in different environments, the model tends to focus on the fine-grained features of birds and achieves higher accuracies. Based on the 100 terabytes of 2-month continuous monitoring data of egrets, our results cover the findings using conventional manual observations, e.g., vertical stratification of egrets according to body size, and also open up opportunities of long-term bird surveys requiring intensive monitoring that is impractical using conventional methods, e.g., the weather influences on egrets, and the relationship of the migration schedules between the great egrets and little egrets.

Sign in / Sign up

Export Citation Format

Share Document