KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 5 of 5

Some of the metrics are blocked by your
consent settings
Computer-assisted screening for cervical cancer using digital image processing of pap smear images
(2020-03-01)
Win, Kyi Pyar
;
Kitjaidure, Yuttana
;
Hamamoto, Kazuhiko
;
Aung, Thet Myo
Cervical cancer can be prevented by having regular screenings to find any precancers and treat them. The Pap test looks for any abnormal or precancerous changes in the cells on the cervix. However, the manual screening of Pap smear in the microscope is subjective with poorly reproducible criteria. Therefore, the aim of this study was to develop a computer-assisted screening system for cervical cancer using digital image processing of Pap smear images. The analysis of Pap smear image is important in the cervical cancer screening system. There were four basic steps in our cervical cancer screening system. In cell segmentation, nuclei were detected using a shape-based iterative method, and the overlapping cytoplasm was separated using a marker-control watershed approach. In the features extraction step, three important features were extracted from the regions of segmented nuclei and cytoplasm. RF (random forest) algorithm was used as a feature selection method. In the classification stage, bagging ensemble classifier, which combined the results of five classifiers-LD (linear discriminant), SVM (support vector machine), KNN (k-nearest neighbor), boosted trees, and bagged trees-was applied. SIPaKMeD and Herlev datasets were used to prove the effectiveness of our proposed system. According to the experimental results, 98.27% accuracy in two-class classification and 94.09% accuracy in five-class classification was achieved using the SIPaKMeD dataset. When the results were compared with five classifiers, our proposed method was significantly better in two-class and five-class problems.
Some of the metrics are blocked by your
consent settings
Cervical cancer detection and classification from pap smear images
(2019-09-16)
Win, Kyi Pyar
;
Kitjaidure, Yuttana
;
Paing, May Phyu
;
Hamamoto, Kazuhiko
In this paper, we propose a framework for detection and classification of cervical cancer from pap smear images. Early detection and accurate diagnosis of cervical cancer can reduce the death rate of cervical cancer patients. Pap smear or pap test is the most popular technique for early detection of cervical cancer. However, the manual analysis is labor intensive and time consuming process which relies on expert cytologist. Hence, it is needed to develop a computer aided diagnosis system to make the pap smear test more accurate and reliable. The objective of this paper is to present an innovative idea of applying random forest algorithm (RF) as a feature selection method using proposed bagging ensemble classifier for improving the predictive performance. The four basic steps of cervical cancer detection and classification system, image enhancement, segmentation, feature extraction and classification were used. K-means clustering combining with morphology operations obtained good segmentation for cell nuclei and cytoplasm. The most important features, shape, color and texture of nuclei and cytoplasm were applied to detect cervical cancer. To improve the accuracy of prediction results, random forest (RF) algorithm was used as a feature selection method. In classification stage, bagging ensemble classifier was applied which aggregated the results of five classifiers, linear discriminant (LD), support vector machine (SVM), weighted k-nearest neighbor (KNN), boosted trees and bagged trees. Herlev data set was used to prove the effectiveness of our proposed method. According to the experimental results, the high classification accuracy was achieved with top10 features using our proposed combined classifier. The accuracy was 97.83% in two class problem and 81.54% in seven class problem. When the results were compared with five classifiers, our proposed method was significantly better in two class and seven class problems.
Some of the metrics are blocked by your
consent settings
Automatic detection of mediastinal lymph nodes using 3D convolutional neural network
(2019-09-16)
Paing, May Phu
;
Pintavirooj, Chuchart
;
Tungjitkusolmun, Supan
;
Win, Kyi Pyar
;
Hamamoto, Kazuhiko
Mediastinal lymph nodes are one of the most critical factors to identify the clinical stages of lung cancer. As the lymph nodes are low in attenuation and cluttering with various shapes and sizes, manual detection is usually error-prone and effort-intensive. This paper introduces a method for automatic detection of mediastinal lymph nodes by proposing three significant contributions. First, we constraint the detection area, mediastinal region, using greylevel thresholding. Next, we apply the watershed method and hessian eigenvalues to separate a cluster of lymph nodes. Finally, we build a three-dimensional convolutional neural network (3D CNN) to distinguish the actual lymph nodes from other false lesions. Our experiment is conducted using 70 CT exams containing 314 lymph nodes and achieved a favorable result with 94 % detection rate.
Some of the metrics are blocked by your
consent settings
Automatic stitching of medical images using feature based approach
(2019-01-01)
Win, Kyi Pyar
;
Kitjaidure, Yuttana
;
Hamamoto, Kazuhiko
Image stitching is a process of creating a panoramic image by combining multiple images that have overlapping regions of the same scene. It is a challenging topic in image processing, multimedia, and medical applications. The proposed system can be applied in medical applications for scoliosis operations and other long limb operations. The problem of the traditional x-ray machine is the narrow view. So, it can’t produce the large view of body x-ray image in a single frame. Therefore, this problem is solved by combining two or more x-ray images into a panorama one. This paper proposes a system which automatically stitches the x-ray images and produced a panorama x-ray image. The proposed stitching method is based on feature based approach, ORB (Oriented FAST and Rotated BRIEF). In feature detection stage, Oriented FAST approach is used. In feature description stage, Rotated BRIEF approach is applied. The two important criterias for determining the stitching performance are stitched image quality and processing time. Therefore, the aim of my proposed system is to produce a panorama x-ray image with high resolution and low processing time based on feature extraction approach. We compared our proposed method with three different features detectors. SIFT, SURF, and Harris corner detectors were tested and measured the rate of correct features detection and computation time. Finally, we measured the quality of result images that produced by stitching system of different feature based methods. According to the experimental results, ORB approach can produce high quality panorama image with least processing time.
Some of the metrics are blocked by your
consent settings
Biomedical Images Stitching using ORB Feature Based Approach
(2018-11-27)
Win, Kyi Pyar
;
Kitjaidure, Yuttana
This paper proposes a system for biomedical images stitching using feature based approach. The proposed system aims to stitch the high resolution images with low processing time. The proposed system is designed with five stages., preprocessing., features extraction., features matching., homography estimation and images stitching. In feature detection stage., ORB feature based approach is used. The proposed method is improved in term of performance and accuracy. The proposed method was compared with many different features detectors., Harris corner detector., SIFT and SURF techniques. According to the experiments., ORB method had the better results than the other feature based methods in the detection rate of the corrected keypoints and processing time.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results