Grading diabetic retinopathy and prostate cancer diagnostic images with deep quantum ordinal regression

Toledo-Cortés, Santiago; Useche, Diego H.; Müller, Henning; González, Fabio A.

doi:10.1016/j.compbiomed.2022.105472

Cited by 19 publications

(13 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The grading task in retinal fundus images could be modeled as either binary, multi-categorical classification or ordinal regression in a multiclass problem, and the diagnostic performance of each model will vary according to it. 33,34 The proposed model is modeled as a multi-categorical classification model. The precision, recall, f1-score, U-kappa scores obtained after experimenting proposed technique in grading DR and DME images are evaluated.…”

Section: Performance Of the Proposed Methodsmentioning

confidence: 99%

An effective deep learning model for grading abnormalities in retinal fundus images using variational auto‐encoders

Sundar

Sumathy

2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Diabetic retinopathy (DR) and Diabetic Macular Edema (DME) are severe diseases that affect the eyes due to damage in blood vessels. Computer-aided automated grading will help clinicians conduct disease diagnoses at ease. Experiments of automated image processing with deep learning techniques using CNN produce promising results, especially in the medical imaging domain. However, the disease grading tasks in retinal images using CNN struggle to retain high-quality information at the output. A novel deep learning model based on variational auto-encoder to grade DR and DME abnormalities in retinal images is proposed. The objective of the proposed model is to extract the most relevant retinal image features efficiently. It focuses on addressing less relevant candidate region generation and translational invariance present in images. The experiments are conducted in IDRID dataset and evaluated using accuracy, U-kappa, sensitivity, specificity and precision metrics. The results outperform compared with other state-of-art techniques.

show abstract

Section: Performance Of the Proposed Methodsmentioning

confidence: 99%

An effective deep learning model for grading abnormalities in retinal fundus images using variational auto‐encoders

Sundar

Sumathy

2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“… 15 , 31 , 32 , 33 , 49 , 50 , 51 , 52 Additionally, various new techniques have been proposed to improve AI model performance, such as knowledge distillation, deep quantum ordinal regression, and pyramid semantic parsing network. 53 , 54 , 55 …”

Section: Development Of Ai Models For Prostate Cancer Managementmentioning

confidence: 99%

“…This can serve as a quality control tool for AI-based diagnoses, allowing pathologists to decide whether to trust the model’s prediction. 54 , 80 …”

Section: Challenges Of Application Of Ai In Clinicmentioning

confidence: 99%

Harnessing artificial intelligence for prostate cancer management

Zhu,

Pan,

Mou

et al. 2024

Cell Reports Medicine

View full text Add to dashboard Cite

“…The strong point of this study is that the radial Bayesian neural network outperformed by a wide margin MFVI, and even outperform deep ensemble and MC-dropout models. Toledo-Cortés et al [66] presented a Deep Probabilistic Learning Ordinal Regression model for the diagnosis of medical images. An evaluation of the method was conducted on two various medical image analysis tasks: the diagnosis of prostate cancer and the estimation of diabetic retinopathy grade on the fundus image.…”

Section: Literature Reviewmentioning

confidence: 99%

Bayesian deep learning methods applied to diabetic retinopathy disease: a review

Ismail

Hassan²

2023

IJEECS

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a complication of diabetes that cause retinal damage; therefore, it is a leading cause of blindness. However, early detection of this disease can dramatically reduce the risk of vision loss. The main problem of early DR detection is that the manual diagnosis by ophthalmology is time-consuming, expensive, and prone to misdiagnosis. Deep learning (DL) models have aided in the early diagnosis of DR, and DL is now frequently utilized in DR detection and classification. The main issues with classical DL models is that they are incapable to quantify the uncertainty in the models, thus they are prone to make wrong decisions in complex cases. However, Bayesian deep learning (BDL) models have recently evolved as unified probabilistic framework to integrate DL and Bayesian models to provides an accurate framework to identify all sources of uncertainty in the model. This paper introduces BDL and most recent research that used BDL approaches to treat diabetic retinopathy are reviewed and discussed. A thorough comparison of the existing Bayesian approaches in this topic is also presented. In addition, available datasets for the fundus retina, which is often employed in DR, are provided and reviewed.

show abstract

Grading diabetic retinopathy and prostate cancer diagnostic images with deep quantum ordinal regression

Cited by 19 publications

References 42 publications

An effective deep learning model for grading abnormalities in retinal fundus images using variational auto‐encoders

An effective deep learning model for grading abnormalities in retinal fundus images using variational auto‐encoders

Harnessing artificial intelligence for prostate cancer management

Bayesian deep learning methods applied to diabetic retinopathy disease: a review

Contact Info

Product

Resources

About