A novel multi-scale based deep convolutional neural network for detecting COVID-19 from X-rays

Karnati, Mohan; Seal, Ayan; Sahu, Geet; Yazidi, Anis; Krejcar, Ondřej

doi:10.1016/j.asoc.2022.109109

Cited by 30 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Performance is evaluated based on two datasets by calculating precision, recall, F 1-score, and accuracy:

where TN is the number of true negatives, TP is the number of true positives, and FN and FP are the number of false negatives [ 31 ] and false positives, respectively [ 31 ]. We calculated the precision of individual subjects for the classification of human emotions.…”

Section: Resultsmentioning

confidence: 99%

“…In Table 1 , it is clearly shown that our proposed method achieves better accuracy measures than existing methods such as discrete wavelet transform (DWT) with multilayer perceptron neural network (MLPNN) and spectral entropy calculation with a deep learning model of bidirectional long-short term memory (BiLSTM) [ 29 , 31 ]. The average accuracy of our proposed method is smaller than the prime pattern network with a support vector machine (SVM) [ 34 ], but our proposed system used the multichannel approach to calculate the features from all 14 channels of EEG.…”

Section: Resultsmentioning

confidence: 99%

“…The loss function in this model is the binary crossentropy used to evaluate the binary classification problem. The performance of the ANN model has then been estimated using the cross-validation procedure utilising 10-fold cross-validation [ 28 , 31 ]. For both datasets, the networks for each person have been trained separately.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Entropy-Based Emotion Recognition from Multichannel EEG Signals Using Artificial Neural Network

Aung

Hassan²,

Brady

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Humans experience a variety of emotions throughout the course of their daily lives, including happiness, sadness, and rage. As a result, an effective emotion identification system is essential for electroencephalography (EEG) data to accurately reflect emotion in real-time. Although recent studies on this problem can provide acceptable performance measures, it is still not adequate for the implementation of a complete emotion recognition system. In this research work, we propose a new approach for an emotion recognition system, using multichannel EEG calculation with our developed entropy known as multivariate multiscale modified-distribution entropy (MM-mDistEn) which is combined with a model based on an artificial neural network (ANN) to attain a better outcome over existing methods. The proposed system has been tested with two different datasets and achieved better accuracy than existing methods. For the GAMEEMO dataset, we achieved an average accuracy ± standard deviation of 95.73% ± 0.67 for valence and 96.78% ± 0.25 for arousal. Moreover, the average accuracy percentage for the DEAP dataset reached 92.57% ± 1.51 in valence and 80.23% ± 1.83 in arousal.

show abstract

“…Performance is evaluated based on two datasets by calculating precision, recall, F 1-score, and accuracy:

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Entropy-Based Emotion Recognition from Multichannel EEG Signals Using Artificial Neural Network

Aung

Hassan²,

Brady

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The detection of small-scale pedestrians is a difficult task in computer vision, mainly because small-scale pedestrians occupy fewer pixels and carry less semantic information than large targets. Many previously developed CNN models, from RCNN-based [19] object detection methods to multiscale feature-based object detection methods built on SPP networks [18] and multiscale deep CNNs (MSCNN) [26], have struggled to solve the small object detection problem. Researchers are becoming increasingly inclined to process features rather than perform a series of operations on images.…”

Section: Attention Mechanismsmentioning

confidence: 99%

An improved YOLO algorithm with multisensing for pedestrian detection

Gong,

Wang,

Huang

et al. 2024

SIViP

View full text Add to dashboard Cite

Although pedestrian detection techniques are improving, this task is still challenging due to the problems of target occlusion, small targets, and complex pedestrian backgrounds in images of different scenes. As a result, the You Only Look Once (YOLO) algorithm exhibits lower detection accuracy. In this paper, the use of multiple dilated convolutions to sample feature images is proposed avoid the information loss incurred repeated sampling, to improve the feature extraction and target detection performance of the algorithm.In addition, a lightweight shuffle-based efficient channel attention (SECA) mechanism is introduced to conduct grouping in the channel dimension and perform parallel processing for each subfeature map channel. A new branch is introduced to enrich the channel feature information for multiscale feature representation. Finally, a distance intersection over union-based nonmaximum suppression (DIoU-NMS) method is introduced to minimize the occurrence of missed targets due to occlusion by taking the prediction box and ground truth box centroid locations information into account without increasing the computational cost over that of normal NMS. Our method is extensively evaluated on several challenging pedestrian detection datasets, achieving 87.73%, 34.7%, 93.96% and 95.23% mean average precision (mAP) values on PASCAL VOC 2012, MS COCO, Caltech Pedestrian and INRIA Person, which are respectively. The experimental results demonstrate the effectiveness of the method.

show abstract

“…Because COVID-19 medical images were still limited in 2021, prior studies often focused on demonstrating the feasibility of deep learning models in distinguishing COVID-19 cases from normal subjects or patients with other respiratory diseases, such as pneumonia [14][15][16]. These studies either used chest X-ray images or CT scans [17][18][19][20][21][22] and were designed as either binary or multi-class classifications [23,24]. In general, the model classification accuracy was higher using chest X-ray images (90%+) than using CT (~85%) and was higher (1-5%) in binary than multi-class classifications [10,25,26].…”

Section: Introductionmentioning

confidence: 99%

Multi-Level Training and Testing of CNN Models in Diagnosing Multi-Center COVID-19 and Pneumonia X-ray Images

Talaat,

Si,

2023

Applied Sciences

View full text Add to dashboard Cite

This study aimed to address three questions in AI-assisted COVID-19 diagnostic systems: (1) How does a CNN model trained on one dataset perform on test datasets from disparate medical centers? (2) What accuracy gains can be achieved by enriching the training dataset with new images? (3) How can learned features elucidate classification results, and how do they vary among different models? To achieve these aims, four CNN models—AlexNet, ResNet-50, MobileNet, and VGG-19—were trained in five rounds by incrementally adding new images to a baseline training set comprising 11,538 chest X-ray images. In each round, the models were tested on four datasets with decreasing levels of image similarity. Notably, all models showed performance drops when tested on datasets containing outlier images or sourced from other clinics. In Round 1, 95.2~99.2% accuracy was achieved for the Level 1 testing dataset (i.e., from the same clinic but set apart for testing only), and 94.7~98.3% for Level 2 (i.e., from an external clinic but similar). However, model performance drastically decreased for Level 3 (i.e., outlier images with rotation or deformation), with the mean sensitivity plummeting from 99% to 36%. For the Level 4 testing dataset (i.e., from another clinic), accuracy decreased from 97% to 86%, and sensitivity from 99% to 67%. In Rounds 2 and 3, adding 25% and 50% of the outlier images to the training dataset improved the average Level-3 accuracy by 15% and 23% (i.e., from 56% to 71% to 83%). In Rounds 4 and 5, adding 25% and 50% of the external images increased the average Level-4 accuracy from 81% to 92% and 95%, respectively. Among the models, ResNet-50 demonstrated the most robust performance across the five-round training/testing phases, while VGG-19 persistently underperformed. Heatmaps and intermediate activation features showed visual correlations to COVID-19 and pneumonia X-ray manifestations but were insufficient to explicitly explain the classification. However, heatmaps and activation features at different rounds shed light on the progression of the models’ learning behavior.

show abstract

A novel multi-scale based deep convolutional neural network for detecting COVID-19 from X-rays

Cited by 30 publications

References 36 publications

Entropy-Based Emotion Recognition from Multichannel EEG Signals Using Artificial Neural Network

Entropy-Based Emotion Recognition from Multichannel EEG Signals Using Artificial Neural Network

An improved YOLO algorithm with multisensing for pedestrian detection

Multi-Level Training and Testing of CNN Models in Diagnosing Multi-Center COVID-19 and Pneumonia X-ray Images

Contact Info

Product

Resources

About