Mdical image segmentation criteria’s disadvantages

Abulraqeb Atef Rawhan Abdulsameea

Article ID: 583
Vol 4, Issue 1, 2021

VIEWS - 365 (Abstract) 312 (PDF)

Abstract


Segmentation is one of the vital procedures in medical image processing. The results of none accurate segmentation may lead to a none accurate diagnosis. To assess the segmentation results there are common used criteria such as Sensitivity, Specificity and Accuracy. This paper discusses of disadvantages of the mentioned criteria in assessment the tumor segmentation on MRI images.  


Keywords


Medical images; Segmentation; Sensitivity; Specificity and Accuracy

Full Text:

PDF


References


1. Priyanka, Balwinder Singh. A review on brain tumor detection using segmentation. IJCSMC 2013; 2: 48–54.

2. Selvaraj D, Dhanasekaran R. MRI brain image segmentation techniques - A review. IJCSE 2013; 4: 364–381.

3. Yogamangalam R, Karthikeyan B. Segmentation techniques comparison in image processing. IJET 2013; 5: 307–313.

4. Srimani PK, Shanthi Mahesh. A comparative study of different segmentation techniques for brain tumour detection. IJETCAS 2013; 4: 192–197.

5. Yuan Been Chen, Oscal T-C Chen. Image segmentation method using thresholds automatically determined from picture contents. Journal on Image and Video Processing 2009; 5: 1–15.

6. MARCO'S BLOG. [web]. Available from: http://marco-za.blogspot.ru/2007/09/under-vs-oversegmentation.html (date of access 13.01.2017).

7. Betty RK, Jonathan AC. Essential Medical Statistics. Blackwell publishing. 2nd ed., 2009; 513 p.

8. Dorit S Hochbaum, Cheng LyuErik Bertelli. Evaluating performance of image segmentation criteria and techniques. EURO Journal on Computational Optimization 2013;1(1–2): 155–180.




DOI: https://doi.org/10.24294/mipt.v0i0.583

Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Abulraqeb Atef Rawhan Abdulsameea

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Creative Commons License

This site is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.