Thyroid Cancer Diagnostic System using Magnetic Resonance Imaging

• Published in: International Conference on Pattern Recognition pp. 4365 - 4370
• Main Authors: Sharafeldeen, A., Elsharkawy, M., Shaffie, A., Khalifa, F., Soliman, A., Naglah, A., Khaled, R., Hussein, M. M., Alrahmawy, M., Elmougy, S., Yousaf, J., Ghazal, M., El-Baz, A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 21.08.2022
• Subjects: Artificial neural networks; Computer-Aided Diagnosis (CAD); Feature extraction; Gray-Level Co-occurrence Matrix (GLCM); Harmonic analysis; Magnetic resonance imaging; Magnetic Resonance Imaging (MRI); Neural Network (NN); Pattern recognition; Reflectivity; Sensitivity; Spherical Harmonic (SH); T2-MRI
• ISSN: 2831-7475
• DOI: 10.1109/ICPR56361.2022.9956125

Early detection and diagnosis of thyroid nodules are very important to rescue patients before the cancer spreads all over the patient's body. A computer-aided diagnosis (CAD) system is proposed to detect the malignancy of thyroid nodules using magnetic resonance imaging (MRI) scans. This system extracts three descriptive features from T2-weighted (T2) MRI. These features are 1 st -order reflectivity, 2 nd -order reflectivity, and spherical harmonic. The 1 st -order reflectivity is represented by sufficient statistics, (i.e. CDF percentiles), extracted from the cumulative distribution function (CDF) generated from it. After-ward, these features are fed to a neural network (NN) individually for diagnosis. Then, the classification outputs for these networks are fused using another NN for final diagnosis. The developed system is trained and tested using leave-one-subject-out (LOSO) cross-validation technique on MRI scans from 63 patients. The proposed fusion system shows incredible improvements in diagnostic accuracy, compared with other machine learning approach and a well-know pretrained deep learning network as well as individual feature classification. The overall sensitivity, specificity, F1-score, and accuracy of the proposed system are 91.3%, 95%, 91.3%, and 93.65%, respectively. The reported results, based on the fusion of reflectivity features as well as morphological feature, show the promise of the developed system in differentiating between benign and malignant thyroid nodules.