Thyroid Nodule Recognition Based on Feature Selection and Pixel Classification Methods

Journal of Digital Imaging, 05/07/2012

Bibicu D et al. – It is found that the proposed approach is capable of identifying thyroid nodules with a correct classification rate of 83 % when whole image is analyzed and with a percent of 91 % when the region of interests (ROIs) are analyzed.

Methods

  • Twenty ultrasound images of normal thyroid and 20 that present thyroid nodules were used.
  • The analysis involves both the whole thyroid ultrasound images and the region of interests (ROIs).

Results

  • The proposed system and the classification results are validated using the receiver operating characteristics which give a better overall view of the classification performance of methods.

Print Article Summary