Automatic Segmentation of Polyps in Endoscopic Image Using Level-Set Formulation

Dutta, Soumayan; Sasmal, Pradipta; Bhuyan, M. K.; Iwahori, Yuji

doi:10.1109/wispnet.2018.8538615

Cited by 7 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers utilized a polyp segmentation method rooted in contour region analysis to extract features. They leveraged curvature, polyp color, areas, and edge shapes as characteristics to effectively delineate and identify polyps within the images [12]. Another active contour model used to find pathological tissues using segmented image regions and classified the extracted tissues into three stages of CRC progression using a fully connected CNN [13].…”

Section: Literature Surveymentioning

confidence: 99%

Predictive Analysis of Colorectal Cancer via CT scans Using Convolutional Neural Networks

Khaiyum,

2023

ijmst

View full text Add to dashboard Cite

In recent years, the area of Medicine and Healthcare has made significant advances with the assistance of computational technology. New diagnostic techniques including image processing were developed which can help healthcare/clinical experts in many ways. One of the domains is cancer prediction and treatment. Cancer is the world's second-largest cause of mortality, claiming the lives of one out of every six individuals. Colorectal cancer (CRC) is a common cancer worldwide. It ranks as the third most frequently detected cancer among men and the second among women, with more than 1.4 million new cancer cases every year. This article proposed an improvised CNN approach to analyze the CT scan images of colorectal cancer to predict and classify them into benign(non-cancerous) and malignant(cancerous). In further work the result with tumorous class with patient’s other parameters are integrated for assessing the risk level of cancer. This model results in 96.8% accuracy and minimal error rate. The main contribution of this work is to assist medical fraternity to automatically analyze the CT scan images for prediction and classification of colorectal cancer.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Predictive Analysis of Colorectal Cancer via CT scans Using Convolutional Neural Networks

Khaiyum,

2023

ijmst

View full text Add to dashboard Cite

show abstract

“…In the last stage, the image was segmented via an active contour applied to the background-subtracted image. Another active contour segmentation method was proposed in [ 17 ], in which the active contour framework was modified to work without edges. The authors claimed that this remodelled active contour framework had the advantages of the contours merging and splitting on their own; on the contrary, the old snake model can merely extend and straighten without much versatility.…”

Section: Related Workmentioning

confidence: 99%

Automatic Polyp Segmentation in Colonoscopy Images Using a Modified Deep Convolutional Encoder-Decoder Architecture

Tang

Lin

et al. 2021

Sensors

View full text Add to dashboard Cite

Colorectal cancer has become the third most commonly diagnosed form of cancer, and has the second highest fatality rate of cancers worldwide. Currently, optical colonoscopy is the preferred tool of choice for the diagnosis of polyps and to avert colorectal cancer. Colon screening is time-consuming and highly operator dependent. In view of this, a computer-aided diagnosis (CAD) method needs to be developed for the automatic segmentation of polyps in colonoscopy images. This paper proposes a modified SegNet Visual Geometry Group-19 (VGG-19), a form of convolutional neural network, as a CAD method for polyp segmentation. The modifications include skip connections, 5 × 5 convolutional filters, and the concatenation of four dilated convolutions applied in parallel form. The CVC-ClinicDB, CVC-ColonDB, and ETIS-LaribPolypDB databases were used to evaluate the model, and it was found that our proposed polyp segmentation model achieved an accuracy, sensitivity, specificity, precision, mean intersection over union, and dice coefficient of 96.06%, 94.55%, 97.56%, 97.48%, 92.3%, and 95.99%, respectively. These results indicate that our model performs as well as or better than previous schemes in the literature. We believe that this study will offer benefits in terms of the future development of CAD tools for polyp segmentation for colorectal cancer diagnosis and management. In the future, we intend to embed our proposed network into a medical capsule robot for practical usage and try it in a hospital setting with clinicians.

show abstract

“…Contrast is a unit of local image variation values [12] [13]. The calculation of the contrast value is presented in (5)…”

Section: Energymentioning

confidence: 99%

Human Intestinal Condition Identification based-on Blended Spatial and Morphological Feature using Artificial Neural Network Classifier

Athiyah¹,

Muhammad

Azhari

2020

KEDS

View full text Add to dashboard Cite

I. Introduction Colorectal cancer is a type of cancer that attacks the intestinal walls cell of humans. Wisconsin Reporting System (WRS), states that the type of colorectal cancer is the third highest cause of death after types of lung cancer and breast cancer, with a case of death of 9.5% of the total world population [1]. In Indonesia, colorectal cancer itself is ranked as the third cause of death after breast cancer and cervical cancer. Therefore, the abnormalities in the human intestinal wall need to be identified early to minimize the growth of cancerous cells that are more virulent, which can cause death. Health screening, such as endoscopy, is a simple step to detect abnormal growths in human intestinal cells wall [2][3]. Also, the process of early detection plays an essential role in health practitioners/gynecologists to determine the prognosis and type of treatment that patients must receive [4]. The right prognosis is accompanied by the right dosage of the drug to help speed the recovery of patients from colorectal cancer outbreaks. Endoscopic screening technique is a common step carried out by the health experts/gynecologist to determine the condition of the human intestine by inserting a camera through the rectum to get an intestine picture [5]. The result of endoscopic screening is a digital image of the area around the intestinal wall [6]. During this time, the interpretation of endoscopic images is carried out manually or taken by the naked eye, thus requires quite a long time to interpret and produce results. This ARTICLE INFO

show abstract

Automatic Segmentation of Polyps in Endoscopic Image Using Level-Set Formulation

Cited by 7 publications

References 9 publications

Predictive Analysis of Colorectal Cancer via CT scans Using Convolutional Neural Networks

Predictive Analysis of Colorectal Cancer via CT scans Using Convolutional Neural Networks

Automatic Polyp Segmentation in Colonoscopy Images Using a Modified Deep Convolutional Encoder-Decoder Architecture

Human Intestinal Condition Identification based-on Blended Spatial and Morphological Feature using Artificial Neural Network Classifier

Contact Info

Product

Resources

About