A Framework for Detecting Thyroid Cancer from Ultrasound and Histopathological Images Using Deep Learning, Meta-Heuristics, and MCDM Algorithms

Abstract

Computer-assisted diagnostic systems have been developed to aid doctors in diagnosing thyroid-related abnormalities. The aim of this research is to improve the diagnosis accuracy of thyroid abnormality detection models that can be utilized to alleviate undue pressure on healthcare professionals. In this research, we proposed deep learning, metaheuristics, and a MCDM algorithms-based framework to detect thyroid-related abnormalities from ultrasound and histopathological images. The proposed method uses three recently developed deep learning techniques (DeiT, Swin Transformer, and Mixer-MLP) to extract features from the thyroid image datasets. The feature extraction techniques are based on the Image Transformer and MLP models. There is a large number of redundant features that can overfit the classifiers and reduce the generalization capabilities of the classifiers. In order to avoid the overfitting problem, six feature transformation techniques (PCA, TSVD, FastICA, ISOMAP, LLE, and UMP) are analyzed to reduce the dimensionality of the data. There are five different classifiers (LR, NB, SVC, KNN, and RF) evaluated using the 5-fold stratified cross-validation technique on the transformed dataset. Both datasets exhibit large class imbalances and hence, the stratified cross-validation technique is used to evaluate the performance. The MEREC-TOPSIS MCDM technique is used for ranking the evaluated models at different analysis stages. In the first stage, the best feature extraction and classification techniques are chosen, whereas, in the second stage, the best dimensionality reduction method is evaluated in wrapper feature selection mode. Two best-ranked models are further selected for the weighted average ensemble learning and features selection using the recently proposed meta-heuristics FOX-optimization algorithm. The PCA+FOX optimization-based feature selection + random forest model achieved the highest TOPSIS score and performed exceptionally well with an accuracy of 99.13%, F2-score of 98.82%, and AUC-ROC score of 99.13% on the ultrasound dataset. Similarly, the model achieved an accuracy score of 90.65%, an F2-score of 92.01%, and an AUC-ROC score of 95.48% on the histopathological dataset. This study exploits the combination novelty of different algorithms in order to improve the thyroid cancer diagnosis capabilities. This proposed framework outperforms the current state-of-the-art diagnostic methods for thyroid-related abnormalities in ultrasound and histopathological datasets and can significantly aid medical professionals by reducing the excessive burden on the medical fraternity.

Automatic Active Lesion Tracking in Multiple Sclerosis Using Unsupervised Machine Learning

“…Recently in healthcare, NLDR techniques have been incorporated to extract important features from medical data. Sharma et al [ 38 ] introduced a framework for thyroid abnormality detection, applying various dimensionality reduction techniques to ultrasound and histopathological datasets. Results based on NLDR methods outperformed current state-of-the-art computer-assisted diagnostic systems.…”

“…We chose to use NLDR methods, LLE and Isomap, to segment active MS lesions. NLDR has been shown to outperform LDR methods in extracting features from imaging datasets [ 21 , 25 , 38 ].…”

Vectorial Image Representation for Image Classification

“…The grade of irregularity or the properties of a texture can be found scattered throughout the entire image. In the field of texture analysis, there exist three major problems: (a) texture classification, focused on determining to which class the sampled texture belongs [2][3][4]; (b) texture segmentation, where an image is sectioned into multiple regions and each region has a specific type of texture [5,6]; and (c) texture synthesis, which focuses on constructing a model that can be employed to produce artificial textures for specific applications such as computer graphics [7,8]. Furthermore, according to reference [9], the characteristics extraction techniques can be classified into three categories: geometrical methods, signal processing, and statistical models.…”

“…Because medical images contain local textural features that can be extracted through local analysis [3,4,26,27], and knowing that the technique reported in this work also extracts texture features based on local analysis, then the VIR-TS transform and the classifier described in Section 2.3 can be applied in medical image recognition. The benefit would be the development of medical diagnostic systems with high efficiency, easy to implement because the definition of the texture unit is based on a linear transformation and not on pattern encoding [21,28], where the overflow of physical memory of the computer is possible [29].…”

Enhancing Thyroid Cancer Diagnostics Through Hybrid Machine Learning and Metabolomics Approaches

“…The neck gland's thyroid carcinoma is treated better with early detection. Healthcare professionals use machine learning algorithms to handle pandemics and natural disasters [14]. These algorithms help physicians identify and treat patients by analyzing enormous medical data.…”