scholarly journals Biologically relevant transfer learning improves transcription factor binding prediction

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Gherman Novakovsky ◽  
Manu Saraswat ◽  
Oriol Fornes ◽  
Sara Mostafavi ◽  
Wyeth W. Wasserman
Keyword(s):  
Transcription Factor ◽  
Deep Learning ◽  
Transfer Learning ◽  
Model Performance ◽  
Fine Tuning ◽  
Binding Prediction ◽  
Single Task ◽  
Biologically Relevant ◽  
Powerful Technique ◽  
Task Model

Abstract Background Deep learning has proven to be a powerful technique for transcription factor (TF) binding prediction but requires large training datasets. Transfer learning can reduce the amount of data required for deep learning, while improving overall model performance, compared to training a separate model for each new task. Results We assess a transfer learning strategy for TF binding prediction consisting of a pre-training step, wherein we train a multi-task model with multiple TFs, and a fine-tuning step, wherein we initialize single-task models for individual TFs with the weights learned by the multi-task model, after which the single-task models are trained at a lower learning rate. We corroborate that transfer learning improves model performance, especially if in the pre-training step the multi-task model is trained with biologically relevant TFs. We show the effectiveness of transfer learning for TFs with ~ 500 ChIP-seq peak regions. Using model interpretation techniques, we demonstrate that the features learned in the pre-training step are refined in the fine-tuning step to resemble the binding motif of the target TF (i.e., the recipient of transfer learning in the fine-tuning step). Moreover, pre-training with biologically relevant TFs allows single-task models in the fine-tuning step to learn useful features other than the motif of the target TF. Conclusions Our results confirm that transfer learning is a powerful technique for TF binding prediction.

scholarly journals Biologically-relevant transfer learning improves transcription factor binding prediction

2020 ◽  
Author(s):  
Gherman Novakovsky ◽  
Manu Saraswat ◽  
Oriol Fornes ◽  
Sara Mostafavi ◽  
Wyeth W. Wasserman
Keyword(s):  
Transcription Factor ◽  
Deep Learning ◽  
Transfer Learning ◽  
Model Performance ◽  
Fine Tuning ◽  
Binding Prediction ◽  
Single Task ◽  
Biologically Relevant ◽  
Powerful Technique ◽  
Task Model

AbstractBackgroundDeep learning has proven to be a powerful technique for transcription factor (TF) binding prediction, but requires large training datasets. Transfer learning can reduce the amount of data required for deep learning, while improving overall model performance, compared to training a separate model for each new task.ResultsWe assess a transfer learning strategy for TF binding prediction consisting of a pre-training step, wherein we train a multi-task model with multiple TFs, and a fine-tuning step, wherein we initialize single-task models for individual TFs with the weights learned by the multi-task model, after which the single-task models are trained at a lower learning rate. We corroborate that transfer learning improves model performance, especially if in the pre-training step the multi-task model is trained with biologically-relevant TFs. We show the effectiveness of transfer learning for TFs with ∼500 ChIP-seq peak regions. Using model interpretation techniques, we demonstrate that the features learned in the pre-training step are refined in the fine-tuning step to resemble the binding motif of the target TF (i.e. the recipient of transfer learning in the fine-tuning step). Moreover, pre-training with biologically-relevant TFs allows single-task models in the fine-tuning step to learn features other than the motif of the target TF.ConclusionsOur results confirm that transfer learning is a powerful technique for TF binding prediction.

scholarly journals Hierarchical shared transfer learning for biomedical named entity recognition

2022 ◽  
Vol 23 (1) ◽  
Author(s):  
Zhaoying Chai ◽  
Han Jin ◽  
Shenghui Shi ◽  
Siyan Zhan ◽  
Lin Zhuo ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Medical Information ◽  
Named Entity Recognition ◽  
Fine Tuning ◽  
Entity Recognition ◽  
Single Task ◽  
Named Entity ◽  
Task Learning ◽  
Biomedical Named Entity Recognition

Abstract Background Biomedical named entity recognition (BioNER) is a basic and important medical information extraction task to extract medical entities with special meaning from medical texts. In recent years, deep learning has become the main research direction of BioNER due to its excellent data-driven context coding ability. However, in BioNER task, deep learning has the problem of poor generalization and instability. Results we propose the hierarchical shared transfer learning, which combines multi-task learning and fine-tuning, and realizes the multi-level information fusion between the underlying entity features and the upper data features. We select 14 datasets containing 4 types of entities for training and evaluate the model. The experimental results showed that the F1-scores of the five gold standard datasets BC5CDR-chemical, BC5CDR-disease, BC2GM, BC4CHEMD, NCBI-disease and LINNAEUS were increased by 0.57, 0.90, 0.42, 0.77, 0.98 and − 2.16 compared to the single-task XLNet-CRF model. BC5CDR-chemical, BC5CDR-disease and BC4CHEMD achieved state-of-the-art results.The reasons why LINNAEUS’s multi-task results are lower than single-task results are discussed at the dataset level. Conclusion Compared with using multi-task learning and fine-tuning alone, the model has more accurate recognition ability of medical entities, and has higher generalization and stability.

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 Evaluation of Scalability and Degree of Fine-Tuning of Deep Convolutional Neural Networks for COVID-19 Screening on Chest X-ray Images Using Explainable Deep-Learning Algorithm

2020 ◽  
Vol 10 (4) ◽  
pp. 213 ◽  
Author(s):  
Ki-Sun Lee ◽  
Jae Young Kim ◽  
Eun-tae Jeon ◽  
Won Suk Choi ◽  
Nan Hee Kim ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Strategies ◽  
Transfer Learning ◽  
Learning Algorithm ◽  
Fine Tuning ◽  
Deep Convolutional Neural Networks ◽  
X Ray ◽  
Backbone Network ◽  
Deep Learning Algorithm ◽  
Chest X Ray

According to recent studies, patients with COVID-19 have different feature characteristics on chest X-ray (CXR) than those with other lung diseases. This study aimed at evaluating the layer depths and degree of fine-tuning on transfer learning with a deep convolutional neural network (CNN)-based COVID-19 screening in CXR to identify efficient transfer learning strategies. The CXR images used in this study were collected from publicly available repositories, and the collected images were classified into three classes: COVID-19, pneumonia, and normal. To evaluate the effect of layer depths of the same CNN architecture, CNNs called VGG-16 and VGG-19 were used as backbone networks. Then, each backbone network was trained with different degrees of fine-tuning and comparatively evaluated. The experimental results showed the highest AUC value to be 0.950 concerning COVID-19 classification in the experimental group of a fine-tuned with only 2/5 blocks of the VGG16 backbone network. In conclusion, in the classification of medical images with a limited number of data, a deeper layer depth may not guarantee better results. In addition, even if the same pre-trained CNN architecture is used, an appropriate degree of fine-tuning can help to build an efficient deep learning model.

scholarly journals Coal-Rock Recognition in Top Coal Caving Using Bimodal Deep Learning and Hilbert-Huang Transform

2017 ◽  
Vol 2017 ◽  
pp. 1-13 ◽  
Author(s):  
Guoxin Zhang ◽  
Zengcai Wang ◽  
Lei Zhao ◽  
Yazhou Qi ◽  
Jinshan Wang
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Acoustic Waves ◽  
Sound Pressure ◽  
Mechanical Vibration ◽  
Training Sample ◽  
Fine Tuning ◽  
Learning Method ◽  
Hilbert Huang Transform ◽  
Coal Rock

This study employs the mechanical vibration and acoustic waves of a hydraulic support tail beam for an accurate and fast coal-rock recognition. The study proposes a diagnosis method based on bimodal deep learning and Hilbert-Huang transform. The bimodal deep neural networks (DNN) adopt bimodal learning and transfer learning. The bimodal learning method attempts to learn joint representation by considering acceleration and sound pressure modalities, which both contribute to coal-rock recognition. The transfer learning method solves the problem regarding DNN, in which a large number of labeled training samples are necessary to optimize the parameters while the labeled training sample is limited. A suitable installation location for sensors is determined in recognizing coal-rock. The extraction features of acceleration and sound pressure signals are combined and effective combination features are selected. Bimodal DNN consists of two deep belief networks (DBN), each DBN model is trained with related samples, and the parameters of the pretrained DBNs are transferred to the final recognition model. Then the parameters of the proposed model are continuously optimized by pretraining and fine-tuning. Finally, the comparison of experimental results demonstrates the superiority of the proposed method in terms of recognition accuracy.

scholarly journals Customize Deep Learning-based De-Identification Systems Using Local Clinical Notes - A Study of Sample Size

2020 ◽  
Author(s):  
Xi Yang ◽  
Jiang Bian ◽  
Yonghui Wu
Keyword(s):  
Deep Learning ◽  
Model Performance ◽  
Fine Tuning ◽  
Identification System ◽  
Local Data ◽  
Clinical Text ◽  
Clinical Notes ◽  
Critical Technology ◽  
Number Of Patients ◽  
Privacy And Confidentiality

ABSTRACTElectronic Health Records (EHRs) are a valuable resource for both clinical and translational research. However, much detailed patient information is embedded in clinical narratives, including a large number of patients’ identifiable information. De-identification of clinical notes is a critical technology to protect the privacy and confidentiality of patients. Previous studies presented many automated de-identification systems to capture and remove protected health information from clinical text. However, most of them were tested only in one institute setting where training and test data were from the same institution. Directly adapting these systems without customization could lead to a dramatic performance drop. Recent studies have shown that fine-tuning is a promising method to customize deep learning-based NLP systems across different institutes. However, it’s still not clear how much local data is required. In this study, we examined the customizing of a deep learning-based de-identification system using different sizes of local notes from UF Health. Our results showed that the fine-tuning could significantly improve the model performance even on a small local dataset. Yet, when the local data exceeded a threshold (e.g., 700 notes in this study), the performance improvement became marginal.

scholarly journals Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test

Healthcare ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 1579
Author(s):  
Wansuk Choi ◽  
Seoyoon Heo
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
High Performance ◽  
Model Fit ◽  
Fine Tuning ◽  
Learning Approaches ◽  
Video Classification ◽  
Video Clips ◽  
Performance Computing

The purpose of this study was to classify ULTT videos through transfer learning with pre-trained deep learning models and compare the performance of the models. We conducted transfer learning by combining a pre-trained convolution neural network (CNN) model into a Python-produced deep learning process. Videos were processed on YouTube and 103,116 frames converted from video clips were analyzed. In the modeling implementation, the process of importing the required modules, performing the necessary data preprocessing for training, defining the model, compiling, model creation, and model fit were applied in sequence. Comparative models were Xception, InceptionV3, DenseNet201, NASNetMobile, DenseNet121, VGG16, VGG19, and ResNet101, and fine tuning was performed. They were trained in a high-performance computing environment, and validation and loss were measured as comparative indicators of performance. Relatively low validation loss and high validation accuracy were obtained from Xception, InceptionV3, and DenseNet201 models, which is evaluated as an excellent model compared with other models. On the other hand, from VGG16, VGG19, and ResNet101, relatively high validation loss and low validation accuracy were obtained compared with other models. There was a narrow range of difference between the validation accuracy and the validation loss of the Xception, InceptionV3, and DensNet201 models. This study suggests that training applied with transfer learning can classify ULTT videos, and that there is a difference in performance between models.

scholarly journals Combining weakly and strongly supervised learning improves strong supervision in Gleason pattern classification

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Sebastian Otálora ◽  
Niccolò Marini ◽  
Henning Müller ◽  
Manfredo Atzori
Keyword(s):  
Supervised Learning ◽  
Transfer Learning ◽  
Data Augmentation ◽  
Model Performance ◽  
Classification Problem ◽  
Heterogeneous Data ◽  
Fine Tuning ◽  
Data Sources ◽  
Gleason Pattern ◽  
Heterogeneous Data Sources

Abstract Background One challenge to train deep convolutional neural network (CNNs) models with whole slide images (WSIs) is providing the required large number of costly, manually annotated image regions. Strategies to alleviate the scarcity of annotated data include: using transfer learning, data augmentation and training the models with less expensive image-level annotations (weakly-supervised learning). However, it is not clear how to combine the use of transfer learning in a CNN model when different data sources are available for training or how to leverage from the combination of large amounts of weakly annotated images with a set of local region annotations. This paper aims to evaluate CNN training strategies based on transfer learning to leverage the combination of weak and strong annotations in heterogeneous data sources. The trade-off between classification performance and annotation effort is explored by evaluating a CNN that learns from strong labels (region annotations) and is later fine-tuned on a dataset with less expensive weak (image-level) labels. Results As expected, the model performance on strongly annotated data steadily increases as the percentage of strong annotations that are used increases, reaching a performance comparable to pathologists ($$\kappa = 0.691 \pm 0.02$$ κ = 0.691 ± 0.02 ). Nevertheless, the performance sharply decreases when applied for the WSI classification scenario with $$\kappa = 0.307 \pm 0.133$$ κ = 0.307 ± 0.133 . Moreover, it only provides a lower performance regardless of the number of annotations used. The model performance increases when fine-tuning the model for the task of Gleason scoring with the weak WSI labels $$\kappa = 0.528 \pm 0.05$$ κ = 0.528 ± 0.05 . Conclusion Combining weak and strong supervision improves strong supervision in classification of Gleason patterns using tissue microarrays (TMA) and WSI regions. Our results contribute very good strategies for training CNN models combining few annotated data and heterogeneous data sources. The performance increases in the controlled TMA scenario with the number of annotations used to train the model. Nevertheless, the performance is hindered when the trained TMA model is applied directly to the more challenging WSI classification problem. This demonstrates that a good pre-trained model for prostate cancer TMA image classification may lead to the best downstream model if fine-tuned on the WSI target dataset. We have made available the source code repository for reproducing the experiments in the paper: https://github.com/ilmaro8/Digital_Pathology_Transfer_Learning

scholarly journals Deep learning prediction of mild cognitive impairment conversion to Alzheimer’s disease at 3 years after diagnosis using longitudinal and whole-brain 3D MRI

2021 ◽  
Vol 7 ◽  
pp. e560
Author(s):  
Ethan Ocasio ◽  
Tim Q. Duong
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Longitudinal Data ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Fine Tuning ◽  
3D Mri ◽  
Whole Brain

Background While there is no cure for Alzheimer’s disease (AD), early diagnosis and accurate prognosis of AD may enable or encourage lifestyle changes, neurocognitive enrichment, and interventions to slow the rate of cognitive decline. The goal of our study was to develop and evaluate a novel deep learning algorithm to predict mild cognitive impairment (MCI) to AD conversion at three years after diagnosis using longitudinal and whole-brain 3D MRI. Methods This retrospective study consisted of 320 normal cognition (NC), 554 MCI, and 237 AD patients. Longitudinal data include T1-weighted 3D MRI obtained at initial presentation with diagnosis of MCI and at 12-month follow up. Whole-brain 3D MRI volumes were used without a priori segmentation of regional structural volumes or cortical thicknesses. MRIs of the AD and NC cohort were used to train a deep learning classification model to obtain weights to be applied via transfer learning for prediction of MCI patient conversion to AD at three years post-diagnosis. Two (zero-shot and fine tuning) transfer learning methods were evaluated. Three different convolutional neural network (CNN) architectures (sequential, residual bottleneck, and wide residual) were compared. Data were split into 75% and 25% for training and testing, respectively, with 4-fold cross validation. Prediction accuracy was evaluated using balanced accuracy. Heatmaps were generated. Results The sequential convolutional approach yielded slightly better performance than the residual-based architecture, the zero-shot transfer learning approach yielded better performance than fine tuning, and CNN using longitudinal data performed better than CNN using a single timepoint MRI in predicting MCI conversion to AD. The best CNN model for predicting MCI conversion to AD at three years after diagnosis yielded a balanced accuracy of 0.793. Heatmaps of the prediction model showed regions most relevant to the network including the lateral ventricles, periventricular white matter and cortical gray matter. Conclusions This is the first convolutional neural network model using longitudinal and whole-brain 3D MRIs without extracting regional brain volumes or cortical thicknesses to predict future MCI to AD conversion at 3 years after diagnosis. This approach could lead to early prediction of patients who are likely to progress to AD and thus may lead to better management of the disease.

scholarly journals Transfer Learning for Inference of Metastatic Origin from Whole Slide Histology

2021 ◽  
Author(s):  
Geoffrey F. Schau ◽  
Hassan Ghani ◽  
Erik A. Burlingame ◽  
Guillaume Thibault ◽  
Joe W. Gray ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Primary Tumor ◽  
Large Scale ◽  
Metastatic Cancer ◽  
Clinical Diagnostics ◽  
Training Data ◽  
Fine Tuning ◽  
Learning Approach ◽  
Whole Slide Images

AbstractAccurate diagnosis of metastatic cancer is essential for prescribing optimal control strategies to halt further spread of metastasizing disease. While pathological inspection aided by immunohistochemistry staining provides a valuable gold standard for clinical diagnostics, deep learning methods have emerged as powerful tools for identifying clinically relevant features of whole slide histology relevant to a tumor’s metastatic origin. Although deep learning models require significant training data to learn effectively, transfer learning paradigms provide mechanisms to circumvent limited training data by first training a model on related data prior to fine-tuning on smaller data sets of interest. In this work we propose a transfer learning approach that trains a convolutional neural network to infer the metastatic origin of tumor tissue from whole slide images of hematoxylin and eosin (H&E) stained tissue sections and illustrate the advantages of pre-training network on whole slide images of primary tumor morphology. We further characterize statistical dissimilarity between primary and metastatic tumors of various indications on patch-level images to highlight limitations of our indication-specific transfer learning approach. Using a primary-to-metastatic transfer learning approach, we achieved mean class-specific areas under receiver operator characteristics curve (AUROC) of 0.779, which outperformed comparable models trained on only images of primary tumor (mean AUROC of 0.691) or trained on only images of metastatic tumor (mean AUROC of 0.675), supporting the use of large scale primary tumor imaging data in developing computer vision models to characterize metastatic origin of tumor lesions.

Sign in / Sign up

Export Citation Format

Share Document