Deep Metric Learning Network using Proxies for Chromosome Classification and Retrieval in Karyotyping Test

AbstractIn karyotyping, the classification of chromosomes is a tedious, complicated, and time-consuming process. It requires extremely careful analysis of chromosomes by well-trained cytogeneticists. To assist cytogeneticists in karyotyping, we introduce Proxy-ResNeXt-CBAM which is a metric learning based network using proxies with a convolutional block attention module (CBAM) designed for chromosome classification. RexNeXt-50 is used as a backbone network. To apply metric learning, the fully connected linear layer of the backbone network (ResNeXt-50) is removed and is replaced with CBAM. The similarity between embeddings, which are the outputs of the metric learning network, and proxies are measured for network training.Proxy-ResNeXt-CBAM is validated on a public chromosome image dataset, and it achieves an accuracy of 95.86%, a precision of 95.87%, a recall of 95.9%, and an F-1 score of 95.79%. Proxy-ResNeXt-CBAM which is the metric learning network using proxies outperforms the baseline networks. In addition, the results of our embedding analysis demonstrate the effectiveness of using proxies in metric learning for optimizing deep convolutional neural networks. As the embedding analysis results show, Proxy-ResNeXt-CBAM obtains a 94.78% Recall@1 in image retrieval, and the embeddings of each chromosome are well clustered according to their similarity.

Download Full-text

A Spatial Pyramid Pooling-Based Deep Convolutional Neural Network for the Classification of Electrocardiogram Beats

Applied Sciences ◽

10.3390/app8091590 ◽

2018 ◽

Vol 8 (9) ◽

pp. 1590 ◽

Cited By ~ 2

Author(s):

Jia Li ◽

Yujuan Si ◽

Liuqi Lang ◽

Lixun Liu ◽

Tao Xu

Keyword(s):

Classification Accuracy ◽

Massachusetts Institute Of Technology ◽

Deep Convolutional Neural Networks ◽

Beat Classification ◽

Spatial Pyramid Pooling ◽

Institute Of Technology ◽

Fixed Input ◽

Fully Connected ◽

Spatial Pyramid

An accurate electrocardiogram (ECG) beat classification can benefit the diagnosis of the cardiovascular disease. Deep convolutional neural networks (CNN) can automatically extract valid features from data, which is an effective way for the classification of the ECG beats. However, the fully-connected layer in CNNs requires a fixed input dimension, which limits the CNNs to receive fixed-scale inputs. Signals of different scales are generally processed into the same size by segmentation and downsampling. If information loss occurs during a uniformly-sized process, the classification accuracy will ultimately be affected. To solve this problem, this paper constructs a new CNN framework spatial pyramid pooling (SPP) method, which solves the deficiency caused by the size of input data. The Massachusetts Institute of Technology-Biotechnology (MIT-BIH) arrhythmia database is employed as the training and testing data for the classification of heartbeat signals into six categories. Compared with the traditional method, which may lose a large amount of important information and easy to be over-fitted, the robustness of the proposed method can be guaranteed by extracting data features from different sizes. Experimental results show that the proposed architecture network can extract more high-quality features and exhibits higher classification accuracy (94%) than the traditional deep CNNs (90.4%).

Download Full-text

CNN-based Classification of Degraded Images

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.10.ipas-028 ◽

2020 ◽

Vol 2020 (10) ◽

pp. 28-1-28-7 ◽

Cited By ~ 1

Author(s):

Kazuki Endo ◽

Masayuki Tanaka ◽

Masatoshi Okutomi

Keyword(s):

Neural Networks ◽

Image Restoration ◽

Image Classification ◽

Convolutional Neural Networks ◽

Deep Convolutional Neural Networks ◽

Alternative Approach ◽

Degraded Image ◽

Degraded Images ◽

Straightforward Approach

Classification of degraded images is very important in practice because images are usually degraded by compression, noise, blurring, etc. Nevertheless, most of the research in image classification only focuses on clean images without any degradation. Some papers have already proposed deep convolutional neural networks composed of an image restoration network and a classification network to classify degraded images. This paper proposes an alternative approach in which we use a degraded image and an additional degradation parameter for classification. The proposed classification network has two inputs which are the degraded image and the degradation parameter. The estimation network of degradation parameters is also incorporated if degradation parameters of degraded images are unknown. The experimental results showed that the proposed method outperforms a straightforward approach where the classification network is trained with degraded images only.

Download Full-text

Deep Convolutional Neural Networks Approach for Classification of Lung Diseases using X-Rays: COVID-19, Pneumonia, and Tuberculosis

International Journal of Performability Engineering ◽

10.23940/ijpe.20.09.p2.13321340 ◽

2020 ◽

Vol 16 (9) ◽

pp. 1332

Author(s):

Patil Narayani ◽

Ingole Kalyani ◽

Mangala T. Rajani

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Lung Diseases ◽

X Rays ◽

Deep Convolutional Neural Networks

Download Full-text

An aggregate method for thorax diseases classification

Scientific Reports ◽

10.1038/s41598-021-81765-9 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Bayu Adhi Nugroho

Keyword(s):

Network Architecture ◽

Classification Problem ◽

Calculation Algorithm ◽

Training Pattern ◽

Deep Network ◽

Network Training ◽

Chest X Ray ◽

Medical Image Classification ◽

Positive Pattern

AbstractA common problem found in real-word medical image classification is the inherent imbalance of the positive and negative patterns in the dataset where positive patterns are usually rare. Moreover, in the classification of multiple classes with neural network, a training pattern is treated as a positive pattern in one output node and negative in all the remaining output nodes. In this paper, the weights of a training pattern in the loss function are designed based not only on the number of the training patterns in the class but also on the different nodes where one of them treats this training pattern as positive and the others treat it as negative. We propose a combined approach of weights calculation algorithm for deep network training and the training optimization from the state-of-the-art deep network architecture for thorax diseases classification problem. Experimental results on the Chest X-Ray image dataset demonstrate that this new weighting scheme improves classification performances, also the training optimization from the EfficientNet improves the performance furthermore. We compare the aggregate method with several performances from the previous study of thorax diseases classifications to provide the fair comparisons against the proposed method.

Download Full-text

Freely scalable and reconfigurable optical hardware for deep learning

Scientific Reports ◽

10.1038/s41598-021-82543-3 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Liane Bernstein ◽

Alexander Sludds ◽

Ryan Hamerly ◽

Vivienne Sze ◽

Joel Emer ◽

...

Keyword(s):

Neural Network ◽

Energy Consumption ◽

Data Transfer ◽

Power Delivery ◽

Optical Data ◽

Optical Multicast ◽

Optical Neural Network ◽

Fully Connected ◽

Management Power

AbstractAs deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available compute power; however, efforts to continue to scale electronic processors are impeded by the costs of communication, thermal management, power delivery and clocking. To improve scalability, we propose a digital optical neural network (DONN) with intralayer optical interconnects and reconfigurable input values. The path-length-independence of optical energy consumption enables information locality between a transmitter and a large number of arbitrarily arranged receivers, which allows greater flexibility in architecture design to circumvent scaling limitations. In a proof-of-concept experiment, we demonstrate optical multicast in the classification of 500 MNIST images with a 3-layer, fully-connected network. We also analyze the energy consumption of the DONN and find that digital optical data transfer is beneficial over electronics when the spacing of computational units is on the order of $$>10\,\upmu $$ > 10 μ m.

Download Full-text

Explainable Fully Connected Visual Words for the Classification of Skin Cancer Confocal Images

11th Hellenic Conference on Artificial Intelligence ◽

10.1145/3411408.3411435 ◽

2020 ◽

Author(s):

Athanasios Kallipolitis ◽

Alexandros Stratigos ◽

Alexios Zarras ◽

Ilias Maglogiannis

Keyword(s):

Skin Cancer ◽

Visual Words ◽

Confocal Images ◽

Fully Connected

Download Full-text

Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time

Scientific Reports ◽

10.1038/s41598-021-89365-3 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Song-Quan Ong ◽

Hamdan Ahmad ◽

Gomesh Nair ◽

Pradeep Isawasan ◽

Abdul Hafiz Ab Majid

Keyword(s):

Deep Learning ◽

Aedes Aegypti ◽

Real Time ◽

Aedes Albopictus ◽

Automated Classification ◽

Expert Performance ◽

Deep Convolutional Neural Networks ◽

Significant Difference ◽

Set Up

AbstractClassification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) by humans remains challenging. We proposed a highly accessible method to develop a deep learning (DL) model and implement the model for mosquito image classification by using hardware that could regulate the development process. In particular, we constructed a dataset with 4120 images of Aedes mosquitoes that were older than 12 days old and had common morphological features that disappeared, and we illustrated how to set up supervised deep convolutional neural networks (DCNNs) with hyperparameter adjustment. The model application was first conducted by deploying the model externally in real time on three different generations of mosquitoes, and the accuracy was compared with human expert performance. Our results showed that both the learning rate and epochs significantly affected the accuracy, and the best-performing hyperparameters achieved an accuracy of more than 98% at classifying mosquitoes, which showed no significant difference from human-level performance. We demonstrated the feasibility of the method to construct a model with the DCNN when deployed externally on mosquitoes in real time.

Download Full-text

Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-021-01492-z ◽

2021 ◽

Vol 21 (S2) ◽

Author(s):

Kun Zeng ◽

Yibin Xu ◽

Ge Lin ◽

Likeng Liang ◽

Tianyong Hao

Keyword(s):

Clinical Trial ◽

Ensemble Learning ◽

Metric Learning ◽

Classification Performance ◽

Ensemble Model ◽

Automated Classification ◽

Eligibility Criteria ◽

Data Imbalance ◽

The Impact

Abstract Background Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data. Methods An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories. Results Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement. Conclusions A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

Download Full-text