Abstract
It is seen that there is an increase in cancer and cancer-related deaths day by day. Early diagnosis is vital for the early treatment of the cancerous area. Computer-aided programs allow for early diagnosis of unhealthy cells that specialist pathologists diagnose as a result of efforts. In this study, kMeans and Fuzzy C Means methods, which are among the global segmentation methods, and SLIC, Quickshift, Felzenszwalb, Watershed and ERS algorithms, which are among the superpixel segmentation methods, were used for automatic cell nucleus detection in high resolution histopathological images with computer aided programs. As a result of the study, the success performances of the segmentation algorithms were analyzed and evaluated. It is seen that better success is obtained in watershed and FCM algorithms in high resolution histopathological images used. Quickshift and SLIC methods gave better results in terms of precision. It is seen that there are k-Means and FCM algorithms that provide the best performance in F measure (F-M) and the true negative rate (TNR) is more successful in Quickshift, k-Means and SLIC methods.
Highlights
CANCER, HAS been among the serious health problems in recent years, is among the world’s top causes of death
It is seen that there are k-Means and FCM algorithms that provide the best performance in F measure (F-M), and the correct negative rate (TNR) is more successful in Quickshift, kMeans, and Simple Linear Iterative Clustering (SLIC) methods
Automatic detection of diseased cellular structures on high-resolution histopathological images is of great importance for cancer detection
Summary
CANCER, HAS been among the serious health problems in recent years, is among the world’s top causes of death. Albayrak and Bilgin [5] used a deep learning-based SegNet method to divide cellular structures in high-resolution histopathological images They observed that SegNet was quite successful in segmentation cellular networks compared to other methods (k-Means, Otsu, Irshad) that are frequently used. The technique used the SLIC algorithm in zones called superpixels with a similar color to form a group They used it to train neural networks to classify whether superpixels are healthy or unhealthy. Yuan et al [16] developed a superpixel-based and boundary-sensitive convolutional neural network for superpixel-based liver disease zone automatic segmentation. They divided them into three classes as inner liver, liver border, and posterior liver. Various methods were used in the segmentation of high-resolution histopathological images, and their success rates are compared This proposed study includes the method performed in part 2, the experimental results obtained within the study’s scope in part 3, and the conclusion in part 4
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
