A Comprehensive Analysis of Deep Learning-Based Approaches for Prediction and Prognosis of Infectious Diseases

Thakur, Kashish; Kaur, Manjot; Kumar, Yogesh

doi:10.1007/s11831-023-09952-7

Cited by 11 publications

(2 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [20] categorizes cataracts into normal and cataract groups, with average accuracies ranging from 91.06% to 93.50% using models like VGG19 and ResNet. Transfer learning is applied in [21], where an ensemble technique combining VGG19, ResNet101V2, and InceptionV3 achieves an F1_score of 95.90% on a test dataset.…”

Section: Introductionmentioning

confidence: 99%

CSDNet: A Novel Deep Learning Framework for Improved Cataract State Detection

P.L,

Vaddi,

Elish

et al. 2024

Diagnostics

View full text Add to dashboard Cite

Cataracts, known for lens clouding and being a common cause of visual impairment, persist as a primary contributor to vision loss and blindness, presenting notable diagnostic and prognostic challenges. This work presents a novel framework called the Cataract States Detection Network (CSDNet), which utilizes deep learning methods to improve the detection of cataract states. The aim is to create a framework that is more lightweight and adaptable for use in environments or devices with limited memory or storage capacity. This involves reducing the number of trainable parameters while still allowing for effective learning of representations from data. Additionally, the framework is designed to be suitable for real-time or near-real-time applications where rapid inference is essential. This study utilizes cataract and normal images from the Ocular Disease Intelligent Recognition (ODIR) database. The suggested model employs smaller kernels, fewer training parameters, and layers to efficiently decrease the number of trainable parameters, thereby lowering computational costs and average running time compared to other pre-trained models such as VGG19, ResNet50, DenseNet201, MIRNet, Inception V3, Xception, and Efficient net B0. The experimental results illustrate that the proposed approach achieves a binary classification accuracy of 97.24% (normal or cataract) and an average cataract state detection accuracy of 98.17% (normal, grade 1—minimal cloudiness, grade 2—immature cataract, grade 3—mature cataract, and grade 4—hyper mature cataract), competing with state-of-the-art cataract detection methods. The resulting model is lightweight at 17 MB and has fewer trainable parameters (175, 617), making it suitable for deployment in environments or devices with constrained memory or storage capacity. With a runtime of 212 ms, it is well-suited for real-time or near-real-time applications requiring rapid inference.

show abstract

Section: Introductionmentioning

confidence: 99%

CSDNet: A Novel Deep Learning Framework for Improved Cataract State Detection

P.L,

Vaddi,

Elish

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Moreover, AI's ability to assess individual and population risk variables can prioritize infectious disease prevention and resource allocation. Additionally, machine learning and deep learning techniques have accelerated medication and vaccine development (3) .…”

Section: Introductionmentioning

confidence: 99%

Automated System for Prediction and Prognosis of Infection Diseases Using Deep Learning-Based Approaches

Thakur,

Sandhu,

Kumar

2023

IJST

View full text Add to dashboard Cite

Objectives: This study explores the potential of deep learning-based techniques to improve disease management and intervention by focusing on their use in infectious disease prediction and prognosis. Methods: The research used deep learning models EfficientNetB0, NASNetLarge, DenseNet169, ResNet152V2, and InceptionResNetV2. For this study, a dataset comprising 29,252 images of different diseases such as COVID-19, MERS, Pneumonia, SARS, and tuberculosis. To visualize pixel intensity, exploratory data analysis was performed on the pictures. Preprocessing eliminated disruptive signals via image augmentation and contrast enhancement. After that, Otsu thresholding and contour feature morphological values retrieved relevant features. Findings: The best successful model was found to be EfficientNetB0. During training, it obtained a 90.22% accuracy rate, a loss of 0.279, having an RMSE value of 0.578. However, InceptionResNetV2 showed the best accuracy, loss, and RMSE values throughout model testing. The precise accuracy, loss, and RMSE results were 88%, 0.399, and 0.631, respectively. Novelty: The novelty resides in exploring methods based on deep learning for predicting and prognosticating infectious diseases, with the potential for handling diseases, strategies for intervention, and public health decisions.

show abstract