Symptoms based endometriosis prediction using machine learning

Visalaxi, S.; Thalavaipillai, Sudalaimuthu M.

doi:10.11591/eei.v10i6.3254

Cited by 13 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pathological 37 and annotated images were provided as input for semantic segmentation using U-Net architecture. As a result of the segmentation process involving various parameters the ground truth area was identified which predicts the region of occurrence as a segmented output as illustrated in Figure 3.…”

Section: Resultsmentioning

confidence: 99%

Automated segmentation of endometriosis using transfer learning technique

Visalaxi

SudalaiMuthu

2022

F1000Res

View full text Add to dashboard Cite

Background: This paper focuses on segmenting the exact location of endometriosis using the state-of-art technique known as U-Net. Endometriosis is a progressive disorder that has a significant impact on women. The lesion-like appearance that grows inside the uterus and sheds for every periodical cycle is known as endometriosis. If the lesion exists and is transferred to other locations in the women’s reproductive system, it may lead to a serious problem. Besides radiologists deep learning techniques exist for recognizing the presence and aggravation of endometriosis. Methods: The proposed method known as structural similarity analysis of endometriosis (SSAE) identifies the similarity between pathologically identified and annotated images obtained from standardized dataset known as GLENDA v1.5 by implementing two systematic approaches. The first approach is based on semantic segmentation and the second approach uses statistical analysis. Semantic segmentation is a cutting-edge technology for identifying exact locations by performing pixel-level classification. In semantic segmentation, U-Net is a transfer-learning architecture that works effectively for biomedical image classification. The SSAE implements the U-Net architecture for segmenting endometriosis based on the region of occurrence. The second approach proves the similarity between pathologically identified images and the corresponding annotated images using a statistical evaluation. Statistical analysis was performed using calculation of both the mean and standard deviation of all four regions by implementing systematic sampling procedure. Results: The SSAE obtains the intersection over union value of 0.72 and the F1 score of 0.74 for the trained dataset. The means of both the laparoscopic and annotated images for all regions were similar. Consequently, the SSAE facilitated the presence of abnormalities in a specific region. Conclusions: The proposed SSAE approach identifies the affected region using U-Net architecture and systematic sampling procedure.

show abstract

Section: Resultsmentioning

confidence: 99%

Automated segmentation of endometriosis using transfer learning technique

Visalaxi

SudalaiMuthu

2022

F1000Res

View full text Add to dashboard Cite

show abstract

“…Rootkit [1][23] identification in distributed computing management hence anticipates a crucial job. This inquiry is related to a few previous studies that deal with distributed computing [24], structure, and acknowledgment systems in general [5].…”

Section: Related Workmentioning

confidence: 88%

Volatile Kernel Rootkit Hidden Process Detection in Cloud Computing

SudalaiMuthu

2022

Preprint

View full text Add to dashboard Cite

Malware assaults on kernel rootkits have grown increasingly nuanced and difficult to detect, giving them control over the functionality of the kernel. It can be difficult to detect the presence of these kernel rootkits within the victim system since they use stolen techniques to conceal the system tasks, kernel modules, and various management structures. The majority of the current rootkit detection methods are system-specific and supported by traditional sources, making them ineffectual for new, obscure, and undiscovered rootkits. In order to identify such rootkits by their distinctive hidden processes, this study suggests a VKRHPDV system. This detection method uses a cross-view, clean-boot-based approach and defines a process-watching framework that continuously keeps track of all running processes and can identify any rumoured or unidentified rootkit with the least amount of performance overhead. The linguistics gap is filled by VKRHPDV, which monitors the kernel while extremely discretely intercepting call events of the tainted package to reconstruct a semantic-level method information structure. The results of an in-depth performance analysis performed on sixty-four rootkit datasets in a cloud environment for each UNIX and Windows kernel show that VKRHPDV can detect process hiding habits in all datasets in the shortest amount of time.

show abstract

“…It includes the size of the tissues, tissue color, mass identified, and blockages in fallopian tubes. These factors were identified by the retrospective study provided by gynecologist and radiologist [10]. The size of the lesion varies from 1 mm to 6mm, the color of the tissue exist in red, dark brown, and black colour.…”

Section: Related Studiesmentioning

confidence: 99%

Feature based analysis of endometriosis using machine learning

Visalaxi

SudalaiMuthu²,

Ramalingam³

2023

IJEECS

View full text Add to dashboard Cite

<span lang="EN-US">Machine learning is a cutting-edge technology used for predicting and diagnosing various diseases. Various machine learning algorithm facilitates the prediction. The decision tree belongs to learning algorithm that performs both classification and prediction. The decision tree constructs the tree-like to evaluate the best features. The decision tree performs well in the prediction of various diseases. Endometriosis is a recurrence disease that creates an emotional impact in women. Endometriosis is a lump-like structure that appears at several locations in reproductive organs of women. The diagnosis of endometriosis was predicted through scanning procedures and laparoscopic procedures. The symptoms identified from laparoscopic surgery were used as the features for predicting the severity of endometriosis. The symptoms include mass-like structure, tissue size, variation in tissue colour, and blockages in fallopian tubes. The decision tree analyze the features of endometriosis by using two criteria such as entropy and Gini index. The entropy and Gini index construct the tree by identifying the size of tissue as major influencing attributes. The Gini index outperforms well with training accuracy of 84.08% and test accuracy of 84.85.</span>

show abstract

Symptoms based endometriosis prediction using machine learning

Cited by 13 publications

References 21 publications

Automated segmentation of endometriosis using transfer learning technique

Automated segmentation of endometriosis using transfer learning technique

Volatile Kernel Rootkit Hidden Process Detection in Cloud Computing

Feature based analysis of endometriosis using machine learning

Contact Info

Product

Resources

About