Rethinking Densely Connected Convolutional Networks for Diagnosing Infectious Diseases

Podder, Prajoy; Alam, Fatema Binte; Mondal, M. Rubaiyat Hossain; Hasan, Junayed; Rohan, Ali; Bharati, Subrato

doi:10.3390/computers12050095

Cited by 12 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the number of COVID-19 instances registered was predicted using a cosine neighborhood-based LSTM. In 2023, Podder et al ( 32 ) developed DenseNet-169 and DenseNet-201 for Covid-19 detection by adjusting the hyperparameters via the Nadam optimization algorithm to enhance the model’s performance. 3312 CXR images were used.…”

Section: Related Workmentioning

confidence: 99%

Prediction of the COVID disease using lung CT images by Deep Learning algorithm: DETS-optimized Resnet 101 classifier

Haennah,

Christopher,

King

2023

Front. Med.

View full text Add to dashboard Cite

As a result of the COVID-19 (coronavirus) disease due to SARS-CoV2 becoming a pandemic, it has spread over the globe. It takes time to evaluate the results of the laboratory tests because of the rising number of cases each day. Therefore, there are restrictions in terms of both therapy and findings. A clinical decision-making system with predictive algorithms is needed to alleviate the pressure on healthcare systems via Deep Learning (DL) algorithms. With the use of DL and chest scans, this research intends to determine COVID-19 patients by utilizing the Transfer Learning (TL)-based Generative Adversarial Network (Pix 2 Pix-GAN). Moreover, the COVID-19 images are then classified as either positive or negative using a Duffing Equation Tuna Swarm (DETS)-optimized Resnet 101 classifier trained on synthetic and real images from the Kaggle lung CT Covid dataset. Implementation of the proposed technique is done using MATLAB simulations. Besides, is evaluated via accuracy, precision, F1-score, recall, and AUC. Experimental findings show that the proposed prediction model identifies COVID-19 patients with 97.2% accuracy, a recall of 95.9%, and a specificity of 95.5%, which suggests the proposed predictive model can be utilized to forecast COVID-19 infection by medical specialists for clinical prediction research and can be beneficial to them.

show abstract

Section: Related Workmentioning

confidence: 99%

Prediction of the COVID disease using lung CT images by Deep Learning algorithm: DETS-optimized Resnet 101 classifier

Haennah,

Christopher,

King

2023

Front. Med.

View full text Add to dashboard Cite

show abstract

“…When predicting heart disease, it's essential to consider various factors such as diabetes, hypertension, high cholesterol levels, and irregular heartbeat rates. Often, the incompleteness of medical data can hinder accurate disease prediction [11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Heart Disease Prediction using SVM

Rahmanul Hoque,

Masum Billah,

Amit Debnath

et al. 2024

Int. J. Sci. Res. Arch.

View full text Add to dashboard Cite

Diagnosing and predicting the outcome of cardiovascular disease are essential tasks in medicine that help ensure patients receive accurate classification and treatment from cardiologists. The use of machine learning in the healthcare sector has grown due to its ability to identify patterns in data. By applying machine learning techniques to classify the presence of cardiovascular diseases, it's possible to decrease the rate of misdiagnosis. This study aims to create a model capable of accurately forecasting cardiovascular diseases to minimize the deaths associated with these conditions. In this paper, two types of SVM model such as linear SVM and polynomial SVM is used. Accuracy, precision, recall and F1 score has been evaluated for comparing linear SVM and polynomial SVM. Polynomial SVM provides better accuracy than linear SVM.

show abstract

“…Brain tumors have the potential to be lethal if they are not treated, highlighting the significance of early diagnosis and treatment in order to enhance patient survival rates. Despite the fact that biopsies of brain tumors can be difficult to perform because of the intricacy of the brain, magnetic resonance imaging (MRI) is frequently utilized as a diagnostic tool [1][2][3][4][5][6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Brain Tumor Classification with Transfer Learning across Multiple Classes: An In-Depth Analysis

Ahmmed,

Podder,

Mondal

et al. 2023

BioMedInformatics

Self Cite

View full text Add to dashboard Cite

This study focuses on leveraging data-driven techniques to diagnose brain tumors through magnetic resonance imaging (MRI) images. Utilizing the rule of deep learning (DL), we introduce and fine-tune two robust frameworks, ResNet 50 and Inception V3, specifically designed for the classification of brain MRI images. Building upon the previous success of ResNet 50 and Inception V3 in classifying other medical imaging datasets, our investigation encompasses datasets with distinct characteristics, including one with four classes and another with two. The primary contribution of our research lies in the meticulous curation of these paired datasets. We have also integrated essential techniques, including Early Stopping and ReduceLROnPlateau, to refine the model through hyperparameter optimization. This involved adding extra layers, experimenting with various loss functions and learning rates, and incorporating dropout layers and regularization to ensure model convergence in predictions. Furthermore, strategic enhancements, such as customized pooling and regularization layers, have significantly elevated the accuracy of our models, resulting in remarkable classification accuracy. Notably, the pairing of ResNet 50 with the Nadam optimizer yields extraordinary accuracy rates, reaching 99.34% for gliomas, 93.52% for meningiomas, 98.68% for non-tumorous images, and 97.70% for pituitary tumors. These results underscore the transformative potential of our custom-made approach, achieving an aggregate testing accuracy of 97.68% for these four distinct classes. In a two-class dataset, Resnet 50 with the Adam optimizer excels, demonstrating better precision, recall, F1 score, and an overall accuracy of 99.84%. Moreover, it attains perfect per-class accuracy of 99.62% for ‘Tumor Positive’ and 100% for ‘Tumor Negative’, underscoring a remarkable advancement in the realm of brain tumor categorization. This research underscores the innovative possibilities of DL models and our specialized optimization methods in the domain of diagnosing brain cancer from MRI images.

show abstract

Rethinking Densely Connected Convolutional Networks for Diagnosing Infectious Diseases

Cited by 12 publications

References 31 publications

Prediction of the COVID disease using lung CT images by Deep Learning algorithm: DETS-optimized Resnet 101 classifier

Prediction of the COVID disease using lung CT images by Deep Learning algorithm: DETS-optimized Resnet 101 classifier

Heart Disease Prediction using SVM

Enhancing Brain Tumor Classification with Transfer Learning across Multiple Classes: An In-Depth Analysis

Contact Info

Product

Resources

About