Open AccessOpen Access


SNCDM: Spinal Tumor Detection from MRI Images Using Optimized Super-Pixel Segmentation

T. Merlin Inbamalar1,*, Dhandapani Samiappan2, R. Ramesh3

1 Department of Electronics and Instrumentation Engineering, Saveetha Engineering College, Chennai, Tamilnadu, India
2 Department of Electronics and Communication Engineering, Saveetha Engineering College, Chennai,Tamilnadu, India
3 Department of Electronics and Communication Engineering, Tagore Engineering College, Chennai, Tamilnadu, India

* Corresponding Author: T. Merlin Inbamalar. Email:

Intelligent Automation & Soft Computing 2023, 36(2), 1899-1913.


Conferring to the American Association of Neurological Surgeons (AANS) survey, 85% to 99% of people are affected by spinal cord tumors. The symptoms are varied depending on the tumor’s location and size. Up-to-the-minute, back pain is one of the essential symptoms, but it does not have a specific symptom to recognize at the earlier stage. Numerous significant research studies have been conducted to improve spine tumor recognition accuracy. Nevertheless, the traditional systems are consuming high time to extract the specific region and features. Improper identification of the tumor region affects the predictive tumor rate and causes the maximum error-classification problem. Consequently, in this work, Super-pixel analytics Numerical Characteristics Disintegration Model (SNCDM) is used to segment the tumor affected region. Estimating the super-pixels of the affected region by this method reduces the variance between the identified pixels. Further, the super-pixels are selected according to the optimized convolution network that effectively extracts the vertebral super-pixels features. Derived super-pixels improve the network learning and training process, which minimizes the maximum error classification problem also the efficiency of the system was evaluated using experimental results and analysis.


Cite This Article

T. Merlin Inbamalar, D. Samiappan and R. Ramesh, "Sncdm: spinal tumor detection from mri images using optimized super-pixel segmentation," Intelligent Automation & Soft Computing, vol. 36, no.2, pp. 1899–1913, 2023.

This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 545


  • 232


  • 1


Share Link