Colorectal Cancer Disease Classification Using Mobilenetv2 Based on Deep Learning

Raju, Mallela Siva Naga; Rao, Mallela Siva B. Srinivasa

doi:10.4018/ijsi.309725

Cited by 3 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4, the network adopts an end-to-end encoder decoder structure, 27 the encoder part is composed of backbone network, feature segmentation module (FIC), and adaptive multi-scale fusion module (Self-RASPP) to complete the task of feature segmentation and extraction. Among them, the backbone network adopts lightweight Mobilenetv2, 28 which can reduce network parameters and speed up segmentation. This article uses a more advanced lightweight Mobilenetv2 pre-training model in segmentation network training to improve the representation ability of macro and micro pixels.…”

Section: Cn-yolo Network Structurementioning

confidence: 99%

“…Calculating the intersection union ratio between the prediction frame and the real frame transforms the target detection problem into a regression problem, effectively optimizes the position and size of the target, and improves the precision of detection. Therefore, the focal-SIOU-loss has better robustness and precision in dealing with difficult samples and unbalanced target categories, so the model can better adapt to a variety of complex scenes and improve the overall performance of target detection tasks 28 …”

Section: Cn-yolo Network Structurementioning

confidence: 99%

“…Therefore, the focal-SIOU-loss has better robustness and precision in dealing with difficult samples and unbalanced target categories, so the model can better adapt to a variety of complex scenes and improve the overall performance of target detection tasks. 28 On the basis of focal loss, the paper fuses SIOU loss for boundary regression. Defining the fused boundary regression loss function focal-SIOU-loss as follows:…”

Section: Focal-siou-loss For Model Convergencementioning

confidence: 99%

See 2 more Smart Citations

CN-YOLO: cascaded network based defect detection approach for insulator aerial images with complex background

Liu,

2024

J. Electron. Imag.

View full text Add to dashboard Cite

Quick and accurate detection of insulator defects from the complex aerial background (such as trees, hillsides, lakes, and buildings) is important work to ensure the safe operation of transmission lines. The existing detection methods have difficulty detecting the defect target due to the strong interference of complex backgrounds in aerial images. To solve this problem, we propose an insulator defect detection model based on a cascaded network. First, we introduce a hierarchical semantic segmentation network to separate the complex background from the target insulator, which is embedded into the main feature extraction branch to form a "segmentation-detection" cascade network to solve the interference problem of complex background when extracting target information; Second, aiming at the problem of direct fusion of conflicting information in different feature layers in the bi-directional path aggregation neck structure in the detection network, we propose an acrossscale feature pyramid with feature refinement structure to enhance the information characteristics of insulator defect targets and improve the multi-scale expression ability of the network. Then, aiming at the problem of difficult samples and imbalance of positive and negative samples in the process of target detection, we propose a focal shape intersection over union loss (focal-SIOU-loss), which improves the precision and stability of the regression process by introducing the weight adjustment mechanism of focal loss and the structural similarity of SIOU Loss. Finally, the experimental results show that, compared with the standard detection models such as YOLOv5, YOLO7, and YOLOv8, the proposed detection model achieves a better performance in the precision, recall rate, and robustness in detecting insulator defects under complex backgrounds.

show abstract

Section: Cn-yolo Network Structurementioning

confidence: 99%

Section: Cn-yolo Network Structurementioning

confidence: 99%

Section: Focal-siou-loss For Model Convergencementioning

confidence: 99%

See 1 more Smart Citation

CN-YOLO: cascaded network based defect detection approach for insulator aerial images with complex background

Liu,

2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…Also, imaging artifacts can be regulated and analyzed apart from the various acquisition parameters, and the ground truth is known. This validation method is more flexible and straightforward to implement [92], [93], [94], [95]. The simulated images can only be approximations of the real ones because the software simulation approach does not take into account all the aspects that could affect genuine picture collection.To generate more realistic phantom images it can be achieved with software models, MRI scanners are used.…”

Section: Evaluation Criteria For Brain Mri Segmentationmentioning

confidence: 99%

A Review on Alzheimer’s Disease Through Analysis of MRI Images Using Deep Learning Techniques

Aparna¹

2023

IEEE Access

View full text Add to dashboard Cite

The anatomical structure of the brain has been studied with the help of magnetic resonance imaging (MRI), which has been used to analyze numerous neurological diseases and define pathological areas. Early detection of Alzheimer's Disease (AD) patients is critical in order to implement preventative measures. Alzheimer's disease (AD) is the most common chronic disease in the elderly, with a high incidence rate. In recent years, deep learning has seen a lot of success in the medical image analysis. Brain diseases can be more accurately categorized using segmented MRI scans due to in-depth analyses of tissue architecture. Many, complex segmentation approaches have been presented for AD diagnosis. Since deep learning algorithms can yield effective results over a large data collection, they have received interest for use in segmenting the brain's structure and classifying AD. Consequently, the deep learning techniques are currently favored over machine learning techniques. We discuss how convolutional neural network concepts can be used to study brain anatomy in order to detect AD. New techniques, their results on open datasets, and the benefits of brain MRI segmentation for Alzheimer's disease categorization are discussed. In this article, the literature on Alzheimer's disease is briefly reviewed, and the possibility of Deep Learning to improve early diagnosis is discussed.INDEX TERMS Alzheimer's disease, brain analysis, classification techniques, deep learning techniques, image processing techniques.

show abstract

“…It depends on the remaining connections between the bottleneck levels in the revised residual structure. The average development layer adds nonlinearity by combining lightweight profundity wise convolutions with highlights [33]. In terms of engineering, MobileNetV2 normally uses a 32-channel fully convolution layer at the beginning, followed by 19 residual bottleneck layers.…”

Section: Mobilenetv2mentioning

confidence: 99%

An Outlook of Medical Image Analysis via Transfer Learning Approaches

Nagaraju¹,

Rao²

2022

View full text Add to dashboard Cite

Artificial intelligence advancements, particularly deep learning algorithms, are helpful for identifying, classifying, and rating designs in clinical images. Clinical diagnosis and scientific research both rely heavily on medical image analysis. The diagnosis of medical conditions frequently involves medical image acquisition techniques like pathology, computed tomography, magnetic resonance imaging, ultrasound, and x-ray. Transfer learning stands out from other deep learning techniques thanks to its simplicity, effectiveness, affordable training costs, and capacity to escape the dataset curse. The diagnosis of anomalies including Alzheimer's disease, diabetic retinopathy, colon cancer, breast cancer, and pulmonary nodule can be made using the medical imaging techniques combined with datasets and computer vision. These approaches are helpful in non-invasive qualitative and quantitative analysis on patients. However, labelling in medical images are still scarce. This paper mainly reviews the application of transfer learning in medical image analysis. Beginners can benefit from this review paper's guidance as they gain a thorough and organized understanding of transfer learning applications for the analysis of medical images. By establishing laws that will aid future advancements in medical image processing, policymakers in adjacent sectors will also profit from the trend of transfer learning in medical imaging.

show abstract

Colorectal Cancer Disease Classification Using Mobilenetv2 Based on Deep Learning

Cited by 3 publications

References 24 publications

CN-YOLO: cascaded network based defect detection approach for insulator aerial images with complex background

CN-YOLO: cascaded network based defect detection approach for insulator aerial images with complex background

A Review on Alzheimer’s Disease Through Analysis of MRI Images Using Deep Learning Techniques

An Outlook of Medical Image Analysis via Transfer Learning Approaches

Contact Info

Product

Resources

About