scholarly journals Deep Learning Frameworks for Rapid Gram Stain Image Data Interpretation: Protocol for a Retrospective Data Analysis

10.2196/16843 ◽  
2020 ◽  
Vol 9 (7) ◽  
pp. e16843
Author(s):  
Hee Kim ◽  
Thomas Ganslandt ◽  
Thomas Miethke ◽  
Michael Neumaier ◽  
Maximilian Kittel
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Image Interpretation ◽  
Image Data ◽  
Data Interpretation ◽  
Routine Care ◽  
Fine Tuning ◽  
Learning Technology ◽  
Gram Stain ◽  
Computational Performance

Background In recent years, remarkable progress has been made in deep learning technology and successful use cases have been introduced in the medical domain. However, not many studies have considered high-performance computing to fully appreciate the capability of deep learning technology. Objective This paper aims to design a solution to accelerate an automated Gram stain image interpretation by means of a deep learning framework without additional hardware resources. Methods We will apply and evaluate 3 methodologies, namely fine-tuning, an integer arithmetic–only framework, and hyperparameter tuning. Results The choice of pretrained models and the ideal setting for layer tuning and hyperparameter tuning will be determined. These results will provide an empirical yet reproducible guideline for those who consider a rapid deep learning solution for Gram stain image interpretation. The results are planned to be announced in the first quarter of 2021. Conclusions Making a balanced decision between modeling performance and computational performance is the key for a successful deep learning solution. Otherwise, highly accurate but slow deep learning solutions can add value to routine care. International Registered Report Identifier (IRRID) DERR1-10.2196/16843

scholarly journals Deep Learning Frameworks for Rapid Gram Stain Image Data Interpretation: Protocol for a Retrospective Data Analysis (Preprint)

2020 ◽  
Author(s):  
Hee Kim ◽  
Thomas Ganslandt ◽  
Thomas Miethke ◽  
Michael Neumaier ◽  
Maximilian Kittel
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Image Interpretation ◽  
Image Data ◽  
Data Interpretation ◽  
Routine Care ◽  
Fine Tuning ◽  
Learning Technology ◽  
Gram Stain ◽  
Computational Performance

BACKGROUND In recent years, remarkable progress has been made in deep learning technology and successful use cases have been introduced in the medical domain. However, not many studies have considered high-performance computing to fully appreciate the capability of deep learning technology. OBJECTIVE This paper aims to design a solution to accelerate an automated Gram stain image interpretation by means of a deep learning framework without additional hardware resources. METHODS We will apply and evaluate 3 methodologies, namely fine-tuning, an integer arithmetic–only framework, and hyperparameter tuning. RESULTS The choice of pretrained models and the ideal setting for layer tuning and hyperparameter tuning will be determined. These results will provide an empirical yet reproducible guideline for those who consider a rapid deep learning solution for Gram stain image interpretation. The results are planned to be announced in the first quarter of 2021. CONCLUSIONS Making a balanced decision between modeling performance and computational performance is the key for a successful deep learning solution. Otherwise, highly accurate but slow deep learning solutions can add value to routine care. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/16843

scholarly journals Deep Learning of COVID-19 Chest X-Rays: New Models or Fine Tuning?

2020 ◽  
Author(s):  
Tuan Pham
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Data Augmentation ◽  
Dominant Role ◽  
Care Center ◽  
Characteristic Curve ◽  
Fine Tuning ◽  
Urgent Care ◽  
X Rays ◽  
Training Time

Chest X-rays have been found to be very promising for assessing COVID-19 patients, especially for resolving emergency-department and urgent-care-center overcapacity. Deep-learning (DL) methods in artificial intelligence (AI) play a dominant role as high-performance classifiers in the detection of the disease using chest X-rays. While many new DL models have been being developed for this purpose, this study aimed to investigate the fine tuning of pretrained convolutional neural networks (CNNs) for the classification of COVID-19 using chest X-rays. Three pretrained CNNs, which are AlexNet, GoogleNet, and SqueezeNet, were selected and fine-tuned without data augmentation to carry out 2-class and 3-class classification tasks using 3 public chest X-ray databases. In comparison with other recently developed DL models, the 3 pretrained CNNs achieved very high classification results in terms of accuracy, sensitivity, specificity, precision, F1 score, and area under the receiver-operating-characteristic curve. AlexNet, GoogleNet, and SqueezeNet require the least training time among pretrained DL models, but with suitable selection of training parameters, excellent classification results can be achieved without data augmentation by these networks. The findings contribute to the urgent need for harnessing the pandemic by facilitating the deployment of AI tools that are fully automated and readily available in the public domain for rapid implementation.

scholarly journals Deep learning based automatic segmentation of metastasis hotspots in thorax bone SPECT images

PLoS ONE ◽  
2020 ◽  
Vol 15 (12) ◽  
pp. e0243253
Author(s):  
Qiang Lin ◽  
Mingyang Luo ◽  
Ruiting Gao ◽  
Tongtong Li ◽  
Zhengxing Man ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fine Tuning ◽  
Disease Stage ◽  
Whole Body ◽  
Learning Technology ◽  
Automatic Assessment ◽  
Original Dataset ◽  
Bone Spect ◽  
Segmentation Models ◽  
Spect Images

SPECT imaging has been identified as an effective medical modality for diagnosis, treatment, evaluation and prevention of a range of serious diseases and medical conditions. Bone SPECT scan has the potential to provide more accurate assessment of disease stage and severity. Segmenting hotspot in bone SPECT images plays a crucial role to calculate metrics like tumor uptake and metabolic tumor burden. Deep learning techniques especially the convolutional neural networks have been widely exploited for reliable segmentation of hotspots or lesions, organs and tissues in the traditional structural medical images (i.e., CT and MRI) due to their ability of automatically learning the features from images in an optimal way. In order to segment hotspots in bone SPECT images for automatic assessment of metastasis, in this work, we develop several deep learning based segmentation models. Specifically, each original whole-body bone SPECT image is processed to extract the thorax area, followed by image mirror, translation and rotation operations, which augments the original dataset. We then build segmentation models based on two commonly-used famous deep networks including U-Net and Mask R-CNN by fine-tuning their structures. Experimental evaluation conducted on a group of real-world bone SEPCT images reveals that the built segmentation models are workable on identifying and segmenting hotspots of metastasis in bone SEPCT images, achieving a value of 0.9920, 0.7721, 0.6788 and 0.6103 for PA (accuracy), CPA (precision), Rec (recall) and IoU, respectively. Finally, we conclude that the deep learning technology have the huge potential to identify and segment hotspots in bone SPECT images.

scholarly journals The Old and the New: Can Physics-Informed Deep-Learning Replace Traditional Linear Solvers?

2021 ◽  
Vol 4 ◽  
Author(s):  
Stefano Markidis
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
High Performance ◽  
Critical Role ◽  
Low Frequency ◽  
Accurate Solution ◽  
Limiting Factor ◽  
Data Set ◽  
Linear Solvers ◽  
Computational Performance

Physics-Informed Neural Networks (PINN) are neural networks encoding the problem governing equations, such as Partial Differential Equations (PDE), as a part of the neural network. PINNs have emerged as a new essential tool to solve various challenging problems, including computing linear systems arising from PDEs, a task for which several traditional methods exist. In this work, we focus first on evaluating the potential of PINNs as linear solvers in the case of the Poisson equation, an omnipresent equation in scientific computing. We characterize PINN linear solvers in terms of accuracy and performance under different network configurations (depth, activation functions, input data set distribution). We highlight the critical role of transfer learning. Our results show that low-frequency components of the solution converge quickly as an effect of the F-principle. In contrast, an accurate solution of the high frequencies requires an exceedingly long time. To address this limitation, we propose integrating PINNs into traditional linear solvers. We show that this integration leads to the development of new solvers whose performance is on par with other high-performance solvers, such as PETSc conjugate gradient linear solvers, in terms of performance and accuracy. Overall, while the accuracy and computational performance are still a limiting factor for the direct use of PINN linear solvers, hybrid strategies combining old traditional linear solver approaches with new emerging deep-learning techniques are among the most promising methods for developing a new class of linear solvers.

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 Pheniqs 2.0: accurate, high-performance Bayesian decoding and confidence estimation for combinatorial barcode indexing

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Lior Galanti ◽  
Dennis Shasha ◽  
Kristin C. Gunsalus
Keyword(s):  
High Performance ◽  
Probability Model ◽  
Random Noise ◽  
Likelihood Estimation ◽  
Automated Analysis ◽  
Confidence Score ◽  
Data Interpretation ◽  
Fine Tuning ◽  
Confidence Estimation ◽  
Sequencing Errors

Abstract Background Systems biology increasingly relies on deep sequencing with combinatorial index tags to associate biological sequences with their sample, cell, or molecule of origin. Accurate data interpretation depends on the ability to classify sequences based on correct decoding of these combinatorial barcodes. The probability of correct decoding is influenced by both sequence quality and the number and arrangement of barcodes. The rising complexity of experimental designs calls for a probability model that accounts for both sequencing errors and random noise, generalizes to multiple combinatorial tags, and can handle any barcoding scheme. The needs for reproducibility and community benchmark standards demand a peer-reviewed tool that preserves decoding quality scores and provides tunable control over classification confidence that balances precision and recall. Moreover, continuous improvements in sequencing throughput require a fast, parallelized and scalable implementation. Results and discussion We developed a flexible, robustly engineered software that performs probabilistic decoding and supports arbitrarily complex barcoding designs. Pheniqs computes the full posterior decoding error probability of observed barcodes by consulting basecalling quality scores and prior distributions, and reports sequences and confidence scores in Sequence Alignment/Map (SAM) fields. The product of posteriors for multiple independent barcodes provides an overall confidence score for each read. Pheniqs achieves greater accuracy than minimum edit distance or simple maximum likelihood estimation, and it scales linearly with core count to enable the classification of > 11 billion reads in 1 h 15 m using < 50 megabytes of memory. Pheniqs has been in production use for seven years in our genomics core facility. Conclusion We introduce a computationally efficient software that implements both probabilistic and minimum distance decoders and show that decoding barcodes using posterior probabilities is more accurate than available methods. Pheniqs allows fine-tuning of decoding sensitivity using intuitive confidence thresholds and is extensible with alternative decoders and new error models. Any arbitrary arrangement of barcodes is easily configured, enabling computation of combinatorial confidence scores for any barcoding strategy. An optimized multithreaded implementation assures that Pheniqs is faster and scales better with complex barcode sets than existing tools. Support for POSIX streams and multiple sequencing formats enables easy integration with automated analysis pipelines.

scholarly journals Pheniqs 2.0: accurate, high performance Bayesian decoding and confidence estimation for combinatorial barcode indexing

2021 ◽  
Author(s):  
Lior Galanti ◽  
Dennis Shasha ◽  
Kristin C. Gunsalus
Keyword(s):  
High Performance ◽  
Probability Model ◽  
Random Noise ◽  
Likelihood Estimation ◽  
Automated Analysis ◽  
Confidence Score ◽  
Data Interpretation ◽  
Fine Tuning ◽  
Confidence Estimation ◽  
Sequencing Errors

AbstractBackgroundSystems biology increasingly relies on deep sequencing with combinatorial index tags to associate biological sequences with their sample, cell, or molecule of origin. Accurate data interpretation depends on the ability to classify sequences based on correct decoding of these combinatorial barcodes. The probability of correct decoding is influenced by both sequence quality and the number and arrangement of barcodes. The rising complexity of experimental designs calls for a probability model that accounts for both sequencing errors and random noise, generalizes to multiple combinatorial tags, and can handle any barcoding scheme. The needs for reproducibility and community benchmark standards demand a peer-reviewed tool that preserves decoding quality scores and provides tunable control over classification confidence that balances precision and recall. Moreover, continuous improvements in sequencing throughput require a fast, parallelized and scalable implementation.ResultsWe developed a flexible, robustly engineered software that performs probabilistic decoding and supports arbitrarily complex barcoding designs. Pheniqs computes the full posterior decoding error probability of observed barcodes by consulting basecalling quality scores and prior distributions, and reports sequences and confidence scores in Sequence Alignment/Map (SAM) fields. The product of posteriors for multiple independent barcodes provides an overall confidence score for each read. Pheniqs achieves greater accuracy than minimum edit distance or simple maximum likelihood estimation, and it scales linearly with core count to enable the classification of >11 billion reads in 1h15m using <50 megabytes of memory. Pheniqs has been in production use for seven years in our genomics core facility.ConclusionsWe introduce a computationally efficient software that implements both probabilistic and minimum distance decoders and show that decoding barcodes using posterior probabilities is more accurate than available methods. Pheniqs allows fine-tuning of decoding sensitivity using intuitive confidence thresholds and is extensible with alternative decoders and new error models. Any arbitrary arrangement of barcodes is easily configured, enabling computation of combinatorial confidence scores for any barcoding strategy. An optimized multithreaded implementation assures that Pheniqs is faster and scales better with complex barcode sets than existing tools. Support for POSIX streams and multiple sequencing formats enables easy integration with automated analysis pipelines.

scholarly journals Deep Learning of COVID-19 Chest X-Rays: New Models or Fine Tuning?

2020 ◽  
Author(s):  
Tuan Pham
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Data Augmentation ◽  
Dominant Role ◽  
Care Center ◽  
Characteristic Curve ◽  
Fine Tuning ◽  
Urgent Care ◽  
X Rays ◽  
Training Time

Chest X-rays have been found to be very promising for assessing COVID-19 patients, especially for resolving emergency-department and urgent-care-center overcapacity. Deep-learning (DL) methods in artificial intelligence (AI) play a dominant role as high-performance classifiers in the detection of the disease using chest X-rays. While many new DL models have been being developed for this purpose, this study aimed to investigate the fine tuning of pretrained convolutional neural networks (CNNs) for the classification of COVID-19 using chest X-rays. Three pretrained CNNs, which are AlexNet, GoogleNet, and SqueezeNet, were selected and fine-tuned without data augmentation to carry out 2-class and 3-class classification tasks using 3 public chest X-ray databases. In comparison with other recently developed DL models, the 3 pretrained CNNs achieved very high classification results in terms of accuracy, sensitivity, specificity, precision, F1 score, and area under the receiver-operating-characteristic curve. AlexNet, GoogleNet, and SqueezeNet require the least training time among pretrained DL models, but with suitable selection of training parameters, excellent classification results can be achieved without data augmentation by these networks. The findings contribute to the urgent need for harnessing the pandemic by facilitating the deployment of AI tools that are fully automated and readily available in the public domain for rapid implementation.

scholarly journals Toward Efficient Image Recognition in Sensor-Based IoT: A Weight Initialization Optimizing Method for CNN Based on RGB Influence Proportion

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2866 ◽  
Author(s):  
Zile Deng ◽  
Yuanlong Cao ◽  
Xinyu Zhou ◽  
Yugen Yi ◽  
Yirui Jiang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Image Data ◽  
Human Vision ◽  
Learning Technology ◽  
Complex Data ◽  
Training Process ◽  
Color Differences ◽  
Weight Initialization ◽  
The Internet Of Things

As the Internet of Things (IoT) is predicted to deal with different problems based on big data, its applications have become increasingly dependent on visual data and deep learning technology, and it is a big challenge to find a suitable method for IoT systems to analyze image data. Traditional deep learning methods have never explicitly taken the color differences of data into account, but from the experience of human vision, colors play differently significant roles in recognizing things. This paper proposes a weight initialization method for deep learning in image recognition problems based on RGB influence proportion, aiming to improve the training process of the learning algorithms. In this paper, we try to extract the RGB proportion and utilize it in the weight initialization process. We conduct several experiments on different datasets to evaluate the effectiveness of our proposal, and it is proven to be effective on small datasets. In addition, as for the access to the RGB influence proportion, we also provide an expedient approach to get the early proportion for the following usage. We assume that the proposed method can be used for IoT sensors to securely analyze complex data in the future.

scholarly journals Detection of Apple Lesions in Orchards Based on Deep Learning Methods of CycleGAN and YOLOV3-Dense

2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Yunong Tian ◽  
Guodong Yang ◽  
Zhe Wang ◽  
En Li ◽  
Zize Liang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Optical Sensors ◽  
Data Augmentation ◽  
Image Data ◽  
Disease Diagnosis ◽  
Lesion Detection ◽  
Training Data ◽  
Yield Reduction ◽  
Learning Technology

Plant disease is one of the primary causes of crop yield reduction. With the development of computer vision and deep learning technology, autonomous detection of plant surface lesion images collected by optical sensors has become an important research direction for timely crop disease diagnosis. In this paper, an anthracnose lesion detection method based on deep learning is proposed. Firstly, for the problem of insufficient image data caused by the random occurrence of apple diseases, in addition to traditional image augmentation techniques, Cycle-Consistent Adversarial Network (CycleGAN) deep learning model is used in this paper to accomplish data augmentation. These methods effectively enrich the diversity of training data and provide a solid foundation for training the detection model. In this paper, on the basis of image data augmentation, densely connected neural network (DenseNet) is utilized to optimize feature layers of the YOLO-V3 model which have lower resolution. DenseNet greatly improves the utilization of features in the neural network and enhances the detection result of the YOLO-V3 model. It is verified in experiments that the improved model exceeds Faster R-CNN with VGG16 NET, the original YOLO-V3 model, and other three state-of-the-art networks in detection performance, and it can realize real-time detection. The proposed method can be well applied to the detection of anthracnose lesions on apple surfaces in orchards.

Sign in / Sign up

Export Citation Format

Share Document