PNN-based classification of retinal diseases using fundus images

Virmani, Jitendra; Singh, Gajendra Pratap; Singh, Yashmeet; Kriti, .

doi:10.1016/b978-0-12-819361-7.00011-7

Cited by 10 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diagnosing myopia by detecting lesions based on fundus images requires sufficient data for the deep learning model to have a steady performance ( Peng et al, 2019 ; Virmani et al, 2019 ). The iChallenge-PM dataset released by Baidu encourage the data-driven methods to automatically detect fundus lesion, it contains three types of fundus diseases images and lesion masks, as illustrate in Figure 1 , previous studies try to design general deep learning based methods to address the fundus disease identification and localization problems, which contain image classification and segmentation that are insufficient and slow, respectively.…”

Section: Methodsmentioning

confidence: 99%

MyopiaDETR: End-to-end pathological myopia detection based on transformer using 2D fundus images

Liu

Wang

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

BackgroundAutomated diagnosis of various retinal diseases based on fundus images can serve as an important clinical decision aid for curing vision loss. However, developing such an automated diagnostic solution is challenged by the characteristics of lesion area in 2D fundus images, such as morphology irregularity, imaging angle, and insufficient data.MethodsTo overcome those challenges, we propose a novel deep learning model named MyopiaDETR to detect the lesion area of normal myopia (NM), high myopia (HM) and pathological myopia (PM) using 2D fundus images provided by the iChallenge-PM dataset. To solve the challenge of morphology irregularity, we present a novel attentional FPN architecture and generate multi-scale feature maps to a traditional Detection Transformer (DETR) for detecting irregular lesion more accurate. Then, we choose the DETR structure to view the lesion from the perspective of set prediction and capture better global information. Several data augmentation methods are used on the iChallenge-PM dataset to solve the challenge of insufficient data.ResultsThe experimental results demonstrate that our model achieves excellent localization and classification performance on the iChallenge-PM dataset, reaching AP50 of 86.32%.ConclusionOur model is effective to detect lesion areas in 2D fundus images. The model not only achieves a significant improvement in capturing small objects, but also a significant improvement in convergence speed during training.

show abstract

Section: Methodsmentioning

confidence: 99%

MyopiaDETR: End-to-end pathological myopia detection based on transformer using 2D fundus images

Liu

Wang

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…To reduce the computational load associated with image processing, raw images were first converted to a grayscale (27, 28) and adjusted to a standard size using the Matlab ® Image Processing Toolbox™ grayscale conversion and resizing functions (29).…”

Section: Methodsmentioning

confidence: 99%

An image processing protocol to extract variables predictive of human embryo fitness for assisted reproduction

Chéles

Ferreira

Jesus

et al. 2022

Preprint

View full text Add to dashboard Cite

OBJECTIVE: To study the application of image processing for segmentation of blastocysts images and extraction of potential variables for prediction of embryo fitness. DESIGN: Retrospective study. SETTING: Single reproductive medical center. IVI-RMA (Valencia, Spain) between 2017 and 2019. PATIENTS: An initial dataset including 353 images from EmbryoScope and 474 images from Geri incubators was acquired, of which 320 images from EmbryoScope and 309 images from Geri incubators were used in this study. INTERVENTION(S): None. MAIN OUTCOME MEASURE(S): Successful segmentation of images into trophectoderm (TE), blastocoel, and inner cell mass (ICM) using the proposed processing steps. RESULTS: A total of 33 variables were automatically generated by digital image processing, each representing a different aspect of the embryo and describing a different characteristic of the expanding blastocyst (EX), ICM, or TE. These variables can be categorized into texture, gray level average, gray level standard deviation, modal value, relations, and light level. The automated and directed steps of the proposed processing protocol exclude spurious results, except when image quality (e.g., focus) prevents correct segmentation. CONCLUSIONS: The proposed image processing protocol that can successfully segment human blastocyst images from two distinct sources and extract 33 variables with potential utility in embryo selection for ART.

show abstract

“…The GLCM method is a matrix that shows various combinations of gray levels that can be obtained in an image and helps identify different locations in the image. [17]. According to [18].…”

Section: Gray Level Co-occurrence (Glcm)mentioning

confidence: 99%

A Non-invasive Approach to Detection Blood Glucose Levels with Hand Skin Image Processing Using Smartphone

Umar

Alyah

Mustapa³

2022

j.teknokes

View full text Add to dashboard Cite

Measuring blood sugar levels today still use invasive techniques that are painful so non-invasive monitoring is needed. This study aims to develop a non-invasive technique to identify and detect blood glucose through hand-skin image processing. This development method is by taking invasive blood glucose hand images and 30 participants aged 20-60 years, data analysis is done by image preprocessing, determining the Gray level co-occurrence matrix (GLCM) value, using the backpropagation algorithm to conduct training and data testing. to define a blood glucose monitoring model. The blood glucose detection model is implemented through the android operating system on smartphones by developing the GULAABLE application on smartphones which is simple and easy to use and without blood sampling. This GULAABLE application is to determine the condition of low or high blood glucose and can be used routinely at a low cost. Validating the results by identifying this non-invasive application compared with the results of invasive glucose measurements by applying to 10 participants, the identification results show an accuracy of 80%, so it can be concluded that the GULAABLE application method on smartphones can be used to monitor blood glucose conditions at any time by simply taking hand skin image.

show abstract

PNN-based classification of retinal diseases using fundus images

Cited by 10 publications

References 42 publications

MyopiaDETR: End-to-end pathological myopia detection based on transformer using 2D fundus images

MyopiaDETR: End-to-end pathological myopia detection based on transformer using 2D fundus images

An image processing protocol to extract variables predictive of human embryo fitness for assisted reproduction

A Non-invasive Approach to Detection Blood Glucose Levels with Hand Skin Image Processing Using Smartphone

Contact Info

Product

Resources

About