STARC: Deep learning Algorithms’ modelling for STructured analysis of retina classification

Mellouli, Khaled; Sharma, Akhilesh; Bhardwaj, Sachit

doi:10.1016/j.bspc.2022.104357

Cited by 11 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mohamad Almustafa et al. (2023) employed five deep learning-based classifiers, namely, EfficientNet, InceptionV2, ResNet50, VGG16 and a three-layer CNN, to classify retinal images with ophthalmological defects.…”

Section: Related Workmentioning

confidence: 99%

EYE-YOLO: a multi-spatial pyramid pooling and Focal-EIOU loss inspired tiny YOLOv7 for fundus eye disease detection

Kumar,

Dhanalakshmi

2024

IJICC

View full text Add to dashboard Cite

PurposeThe purpose of this work is to present an approach for autonomous detection of eye disease in fundus images. Furthermore, this work presents an improved variant of the Tiny YOLOv7 model developed specifically for eye disease detection. The model proposed in this work is a highly useful tool for the development of applications for autonomous detection of eye diseases in fundus images that can help and assist ophthalmologists.Design/methodology/approachThe approach adopted to carry out this work is twofold. Firstly, a richly annotated dataset consisting of eye disease classes, namely, cataract, glaucoma, retinal disease and normal eye, was created. Secondly, an improved variant of the Tiny YOLOv7 model was developed and proposed as EYE-YOLO. The proposed EYE-YOLO model has been developed by integrating multi-spatial pyramid pooling in the feature extraction network and Focal-EIOU loss in the detection network of the Tiny YOLOv7 model. Moreover, at run time, the mosaic augmentation strategy has been utilized with the proposed model to achieve benchmark results. Further, evaluations have been carried out for performance metrics, namely, precision, recall, F1 Score, average precision (AP) and mean average precision (mAP).FindingsThe proposed EYE-YOLO achieved 28% higher precision, 18% higher recall, 24% higher F1 Score and 30.81% higher mAP than the Tiny YOLOv7 model. Moreover, in terms of AP for each class of the employed dataset, it achieved 9.74% higher AP for cataract, 27.73% higher AP for glaucoma, 72.50% higher AP for retina disease and 13.26% higher AP for normal eye. In comparison to the state-of-the-art Tiny YOLOv5, Tiny YOLOv6 and Tiny YOLOv8 models, the proposed EYE-YOLO achieved 6–23.32% higher mAP.Originality/valueThis work addresses the problem of eye disease recognition as a bounding box regression and detection problem. Whereas, the work in the related research is largely based on eye disease classification. The other highlight of this work is to propose a richly annotated dataset for different eye diseases useful for training deep learning-based object detectors. The major highlight of this work lies in the proposal of an improved variant of the Tiny YOLOv7 model focusing on eye disease detection. The proposed modifications in the Tiny YOLOv7 aided the proposed model in achieving better results as compared to the state-of-the-art Tiny YOLOv8 and YOLOv8 Nano.

show abstract

Section: Related Workmentioning

confidence: 99%

EYE-YOLO: a multi-spatial pyramid pooling and Focal-EIOU loss inspired tiny YOLOv7 for fundus eye disease detection

Kumar,

Dhanalakshmi

2024

IJICC

View full text Add to dashboard Cite

show abstract

“…Traditional computer vision techniques for brain tumor detection often involve manual feature extraction and classification using techniques such as support vector machines (SVM), decision trees, and Random Forest [23,24]. In recent years, deep learning techniques such as convolutional neural networks (CNNs) have become increasingly popular for brain tumor detection due to their ability to automatically learn features from medical imaging data [25][26][27]. These models have shown promising results in detecting and segmenting brain tumors, as well as in classifying different types of tumors.…”

Section: Related Studiesmentioning

confidence: 99%

“…PEER REVIEW 9 of 17 The model is then compiled using the Adam optimizer [27], a sparse categorical crossentropy loss function [28], and accuracy as the evaluation metric. The Adam optimizer is an algorithm for stochastic optimization that uses adaptive learning rates, while the sparse categorical cross-entropy loss function is used for multi-class classification problems.…”

Section: The Proposed Deep Modelmentioning

confidence: 99%

“…The SoftMax activation function is used to convert the output of the last layer into a probability distribution over the three classes. The visualization of the proposed deep model is shown in Figure7.The model is then compiled using the Adam optimizer[27], a sparse categorical cross-entropy loss function [28], and accuracy as the evaluation metric. The Adam optimizer is an algorithm for stochastic optimization that uses adaptive learning rates, while the sparse categorical cross-entropy loss function is used for multi-class classification problems.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Efficient Brain Tumor Detection with Lightweight End-to-End Deep Learning Model

Hammad

ElAffendi

Ateya

et al. 2023

Cancers

View full text Add to dashboard Cite

In the field of medical imaging, deep learning has made considerable strides, particularly in the diagnosis of brain tumors. The Internet of Medical Things (IoMT) has made it possible to combine these deep learning models into advanced medical devices for more accurate and efficient diagnosis. Convolutional neural networks (CNNs) are a popular deep learning technique for brain tumor detection because they can be trained on vast medical imaging datasets to recognize cancers in new images. Despite its benefits, which include greater accuracy and efficiency, deep learning has disadvantages, such as high computing costs and the possibility of skewed findings due to inadequate training data. Further study is needed to fully understand the potential and limitations of deep learning in brain tumor detection in the IoMT and to overcome the obstacles associated with real-world implementation. In this study, we propose a new CNN-based deep learning model for brain tumor detection. The suggested model is an end-to-end model, which reduces the system’s complexity in comparison to earlier deep learning models. In addition, our model is lightweight, as it is built from a small number of layers compared to other previous models, which makes the model suitable for real-time applications. The optimistic findings of a rapid increase in accuracy (99.48% for binary class and 96.86% for multi-class) demonstrate that the new framework model has excelled in the competition. This study demonstrates that the suggested deep model outperforms other CNNs for detecting brain tumors. Additionally, the study provides a framework for secure data transfer of medical lab results with security recommendations to ensure security in the IoMT.

show abstract

“…In relation to lung disease, CNNs have for example been used for classification of lung tumor types, including both histological and genetic phenotypes (24)(25)(26)(27), murine lung fibrosis (28) and for segmentation of features of interest for diagnosis of pulmonary disease, treatment or follow-up (29)(30)(31). The use of CNNs not only greatly reduces analysis time and cost, but also the bias and reproducibility issues displayed by human observers.…”

Section: Introductionmentioning

confidence: 99%

Deep learning for rapid and reproducible histology scoring of lung injury in a porcine model

Silva

Rashed

Hedlund

et al. 2023

Preprint

View full text Add to dashboard Cite

Acute respiratory distress syndrome (ARDS) is a life-threatening condition with mortality rates between 30-50%. Althoughin vitromodels replicate some aspects of ARDS, small and large animal models remain the primary research tools due to the multifactorial nature of the disease. When using these animal models, histology serves as the gold standard method to confirm lung injury and exclude other diagnoses as high-resolution chest images are often not feasible. Semi-quantitative scoring performed by independent observers is the most common form of histologic analysis in pre-clinical animal models of ARDS. Despite progress in standardizing analysis procedures, objectively comparing histological injuries remains challenging, even for highly-trained pathologists. Standardized scoring simplifies the task and allows better comparisons between research groups and across different injury models, but it is time-consuming, and interobserver variability remains a significant concern. Convolutional neural networks (CNNs), which have emerged as a key tool in image analysis, could automate this process, potentially enabling faster and more reproducible analysis. Here we explored the reproducibility of human standardized scoring for an animal model of ARDS and its suitability for training CNNs for automated scoring at the whole slide level. We found large variations between human scorers, even for pre-clinical experts and board-certified pathologies in evaluating ARDS animal models. We demonstrate that CNNs (VGG16, EfficientNetB4) are suitable for automated scoring and achieve up to 83% F1-score and 78% accuracy. Thus, CNNs for histopathological classification of acute lung injury could help reduce human variability and eliminate a time-consuming manual research task with acceptable performance.

show abstract

STARC: Deep learning Algorithms’ modelling for STructured analysis of retina classification

Cited by 11 publications

References 21 publications

EYE-YOLO: a multi-spatial pyramid pooling and Focal-EIOU loss inspired tiny YOLOv7 for fundus eye disease detection

EYE-YOLO: a multi-spatial pyramid pooling and Focal-EIOU loss inspired tiny YOLOv7 for fundus eye disease detection

Efficient Brain Tumor Detection with Lightweight End-to-End Deep Learning Model

Deep learning for rapid and reproducible histology scoring of lung injury in a porcine model

Contact Info

Product

Resources

About