Intelligent Diagnosis of Thyroid Ultrasound Imaging Using an Ensemble of Deep Learning Methods

Automated Quality Assessment of Medical Images in Echocardiography Using Neural Networks with Adaptive Ranking and Structure-Aware Learning

The quality of medical images is crucial for accurately diagnosing and treating various diseases. However, current automated methods for assessing image quality are based on neural networks, which often focus solely on pixel distortion and overlook the significance of complex structures within the images. This study introduces a novel neural network model designed explicitly for automated image quality assessment that addresses pixel and semantic distortion. The model introduces an adaptive ranking mechanism enhanced with contrast sensitivity weighting to refine the detection of minor variances in similar images for pixel distortion assessment. More significantly, the model integrates a structure-aware learning module employing graph neural networks. This module is adept at deciphering the intricate relationships between an image's semantic structure and quality. When evaluated on two ultrasound imaging datasets, the proposed method outshines existing leading models in performance. Additionally, it boasts seamless integration into clinical workflows, enabling real-time image quality assessment, crucial for precise disease diagnosis and treatment.

Learning technology for detection and grading of cancer tissue using tumour ultrasound images1

BACKGROUND

Early diagnosis of breast cancer is crucial to perform effective therapy. Many medical imaging modalities including MRI, CT, and ultrasound are used to diagnose cancer.

OBJECTIVE

This study aims to investigate feasibility of applying transfer learning techniques to train convoluted neural networks (CNNs) to automatically diagnose breast cancer via ultrasound images.

METHODS

Transfer learning techniques helped CNNs recognise breast cancer in ultrasound images. Each model's training and validation accuracies were assessed using the ultrasound image dataset. Ultrasound images educated and tested the models.

RESULTS

MobileNet had the greatest accuracy during training and DenseNet121 during validation. Transfer learning algorithms can detect breast cancer in ultrasound images.

CONCLUSIONS

Based on the results, transfer learning models may be useful for automated breast cancer diagnosis in ultrasound images. However, only a trained medical professional should diagnose cancer, and computational approaches should only be used to help make quick decisions.

[Review on ultrasonographic diagnosis of thyroid diseases based on deep learning]

In recent years, the incidence of thyroid diseases has increased significantly and ultrasound examination is the first choice for the diagnosis of thyroid diseases. At the same time, the level of medical image analysis based on deep learning has been rapidly improved. Ultrasonic image analysis has made a series of milestone breakthroughs, and deep learning algorithms have shown strong performance in the field of medical image segmentation and classification. This article first elaborates on the application of deep learning algorithms in thyroid ultrasound image segmentation, feature extraction, and classification differentiation. Secondly, it summarizes the algorithms for deep learning processing multimodal ultrasound images. Finally, it points out the problems in thyroid ultrasound image diagnosis at the current stage and looks forward to future development directions. This study can promote the application of deep learning in clinical ultrasound image diagnosis of thyroid, and provide reference for doctors to diagnose thyroid disease.

Disease Prediction Using Graph Machine Learning Based on Electronic Health Data: A Review of Approaches and Trends

Graph machine-learning (ML) methods have recently attracted great attention and have made significant progress in graph applications. To date, most graph ML approaches have been evaluated on social networks, but they have not been comprehensively reviewed in the health informatics domain. Herein, a review of graph ML methods and their applications in the disease prediction domain based on electronic health data is presented in this study from two levels: node classification and link prediction. Commonly used graph ML approaches for these two levels are shallow embedding and graph neural networks (GNN). This study performs comprehensive research to identify articles that applied or proposed graph ML models on disease prediction using electronic health data. We considered journals and conferences from four digital library databases (i.e., PubMed, Scopus, ACM digital library, and IEEEXplore). Based on the identified articles, we review the present status of and trends in graph ML approaches for disease prediction using electronic health data. Even though GNN-based models have achieved outstanding results compared with the traditional ML methods in a wide range of disease prediction tasks, they still confront interpretability and dynamic graph challenges. Though the disease prediction field using ML techniques is still emerging, GNN-based models have the potential to be an excellent approach for disease prediction, which can be used in medical diagnosis, treatment, and the prognosis of diseases.

Ultrasound-based deep learning using the VGGNet model for the differentiation of benign and malignant thyroid nodules: A meta-analysis

Objective

The aim of this study was to evaluate the accuracy of deep learning using the convolutional neural network VGGNet model in distinguishing benign and malignant thyroid nodules based on ultrasound images.

Methods

Relevant studies were selected from PubMed, Embase, Cochrane Library, China National Knowledge Infrastructure (CNKI), and Wanfang databases, which used the deep learning-related convolutional neural network VGGNet model to classify benign and malignant thyroid nodules based on ultrasound images. Cytology and pathology were used as gold standards. Furthermore, reported eligibility and risk bias were assessed using the QUADAS-2 tool, and the diagnostic accuracy of deep learning VGGNet was analyzed with pooled sensitivity, pooled specificity, diagnostic odds ratio, and the area under the curve.

Results

A total of 11 studies were included in this meta-analysis. The overall estimates of sensitivity and specificity were 0.87 [95% CI (0.83, 0.91)] and 0.85 [95% CI (0.79, 0.90)], respectively. The diagnostic odds ratio was 38.79 [95% CI (22.49, 66.91)]. The area under the curve was 0.93 [95% CI (0.90, 0.95)]. No obvious publication bias was found.

Conclusion

Deep learning using the convolutional neural network VGGNet model based on ultrasound images performed good diagnostic efficacy in distinguishing benign and malignant thyroid nodules.

Systematic Review Registration

https://www.crd.york.ac.nk/prospero, identifier CRD42022336701.

Tracing and Forecasting Metabolic Indices of Cancer Patients Using Patient-Specific Deep Learning Models

We develop a patient-specific dynamical system model from the time series data of the cancer patient’s metabolic panel taken during the period of cancer treatment and recovery. The model consists of a pair of stacked long short-term memory (LSTM) recurrent neural networks and a fully connected neural network in each unit. It is intended to be used by physicians to trace back and look forward at the patient’s metabolic indices, to identify potential adverse events, and to make short-term predictions. When the model is used in making short-term predictions, the relative error in every index is less than 10% in the L∞ norm and less than 6.3% in the L1 norm in the validation process. Once a master model is built, the patient-specific model can be calibrated through transfer learning. As an example, we obtain patient-specific models for four more cancer patients through transfer learning, which all exhibit reduced training time and a comparable level of accuracy. This study demonstrates that this modeling approach is reliable and can deliver clinically acceptable physiological models for tracking and forecasting patients’ metabolic indices.

The New Entity of Subacute Thyroiditis amid the COVID-19 Pandemic: From Infection to Vaccine

This is a review of full-length articles strictly concerning subacute thyroiditis (SAT) in relation to the SARS-CoV-2 virus infection (SVI) and COVID-19 vaccine (COV) that were published between the 1st of March 2020 and the 21st of March 2022 in PubMed-indexed journals. A total of 161 cases were reported as follows: 81 cases of SAT-SVI (2 retrospective studies, 5 case series, and 29 case reports), 80 respective cases of SAT-COV (1 longitudinal study, 14 case series, 17 case reports; also, 1 prospective study included 12 patients, with 6 patients in each category). To our knowledge, this represents the largest cohort of reported cases until the present time. SAT-SVI was detected in adults aged between 18 and 85 years, mostly in middle-aged females. SAT-COVID-19 timing classifies SAT as viral (synchronous with infection, which is an original feature of SATs that usually follow a viral infection) and post-viral (during the recovery period or after infection, usually within 6 to 8 weeks, up to a maximum 24 weeks). The clinical spectrum has two patterns: either that accompanying a severe COVID-19 infection with multi-organ spreading (most frequent with lung involvement) or as an asymptomatic infection, with SAT being the single manifestation or the first presentation. Either way, SAT may remain unrecognized. Some data suggest that more intense neck pain, more frequent fever, and more frequent hypothyroidism at 3 months are identified when compared with non-SAT-SVI, but other authors have identified similar presentations and outcomes. Post-COVID-19 fatigue may be due to residual post-SAT hypothyroidism. The practical importance of SAT-SVI derives from the fact that thyroid hormone anomalies aggravate the general status of severe infections (particular concerns being tachycardia/arrhythmias, cardiac insufficiency, and ischemic events). If misdiagnosed, SAT results in unnecessary treatment with anti-thyroid drugs or even antibiotics for fever of unknown cause. Once recognized, SAT does not seem to require a particular approach when compared with non-COVID-19 cases, including the need for glucocorticoid therapy and the rate of permanent hypothyroidism. A complete resolution of thyroid hormone anomalies and inflammation is expected, except for cases with persistent hypothyroidism. SAT-COV follows within a few hours to a few weeks, with an average of 2 weeks (no particular pattern is related to the first or second vaccine dose). Pathogenesis includes molecular mimicry and immunoinflammatory anomalies, and some have suggested that this is part of ASIA syndrome (autoimmune/inflammatory syndrome induced by adjuvants). An alternative hypothesis to vaccine-related increased autoimmunity is vaccine-induced hyperviscosity; however, this is supported by incomplete evidence. From what we know so far concerning the risk factors, a prior episode of non-SVI-SAT is not associated with a higher risk of SAT-COV, nor is a previous history of coronavirus infection by itself. Post-vaccine SAT usually has a less severe presentation and a good outcome. Generally, the female sex is prone to developing any type of SAT. HLA susceptibility is probably related to both new types of SATs. The current low level of statistical evidence is expected to change in the future. Practitioners should be aware of SAT-COV, which does not restrict immunization protocols in any case.

Artificial Intelligence-Driven Prediction Modeling and Decision Making in Spine Surgery Using Hybrid Machine Learning Models

Healthcare systems worldwide generate vast amounts of data from many different sources. Although of high complexity for a human being, it is essential to determine the patterns and minor variations in the genomic, radiological, laboratory, or clinical data that reliably differentiate phenotypes or allow high predictive accuracy in health-related tasks. Convolutional neural networks (CNN) are increasingly applied to image data for various tasks. Its use for non-imaging data becomes feasible through different modern machine learning techniques, converting non-imaging data into images before inputting them into the CNN model. Considering also that healthcare providers do not solely use one data modality for their decisions, this approach opens the door for multi-input/mixed data models which use a combination of patient information, such as genomic, radiological, and clinical data, to train a hybrid deep learning model. Thus, this reflects the main characteristic of artificial intelligence: simulating natural human behavior. The present review focuses on key advances in machine and deep learning, allowing for multi-perspective pattern recognition across the entire information set of patients in spine surgery. This is the first review of artificial intelligence focusing on hybrid models for deep learning applications in spine surgery, to the best of our knowledge. This is especially interesting as future tools are unlikely to use solely one data modality. The techniques discussed could become important in establishing a new approach to decision-making in spine surgery based on three fundamental pillars: (1) patient-specific, (2) artificial intelligence-driven, (3) integrating multimodal data. The findings reveal promising research that already took place to develop multi-input mixed-data hybrid decision-supporting models. Their implementation in spine surgery may hence be only a matter of time.

COVID-19 infection: from stress-related cortisol levels to adrenal glands infarction

Cortisol is a key element in acute stress including a severe infection. However, in coronavirus-associated disease, 20% of subjects experience hypocortisolemia due to direct or immune damage of pituitary and adrenal glands. One extreme form of adrenal insufficiency is found in 2∕3 of cases with viral and post-viral adrenal infarction (AI) (with∕without adrenal hemorrhage) that is mostly associated with a severe coronavirus disease 2019 (COVID-19) infection; it requires prompt glucocorticoid intervention. Some reports are incidental findings at computed tomography (CT)∕magnetic resonance imaging (MRI) scans for non-adrenal complications like pulmonary spreading and others are seen on post-mortem analysis. This is a review of PubMed-accessible, English papers focusing on AI in addition to the infection, between March 1, 2020 and November 1, 2021. Exclusion criteria were acute adrenal insufficiency without the histopathological (HP) and∕or imaging report of adrenal enlargement, necrosis, etc., respective adrenal failure due to pituitary causes, or non-COVID-19-related adrenal events. We identified a total of 84 patients (different levels of statistical evidence), as follows: a retrospective study on 51 individuals, two post-mortem studies comprising nine, respectively 12 patients, a case series of five subjects, seven single-case reports. HP aspects include necrosis associated with ischemia, cortical lipid degeneration (+/- focal adrenalitis), and infarcts at the level of adrenal cortex, blood clot into vessels, acute fibrinoid necrosis in arterioles and capsules, as well as subendothelial vacuolization. Collateral potential contributors to adrenal damage are thrombotic events, coagulation anomalies, antiphospholipid syndrome, endothelial dysfunction, severe COVID-19 infection with multiorgan failure, etc. Clinical picture is variable from acute primary adrenal insufficiency to asymptomatic or mild evolution, even a retrospective diagnostic; it may be a part of long COVID-19 syndrome; glucocorticoid therapy for non-adrenal considerations might mask cortisol deficient status due to AI∕hemorrhage. Despite its rarity, the COVID-19-associated AI/hemorrhage represents a challenging new chapter, a condition that is essential to be recognized due to its gravity since prompt intervention with glucocorticoid replacement is lifesaving.

An overview of deep learning applications in precocious puberty and thyroid dysfunction

In the last decade, deep learning methods have garnered a great deal of attention in endocrinology research. In this article, we provide a summary of current deep learning applications in endocrine disorders caused by either precocious onset of adult hormone or abnormal amount of hormone production. To give access to the broader audience, we start with a gentle introduction to deep learning and its most commonly used architectures, and then we focus on the research trends of deep learning applications in thyroid dysfunction classification and precocious puberty diagnosis. We highlight the strengths and weaknesses of various approaches and discuss potential solutions to different challenges. We also go through the practical considerations useful for choosing (and building) the deep learning model, as well as for understanding the thought process behind different decisions made by these models. Finally, we give concluding remarks and future directions.

Deep Learning Based Fast Screening Approach on Ultrasound Images for Thyroid Nodules Diagnosis

Thyroid nodules are widespread in the United States and the rest of the world, with a prevalence ranging from 19 to 68%. The problem with nodules is whether they are malignant or benign. Ultrasonography is currently recommended as the initial modality for evaluating thyroid nodules. However, obtaining a good diagnosis from ultrasound imaging depends entirely on the radiologists levels of experience and other circumstances. There is a tremendous demand for automated and more reliable methods to screen ultrasound images more efficiently. This research proposes an efficient and quick detection deep learning approach for thyroid nodules. An open and publicly available dataset, Thyroid Digital Image Database (TDID), is used to determine the robustness of the suggested method. Each image is formatted into a pyramid tile-based data structure, which the proposed VGG-16 model evaluates to provide segmentation results for nodular detection. The proposed method adopts a top-down approach to hierarchically integrate high- and low-level features to distinguish nodules of varied sizes by employing fuse features effectively. The results demonstrated that the proposed method outperformed the U-Net model, achieving an accuracy of 99%, and was two times faster than the competitive model.

COVID-19 and Artificial Intelligence: An Approach to Forecast the Severity of Diagnosis

(1) Background: The new SARS-COV-2 pandemic overwhelmed intensive care units, clinicians, and radiologists, so the development of methods to forecast the diagnosis' severity became a necessity and a helpful tool. (2) Methods: In this paper, we proposed an artificial intelligence-based multimodal approach to forecast the future diagnosis' severity of patients with laboratory-confirmed cases of SARS-CoV-2 infection. At hospital admission, we collected 46 clinical and biological variables with chest X-ray scans from 475 COVID-19 positively tested patients. An ensemble of machine learning algorithms (AI-Score) was developed to predict the future severity score as mild, moderate, and severe for COVID-19-infected patients. Additionally, a deep learning module (CXR-Score) was developed to automatically classify the chest X-ray images and integrate them into AI-Score. (3) Results: The AI-Score predicted the COVID-19 diagnosis' severity on the testing/control dataset (95 patients) with an average accuracy of 98.59%, average specificity of 98.97%, and average sensitivity of 97.93%. The CXR-Score module graded the severity of chest X-ray images with an average accuracy of 99.08% on the testing/control dataset (95 chest X-ray images). (4) Conclusions: Our study demonstrated that the deep learning methods based on the integration of clinical and biological data with chest X-ray images accurately predicted the COVID-19 severity score of positive-tested patients.

Classification and Diagnosis of Residual Thyroid Tissue in SPECT Images Based on Fine-Tuning Deep Convolutional Neural Network

Patients with thyroid cancer will take a small dose of 131I after undergoing a total thyroidectomy. Single-photon emission computed tomography (SPECT) is used to diagnose whether thyroid tissue remains in the body. However, it is difficult for human eyes to observe the specificity of SPECT images in different categories, and it is difficult for doctors to accurately diagnose the residual thyroid tissue in patients based on SPECT images. At present, the research on the classification of thyroid tissue residues after thyroidectomy is still in a blank state. This paper proposes a ResNet-18 fine-tuning method based on the convolutional neural network model. First, preprocess the SPECT images to improve the image quality and remove background interference. Secondly, use the preprocessed image samples to fine-tune the pretrained ResNet-18 model to obtain better features and finally use the Softmax classifier to diagnose the residual thyroid tissue. The method has been tested on SPECT images of 446 patients collected by local hospital and compared with the widely used lightweight network SqueezeNet model and ShuffleNetV2 model. Due to the small data set, this paper conducted 10 random grouping experiments. Each experiment divided the data set into training set and test set at a ratio of 3:1. The accuracy and sensitivity rates of the model proposed in this paper are 96.69% and 94.75%, which are significantly higher than other models (p < 0.05). The specificity and precision rates are 99.6% and 99.96%, respectively, and there is no significant difference compared with other models. (p > 0.05). The area under the curve of the proposed model, SqueezeNet, and ShuffleNetv2 are 0.988 (95% CI, 0.941-1.000), 0.898 (95% CI, 0.819-0.951) (p = 0.0257), and 0.885 (95% CI, 0.803-0.941) (p = 0.0057) (p < 0.05). We prove that this thyroid tissue residue classification system can be used as a computer-aided diagnosis method to effectively improve the diagnostic accuracy of thyroid tissue residues. While more accurately diagnosing patients with residual thyroid tissue in the body, we try our best to avoid the occurrence of overtreatment, which reflects its potential clinical application value.