Enhanced thyroid nodule segmentation through U-Net and VGG16 fusion with feature engineering: A comprehensive study.

BACKGROUND AND OBJECTIVE: The thyroid gland, a key component of the endocrine system, is pivotal in regulating bodily functions. Thermography, a non-invasive imaging technique utilizing infrared cameras, has emerged as a diagnostic tool for thyroid-related conditions, offering advantages such as early detection and risk stratification. Artificial intelligence (AI) has demonstrated success in medical diagnostics, and its integration into thermal imaging analysis holds promise for improving diagnostic capabilities. This study aims to explore the potential of AI, specifically convolutional neural networks (CNNs), in enhancing the analysis of thyroid thermograms for the detection of nodules and abnormalities. METHODS: Artificial intelligence (AI) and machine learning techniques are integrated to enhance thyroid thermal image analysis. Specifically, a fusion of U-Net and VGG16, combined with feature engineering (FE), is proposed for accurate thyroid nodule segmentation. The novelty of this research lies in leveraging feature engineering in transfer learning for the segmentation of thyroid nodules, even in the presence of a limited dataset. RESULTS: The study presents results from four conducted studies, demonstrating the efficacy of this approach even with a limited dataset. It's observed that in study 4, using FE has led to a significant improvement in the value of the dice coefficient. Even for the small size of the masked region, incorporating radiomics with FE resulted in significant improvements in the segmentation dice coefficient. It's promising that one can achieve higher dice coefficients by employing different models and refining them. CONCLUSION: The findings here underscore the potential of AI for precise and efficient segmentation of thyroid nodules, paving the way for improved thyroid health assessment.

Comparing Different Algorithms for the Pseudo-Coloring of Myocardial Perfusion Single-Photon Emission Computed Tomography Images.

Single-photon emission computed tomography (SPECT) images can significantly help physicians in diagnosing patients with coronary artery or suspected coronary artery diseases. However, these images are grayscale with qualities that are not readily visible. The objective of this study was to evaluate the effectiveness of different pseudo-coloring algorithms of myocardial perfusion SPECT images. Data were collected using a Siemens Symbia T2 dual-head SPECT/computed tomography (CT) scanner. After pseudo-coloring, the images were assessed both qualitatively and quantitatively. The qualities of different pseudo-color images were examined by three experts, while the images were evaluated quantitatively by obtaining indices such as mean squared error (MSE), peak signal-to-noise ratio (PSNR), normalized color difference (NCD), and structure similarity index metric (SSIM). The qualitative evaluation demonstrated that the warm color map (WCM), followed by the jet color map, outperformed the remaining algorithms in terms of revealing the non-visible qualities of the images. Furthermore, the quantitative evaluation results demonstrated that the WCM had the highest PSNR and SSIM but the lowest MSE. Overall, the WCM could outperform the other color maps both qualitatively and quantitatively. The novelty of this study includes comparing different pseudo-coloring methods to improve the quality of myocardial perfusion SPECT images and utilizing our collected datasets.

Nailfold microvascular changes in patients with systemic lupus erythematosus and their associative factors.

OBJECTIVES: The aim of this study was to determine capillaroscopic changes in patients with systemic lupus erythematosus (SLE) and their predictors. METHODS: Fifty-nine SLE patients and 31 controls were enrolled in a cross-sectional study. Nailfold capillaroscopy examinations were performed, and qualitative semi-quantitative and quantitative parameters were evaluated in all fingers. Demographic features and lupus characteristics, such as renal involvement, medications, laboratory data, disease activity (SLEDAI) and damage, were recorded. The predictors of capillaroscopic abnormalities were obtained by backward stepwise regression analysis. RESULTS: Capillary numbers of right hands were significantly lower in patients than in controls [8.74 (1.66) vs. 9.63 (1.80), P = 0.0001]. Capillaries were wider in patients than in controls in right [56.32 µm (16.76) vs. 50.43 µm (10.16), P = 0.002] and left hands [54.40 (15.02) vs. 49.71 (9.77), P = 0.005]. Capillaries were shorter in SLE patients than in controls. Multivariate analysis revealed that the main associative factors of microvascular abnormalities were gender, drinking tea and hydroxychloroquine use for giant capillaries, SLEDAI and low C3 for avascularity and age, lupus nephritis and corticosteroid use for ramification. CONCLUSION: Most nailfold capillaroscopic abnormalities were more common in SLE patients than in controls. Hydroxychloroquine, corticosteroids, SLEDAI, low complement and lupus nephritis may be the major prognostic factors for microvascular changes in SLE patients.

Practical issues in assessing nailfold capillaroscopic images: a summary.

Nailfold capillaroscopy (NC) is a highly sensitive, safe, and non-invasive technique to assess involvement rate of microvascularity in dermatomyositis and systemic sclerosis. A large number of studies have focused on NC pattern description, classification, and scoring system validation, but minimal information has been published on the accuracy and precision of the measurement. The objective of this review article is to identify different factors affecting the reliability and validity of the assessment in NC. Several factors can affect the reliability of the examination, e.g., physiological artifacts, the nailfold imaging instrument, human factors, and the assessment rules and standards. It is impossible to avoid all artifacts, e.g., skin transparency, physically injured fingers, and skin pigmentation. However, minimization of the impact of some of these artifacts by considering some protocols before the examination and by using specialized tools, training, guidelines, and software can help to reduce errors in the measurement and assessment of NC images. Establishing guidelines and instructions for automatic characterization and measurement based on machine learning techniques also may reduce ambiguities and the assessment time.

Rapid extraction of the hottest or coldest regions of medical thermographic images.

Early detection of breast tumors, feet pre-ulcers diagnosing in diabetic patients, and identifying the location of pain in patients are essential to physicians. Hot or cold regions in medical thermographic images have potential to be suspicious. Hence extracting the hottest or coldest regions in the body thermographic images is an important task. Lazy snapping is an interactive image cutout algorithm that can be applied to extract the hottest or coldest regions in the body thermographic images quickly with easy detailed adjustment. The most important advantage of this technique is that it can provide the results for physicians in real time readily. In other words, it is a good interactive image segmentation algorithm since it has two basic characteristics: (1) the algorithm produces intuitive segmentation that reflects the user intent with given a certain user input and (2) the algorithm is efficient enough to provide instant visual feedback. Comparing to other methods used by the authors for segmentation of breast thermograms such as K-means, fuzzy c-means, level set, and mean shift algorithms, lazy snapping was more user-friendly and could provide instant visual feedback. In this study, twelve test cases were presented and by applying lazy snapping algorithm, the hottest or coldest regions were extracted from the corresponding body thermographic images. The time taken to see the results varied from 7 to 30 s for these twelve cases. It was concluded that lazy snapping was much faster than other methods applied by the authors such as K-means, fuzzy c-means, level set, and mean shift algorithms for segmentation. Graphical abstract Time taken to implement lazy snapping algorithm to extract suspicious regions in different presented thermograms (in seconds). In this study, ten test cases are presented that by applying lazy snapping algorithm, the hottest or coldest regions were extracted from the corresponding body thermographic images. The time taken to see the results varied from 7 to 30 s for the ten cases. It concludes lazy snapping is much faster than other methods applied by the authors.

Image enhancement effect on inter and intra-observer reliability of nailfold capillary assessment.

BACKGROUND: Nailfold capillaroscopy (NC) is a diagnostic imaging technique that is used to assess the blood capillary network in the nailfold area. NC is routinely used for patients with microcirculation problems, such as systemic sclerosis and other connective tissue diseases. Experts commonly use subjective evaluation as a reference point in images of nailfold video capillaroscopy, so it is important to reduce the inherent ambiguities in human judgment and diagnosis. Image quality is an important factor that affects measurement error and assessment time of NC images. OBJECTIVE: In this study, a new image enhancement technique was introduced and evaluated subjectively. METHODS: In total, 475 nailfold video capillaroscopy images from 18 healthy subjects and 41 systemic lupus erythematosus patients were used. The images were randomly divided into two sets, one each with 275 and 200. Eight independent observers who were familiar with the capillaroscopy technique participated in this study. The set of 275 images was evaluated by three observers with the forced-choice pairwise comparison method. Elliptic broken line (EBL) was used to count the number of capillaries. The intra- and inter-observer reliability of the original and enhanced images was evaluated on 200 images by five observers. RESULT: Except for eight images, all observers preferred the enhanced images in the visual quality comparison method. The intra-class correlation coefficient (ICC) of intra- and inter-observer reliability increased from 0.76-0.84 to 0.82-0.89, respectively, when using the enhancement method. CONCLUSION: By improving the image quality, more capillary details will be visible, and an observer can document more details that may not be visible in the original image and can do so more efficiently.

Elliptical broken line method for calculating capillary density in nailfold capillaroscopy: Proposal and evaluation.

Nailfold capillaroscopy is a practical method for identifying and obtaining morphological changes in capillaries which might reveal relevant information about diseases and health. Capillaroscopy is harmless, and seems simple and repeatable. However, there is lack of established guidelines and instructions for acquisition as well as the interpretation of the obtained images; which might lead to various ambiguities. In addition, assessment and interpretation of the acquired images are very subjective. In an attempt to overcome some of these problems, in this study a new modified technique for assessment of nailfold capillary density is introduced. The new method is named elliptic broken line (EBL) which is an extension of the two previously known methods by defining clear criteria for finding the apex of capillaries in different scenarios by using a fitted elliptic. A graphical user interface (GUI) is developed for pre-processing, manual assessment of capillary apexes and automatic correction of selected apexes based on 90° rule. Intra- and inter-observer reliability of EBL and corrected EBL is evaluated in this study. Four independent observers familiar with capillaroscopy performed the assessment for 200 nailfold videocapillaroscopy images, form healthy subject and systemic lupus erythematosus patients, in two different sessions. The results show elevation from moderate (ICC=0.691) and good (ICC=0.753) agreements to good (ICC=0.750) and good (ICC=0.801) for intra- and inter-observer reliability after automatic correction of EBL. This clearly shows the potential of this method to improve the reliability and repeatability of assessment which motivates us for further development of automatic tool for EBL method.

Capillary density: An important parameter in nailfold capillaroscopy.

Nailfold capillaroscopy is one of the various noninvasive bioengineering methods used to investigate skin microcirculation. It is an effective examination for assessing microvascular changes in the peripheral circulation; hence it has a significant role for the diagnosis of Systemic sclerosis with the classic changes of giant capillaries as well as the decline in capillary density with capillary dropout. The decline in capillary density is one of microangiopathic features existing in connective tissue disease. It is detectable with nailfold capillaroscopy. This parameter is assessed by applying quantitative measurement. In this article, we reviewed a common method for calculating the capillary density and the relation between the number of capillaries as well as the existence of digital ulcers, pulmonary arterial hypertension, autoantibodies, scleroderma patterns and different scoring system.

Using shape contexts method for registration of contra lateral breasts in thermal images.

AIM: To achieve symmetric boundaries for left and right breasts boundaries in thermal images by registration. METHODS: The proposed method for registration consists of two steps. In the first step, shape context, an approach as presented by Belongie and Malik was applied for registration of two breast boundaries. The shape context is an approach to measure shape similarity. Two sets of finite sample points from shape contours of two breasts are then presented. Consequently, the correspondences between the two shapes are found. By finding correspondences, the sample point which has the most similar shape context is obtained. RESULTS: In this study, a line up transformation which maps one shape onto the other has been estimated in order to complete shape. The used of a thin plate spline permitted good estimation of a plane transformation which has capability to map unselective points from one shape onto the other. The obtained aligning transformation of boundaries points has been applied successfully to map the two breasts interior points. Some of advantages for using shape context method in this work are as follows: (1) no special land marks or key points are needed; (2) it is tolerant to all common shape deformation; and (3) although it is uncomplicated and straightforward to use, it gives remarkably powerful descriptor for point sets significantly upgrading point set registration. Results are very promising. The proposed algorithm was implemented for 32 cases. Boundary registration is done perfectly for 28 cases. CONCLUSION: We used shape contexts method that is simple and easy to implement to achieve symmetric boundaries for left and right breasts boundaries in thermal images.