This dissertation focuses on the use of deep learning and machine learning techniques to diagnose Thyroid Disease. Those techniques have recently made unprecedented progress and exhibit incredible abilities to discover intricate structures from high dimensional data. Deep learning approaches have achieved state-of-the-art performances by a significant margin for many computer vision tasks in various cases. The contributions of this dissertation are stated in three folds. First, a fast screening approach leveraging deep learning is proposed to solve the thyroid nodules problem. Second, the importance and effectiveness of medical data fusion are illustrated in developing machine learning classifiers. Third, the potential use of the deep learning model and iridology can address medical images for the thyroid problems. In particular, we investigate deep learning and machine learning ways of addressing classification, detection, segmentation of medical images for thyroid disease. For classification, a newly developed dataset has been used with fewer attributes for the early prediction of thyroid disease to allow doctors to get more precise and accurate results in less time. For detection and classification, the motivation is to provide a quick, supportive, non-invasive system for physicians to screen thyroid disorder through human iris images. For the segmentation, to distinguish between healthy tissues and the thyroid nodule region, an automated deep learning technique is used for detecting and segmenting thyroid nodules in ultrasound images. Experimental results demonstrate that the developed computational methods in this study are effective and efficient in learning from medical imaging data.

This dissertation focuses on the use of deep learning and machine learning techniques to diagnose Thyroid Disease. Those techniques have recently made unprecedented progress and exhibit incredible abilities to discover intricate structures from high dimensional data. Deep learning approaches have achieved state-of-the-art performances by a significant margin for many computer vision tasks in various cases. The contributions of this dissertation are stated in three folds. First, a fast screening approach leveraging deep learning is proposed to solve the thyroid nodules problem. Second, the importance and effectiveness of medical data fusion are illustrated in developing machine learning classifiers. Third, the potential use of the deep learning model and iridology can address medical images for the thyroid problems. In particular, we investigate deep learning and machine learning ways of addressing classification, detection, segmentation of medical images for thyroid disease. For classification, a newly developed dataset has been used with fewer attributes for the early prediction of thyroid disease to allow doctors to get more precise and accurate results in less time. For detection and classification, the motivation is to provide a quick, supportive, non-invasive system for physicians to screen thyroid disorder through human iris images. For the segmentation, to distinguish between healthy tissues and the thyroid nodule region, an automated deep learning technique is used for detecting and segmenting thyroid nodules in ultrasound images. Experimental results demonstrate that the developed computational methods in this study are effective and efficient in learning from medical imaging data.

[1] “Global spending on health 2020: weathering the storm.” [Online]. Available: https://apps.who.int/iris/handle/10665/337859?locale-attribute=en&. [Accessed: 29-Nov-2021].
[2] “Research, Statistics, Data & Systems | CMS.” [Online]. Available: https://www.cms.gov/Research-Statistics-Data-and-Systems/Research-Statistics-Data-and-Systems. [Accessed: 29-Nov-2021].
[3] “HHS.gov.” [Online]. Available: https://www.hhs.gov/. [Accessed: 29-Nov-2021].
[4] L. M. Etheredge, “A rapid-learning health system,” Health Aff. (Millwood)., vol. 26, no. 2, Mar. 2007, doi: 10.1377/HLTHAFF.26.2.W107.
[5] J. Adler-Milstein and A. K. Jha, “Hitech act drove large gains in hospital electronic health record adoption,” Health Affairs, vol. 36, no. 8. pp. 1416–1422, 2017, doi: 10.1377/hlthaff.2016.1651.
[6] B. H. Gray, T. Bowden, I. Johansen, and S. Koch, “Issues in international health policy: electronic health records: an international perspective on ‘meaningful use’.,” Issue Brief (Commonw. Fund), vol. 28, no. November, pp. 1–18, 2011.
[7] NEJM Catalyst and A. Compton-Phillips, “Care Redesign: What Data Can Really Do for Health Care,” 2017.
[8] “Office-based Health Care Professionals Participating in the CMS EHR Incentive Programs | HealthIT.gov.” [Online]. Available: https://www.healthit.gov/data/quickstats/office-based-health-care-professionals-participating-cms-ehr-incentive-programs. [Accessed: 29-Nov-2021].
[9] P. Densen, “Challenges and Opportunities Facing Medical Education,” Trans. Am. Clin. Climatol. Assoc., vol. 122, p. 48, 2011.
[10] “The ICD-10 classification of mental and behavioural disorders : diagnostic criteria for research.” [Online]. Available: https://apps.who.int/iris/handle/10665/37108. [Accessed: 29-Nov-2021].
[11] “World report on ageing and health.” [Online]. Available: https://apps.who.int/iris/handle/10665/186463. [Accessed: 29-Nov-2021].
[12] K. E. Joynt and A. K. Jha, “Characteristics of hospitals receiving penalties under the Hospital Readmissions Reduction Program,” JAMA, vol. 309, no. 4, pp. 342–343, Jan.2013, doi: 10.1001/JAMA.2012.94856.
[13] E. P. Balogh et al., “Improving Diagnosis in Health Care,” Improv. Diagnosis Heal. Care, pp. 1–472, Dec.2015, doi: 10.17226/21794.
[14] K. Y. He, D. Ge, and M. M. He, “Big Data Analytics for Genomic Medicine,” Int. J. Mol. Sci., vol. 18, no. 2, Feb.2017, doi: 10.3390/IJMS18020412.
[15] S. Nepal, R. Ranjan, and K. K. R. Choo, “Trustworthy processing of healthcare big data in hybrid clouds,” IEEE Cloud Comput., vol. 2, no. 2, pp. 78–84, Mar.2015, doi: 10.1109/MCC.2015.36.
[16] A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, Feb.2017, doi: 10.1038/NATURE21056.
[17] K. Doi, “Computer-aided diagnosis in medical imaging: historical review, current status and future potential,” Comput. Med. Imaging Graph., vol. 31, no. 4–5, pp. 198–211, 2007, doi: 10.1016/J.COMPMEDIMAG.2007.02.002.
[18] A. L. Fogel and J. C. Kvedar, “Artificial intelligence powers digital medicine,” npj Digit. Med. 2018 11, vol. 1, no. 1, pp. 1–4, Mar.2018, doi: 10.1038/s41746-017-0012-2.
[19] K. Suzuki, P. Yan, F. Wang, and D. Shen, “Machine Learning in Medical Imaging,” Int. J. Biomed. Imaging, vol. 2012, Mar. 2012, doi: 10.1155/2012/123727.
[20] J. Tang, R. M. Rangayyan, J. Xu, I. E. ElNaqa, and Y. Yang, “Computer-aided detection and diagnosis of breast cancer with mammography: Recent advances,” IEEE Trans. Inf. Technol. Biomed., vol. 13, no. 2, pp. 236–251, 2009, doi: 10.1109/TITB.2008.2009441.
[21] I. Sluimer, A. Schilham, M. Prokop, and B. VanGinneken, “Computer analysis of computed tomography scans of the lung: A survey,” IEEE Trans. Med. Imaging, vol. 25, no. 4, pp. 385–405, Apr. 2006, doi: 10.1109/TMI.2005.862753.
[22] Y. Zhang, J. M. Gorriz, and Z. Dong, “Deep Learning in Medical Image Analysis,” J. Imaging 2021, Vol. 7, Page 74, vol. 7, no. 4, p. 74, Apr. 2021, doi: 10.3390/JIMAGING7040074.
[23] S. Zhang et al., “Using the K-nearest neighbor algorithm for the classification of lymph node metastasis in gastric cancer,” Comput. Math. Methods Med., 2012, doi: 10.1155/2012/876545.
[24] P. Chalekar, S. Shroff, S. Pise, and S. Panicker, “USE OF K-NEAREST NEIGHBOR IN THYROID DISEASE CLASSIFICATION,” Int. J. Curr. Eng. Sci. Res., vol. 1, no. 2, pp. 2394–0697, 2014.
[25] Z. Mushtaq, A. Yaqub, A. Hassan, and S. F. Su, “Performance analysis of supervised classifiers using PCA based techniques on breast cancer,” in 2019 International Conference on Engineering and Emerging Technologies, ICEET, 2019, pp. 1–6, doi: 10.1109/CEET1.2019.8711868.
[26] N. Aboudi, R. Guetari, and N. Khlifa, “Multi-objectives optimization of features selection for the classification of thyroid nodules in ultrasound images,” IET Image Process., vol. 14, no. 9, pp. 1937–1947, Jul. 2020, doi: 10.1049/IET-IPR.2019.1540.
[27] M. Deepika and K. Kalaiselvi, “A Empirical study on Disease Diagnosis using Data Mining Techniques,” in Proceedings of the International Conference on Inventive Communication and Computational Technologies, ICICCT, 2018, no. Icicct, pp. 615–620, doi: 10.1109/ICICCT.2018.8473185.
[28] Zhi-Hua Zhou, Ensemble Methods: Foundations and Algorithms - Zhi-Hua Zhou - Google Books. 2012.
[29] E. Turanoglu-Bekar, G. Ulutagay, and S. Kantarcı-Savas, “Classification of Thyroid Disease by Using Data Mining Models: A Comparison of Decision Tree Algorithms,” Oxford J. Intell. Decis. Data Sci., vol. 2016, no. 2, pp. 13–28, 2016, doi: 10.5899/2016/ojids-00002.
[30] D. Lavanya and K. U. Rani, “Performance Evaluation of Decision Tree Classifiers on Medical Datasets,” Int. J. Comput. Appl., vol. 26, no. 4, pp. 1–4, 2011, doi: 10.5120/3095-4247.
[31] Y. Yang, G. Chen, and G. Reniers, “Vulnerability assessment of atmospheric storage tanks to floods based on logistic regression,” Reliab. Eng. Syst. Saf., vol. 196, p. 106721, 2020, doi: 10.1016/j.ress.2019.106721.
[32] “U-Net Image Segmentation with Convolutional Networks | by Buse Yaren Tekin, M.Sc. | Sep, 2021 | Towards AI.” [Online]. Available: https://pub.towardsai.net/u-net-image-segmentation-with-convolutional-networks-90809950e0d3. [Accessed: 26-Nov-2021].
[33] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9351, pp. 234–241, 2015, doi: 10.1007/978-3-319-24574-4_28.
[34] H. Abbad Ur Rehman, C. Y. Lin, Z. Mushtaq, and S. F. Su, “Performance Analysis of Machine Learning Algorithms for Thyroid Disease,” Arab. J. Sci. Eng., 2021, doi: 10.1007/s13369-020-05206-x.
[35] H. Abbad Ur Rehman, C. Y. Lin, and Z. Mushtaq, “Effective K-Nearest Neighbor Algorithms Performance Analysis of Thyroid Disease,” J. Chinese Inst. Eng. Trans. Chinese Inst. Eng. vol. 44, no. 1, pp. 77–87, 2021, doi: 10.1080/02533839.2020.1831967.
[36] D. Fresilli et al., “Thyroid Nodule Characterization: How to Assess the Malignancy Risk. Update of the Literature,” Diagnostics 2021, Vol. 11, Page 1374, vol. 11, no. 8, p. 1374, Jul.2021, doi: 10.3390/DIAGNOSTICS11081374.
[37] V. Kumar et al., “Automated Segmentation of Thyroid Nodule, Gland, and Cystic Components from Ultrasound Images Using Deep Learning,” IEEE Access, vol. 8, pp. 63482–63496, 2020, doi: 10.1109/ACCESS.2020.2982390.
[38] R. L. Siegel, K. D. Miller, and A. Jemal, “Cancer statistics, 2019,” CA. Cancer J. Clin., vol. 69, no. 1, pp. 7–34, Jan.2019, doi: 10.3322/CAAC.21551.
[39] L. Ma, C. Ma, Y. Liu, and X.Wang, “Thyroid diagnosis from SPECT images using convolutional neural network with optimization,” Comput. Intell. Neurosci., vol. 2019, 2019, doi: 10.1155/2019/6212759.
[40] D. T. Nguyen, J. K. Kang, T. D. Pham, G.Batchuluun, and K. R. Park, “Ultrasound Image-Based Diagnosis of Malignant Thyroid Nodule Using Artificial Intelligence,” Sensors 2020, Vol. 20, Page 1822, vol. 20, no. 7, p. 1822, Mar.2020, doi: 10.3390/S20071822.
[41] X. Li et al., “Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study,” Lancet Oncol., vol. 20, no. 2, pp. 193–201, Feb.2019, doi: 10.1016/S1470-2045(18)30762-9.
[42] Y. Sharifi, M. A. Bakhshali, T. Dehghani, M. DanaiAshgzari, M. Sargolzaei, and S. Eslami, “Deep learning on ultrasound images of thyroid nodules,” Biocybern. Biomed. Eng., vol. 41, no. 2, pp. 636–655, Apr.2021, doi: 10.1016/J.BBE.2021.02.008.
[43] P. A, G. S, H. S, and S. D, “Classification of Thyroid Nodules in Ultrasound Images Using Direction-Independent Features Extracted by Two-Threshold Binary Decomposition,” Technol. Cancer Res. Treat., vol. 18, 2019, doi: 10.1177/1533033819830748.
[44] H. A. Nugroho, Zulfanahri, E. L. Frannita, I. Ardiyanto, and L. Choridah, “Computer aided diagnosis for thyroid cancer system based on internal and external characteristics,” J. King Saud Univ. - Comput. Inf. Sci., vol. 33, no. 3, pp. 329–339, Mar. 2021, doi: 10.1016/J.JKSUCI.2019.01.007.
[45] J. Song et al., “Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules,” Medicine (Baltimore)., vol. 98, no. 15, p. e15133, Apr. 2019, doi: 10.1097/MD.0000000000015133.
[46] K. S.Y et al., “Deep convolutional neural network for the diagnosis of thyroid nodules on ultrasound,” Head Neck, vol. 41, no. 4, pp. 885–891, Apr. 2019, doi: 10.1002/HED.25415.
[47] T. Liu et al., “Automated detection and classification of thyroid nodules in ultrasound images using clinical-knowledge-guided convolutional neural networks,” Med. Image Anal., vol. 58, p. 101555, Dec. 2019, doi: 10.1016/J.MEDIA.2019.101555.
[48] V. CM et al., “Intelligent Diagnosis of Thyroid Ultrasound Imaging Using an Ensemble of Deep Learning Methods,” Medicina (Kaunas)., vol. 57, no. 4, 2021, doi: 10.3390/MEDICINA57040395.
[49] W. Yang et al., “Integrate domain knowledge in training multi-task cascade deep learning model for benign–malignant thyroid nodule classification on ultrasound images,” Eng. Appl. Artif. Intell., vol. 98, Feb.2021, doi: 10.1016/J.ENGAPPAI.2020.104064.
[50] F. Abdolali, J. Kapur, J. L. Jaremko, M. Noga, A. R. Hareendranathan, and K. Punithakumar, “Automated thyroid nodule detection from ultrasound imaging using deep convolutional neural networks,” Comput. Biol. Med., vol. 122, p. 103871, Jul. 2020, doi: 10.1016/J.COMPBIOMED.2020.103871.
[51] L. Pedraza, C. Vargas, F. Narváez, O. Durán, E. Muñoz, and E. Romero, “An open access thyroid ultrasound image database,” in 10th International Symposium on Medical Information Processing and Analysis, 2015, vol. 9287, pp. 188–193, doi: 10.1117/12.2073532.
[52] F. N. Tessler, W. D. Middleton, and E. G. Grant, “Thyroid imaging reporting and data system (TI-RADS): A user’s guide,” Radiology, vol. 287, no. 1, pp. 29–36, Apr.2018, doi: 10.1148/RADIOL.2017171240.
[53] B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Freeman, “LabelMe: A Database and Web-Based Tool for Image Annotation,” Int. J. Comput. Vis. 2007 771, vol. 77, no. 1, pp. 157–173, Oct. 2007, doi: 10.1007/S11263-007-0090-8.
[54] E. Shelhamer, J. Long, and T. Darrell, “Fully Convolutional Networks for Semantic Segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 4, pp. 640–651, Apr. 2017, doi: 10.1109/TPAMI.2016.2572683.
[55] T. Falk et al., “U-Net: deep learning for cell counting detection and morphometry,” Nat. Methods 2018 161, vol. 16, no. 1, pp. 67–70, Dec. 2018, doi: 10.1038/s41592-018-0261-2.
[56] J. Gupta, D. Jhunjhunu Wala, R. Juston, M. MC, “Image Segmentation Keras: Implementation of Segnet, FCN, UNet, PSP Net and Other Models in Keras.” [Online]. Available: https://github.com/divamgupta/image-segmentation-keras. [Accessed: 20-Oct-2021].
[57] H. Pan, Q. Zhou, and L. J. Latecki, “SGUNet: Semantic Guided UNet for Thyroid Nodule Segmentation.,” IEEE Int. Symp. Biomed. Imaging, 2021.
[58] J. Wu, Z. Zhang, J. Zhao, and Y. Qiang, “Ultrasound Image Segmentation of Thyroid Nodules Based On Joint Up-sampling,” J. Phys. Conf. Ser., vol. 1651, no. 1, p. 012157, Nov.2020, doi: 10.1088/1742-6596/1651/1/012157.
[59] S. O. Haji and R. Z. Yousif, “A novel neutrosophic method for automatic seed point selection in thyroid nodule images,” Biomed Res. Int., vol. 2019, 2019, doi: 10.1155/2019/7632308.
[60] “Thyroid Patient Information | American Thyroid Association.” [Online]. Available: https://www.thyroid.org/thyroid-information/. [Accessed: 10-Jul-2021].
[61] S. Shroff, S. Pise, P. Chalekar, and S. S. Panicker, “Thyroid disease diagnosis: A survey,” in Proceedings of 2015 IEEE 9th International Conference on Intelligent Systems and Control, ISCO 2015, 2015, pp. 1–6, doi: 10.1109/ISCO.2015.7282384.
[62] “Hyperthyroidism | Graves’ Disease | Overactive Thyroid | MedlinePlus.” [Online]. Available: https://medlineplus.gov/hyperthyroidism.html. [Accessed: 15-Mar-2020].
[63] “Hypothyroidism | Hashimoto’s Disease | MedlinePlus.” [Online]. Available: https://medlineplus.gov/hypothyroidism.html. [Accessed: 15-Mar-2020].
[64] R. Pal, T. Anand, and S. K. Dubey, “Evaluation and performance analysis of classification techniques for thyroid detection,” Int. J. Bus. Inf. Syst., vol. 28, no. 2, pp. 163–177, 2018.
[65] “Thyroid Function Tests | American Thyroid Association.” [Online]. Available: https://www.thyroid.org/thyroid-function-tests/. [Accessed: 15-Mar-2020].
[66] “What Is Thyroid Cancer?” [Online]. Available: https://www.cancer.org/cancer/thyroid-cancer/about/what-is-thyroid-cancer. [Accessed: 01-Jan-2020].
[67] K. Chandel, V. Kunwar, S. Sabitha, T. Choudhury, and S. Mukherjee, “A comparative study on thyroid disease detection using K-nearest neighbor and Naive Bayes classification techniques,” CSI Trans. ICT, vol. 4, no. 2–4, pp. 313–319, 2016, doi: 10.1007/s40012-016-0100-5.
[68] V. Prasad, T. S. Rao, and M. S. P. Babu, “Thyroid disease diagnosis via hybrid architecture composing rough data sets theory and machine learning algorithms,” Soft Comput., vol. 20, no. 3, pp. 1179–1189, 2016, doi: 10.1007/s00500-014-1581-5.
[69] Z. Mushtaq, A. Yaqub, S. Sani, and A. Khalid, “Effective K-nearest neighbor classifications for Wisconsin breast cancer data sets,” J. Chinese Inst. Eng., vol. 00, no. 00, pp. 1–13, 2019, doi: 10.1080/02533839.2019.1676658.
[70] D. Tomar and S. Agarwal, “A survey on data mining approaches for healthcare,” Int. J. Bio-Science Bio-Technology, vol. 5, no. 5, pp. 241–266, 2013, doi: 10.14257/ijbsbt.2013.5.5.25.
[71] F. Firouzi, “Kidney Diseases Diagnosis by Using Fuzzy Logic,” in Proceeding of the 2015 International Conference on Industrial Engineering and Operations Management, 2015, pp. 2369–2375.
[72] M. Durairaj and V. Ranjani, “Data Mining Applications In Healthcare Sector: A Study,” Int. J. Sci. Technol. Res., vol. 2, no. 10, pp. 29–35, 2013.
[73] D. Y. Liu, H. L. Chen, B. Yang, X. E. Lv, L. N. Li, and J. Liu, “Design of an enhanced Fuzzy k-nearest neighbor classifier based computer aided diagnostic system for thyroid disease,” J. Med. Syst., vol. 36, no. 5, pp. 3243–3254, 2012, doi: 10.1007/s10916-011-9815-x.
[74] U. R. Acharya, S. Vinitha Sree, F. Molinari, R. Garberoglio, A. Witkowska, and J. S. Suri, “Automated benign and malignant thyroid lesion characterization and classification in 3D contrast-enhanced ultrasound,” in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2012, pp. 452–455, doi: 10.1109/EMBC.2012.6345965.
[75] M. R. N. Kousarrizi, F. Seiti, and M. Teshnehlab, “An Experimental Comparative Study on Thyroid Disease Diagnosis Based on Feature Subset Selection and classification,” Int. J. Electr. Comput. Sci., vol. 12, no. 01, pp. 13–19, 2012.
[76] H. L. Chen, B. Yang, G. Wang, J. Liu, Y. D. Chen, and D. Y. Liu, “A three-stage expert system based on support vector machines for thyroid disease diagnosis,” J. Med. Syst., vol. 36, no. 3, pp. 1953–1963, 2012, doi: 10.1007/s10916-011-9655-8.
[77] E. Dogantekin, A. Dogantekin, and D. Avci, “An expert system based on Generalized Discriminant Analysis and Wavelet Support Vector Machine for diagnosis of thyroid diseases,” Expert Syst. Appl., vol. 38, no. 1, pp. 146–150, 2011, doi: 10.1016/j.eswa.2010.06.029.
[78] A. Keleş and A. Keleş, “ESTDD: Expert system for thyroid diseases diagnosis,” Expert Syst. Appl., vol. 34, no. 1, pp. 242–246, 2008, doi: 10.1016/j.eswa.2006.09.028.
[79] L. Ozyilmaz and T. Yildirim, “Diagnosis of thyroid disease using artificial neural network methods,” in ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age, 2002, vol. 4, pp. 2033–2036, doi: 10.1109/ICONIP.2002.1199031.
[80] “Teaching Hospital - Dera Ghazi Khan.” [Online]. Available: http://thdgkhan.org/. [Accessed: 15-Mar-2020].
[81] “Scikit-learn: Machine Learning in Python,” J. Mach. Learn. Res., vol. 1, pp. 2825–2830, 2000, doi: 10.1162/153244303322753724.
[82] B. Sahu, S. Mohanty, and S. Rout, “A Hybrid Approach for Breast Cancer Classification and Diagnosis,” ICST Trans. Scalable Inf. Syst., vol. 0, no. 0, p. 156086, 2018, doi: 10.4108/eai.19-12-2018.156086.
[83] “Anaconda | The World’s Most Popular Data Science Platform.” [Online]. Available: https://www.anaconda.com/. [Accessed: 05-Jan-2020].
[84] “Feature Importance and Feature Selection With XGBoost in Python.” [Online]. Available: https://machinelearningmastery.com/feature-importance-and-feature-selection-with-xgboost-in-python/. [Accessed: 15-Mar-2020].
[85] A. Tyagi, R. Mehra, and A. Saxena, “Interactive thyroid disease prediction system using machine learning technique,” in PDGC 2018 - 2018 5th International Conference on Parallel, Distributed and Grid Computing, 2018, pp. 689–693, doi: 10.1109/PDGC.2018.8745910.
[86] “Thyroid Eye Disease - NORD (National Organization for Rare Disorders).” [Online]. Available: https://rarediseases.org/rare-diseases/thyroid-eye-disease/. [Accessed: 10-Jul-2021].
[87] “Thyroid Cancer: Statistics | Cancer.Net.” [Online]. Available: https://www.cancer.net/cancer-types/thyroid-cancer/statistics. [Accessed: 10-Jul-2021].
[88] “General Information/Press Room | American Thyroid Association.” [Online]. Available: https://www.thyroid.org/media-main/press-room/. [Accessed: 03-Aug-2021].
[89] N. Shah, “Prevalence and Manifestations of Hypothyroidism among Population of Hyderabad, Sindh, Pakistan,” Pure Appl. Biol., vol. 10, no. 3, pp. 668–675, 2021, doi: 10.19045/bspab.2021.100069.
[90] H. S. Shon, E. Batbaatar, K. O. Kim, E. J. Cha, and K. -A. Kim, “Classification of Kidney Cancer Data Using Cost-Sensitive Hybrid Deep Learning Approach,” Symmetry 2020, Vol. 12, Page 154, vol. 12, no. 1, p. 154, Jan.2020, doi: 10.3390/SYM12010154.
[91] B. Jensen, Iridology simplified. Healthy Living Publications, 2011.
[92] Y. -H. Li, M. S. Aslam, K. -L. Yang, C. -A. Kao, and S. -Y. Teng, “Classification of Body Constitution Based on TCM Philosophy and Deep Learning,” Symmetry 2020, Vol. 12, Page 803, vol. 12, no. 5, p. 803, May 2020, doi: 10.3390/SYM12050803.
[93] “Camera Iriscope | Iridoscope | Iris Lighting | Professional iridology.” [Online]. Available: https://www.irislab.com/. [Accessed: 10-Jul-2021].
[94] B. Jensen, Iridology Simplified. Bernard Jensen Intl, 1980.
[95] S. Muzamil, T. Hussain, A. Haider, U. Waraich, U. Ashiq, and E. Ayguadé, “An Intelligent Iris Based Chronic Kidney Identification System,” Symmetry 2020, Vol. 12, Page 2066, vol. 12, no. 12, p. 2066, Dec.2020, doi: 10.3390/SYM12122066.
[96] T. Hussain, A. Haider, and A. Taleb-Ahmed, “A Heterogeneous Multi-Core Based Biomedical Application Processing System and Programming Toolkit,” J. Signal Process. Syst., vol. 91, no. 8, pp. 963–978, Aug.2019, doi: 10.1007/S11265-018-1437-9.
[97] R. Passarella, Erwin, and M. Fachrurrozi, “Development of Iridology System Database for Colon Disorders Identification using Image Processing,” Indian J. Bioinforma. Biotechnol., vol. 2, no. 6, pp. 100–103, 2013.
[98] A. Haider et al., “An Iris based Smart System for Stress Identification,” in 1st International Conference on Electrical, Communication and Computer Engineering, ICECCE 2019, 2019, doi: 10.1109/ICECCE47252.2019.8940707.
[99] A. S, A. MU, S. M, T. A, and Y. U. U, “Arteriovenous ratio and papilledema based hybrid decision support system for detection and grading of hypertensive retinopathy.,” Comput. Methods Programs Biomed., vol. 154, pp. 123–141, Nov.2017, doi: 10.1016/J.CMPB.2017.11.014.
[100] S. M, H. T, A. MU, and K. SA, “An incremental learning approach to automatically recognize pulmonary diseases from the multi-vendor chest radiographs,” Comput. Biol. Med., vol. 134, Jul.2021, doi: 10.1016/J.COMPBIOMED.2021.104435.
[101] F. Hernandez, R. Vega, F. Tapia, D. Morocho, and W. Fuertes, “Early detection of Alzheimer’s using digital image processing through iridology, an alternative method,” Iber. Conf. Inf. Syst. Technol. Cist., vol. 2018-June, pp. 1–7, Jun.2018, doi: 10.23919/CISTI.2018.8399151.
[102] W. Chen, Q. Sun, X. Chen, G. Xie, H. Wu, and C. Xu, “Deep learning methods for heart sounds classification: A systematic review,” Entropy, vol. 23, no. 6, pp. 1–18, 2021, doi: 10.3390/e23060667.
[103] J. F. Banzi and Z. Xue, “An Automated Tool for Non-contact, Real Time Early Detection of Diabetes by Computer Vision,” Int. J. Mach. Learn. Comput., vol. 5, no. 3, pp. 225–229, Jun.2015, doi: 10.7763/IJMLC.2015.V5.511.
[104] “Stochastic gradient descent - Wikipedia.” [Online]. Available: https://en.wikipedia.org/wiki/Stochastic_gradient_descent. [Accessed: 10-Jul-2021].
[105] “Thyroid-Stimulating Hormone | AACC.org.” [Online]. Available: https://www.aacc.org/cln/articles/2013/may/tsh-harmonization. [Accessed: 02-Sep-2021].
[106] L. Frank, “The reliability of iridology in the diagnosis of previous acute appendicitis, as evidenced by appendectomy,” University of Johannesburg, 2012.
[107] “Stanford University CS231n: Convolutional Neural Networks for Visual Recognition.” [Online]. Available: http://cs231n.stanford.edu/. [Accessed: 10-Jul-2021].
[108] X. Glorot, A. Bordes, and Y. Bengio, “Deep Sparse Rectifier Neural Networks,” 2011.
[109] V. Nair and G. E. Hinton, “Rectified Linear Units Improve Restricted Boltzmann Machines.”
[110] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” J. Mach. Learn. Res., vol. 15, no. 56, pp. 1929–1958, 2014.
[111] Z. Mushtaq, A. Yaqub, S. Sani, and A. Khalid, “Effective K-nearest neighbor classifications for Wisconsin breast cancer data sets,” J. Chinese Inst. Eng. Trans. Chinese Inst. Eng. A, vol. 43, no. 1, pp. 80–92, Jan.2020, doi: 10.1080/02533839.2019.1676658.
[112] S. H. S. Basha, S. R. Dubey, V. Pulabaigari, and S. Mukherjee, “Impact of fully connected layers on performance of convolutional neural networks for image classification,” Neurocomputing, vol. 378, pp. 112–119, Feb.2020, doi: 10.1016/J.NEUCOM.2019.10.008.
[113] A. Bansal, C. Castillo, R. Ranjan, and R. Chellappa, “The do’s and don’ts for CNN-Based face verification,” in Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017, 2017, vol. 2018-Janua, pp. 2545–2554, doi: 10.1109/ICCVW.2017.299.