A Transfer Learning Approach for Diabetic Retinopathy and Diabetic Macular Edema Severity Grading

Nasir, Nida; Afreen, Neda; Patel, Ranjeeta; Kaur, Simran; Sameer, Mustafa

doi:10.18280/ria.350608

Cited by 16 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results are forwarded back to the main node for additional processing when the sub-issues have been resolved [18]. The use of big data analytics in the diabetic retinopathy healthcare sector has increased recently, with Apache Spark engine as a key tool for processing and analyzing enormous amounts of healthcare data [19][20][21][22][23].…”

Section: Deployment and Monitoring And Resultsmentioning

confidence: 99%

Apache Spark for Analysis of Electronic Health Records: A Case Study of Diabetes Management

Sharma,

Parashar,

Mengshetti

et al. 2023

RIA

View full text Add to dashboard Cite

Electronic Health Records (EHRs), heralded for their potential to revolutionize healthcare outcomes, function as repositories for invaluable data. This study offers a compelling exploration into the integration of Apache Spark for EHR analysis, with a specific focus on elevating diabetes care. Leveraging Apache Spark alongside a robust machine learning framework, we automated EHR analysis by processing extensive datasets, conducting thorough preprocessing, and extracting pertinent features. The inherent distributed processing capabilities of Apache Spark facilitated concurrent training and evaluation of machine learning models. Its in-memory data processing markedly reduced reliance on disk input/output, thereby enhancing performance and scalability. This methodology enabled swift and thorough EHR data analysis, with ensuing insights effectively visualized and reported. This empowered healthcare professionals to make informed decisions. The iterative nature of the process allowed for continuous refinement, enhancing healthcare outcomes based on insightful data. The synergy between Apache Spark and machine learning techniques in EHR analysis emerged as a potent and efficient strategy. This approach exhibits promise in significantly advancing healthcare outcomes by enabling effective prediction and management of diabetes, ultimately contributing to superior patient care and reducing healthcare costs. The findings underscore the transformative potential of integrating contemporary data analysis tools within the healthcare sector.

show abstract

Section: Deployment and Monitoring And Resultsmentioning

confidence: 99%

Apache Spark for Analysis of Electronic Health Records: A Case Study of Diabetes Management

Sharma,

Parashar,

Mengshetti

et al. 2023

RIA

View full text Add to dashboard Cite

show abstract

“…AI has been tested in different areas of the medical profession. The distinction between normal and malignant breast cancer cells using electric circuit networks [32] or the detection of diabetic retinopathy by the employment of Convolutional Neural Networks [33,34] Biosensors have also proven to be helpful for COVID-19 diagnosis [35], as similar devices have been found useful to identify hematuria [36] or kidney stones [37]. Integrating AI in identifying specific chest CT scan patterns can significantly improve the diagnostic precision of COVID-19 pneumonia.…”

Section: Discussionmentioning

confidence: 99%

Chest CT Scan Features of COVID-19 in a Hospitalized High-Altitude Population

Calderón-Gerstein,

Torres - Samaniego,

Pazos-Sovero

2024

OBM Genet

View full text Add to dashboard Cite

There is a lack of knowledge regarding the type of lung compromise in high-altitude residents with COVID-19. This study aims to evaluate the lung compromise in chest CT scans of high-altitude dwellers hospitalized with COVID-19. Retrospective study that took place in "Daniel Alcides Carrión" Regional Hospital, located 3,250 meters above sea level in the city of Huancayo, Perú. 464 medical charts and chest CT images of hospitalized patients with confirmed COVID-19 from January to March 2021 were reviewed. The mean age was 56 years, 63.1% of the patients were male, and 85.8% of individuals had a CORADS 5. Ground glass infiltrates were found in 93.8% of the patients; alveolar consolidations were present in 86% and were usually bilateral. Thickened septa were described in 46%, lattice pattern in 38.8%, reticular components in 39%, and the crazy paving pattern in 36.9%. Most patients (84.5%) had central and peripheral lesions; only 4% had limited peripheral compromise, and 10% solely central distribution. The left posterior basal segment was the most affected pulmonary segment in 27% of the cases, and the right basal posterior in 26%. Less affected segments were the right and left apical (14% and 13%, respectively). Lung compromise in patients with COVID-19 in this high-altitude population was severe, with mostly bilateral compromise, increased diameter of the pulmonary artery, periaortic and subaortic lymph nodes enlargement, and extensive ground glass and alveolar lesions.

show abstract

“…Those architectures were already pre-trained on ImageNet and gives a satisfactory classification performance. The APTOS2019 [5] dataset was then fine-tuned in those pre-trained models and then trained with 0.001 learning rate using Adam optimizer, batch size of 16, and 150 of epoch. To prevent overfitting, we use an early stopping monitor to monitor the validation loss and configured it with 15 patience, and min delta of 0.005. for loss computing, we use categorical crossentropy.…”

Section: Modellingmentioning

confidence: 99%

“…Their experiment results clearly show signs of overfitting and should possibly be improved. Their works also lack preprocessing techniques that possibly can contribute to providing better results [5].…”

Section: Introductionmentioning

confidence: 99%

Severity Classification of Diabetic Retinopathy Using Ensemble Stacking Method

Handoyo¹,

Kusuma²

2022

RIA

View full text Add to dashboard Cite

Diabetic retinopathy (DR), is a complication resulting from the disease that can lead to blindness if not detected early. Recently, many classification systems for diabetic retinopathy have been developed. However, several problems were found, namely, the classification results in certain classes still have less than optimal accuracy values, the lack of in-depth analysis for the results, and the overall accuracy that can still be improved. In this work, we experiment by evaluating and combining new deep learning models such as EfficientNet, EfficientNetV2, LCNet, MobileNetV3, TinyNet, and FBNetV3 using ensemble stacking techniques with four different meta-learners: decision trees, logistic regression, ANN, and SVM to provide better accuracy in classifying the severity of diabetic retinopathy. Our work offers satisfactory classification results on the APTOS 2019 dataset with training, validation, testing, and F1 score accuracy of 96.56%, 95.33%, 84.17%, and 70.16%, respectively.

show abstract

A Transfer Learning Approach for Diabetic Retinopathy and Diabetic Macular Edema Severity Grading

Cited by 16 publications

References 24 publications

Apache Spark for Analysis of Electronic Health Records: A Case Study of Diabetes Management

Apache Spark for Analysis of Electronic Health Records: A Case Study of Diabetes Management

Chest CT Scan Features of COVID-19 in a Hospitalized High-Altitude Population

Severity Classification of Diabetic Retinopathy Using Ensemble Stacking Method

Contact Info

Product

Resources

About