Deep-learning based system for effective and automatic blood vessel segmentation from Retinal fundus images

Singh, Law Kumar; Khanna, Munish; Thawkar, Shankar; Singh, Rekha

doi:10.1007/s11042-023-15348-3

Cited by 36 publications

(4 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of deep neural networks and their variants in predicting hemoglobin concentration from eyelid images [ 26 , 41 , 42 ] is well-documented. However, the extensive parameters and computational complexities of these models restrict their practicality in mobile medical applications.…”

Section: Discussionmentioning

confidence: 99%

Real-time non-invasive hemoglobin prediction using deep learning-enabled smartphone imaging

Chen,

Hu,

Zhu

et al. 2024

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Accurate measurement of hemoglobin concentration is essential for various medical scenarios, including preoperative evaluations and determining blood loss. Traditional invasive methods are inconvenient and not suitable for rapid, point-of-care testing. Moreover, current models, due to their complex parameters, are not well-suited for mobile medical settings, which limits the ability to conduct frequent and rapid testing. This study aims to introduce a novel, compact, and efficient system that leverages deep learning and smartphone technology to accurately estimate hemoglobin levels, thereby facilitating rapid and accessible medical assessments. Methods The study employed a smartphone application to capture images of the eye, which were subsequently analyzed by a deep neural network trained on data from invasive blood test data. Specifically, the EGE-Unet model was utilized for eyelid segmentation, while the DHA(C3AE) model was employed for hemoglobin level prediction. The performance of the EGE-Unet was evaluated using statistical metrics including mean intersection over union (MIOU), F1 Score, accuracy, specificity, and sensitivity. The DHA(C3AE) model’s performance was assessed using mean absolute error (MAE), mean-square error (MSE), root mean square error (RMSE), and R^2. Results The EGE-Unet model demonstrated robust performance in eyelid segmentation, achieving an MIOU of 0.78, an F1 Score of 0.87, an accuracy of 0.97, a specificity of 0.98, and a sensitivity of 0.86. The DHA(C3AE) model for hemoglobin level prediction yielded promising outcomes with an MAE of 1.34, an MSE of 2.85, an RMSE of 1.69, and an R^2 of 0.34. The overall size of the model is modest at 1.08 M, with a computational complexity of 0.12 FLOPs (G). Conclusions This system presents a groundbreaking approach that eliminates the need for supplementary devices, providing a cost-effective, swift, and accurate method for healthcare professionals to enhance treatment planning and improve patient care in perioperative environments. The proposed system has the potential to enable frequent and rapid testing of hemoglobin levels, which can be particularly beneficial in mobile medical settings. Trial Registration The clinical trial was registered on the Chinese Clinical Trial Registry (No. ChiCTR2100044138) on 20/02/2021.

show abstract

Section: Discussionmentioning

confidence: 99%

Real-time non-invasive hemoglobin prediction using deep learning-enabled smartphone imaging

Chen,

Hu,

Zhu

et al. 2024

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…The decision curve was constructed using “rmda” package and corresponding calibration curves were created using the "rms" package. The variables for the model were selected through stepwise use of Akaike’s information criterion (AIC) 15 and predictive models used multivariable logistic regression. Receiver operating characteristic curves (ROC) analysis was performed using the “pROC” package.…”

Section: Methodsmentioning

confidence: 99%

“…Deep learning-based artificial intelligence (AI) has recently made tremendous progress and has made great achievements in the field of vision and image processing. Law Kumar Singh et al propose an enhanced customized R2-ATT U-Net deep learning network for retinal blood vessel extraction, aiding in the early detection of eye diseases 15 . Similarly, Charu Bhardwaj et al reported a deep-learning ensemble approach for the grading of diabetic retinopathy severity 16 .…”

Section: Introductionmentioning

confidence: 99%

Model based on the automated AI-driven CT quantification is effective for the diagnosis of refractory Mycoplasma pneumoniae pneumonia

Qian,

Tao,

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The prediction of refractory Mycoplasma pneumoniae pneumonia (RMPP) remains a clinically significant challenge. This study aimed to develop an early predictive model utilizing artificial intelligence (AI)-derived quantitative assessment of lung lesion extent on initial computed tomography (CT) scans and clinical indicators for RMPP in pediatric inpatients. A retrospective cohort study was conducted on patients with M. pneumoniae pneumonia (MP) admitted to the Children’s Hospital of Nanjing Medical University, China from January 2019 to December 2020. An early prediction model was developed by stratifying the patients with Mycoplasma pneumoniae pneumonia (MPP) into two cohorts according to the presence or absence of refractory pneumonia. A retrospective cohort of 126 children diagnosed with Mycoplasma pneumoniae pneumonia (MPP) was utilized as a training set, with 85 cases classified as RMPP. Subsequently, a prospective cohort comprising 54 MPP cases, including 37 instances of RMPP, was assembled as a validation set to assess the performance of the predictive model for RMPP from January to December 2021. We defined a constant Φ which can combine the volume and CT value of pulmonary lesions and be further used to calculate the logarithm of Φ to the base of 2 (Log2Φ). A clinical-imaging prediction model was then constructed utilizing Log2Φ and clinical characteristics. Performance was evaluated by the area under the receiver operating characteristic curve (AUC). The clinical model demonstrated AUC values of 0.810 and 0.782, while the imaging model showed AUC values of 0.764 and 0.769 in the training and test sets, respectively. The clinical-imaging model, incorporating Log2Φ, temperature(T), aspartate aminotransferase (AST), preadmission fever duration (PFD), and preadmission macrolides therapy duration (PMTD), achieved the highest AUC values of 0.897 and 0.895 in the training and test sets, respectively. A prognostic model developed through automated quantification of lung disease on CT scans, in conjunction with clinical data in MPP may be utilized for the early identification of RMPP.

show abstract

“…Several machine learning algorithms, image processing, and data mining approaches have been suggested to classify DR's early diagnosis and severity level. Although the applied CAD methods have been familiar and beneficial, they still present significant challenges in the medical field [13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Improved Support Vector Machine based on CNN-SVD for vision-threatening diabetic retinopathy detection and classification

Bilal,

Imran,

Baig

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The integration of artificial intelligence (AI) in diagnosing diabetic retinopathy, a major contributor to global vision impairment, is becoming increasingly pronounced. Notably, the detection of vision-threatening diabetic retinopathy (VTDR) has been significantly fortified through automated techniques. Traditionally, the reliance on manual analysis of retinal images, albeit slow and error-prone, constituted the conventional approach. Addressing this, our study introduces a novel methodology that amplifies the robustness and precision of the detection process. This is complemented by the groundbreaking Hierarchical Block Attention (HBA) and HBA-U-Net architecture, which notably propel attention mechanisms in image segmentation. This innovative model refines image processing without imposing excessive computational demands by honing in on individual pixel intricacies, spatial relationships, and channel-specific attention. Building upon this innovation, our proposed method employs a multi-stage strategy encompassing data pre-processing, feature extraction via a hybrid CNN-SVD model, and classification employing an amalgamation of Improved Support Vector Machine-Radial Basis Function (ISVM-RBF), DT, and KNN techniques. Rigorously tested on the IDRiD dataset classified into five severity tiers, the hybrid model yields remarkable performance, achieving a 99.18% accuracy, 98.15% sensitivity, and 100% specificity in VTDR detection, thus surpassing existing methods. These results underscore a more potent avenue for diagnosing and addressing this crucial ocular condition while underscoring AI’s transformative potential in medical care, particularly in ophthalmology.

show abstract

Deep-learning based system for effective and automatic blood vessel segmentation from Retinal fundus images

Cited by 36 publications

References 84 publications

Real-time non-invasive hemoglobin prediction using deep learning-enabled smartphone imaging

Real-time non-invasive hemoglobin prediction using deep learning-enabled smartphone imaging

Model based on the automated AI-driven CT quantification is effective for the diagnosis of refractory Mycoplasma pneumoniae pneumonia

Improved Support Vector Machine based on CNN-SVD for vision-threatening diabetic retinopathy detection and classification

Contact Info

Product

Resources

About