Attention-Based UNet Deep Learning Model for Plaque Segmentation in Carotid Ultrasound for Stroke Risk Stratification: An Artificial Intelligence Paradigm

Jain, Pankaj K.; Dubey, Abhishek; Saba, Luca; Khanna, Narinder N.; Laird, John R.; Nicolaides, Andrew; Fouda, Mostafa M.; Suri, Jasjit S.; Sharma, Neeraj

doi:10.3390/jcdd9100326

Cited by 26 publications

(12 citation statements)

References 101 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jain et al. ( Jain et al., 2022 ) compared the Attention-UNet model with the UNet, UNet + + and UNet3P models, the AUC (Area Under Curve) value is 0.97, while the AUC values of other models are 0.964,0.966 and 0.965, respectively. The results show that the attention mechanism is beneficial to segment very bright and blurred plaque images that are difficult to diagnose using other methods.…”

Section: Improved U-net Network Structurementioning

confidence: 99%

Research of segmentation recognition of small disease spots on apple leaves based on hybrid loss function and CBAM

Zhang

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

Identification technology of apple diseases is of great significance in improving production efficiency and quality. This paper has used apple Alternaria blotch and brown spot disease leaves as the research object and proposes a disease spot segmentation and disease identification method based on DFL-UNet+CBAM to address the problems of low recognition accuracy and poor performance of small spot segmentation in apple leaf disease recognition. The goal of this paper is to accurately prevent and control apple diseases, avoid fruit quality degradation and yield reduction, and reduce the resulting economic losses. DFL-UNet+CBAM model has employed a hybrid loss function of Dice Loss and Focal Loss as the loss function and added CBAM attention mechanism to both effective feature layers extracted by the backbone network and the results of the first upsampling, enhancing the model to rescale the inter-feature weighting relationships, enhance the channel features of leaf disease spots and suppressing the channel features of healthy parts of the leaf, and improving the network’s ability to extract disease features while also increasing model robustness. In general, after training, the average loss rate of the improved model decreases from 0.063 to 0.008 under the premise of ensuring the accuracy of image segmentation. The smaller the loss value is, the better the model is. In the lesion segmentation and disease identification test, MIoU was 91.07%, MPA was 95.58%, F1 Score was 95.16%, MIoU index increased by 1.96%, predicted disease area and actual disease area overlap increased, MPA increased by 1.06%, predicted category correctness increased, F1 Score increased by 1.14%, the number of correctly identified lesion pixels increased, and the segmentation result was more accurate. Specifically, compared to the original U-Net model, the segmentation of Alternaria blotch disease, the MIoU value increased by 4.41%, the MPA value increased by 4.13%, the Precision increased by 1.49%, the Recall increased by 4.13%, and the F1 Score increased by 2.81%; in the segmentation of brown spots, MIoU values increased by 1.18%, MPA values by 0.6%, Precision by 0.78%, Recall by 0.6%, and F1 Score by 0.69%. The spot diameter of the Alternaria blotch disease is 0.2-0.3cm in the early stage, 0.5-0.6cm in the middle and late stages, and the spot diameter of the brown spot disease is 0.3-3cm. Obviously, brown spot spots are larger than Alternaria blotch spots. The segmentation performance of smaller disease spots has increased more noticeably, according to the quantitative analysis results, proving that the model’s capacity to segment smaller disease spots has greatly improved. The findings demonstrate that for the detection of apple leaf diseases, the method suggested in this research has a greater recognition accuracy and better segmentation performance. The model in this paper can obtain more sophisticated semantic information in comparison to the traditional U-Net, further enhance the recognition accuracy and segmentation performance of apple leaf spots, and address the issues of low accuracy and low efficiency of conventional disease recognition methods as well as the challenging convergence of conventional deep convolutional networks.

show abstract

Section: Improved U-net Network Structurementioning

confidence: 99%

Research of segmentation recognition of small disease spots on apple leaves based on hybrid loss function and CBAM

Zhang

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…Consequently, supervised learning faces challenges in massive data analyses [331], suggesting that unsupervised models might soon become the standard, especially in contexts where binary masks or labeled data are not mandatory. Medical image processing has vast untapped potential for such unsupervised deep learning models [332].…”

Section: The Technological Revolution In Stroke Diagnostics and Rehab...mentioning

confidence: 99%

Integrative Approaches in Acute Ischemic Stroke: From Symptom Recognition to Future Innovations

Saceleanu,

Toader,

Ples

et al. 2023

Biomedicines

View full text Add to dashboard Cite

Among the high prevalence of cerebrovascular diseases nowadays, acute ischemic stroke stands out, representing a significant worldwide health issue with important socio-economic implications. Prompt diagnosis and intervention are important milestones for the management of this multifaceted pathology, making understanding the various stroke-onset symptoms crucial. A key role in acute ischemic stroke management is emphasizing the essential role of a multi-disciplinary team, therefore, increasing the efficiency of recognition and treatment. Neuroimaging and neuroradiology have evolved dramatically over the years, with multiple approaches that provide a higher understanding of the morphological aspects as well as timely recognition of cerebral artery occlusions for effective therapy planning. Regarding the treatment matter, the pharmacological approach, particularly fibrinolytic therapy, has its merits and challenges. Endovascular thrombectomy, a game-changer in stroke management, has witnessed significant advances, with technologies like stent retrievers and aspiration catheters playing pivotal roles. For select patients, combining pharmacological and endovascular strategies offers evidence-backed benefits. The aim of our comprehensive study on acute ischemic stroke is to efficiently compare the current therapies, recognize novel possibilities from the literature, and describe the state of the art in the interdisciplinary approach to acute ischemic stroke. As we aspire for holistic patient management, the emphasis is not just on medical intervention but also on physical therapy, mental health, and community engagement. The future holds promising innovations, with artificial intelligence poised to reshape stroke diagnostics and treatments. Bridging the gap between groundbreaking research and clinical practice remains a challenge, urging continuous collaboration and research.

show abstract

“…They constructed an extensive feature database and trained it using LR and RF models. [135,136] can offer a more focused and streamlined classification of species, ultimately improving the accuracy and reliability of the gene classification scheme.…”

Section: Benchmarking: a Comparative Analysismentioning

confidence: 99%

GeneAI 3.0: Powerful, Novel, Generalized Hybrid and Ensemble Deep Learning Frameworks for miRNA Classification of species-specific Stationary Patterns from Nucleotides

Singh

Khanna

Rout

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Background and Motivation: Due to the intricate relationship between the small non-coding ribonucleic acid (miRNA) sequences, the classification of miRNA species, namely Human, Gorilla, Rat, and Mouse is challenging. Previous methods are not robust and accurate. In this study, we present GeneAI 3.0 (AtheroPoint™, Roseville, CA, USA), a powerful, novel, and generalized method for extracting features from the fixed patterns of purines and pyrimidines in each miRNA sequence in ensemble paradigms in machine learning (EML) and convolutional neural network (CNN)-based deep learning (EDL) frameworks. Method: GeneAI 3.0 utilized five conventional (Entropy, Dissimilarity, Energy, Homogeneity, and Contrast), and three contemporary (Shannon entropy, Hurst exponent, Fractal dimension) features, to generate a compositefeature set from given miRNA sequences which were then passed into our ML and DL classification framework. A set of 11 new classifiers was designed consisting of five EML and six EDL for binary/multiclass classification. It was benchmarked against 9 solo ML (SML), 6 solo DL (SDL), 12 hybrid DL (HDL) models, resulting in a total of 11+27=38 models were designed. Four hypotheses were formulated and validated using explainable AI (XAI) as well as reliability/statistical tests. Results: The order of the mean performance using accuracy (ACC)/area-under-the-curve (AUC) of the 24 DL classifiers was: EDL>HDL>SDL. The mean performance of EDL models with CNN layers was superior to that without CNN layers by 0.73%/0.92%. Mean performance of EML models was superior to SML models with improvements of ACC/AUC by 6.24%/6.46%. EDL models performed significantly better than EML models, with a mean increase in ACC/AUC of 7.09%/6.96%. The GeneAI 3.0 tool produced expected XAI feature plots, and the statistical tests showed significant p-values. Conclusions: Ensemble models with composite features are highly effective and generalized models for effectively classifying miRNA sequences.

show abstract

Attention-Based UNet Deep Learning Model for Plaque Segmentation in Carotid Ultrasound for Stroke Risk Stratification: An Artificial Intelligence Paradigm

Cited by 26 publications

References 101 publications

Research of segmentation recognition of small disease spots on apple leaves based on hybrid loss function and CBAM

Research of segmentation recognition of small disease spots on apple leaves based on hybrid loss function and CBAM

Integrative Approaches in Acute Ischemic Stroke: From Symptom Recognition to Future Innovations

GeneAI 3.0: Powerful, Novel, Generalized Hybrid and Ensemble Deep Learning Frameworks for miRNA Classification of species-specific Stationary Patterns from Nucleotides

Contact Info

Product

Resources

About