Diagnosis of Thyroid Nodules: Performance of a Deep Learning Convolutional Neural Network Model vs. Radiologists

Using multimodal ultrasound including full-time-series contrast-enhanced ultrasound cines for identifying the nature of thyroid nodules

Background

Based on the conventional ultrasound images of thyroid nodules, contrast-enhanced ultrasound (CEUS) videos were analyzed to investigate whether CEUS improves the classification accuracy of benign and malignant thyroid nodules using machine learning (ML) radiomics and compared with radiologists.

Materials and methods

The B-mode ultrasound (B-US), real-time elastography (RTE), color doppler flow images (CDFI) and CEUS cines of patients from two centers were retrospectively gathered. Then, the region of interest (ROI) was delineated to extract the radiomics features. Seven ML algorithms combined with four kinds of radiomics data (B-US, B-US + CDFI + RTE, CEUS, and B-US + CDFI + RTE + CEUS) were applied to establish 28 models. The diagnostic performance of ML models was compared with interpretations from expert and nonexpert readers.

Results

A total of 181 thyroid nodules from 181 patients of 64 men (mean age, 42 years +/- 12) and 117 women (mean age, 46 years +/- 12) were included. Adaptive boosting (AdaBoost) achieved the highest area under the receiver operating characteristic curve (AUC) of 0.89 in the test set among 28 models when combined with B-US + CDFI + RTE + CEUS data and an AUC of 0.72 and 0.66 when combined with B-US and B-US + CDFI + RTE data. The AUC achieved by senior and junior radiologists was 0.78 versus (vs.) 0.69 (p > 0.05), 0.79 vs. 0.64 (p < 0.05), and 0.88 vs. 0.69 (p < 0.05) combined with B-US, B-US+CDFI+RTE and B-US+CDFI+RTE+CEUS, respectively.

Conclusion

With the addition of CEUS, the diagnostic performance was enhanced for all seven classifiers and senior radiologists based on conventional ultrasound images, while no enhancement was observed for junior radiologists. The diagnostic performance of ML models was similar to senior radiologists, but superior to those junior radiologists.

From Bench-to-Bedside: How Artificial Intelligence is Changing Thyroid Nodule Diagnostics, a Systematic Review

CONTEXT

Use of artificial intelligence (AI) to predict clinical outcomes in thyroid nodule diagnostics has grown exponentially over the past decade. The greatest challenge is in understanding the best model to apply to one's own patient population, and how to operationalize such a model in practice.

EVIDENCE ACQUISITION

A literature search of PubMed and IEEE Xplore was conducted for English-language publications between January 1, 2015 and January 1, 2023, studying diagnostic tests on suspected thyroid nodules that used AI. We excluded articles without prospective or external validation, nonprimary literature, duplicates, focused on nonnodular thyroid conditions, not using AI, and those incidentally using AI in support of an experimental diagnostic outside standard clinical practice. Quality was graded by Oxford level of evidence.

EVIDENCE SYNTHESIS

A total of 61 studies were identified; all performed external validation, 16 studies were prospective, and 33 compared a model to physician prediction of ground truth. Statistical validation was reported in 50 papers. A diagnostic pipeline was abstracted, yielding 5 high-level outcomes: (1) nodule localization, (2) ultrasound (US) risk score, (3) molecular status, (4) malignancy, and (5) long-term prognosis. Seven prospective studies validated a single commercial AI; strengths included automating nodule feature assessment from US and assisting the physician in predicting malignancy risk, while weaknesses included automated margin prediction and interobserver variability.

CONCLUSION

Models predominantly used US images to predict malignancy. Of 4 Food and Drug Administration-approved products, only S-Detect was extensively validated. Implementing an AI model locally requires data sanitization and revalidation to ensure appropriate clinical performance.

Artificial intelligence assisted diagnosis of early tc markers and its application

Thyroid cancer (TC) is a common endocrine malignancy with an increasing incidence worldwide. Early diagnosis is particularly important for TC patients, because it allows patients to receive treatment as early as possible. Artificial intelligence (AI) provides great advantages for complex healthcare systems by analyzing big data based on machine learning. Nowadays, AI is widely used in the early diagnosis of cancer such as TC. Ultrasound detection and fine needle aspiration biopsy are the main methods for early diagnosis of TC. AI has been widely used in the detection of malignancy in thyroid nodules by ultrasound images, cytopathology images and molecular markers. It shows great potential in auxiliary medical diagnosis. The latest clinical trial has shown that the performance of AI models matches with the diagnostic efficiency of experienced clinicians, and more efficient AI tools will be developed in the future. Therefore, in this review, we summarized the recent advances in the application of AI algorithms in assessing the risk of malignancy in thyroid nodules. The objective of this review was to provide a data base for the clinical use of AI-assisted diagnosis in TC, as well as to provide new ideas for the next generation of AI-assisted diagnosis in TC.

Deep Learning-Assisted Identification of Femoroacetabular Impingement (FAI) on Routine Pelvic Radiographs

To use a novel deep learning system to localize the hip joints and detect findings of cam-type femoroacetabular impingement (FAI). A retrospective search of hip/pelvis radiographs obtained in patients to evaluate for FAI yielded 3050 total studies. Each hip was classified separately by the original interpreting radiologist in the following manner: 724 hips had severe cam-type FAI morphology, 962 moderate cam-type FAI morphology, 846 mild cam-type FAI morphology, and 518 hips were normal. The anteroposterior (AP) view from each study was anonymized and extracted. After localization of the hip joints by a novel convolutional neural network (CNN) based on the focal loss principle, a second CNN classified the images of the hip as cam positive, or no FAI. Accuracy was 74% for diagnosing normal vs. abnormal cam-type FAI morphology, with aggregate sensitivity and specificity of 0.821 and 0.669, respectively, at the chosen operating point. The aggregate AUC was 0.736. A deep learning system can be applied to detect FAI-related changes on single view pelvic radiographs. Deep learning is useful for quickly identifying and categorizing pathology on imaging, which may aid the interpreting radiologist.

Thyroid Cancer Polygenic Risk Score Improves Classification of Thyroid Nodules as Benign or Malignant

CONTEXT

Thyroid nodule ultrasound-based risk stratification schemas rely on the presence of high-risk sonographic features. However, some malignant thyroid nodules have benign appearance on thyroid ultrasound. New methods for thyroid nodule risk assessment are needed.

OBJECTIVE

We investigated polygenic risk score (PRS) accounting for inherited thyroid cancer risk combined with ultrasound-based analysis for improved thyroid nodule risk assessment.

METHODS

The convolutional neural network classifier was trained on thyroid ultrasound still images and cine clips from 621 thyroid nodules. Phenome-wide association study (PheWAS) and PRS PheWAS were used to optimize PRS for distinguishing benign and malignant nodules. PRS was evaluated in 73 346 participants in the Colorado Center for Personalized Medicine Biobank.

RESULTS

When the deep learning model output was combined with thyroid cancer PRS and genetic ancestry estimates, the area under the receiver operating characteristic curve (AUROC) of the benign vs malignant thyroid nodule classifier increased from 0.83 to 0.89 (DeLong, P value = .007). The combined deep learning and genetic classifier achieved a clinically relevant sensitivity of 0.95, 95% CI [0.88-0.99], specificity of 0.63 [0.55-0.70], and positive and negative predictive values of 0.47 [0.41-0.58] and 0.97 [0.92-0.99], respectively. AUROC improvement was consistent in European ancestry-stratified analysis (0.83 and 0.87 for deep learning and deep learning combined with PRS classifiers, respectively). Elevated PRS was associated with a greater risk of thyroid cancer structural disease recurrence (ordinal logistic regression, P value = .002).

CONCLUSION

Augmenting ultrasound-based risk assessment with PRS improves diagnostic accuracy.

Value of Artificial Intelligence in Improving the Accuracy of Diagnosing TI-RADS Category 4 Nodules

OBJECTIVE

Considerable heterogeneity is observed in the malignancy rates of thyroid nodules classified as category 4 according to the Thyroid Imaging Reporting and Data System (TI-RADS). This study was aimed at comparing the diagnostic performance of artificial intelligence algorithms and radiologists with different experience levels in distinguishing benign and malignant TI-RADS 4 (TR4) nodules.

METHODS

Between January 2019 and September 2022, 1117 TR4 nodules with well-defined pathological findings were collected for this retrospective study. An independent external data set of 125 TR4 nodules was incorporated for testing purposes. Traditional feature-based machine learning (ML) models, deep convolutional neural networks (DCNN) models and a fusion model that integrated the prediction outcomes from all models were used to classify benign and malignant TR4 nodules. A fivefold cross-validation approach was employed, and the diagnostic performance of each model and radiologists was compared.

RESULTS

In the external test data set, the area under the receiver operating characteristic curve (AUROC) of the three DCNN-based secondary transfer learning models-InceptionV3, DenseNet121 and ResNet50-were 0.852, 0.837 and 0.856, respectively. These values were higher than those of the three traditional ML models-logistic regression, multilayer perceptron and random forest-at 0.782, 0.790, and 0.767, respectively, and higher than that of an experienced radiologist (0.815). The fusion diagnostic model we developed, with an AUROC of 0.880, was found to outperform the experienced radiologist in diagnosing TR4 nodules.

CONCLUSION

The integration of artificial intelligence algorithms into medical imaging studies could improve the accuracy of identifying high-risk TR4 nodules pre-operatively and have significant clinical application potential.

Artificial intelligence in the diagnosis of thyroid cancer: Recent advances and future directions

The diagnosis and management of thyroid cancer is fraught with challenges despite the advent of innovative diagnostic, surgical, and chemotherapeutic modalities. Challenges like inaccuracy in prognostication, uncertainty in cytopathological diagnosis, trouble in differentiating follicular neoplasms, intra-observer and inter-observer variability on ultrasound imaging preclude personalised treatment in thyroid cancer. Artificial intelligence (AI) is bringing a paradigm shift to the healthcare, powered by quick advancement of the analytic techniques. Several recent studies have shown remarkable progress in thyroid cancer diagnostics based on AI-assisted algorithms. Application of AI techniques in thyroid ultrasonography and cytopathology have shown remarkable impro-vement in sensitivity and specificity over the traditional diagnostic modalities. AI has also been explored in the development of treatment algorithms for indeterminate nodules and for prognostication in the patients with thyroid cancer. The benefits of high repeatability and straightforward implementation of AI in the management of thyroid cancer suggest that it holds promise for clinical application. Limited clinical experience and lack of prospective validation studies remain the biggest drawbacks. Developing verified and trustworthy algorithms after extensive testing and validation using prospective, multi-centre trials is crucial for the future use of AI in the pipeline of precision medicine in the management of thyroid cancer.

Artificial Intelligence in Thyroidology: A Narrative Review of the Current Applications, Associated Challenges, and Future Directions

Background: The use of artificial intelligence (AI) in health care has grown exponentially with the promise of facilitating biomedical research and enhancing diagnosis, treatment, monitoring, disease prevention, and health care delivery. We aim to examine the current state, limitations, and future directions of AI in thyroidology. Summary: AI has been explored in thyroidology since the 1990s, and currently, there is an increasing interest in applying AI to improve the care of patients with thyroid nodules (TNODs), thyroid cancer, and functional or autoimmune thyroid disease. These applications aim to automate processes, improve the accuracy and consistency of diagnosis, personalize treatment, decrease the burden for health care professionals, improve access to specialized care in areas lacking expertise, deepen the understanding of subtle pathophysiologic patterns, and accelerate the learning curve of less experienced clinicians. There are promising results for many of these applications. Yet, most are in the validation or early clinical evaluation stages. Only a few are currently adopted for risk stratification of TNODs by ultrasound and determination of the malignant nature of indeterminate TNODs by molecular testing. Challenges of the currently available AI applications include the lack of prospective and multicenter validations and utility studies, small and low diversity of training data sets, differences in data sources, lack of explainability, unclear clinical impact, inadequate stakeholder engagement, and inability to use outside of the research setting, which might limit the value of their future adoption. Conclusions: AI has the potential to improve many aspects of thyroidology; however, addressing the limitations affecting the suitability of AI interventions in thyroidology is a prerequisite to ensure that AI provides added value for patients with thyroid disease.

Value of TI-RADS and elastography strain ratio in predicting malignant thyroid nodules: experience from a single center in Egypt

Introduction

Thyroid nodules are highly prevalent in the general population; therefore, it is crucial to discriminate benign from malignant nodules. A practical thyroid imaging reporting and data system (TI-RADS) for thyroid nodules and ultrasound elastography are valuable tools not only for characterization of nodules but also for the selection of tumors for fine-needle aspiration cytology (FNAC).

Objective

This study aimed to evaluate the diagnostic accuracy of US evaluation in the prediction of malignant thyroid nodules and evaluate the role of the elastography score, strain ratio (SR), and the TI-RADS scoring system as non-invasive tools in differentiation between malignant and benign thyroid nodules.

Material and methods

A total of 1269 patients were evaluated between February 2017 and April 2020 by a single expert thyroid ultrasound operator. The final diagnosis was achieved from cytological and/or histological evaluation and follow-up for at least 1 year.

Results

There were 1088 females and 181 males with a mean age of 44 ± 10 SD. The final diagnosis was 1197 benign nodules and 72 malignant nodules. Most malignant nodules were scored elastography score 4 (83.3%) and TI-RADS category 5 (86.11%). We found that nodules with antero-posterior to transverse (A-P/T) diameter > 1, have 21 times more risk to be malignant than those with A-P/T diameter < 1, patients with solitary thyroid nodules have 4.5 times to develop malignancy compared to those with multinodular goiter (MNG), nodules with absent halo have 4 times more risk of malignancy. Furthermore, microcalcifications in thyroid nodules increase the risk of malignancy 9 times compared to those without calcifications. SR was found to be an excellent discriminator to differentiate between benign and malignant nodules with P < 0.001. Also, we found that for every unit increase in SR, the risk of malignancy increased by 20%. We reported that the accuracy of ultrasonography in the detection of malignant thyroid nodules had a sensitivity of 89%, specificity of 98%, 70% PPV, and 99.3% NPV, with an overall accuracy of 97.2%.

Conclusion

The application of ultrasonographic non-invasive criteria for thyroid nodules in clinical practice might significantly reduce the number of unnecessary FNAC. Elastography, SR, and TI-RADS classification could be good predictors for malignant thyroid nodules.

Diagnosis of thyroid micronodules on ultrasound using a deep convolutional neural network

To assess the performance of deep convolutional neural network (CNN) to discriminate malignant and benign thyroid nodules < 10 mm in size and compare the diagnostic performance of CNN with those of radiologists. Computer-aided diagnosis was implemented with CNN and trained using ultrasound (US) images of 13,560 nodules ≥ 10 mm in size. Between March 2016 and February 2018, US images of nodules < 10 mm were retrospectively collected at the same institution. All nodules were confirmed as malignant or benign from aspirate cytology or surgical histology. Diagnostic performances of CNN and radiologists were assessed and compared for area under curve (AUC), sensitivity, specificity, accuracy, positive predictive value, and negative predictive value. Subgroup analyses were performed based on nodule size with a cut-off value of 5 mm. Categorization performances of CNN and radiologists were also compared. A total of 370 nodules from 362 consecutive patients were assessed. CNN showed higher negative predictive value (35.3% vs. 22.6%, P = 0.048) and AUC (0.66 vs. 0.57, P = 0.04) than radiologists. CNN also showed better categorization performance than radiologists. In the subgroup of nodules ≤ 5 mm, CNN showed higher AUC (0.63 vs. 0.51, P = 0.08) and specificity (68.2% vs. 9.1%, P < 0.001) than radiologists. Convolutional neural network trained with thyroid nodules ≥ 10 mm in size showed overall better diagnostic performance than radiologists in the diagnosis and categorization of thyroid nodules < 10 mm, especially in nodules ≤ 5 mm.

Differentiation of Benign and Malignant Thyroid Nodules with ANFIS by Using Genetic Algorithm and Proposing a Novel CAD-Based Risk Stratification System of Thyroid Nodules

The thyroid nodule risk stratification guidelines used in the literature are based on certain well-known sonographic features of nodules and are still subjective since the application of these characteristics strictly depends on the reading physician. These guidelines classify nodules according to the sub-features of limited sonographic signs. This study aims to overcome these limitations by examining the relationships of a wide range of ultrasound (US) signs in the differential diagnosis of nodules by using artificial intelligence methods. An innovative method based on training Adaptive-Network Based Fuzzy Inference Systems (ANFIS) by using Genetic Algorithm (GA) is used to differentiate malignant from benign thyroid nodules. The comparison of the results from the proposed method to the results from the commonly used derivative-based algorithms and Deep Neural Network (DNN) methods yielded that the proposed method is more successful in differentiating malignant from benign thyroid nodules. Furthermore, a novel computer aided diagnosis (CAD) based risk stratification system for the thyroid nodule's US classification that is not present in the literature is proposed.

Artificial Intelligence for Pre-operative Diagnosis of Malignant Thyroid Nodules Based on Sonographic Features and Cytology Category

BACKGROUND

Current diagnosis and classification of thyroid nodules are susceptible to subjective factors. Despite widespread use of ultrasonography (USG) and fine needle aspiration cytology (FNAC) to assess thyroid nodules, the interpretation of results is nuanced and requires specialist endocrine surgery input. Using readily available pre-operative data, the aims of this study were to develop artificial intelligence (AI) models to classify nodules into likely benign or malignant and to compare the diagnostic performance of the models.

METHODS

Patients undergoing surgery for thyroid nodules between 2010 and 2020 were recruited from our institution's database into training and testing groups. Demographics, serum TSH level, cytology, ultrasonography features and histopathology data were extracted. The training group USG images were re-reviewed by a study radiologist experienced in thyroid USG, who reported the relevant features and supplemented with data extracted from existing reports to reduce sampling bias. Testing group USG features were extracted solely from existing reports to reflect real-life practice of a non-thyroid specialist. We developed four AI models based on classification algorithms (k-Nearest Neighbour, Support Vector Machine, Decision Tree, Naïve Bayes) and evaluated their diagnostic performance of thyroid malignancy.

RESULTS

In the training group (n = 857), 75% were female and 27% of cases were malignant. The testing group (n = 198) consisted of 77% females and 17% malignant cases. Mean age was 54.7 ± 16.2 years for the training group and 50.1 ± 17.4 years for the testing group. Following validation with the testing group, support vector machine classifier was found to perform best in predicting final histopathology with an accuracy of 89%, sensitivity 89%, specificity 83%, F-score 94% and AUROC 0.86.

CONCLUSION

We have developed a first of its kind, pilot AI model that can accurately predict malignancy in thyroid nodules using USG features, FNAC, demographics and serum TSH. There is potential for a model like this to be used as a decision support tool in under-resourced areas as well as by non-thyroid specialists.

Diagnostic performance of artificial intelligence-based computer-aided diagnosis system in longitudinal and transverse ultrasonic views for differentiating thyroid nodules

OBJECTIVE

To evaluate the diagnostic performance of different ultrasound sections of thyroid nodule (TN) using computer-aided diagnosis system based on artificial intelligence (AI-CADS) in predicting thyroid malignancy.

MATERIALS AND METHODS

This is a retrospective study. From January 2019 to July 2019, patients with preoperative thyroid ultrasound data and postoperative pathological results were enrolled, which were divided into two groups: lower risk group (ACR TI-RADS 1, 2 and 3) and higher risk group (ACR TI-RADS 4 and 5). The malignant risk scores (MRS) of TNs were obtained from longitudinal and transverse sections using AI-CADS. The diagnostic performance of AI-CADS and the consistency of each US characteristic were evaluated between these sections. The receiver operating characteristic (ROC) curve and the Cohen κ-statistic were performed.

RESULTS

A total of 203 patients (45.61 ± 11.59 years, 163 female) with 221 TNs were enrolled. The area under the ROC curve (AUC) of criterion 3 [0.86 (95%CI: 0.80~0.91)] was lower than criterion 1 [0.94 (95%CI: 0.90~ 0.99)], 2 [0.93 (95%CI: 0.89~0.97)] and 4 [0.94 (95%CI: 0.90, 0.99)] significantly (P<0.001, P=0.01, P<0.001, respectively). In the higher risk group, the MRS of transverse section was higher than longitudinal section (P<0.001), and the agreement of extrathyroidal extension and shape was moderate and fair (κ =0.48, 0.31 respectively). The diagnostic agreement of other ultrasonic features was substantial or almost perfect (κ >0.60).

CONCLUSION

The diagnostic performance of computer-aided diagnosis system based on artificial intelligence (AI-CADS) in longitudinal and transverse ultrasonic views for differentiating thyroid nodules (TN) was different, which was higher in the transverse section. It was more dependent on the section for the AI-CADS diagnosis of suspected malignant TNs.

Advancements in Thyroidectomy: A Mini Review

Demand for minimally invasive surgery has driven the development of new gadgets and surgical techniques. Yet, questions about safety and skeptical views on new technology have prevented proliferation of new modes of surgery. This skepticism is perhaps due to unfamiliarity of new fields. Likewise, there are currently various remote-access techniques available for thyroid surgeons that only few regions in the world have adapted. This review will explore the history of minimally invasive techniques in thyroid surgery and introduce new technology to be implemented.

Development of a Machine Learning-Based Screening Method for Thyroid Nodules Classification by Solving the Imbalance Challenge in Thyroid Nodules Data

BACKGROUND

This study aims to show the impact of imbalanced data and the typical evaluation methods in developing and misleading assessments of machine learning-based models for preoperative thyroid nodules screening.

STUDY DESIGN

A retrospective study.

METHODS

The ultrasonography features for 431 thyroid nodules cases were extracted from medical records of 313 patients in Babol, Iran. Since thyroid nodules are commonly benign, the relevant data are usually unbalanced in classes. It can lead to the bias of learning models toward the majority class. To solve it, a hybrid resampling method called the Smote-was used to creating balance data. Following that, the support vector classification (SVC) algorithm was trained by balance and unbalanced datasets as Models 2 and 3, respectively, in Python language programming. Their performance was then compared with the logistic regression model as Model 1 that fitted traditionally.

RESULTS

The prevalence of malignant nodules was obtained at 14% (n = 61). In addition, 87% of the patients in this study were women. However, there was no difference in the prevalence of malignancy for gender. Furthermore, the accuracy, area under the curve, and geometric mean values were estimated at 92.1%, 93.2%, and 76.8% for Model 1, 91.3%, 93%, and 77.6% for Model 2, and finally, 91%, 92.6% and 84.2% for Model 3, respectively. Similarly, the results identified Micro calcification, Taller than wide shape, as well as lack of ISO and hyperechogenicity features as the most effective malignant variables.

CONCLUSION

Paying attention to data challenges, such as data imbalances, and using proper criteria measures can improve the performance of machine learning models for preoperative thyroid nodules screening.

Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning

A thyroid nodule, which is defined as abnormal growth of thyroid cells, indicates excessive iodine intake, thyroid degeneration, inflammation, and other diseases. Although thyroid nodules are always non-malignant, the malignancy likelihood of a thyroid nodule grows steadily every year. In order to reduce the burden on doctors and avoid unnecessary fine needle aspiration (FNA) and surgical resection, various studies have been done to diagnose thyroid nodules through deep-learning-based image recognition analysis. In this study, to predict the benign and malignant thyroid nodules accurately, a novel deep learning framework is proposed. Five hundred eight ultrasound images were collected from the Third Hospital of Hebei Medical University in China for model training and validation. First, a ResNet18 model, pretrained on ImageNet, was trained by an ultrasound image dataset, and a random sampling of training dataset was applied 10 times to avoid accidental errors. The results show that our model has a good performance, the average area under curve (AUC) of 10 times is 0.997, the average accuracy is 0.984, the average recall is 0.978, the average precision is 0.939, and the average F1 score is 0.957. Second, Gradient-weighted Class Activation Mapping (Grad-CAM) was proposed to highlight sensitive regions in an ultrasound image during the learning process. Grad-CAM is able to extract the sensitive regions and analyze their shape features. Based on the results, there are obvious differences between benign and malignant thyroid nodules; therefore, shape features of the sensitive regions are helpful in diagnosis to a great extent. Overall, the proposed model demonstrated the feasibility of employing deep learning and ultrasound images to estimate benign and malignant thyroid nodules.

A comparison of artificial intelligence versus radiologists in the diagnosis of thyroid nodules using ultrasonography: a systematic review and meta-analysis

BACKGROUND

Thyroid nodules are common. Ultrasonography (US) is the first investigation for thyroid nodules. Artificial Intelligence (AI) is widely integrated into medical diagnosis to provide additional information. The primary objective of this study was to accumulate the pooled sensitivity and specificity between all available AI and radiologists using thyroid US imaging. The secondary objective was to compare AI's diagnostic performance to that of radiologists.

MATERIALS AND METHODS

A systematic review meta-analysis. PubMed, Scopus, Web of Science, and Cochrane Library data were searched for studies from inception until June 11, 2020.

RESULTS

Twenty five studies were included in this meta-analysis. The pooled sensitivity and specificity of AI were 0.86 (95% CI 0.81-0.91) and 0.78 (95% CI 0.73-0.83), respectively. The pooled sensitivity and specificity of radiologists were 0.85 (95% CI 0.80-0.89) and 0.82 (95% CI 0.77-0.86), respectively. The accuracy of AI and radiologists is equivalent in terms of AUC [AI 0.89 (95% CI 0.86-0.92), radiologist 0.91 (95% CI 0.88-0.93)]. The diagnostic odd ratio (DOR) between AI 23.10 (95% CI 14.20-37.58) and radiologists 27.12 (95% CI 17.45-42.16) had no statistically significant difference (P = 0.56). Meta-regression analysis revealed that Deep Learning AI had significantly greater sensitivity and specificity than classic machine learning AI (P < 0.001).

CONCLUSION

AI demonstrated comparable performance to radiologists in diagnosing benign and malignant thyroid nodules using ultrasonography. Additional research to establish its equivalency should be conducted.

Toward Reduction in False-Positive Thyroid Nodule Biopsies with a Deep Learning-based Risk Stratification System Using US Cine-Clip Images

PURPOSE

To develop a deep learning-based risk stratification system for thyroid nodules using US cine images.

MATERIALS AND METHODS

In this retrospective study, 192 biopsy-confirmed thyroid nodules (175 benign, 17 malignant) in 167 unique patients (mean age, 56 years ± 16 [SD], 137 women) undergoing cine US between April 2017 and May 2018 with American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS)-structured radiology reports were evaluated. A deep learning-based system that exploits the cine images obtained during three-dimensional volumetric thyroid scans and outputs malignancy risk was developed and compared, using fivefold cross-validation, against a two-dimensional (2D) deep learning-based model (Static-2DCNN), a radiomics-based model using cine images (Cine-Radiomics), and the ACR TI-RADS level, with histopathologic diagnosis as ground truth. The system was used to revise the ACR TI-RADS recommendation, and its diagnostic performance was compared against the original ACR TI-RADS.

RESULTS

The system achieved higher average area under the receiver operating characteristic curve (AUC, 0.88) than Static-2DCNN (0.72, P = .03) and tended toward higher average AUC than Cine-Radiomics (0.78, P = .16) and ACR TI-RADS level (0.80, P = .21). The system downgraded recommendations for 92 benign and two malignant nodules and upgraded none. The revised recommendation achieved higher specificity (139 of 175, 79.4%) than the original ACR TI-RADS (47 of 175, 26.9%; P < .001), with no difference in sensitivity (12 of 17, 71% and 14 of 17, 82%, respectively; P = .63).

CONCLUSION

The risk stratification system using US cine images had higher diagnostic performance than prior models and improved specificity of ACR TI-RADS when used to revise ACR TI-RADS recommendation.Keywords: Neural Networks, US, Abdomen/GI, Head/Neck, Thyroid, Computer Applications-3D, Oncology, Diagnosis, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2022.

Personalized Diagnosis in Differentiated Thyroid Cancers by Molecular and Functional Imaging Biomarkers: Present and Future

Personalized diagnosis can save unnecessary thyroid surgeries, in cases of indeterminate thyroid nodules, when clinicians tend to aggressively treat all these patients. Personalized diagnosis benefits from a combination of imagery and molecular biomarkers, as well as artificial intelligence algorithms, which are used more and more in our timeline. Functional imaging diagnosis such as SPECT, PET, or fused images (SPECT/CT, PET/CT, PET/MRI), is exploited at maximum in thyroid nodules, with a long history in the past and a bright future with many suitable radiotracers that could properly contribute to diagnosing malignancy in thyroid nodules. In this way, patients will be spared surgery complications, and apparently more expensive diagnostic workouts will financially compensate each patient and also the healthcare system. In this review we will summarize essential available diagnostic tools for malignant and benignant thyroid nodules, beginning with functional imaging, molecular analysis, and combinations of these two and other future strategies, including AI or NIS targeted gene therapy for thyroid carcinoma diagnosis and treatment as well.

Artificial Intelligence (AI) Tools for Thyroid Nodules on Ultrasound, From the AJR Special Series on AI Applications

Artificial intelligence (AI) methods for evaluating thyroid nodules on ultrasound have been widely described in the literature, with reported performance of AI tools matching or in some instances surpassing radiologists. As these data have accumulated, products for classification and risk stratification of thyroid nodules on ultrasound have become commercially available. This article reviews FDA-approved products currently on the market, with a focus on product features, reported performance, and considerations for implementation. The products perform risk stratification primarily using the Thyroid Imaging Reporting and Data System (TI-RADS), though may provide additional prediction tools independent of TI-RADS. Key issues in implementation include integration with radiologist interpretation, impact on workflow and efficiency, and performance monitoring. AI applications beyond nodule classification, including report construction and incidental findings follow-up, are also described. Anticipated future directions of research and development in AI tools for thyroid nodules are highlighted.

Radiomic Detection of Malignancy within Thyroid Nodules Using Ultrasonography-A Systematic Review and Meta-Analysis

Background: Despite investigation, 95% of thyroid nodules are ultimately benign. Radiomics is a field that uses radiological features to inform individualized patient care. We aimed to evaluate the diagnostic utility of radiomics in classifying undetermined thyroid nodules into benign and malignant using ultrasonography (US). Methods: A diagnostic test accuracy systematic review and meta-analysis was performed in accordance with PRISMA guidelines. Sensitivity, specificity, and area under curve (AUC) delineating benign and malignant lesions were recorded. Results: Seventy-five studies including 26,373 patients and 46,175 thyroid nodules met inclusion criteria. Males accounted for 24.6% of patients, while 75.4% of patients were female. Radiomics provided a pooled sensitivity of 0.87 (95% CI: 0.86−0.87) and a pooled specificity of 0.84 (95% CI: 0.84−0.85) for characterizing benign and malignant lesions. Using convolutional neural network (CNN) methods, pooled sensitivity was 0.85 (95% CI: 0.84−0.86) and pooled specificity was 0.82 (95% CI: 0.82−0.83); significantly lower than studies using non-CNN: sensitivity 0.90 (95% CI: 0.89−0.90) and specificity 0.88 (95% CI: 0.87−0.89) (p < 0.05). The diagnostic ability of radiologists and radiomics were comparable for both sensitivity (OR 0.98) and specificity (OR 0.95). Conclusions: Radiomic analysis using US provides a reproducible, reliable evaluation of undetermined thyroid nodules when compared to current best practice.

Ultrasonographic morphological characteristics determined using a deep learning-based computer-aided diagnostic system of breast cancer

To investigate the correlations between ultrasonographic morphological characteristics quantitatively assessed using a deep learning-based computer-aided diagnostic system (DL-CAD) and histopathologic features of breast cancer.This retrospective study included 282 women with invasive breast cancer (<5 cm; mean age, 54.4 [range, 29-85] years) who underwent surgery between February 2016 and April 2017. The morphological characteristics of breast cancer on B-mode ultrasonography were analyzed using DL-CAD, and quantitative scores (0-1) were obtained. Associations between quantitative scores and tumor histologic type, grade, size, subtype, and lymph node status were compared.Two-hundred and thirty-six (83.7%) tumors were invasive ductal carcinoma, 18 (6.4%) invasive lobular carcinoma, and 28 (9.9%) micropapillary, apocrine, and mucinous. The mean size was 1.8 ± 1.0 (standard deviation) cm, and 108 (38.3%) cases were node positive. Irregular shape score was associated with tumor size (P < .001), lymph nodes status (P = .001), and estrogen receptor status (P = .016). Not-circumscribed margin (P < .001) and hypoechogenicity (P = .003) scores correlated with tumor size, and non-parallel orientation score correlated with histologic grade (P = .024). Luminal A tumors exhibited more irregular features (P = .048) with no parallel orientation (P = .002), whereas triple-negative breast cancer showed a rounder/more oval and parallel orientation.Quantitative morphological characteristics of breast cancers determined using DL-CAD correlated with histopathologic features and could provide useful information about breast cancer phenotypes.

Accuracy of Ultrasound Diagnosis of Thyroid Nodules Based on Artificial Intelligence-Assisted Diagnostic Technology: A Systematic Review and Meta-Analysis

BACKGROUND

Ultrasonography (US) is the most common method of identifying thyroid nodules, but US images require an experienced surgeon for identification. Many artificial intelligence (AI) techniques such as computer-aided diagnostic systems (CAD), deep learning (DL), and machine learning (ML) have been used to assist in the diagnosis of thyroid nodules, but whether AI techniques can improve the diagnostic accuracy of thyroid nodules still needs to be explored.

OBJECTIVE

To clarify the accuracy of AI-based thyroid nodule US images for differentiating benign and malignant thyroid nodules.

METHODS

A search strategy of "subject terms + key words" was used to search PubMed, Cochrane Library, Embase, Web of Science, China Biology Medicine (CBM), and China National Knowledge Infrastructure (CNKI) for studies on AI-assisted diagnosis of thyroid nodules based on US images. The summarized receiver operating characteristic (SROC) curve and the pooled sensitivity and specificity were used to assess the performance of the diagnostic tests. The quality assessment of diagnostics accuracy studies-2 (QUADAS-2) tool was used to assess the methodological quality of the included studies. The Review Manager 5.3 and Stata 15 were used to process the data. Subgroup analysis was based on the integrity of data collection.

RESULTS

A total of 25 studies with 17,429 US images of thyroid nodules were included. AI-assisted diagnostic techniques had better diagnostic efficacy in the diagnosis of benign and malignant thyroid nodules: sensitivity 0.88 (95% CI: (0.85-0.90)), specificity 0.81 (95% CI: 0.74-0.86), diagnostic odds ratio (DOR) 30 (95% CI: 19-46). The SROC curve indicated that the area under the curve (AUC) was 0.92 (95% CI: 0.89-0.94). Threshold effect analysis showed a Spearman correlation coefficient: 0.17 < 0.5, suggesting no threshold effect for the included studies. After a meta-regression analysis of 4 different subgroups, the results showed a statistically significant effect of mean age ≥50 years on heterogeneity. Compared with studies with an average age of ≥50 years, AI-assisted diagnostic techniques had higher diagnostic performance in studies with an average age of <50 years (0.89 (95% CI: 0.87-0.92) vs. 0.80 (95% CI: 0.73-0.88)), (0.83 (95% CI: 0.77-0.88) vs. 0.73 (95% CI: 0.60-0.87)).

CONCLUSIONS

AI-assisted diagnostic techniques had good diagnostic efficacy for thyroid nodules. For the diagnosis of <50 year olds, AI-assisted diagnostic technology was more effective in diagnosis.

Classification of malignant tumors by a non-sequential recurrent ensemble of deep neural network model

Many significant efforts have so far been made to classify malignant tumors by using various machine learning methods. Most of the studies have considered a particular tumor genre categorized according to its originating organ. This has enriched the domain-specific knowledge of malignant tumor prediction, we are devoid of an efficient model that may predict the stages of tumors irrespective of their origin. Thus, there is ample opportunity to study if a heterogeneous collection of tumor images can be classified according to their respective stages. The present research work has prepared a heterogeneous tumor dataset comprising eight different datasets from The Cancer Imaging Archives and classified them according to their respective stages, as suggested by the American Joint Committee on Cancer. The proposed model has been used for classifying 717 subjects comprising different imaging modalities and varied Tumor-Node-Metastasis stages. A new non-sequential deep hybrid model ensemble has been developed by exploiting branched and re-injected layers, followed by bidirectional recurrent layers to classify tumor images. Results have been compared with standard sequential deep learning models and notable recent studies. The training and validation accuracy along with the ROC-AUC scores have been found satisfactory over the existing models. No model or method in the literature could ever classify such a diversified mix of tumor images with such high accuracy. The proposed model may help radiologists by acting as an auxiliary decision support system and speed up the tumor diagnosis process.

Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer

Differentiated thyroid cancer (DTC) from follicular epithelial cells is the most common form of thyroid cancer. Beyond the common papillary thyroid carcinoma (PTC), there are a number of rare but difficult-to-diagnose pathological classifications, such as follicular thyroid carcinoma (FTC). We employed deep convolutional neural networks (CNNs) to facilitate the clinical diagnosis of differentiated thyroid cancers. An image dataset with thyroid ultrasound images of 421 DTCs and 391 benign patients was collected. Three CNNs (InceptionV3, ResNet101, and VGG19) were retrained and tested after undergoing transfer learning to classify malignant and benign thyroid tumors. The enrolled cases were classified as PTC, FTC, follicular variant of PTC (FVPTC), Hürthle cell carcinoma (HCC), or benign. The accuracy of the CNNs was as follows: InceptionV3 (76.5%), ResNet101 (77.6%), and VGG19 (76.1%). The sensitivity was as follows: InceptionV3 (83.7%), ResNet101 (72.5%), and VGG19 (66.2%). The specificity was as follows: InceptionV3 (83.7%), ResNet101 (81.4%), and VGG19 (76.9%). The area under the curve was as follows: Incep-tionV3 (0.82), ResNet101 (0.83), and VGG19 (0.83). A comparison between performance of physicians and CNNs was assessed and showed significantly better outcomes in the latter. Our results demonstrate that retrained deep CNNs can enhance diagnostic accuracy in most DTCs, including follicular cancers.

Diagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network

To compare the diagnostic performances of physicians and a deep convolutional neural network (CNN) predicting malignancy with ultrasonography images of thyroid nodules with atypia of undetermined significance (AUS)/follicular lesion of undetermined significance (FLUS) results on fine-needle aspiration (FNA). This study included 202 patients with 202 nodules ≥ 1 cm AUS/FLUS on FNA, and underwent surgery in one of 3 different institutions. Diagnostic performances were compared between 8 physicians (4 radiologists, 4 endocrinologists) with varying experience levels and CNN, and AUS/FLUS subgroups were analyzed. Interobserver variability was assessed among the 8 physicians. Of the 202 nodules, 158 were AUS, and 44 were FLUS; 86 were benign, and 116 were malignant. The area under the curves (AUCs) of the 8 physicians and CNN were 0.680–0.722 and 0.666, without significant differences (P > 0.05). In the subgroup analysis, the AUCs for the 8 physicians and CNN were 0.657–0.768 and 0.652 for AUS, 0.469–0.674 and 0.622 for FLUS. Interobserver agreements were moderate (k = 0.543), substantial (k = 0.652), and moderate (k = 0.455) among the 8 physicians, 4 radiologists, and 4 endocrinologists. For thyroid nodules with AUS/FLUS cytology, the diagnostic performance of CNN to differentiate malignancy with US images was comparable to that of physicians with variable experience levels.

Artificial Intelligence in Thyroid Field-A Comprehensive Review

Simple Summary

The incidence of thyroid pathologies has been increasing worldwide. Historically, the detection of thyroid neoplasms relies on medical imaging analysis, depending mainly on the experience of clinicians. The advent of artificial intelligence (AI) techniques led to a remarkable progress in image-recognition tasks. AI represents a powerful tool that may facilitate understanding of thyroid pathologies, but actually, the diagnostic accuracy is uncertain. This article aims to provide an overview of the basic aspects, limitations and open issues of the AI methods applied to thyroid images. Medical experts should be familiar with the workflow of AI techniques in order to avoid misleading outcomes.

Abstract

Artificial intelligence (AI) uses mathematical algorithms to perform tasks that require human cognitive abilities. AI-based methodologies, e.g., machine learning and deep learning, as well as the recently developed research field of radiomics have noticeable potential to transform medical diagnostics. AI-based techniques applied to medical imaging allow to detect biological abnormalities, to diagnostic neoplasms or to predict the response to treatment. Nonetheless, the diagnostic accuracy of these methods is still a matter of debate. In this article, we first illustrate the key concepts and workflow characteristics of machine learning, deep learning and radiomics. We outline considerations regarding data input requirements, differences among these methodologies and their limitations. Subsequently, a concise overview is presented regarding the application of AI methods to the evaluation of thyroid images. We developed a critical discussion concerning limits and open challenges that should be addressed before the translation of AI techniques to the broad clinical use. Clarification of the pitfalls of AI-based techniques results crucial in order to ensure the optimal application for each patient.

Matrix 3D ultrasound-assisted thyroid nodule volume estimation and radiofrequency ablation: a phantom study

Background

Two-dimensional (2D) ultrasound is well established for thyroid nodule assessment and treatment guidance. However, it is hampered by a limited field of view and observer variability that may lead to inaccurate nodule classification and treatment. To cope with these limitations, we investigated the use of real-time three-dimensional (3D) ultrasound to improve the accuracy of volume estimation and needle placement during radiofrequency ablation. We assess a new 3D matrix transducer for nodule volume estimation and image-guided radiofrequency ablation.

Methods

Thirty thyroid nodule phantoms with thermochromic dye underwent volume estimation and ablation guided by a 2D linear and 3D mechanically-swept array and a 3D matrix transducer.

Results

The 3D matrix nodule volume estimations had a lower median difference with the ground truth (0.4 mL) compared to the standard 2D approach (2.2 mL, p < 0.001) and mechanically swept 3D transducer (2.0 mL, p = 0.016). The 3D matrix-guided ablation resulted in a similar nodule ablation coverage when compared to 2D-guidance (76.7% versus 80.8%, p = 0.542). The 3D mechanically swept transducer performed worse (60.1%, p = 0.015). However, 3D matrix and 2D guidance ablations lead to a larger ablated volume outside the nodule than 3D mechanically swept (5.1 mL, 4.2 mL (p = 0.274), 0.5 mL (p < 0.001), respectively). The 3D matrix and mechanically swept approaches were faster with 80 and 72.5 s/mL ablated than 2D with 105.5 s/mL ablated.

Conclusions

The 3D matrix transducer estimates volumes more accurately and can facilitate accurate needle placement while reducing procedure time.

Prediction of thyroid nodule histopathology by expert ultrasound evaluation

OBJECTIVE

The basis of thyroid nodule diagnostics is ultrasound-guided fine needle biopsy with cytological evaluation (FNC) if ultrasound appearance is not clearly benign. The aim of this study was to investigate the predictive potential of dedicated, expert high-resolution ultrasound, to see if histopathological entities of thyroid nodules can be diagnosed without invasive FNC biopsies.

DESIGN

Prospective case-cohort study.

METHODS

187 patients with 221 thyroid nodules were examined with ultrasound and prospectively assigned to the expected histopathological diagnosis: colloid nodule, adenomatoid colloid nodule, follicular adenoma, follicular carcinoma, follicular variant of papillary thyroid carcinoma, papillary thyroid carcinoma, or other thyroid cancer. In 101 of these, we later obtained histopathological reports for comparison.

RESULTS

Overall accuracy for classification into discrete histopathological categories by expert ultrasound was 71.3% and Cohen's Kappa was 0.62. The sensitivity and specificity for detecting malignancy were 97.3% and 78.1%. The diagnostic accuracy for malignancy was 85.1%. ACR-TIRADS scores for the same nodules had a sensitivity of 97.3%, specificity of 26.6%, and accuracy of 52.5%.

CONCLUSION

Dedicated expert high-resolution ultrasound without FNC can reliably distinguish benign vs malignant nodules, but also differentiate between several histopathological entities in thyroid nodules. There is potential for a reduction in the number of invasive FNC biopsies and diagnostic operations.

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

Background and Objectives: At present, thyroid disorders have a great incidence in the worldwide population, so the development of alternative methods for improving the diagnosis process is necessary. Materials and Methods: For this purpose, we developed an ensemble method that fused two deep learning models, one based on convolutional neural network and the other based on transfer learning. For the first model, called 5-CNN, we developed an efficient end-to-end trained model with five convolutional layers, while for the second model, the pre-trained VGG-19 architecture was repurposed, optimized and trained. We trained and validated our models using a dataset of ultrasound images consisting of four types of thyroidal images: autoimmune, nodular, micro-nodular, and normal. Results: Excellent results were obtained by the ensemble CNN-VGG method, which outperformed the 5-CNN and VGG-19 models: 97.35% for the overall test accuracy with an overall specificity of 98.43%, sensitivity of 95.75%, positive and negative predictive value of 95.41%, and 98.05%. The micro average areas under each receiver operating characteristic curves was 0.96. The results were also validated by two physicians: an endocrinologist and a pediatrician. Conclusions: We proposed a new deep learning study for classifying ultrasound thyroidal images to assist physicians in the diagnosis process.

Artificial intelligence in ultrasound

Ultrasound (US), a flexible green imaging modality, is expanding globally as a first-line imaging technique in various clinical fields following with the continual emergence of advanced ultrasonic technologies and the well-established US-based digital health system. Actually, in US practice, qualified physicians should manually collect and visually evaluate images for the detection, identification and monitoring of diseases. The diagnostic performance is inevitably reduced due to the intrinsic property of high operator-dependence from US. In contrast, artificial intelligence (AI) excels at automatically recognizing complex patterns and providing quantitative assessment for imaging data, showing high potential to assist physicians in acquiring more accurate and reproducible results. In this article, we will provide a general understanding of AI, machine learning (ML) and deep learning (DL) technologies; We then review the rapidly growing applications of AI-especially DL technology in the field of US-based on the following anatomical regions: thyroid, breast, abdomen and pelvis, obstetrics heart and blood vessels, musculoskeletal system and other organs by covering image quality control, anatomy localization, object detection, lesion segmentation, and computer-aided diagnosis and prognosis evaluation; Finally, we offer our perspective on the challenges and opportunities for the clinical practice of biomedical AI systems in US.

Differential Diagnosis of Malignant Thyroid Calcification Nodule Based on Computed Tomography Image Texture

Purpose: Calcification nodules in thyroid can be found in thyroid disease. Current clinical computed tomography systems can be used to detect calcification nodules. Our aim is to identify the nature of thyroid calcification nodule based on plain CT images. Method: Sixty-three patients (36 benign and 27 malignant nodules) found thyroid calcification nodules were retrospectively analyzed, together with computed tomography images and pathology finding. The regions of interest (ROI) of 6464 pixels containing calcification nodules were manually delineated by radiologists in CT plain images. We extracted thirty-one texture features from each ROI. And nineteen texture features were picked up after feature optimization by logistic regression analysis. All the texture features were normalized to [0, 1]. Four classification algorithms, including ensemble learning, support vector machine, K-nearest neighbor, decision tree, were used as classification algorithms to identity the benign and malignant nodule. Accuracy, PPV, NPV, SEN, and AUC were calculated to evaluate the performance of different classifiers. Results: Nineteen texture features were selected after feature optimization by logistic regression analysis (P <0.05). Both Ensemble Learning and Support Vector Machine achieved the highest accuracy of 97.1%. The PPV, NPV, SEN, and SPC are 96.9%, 97.4%, 98.4%, and 95.0%, respectively. The AUC was 1. Conclusion: Texture features extracted from calcification nodules could be used as biomarkers to identify benign or malignant thyroid calcification.

A generic deep learning framework to classify thyroid and breast lesions in ultrasound images

Breast and thyroid cancers are the two common cancers to affect women worldwide. Ultrasonography (US) is a commonly used non-invasive imaging modality to detect breast and thyroid cancers, but its clinical diagnostic accuracy for these cancers is controversial. Both thyroid and breast cancers share some similar high frequency ultrasound characteristics such as taller-than-wide shape ratio, hypo-echogenicity, and ill-defined margins. This study aims to develop an automatic scheme for classifying thyroid and breast lesions in ultrasound images using deep convolutional neural networks (DCNN). In particular, we propose a generic DCNN architecture with transfer learning and the same architectural parameter settings to train models for thyroid and breast cancers (TNet and BNet) respectively, and test the viability of such a generic approach with ultrasound images collected from clinical practices. In addition, the potentials of the thyroid model in learning the common features and its performance of classifying both breast and thyroid lesions are investigated. A retrospective dataset of 719 thyroid and 672 breast images captured from US machines of different makes between October 2016 and December 2018 is used in this study. Test results show that both TNet and BNet built on the same DCNN architecture have achieved good classification results (86.5% average accuracy for TNet and 89% for BNet). Furthermore, we used TNet to classify breast lesions and the model achieves sensitivity of 86.6% and specificity of 87.1%, indicating its capability in learning features commonly shared by thyroid and breast lesions. We further tested the diagnostic performance of the TNet model against that of three radiologists. The area under curve (AUC) for thyroid nodule classification is 0.861 (95% CI: 0.792-0.929) for the TNet model and 0.757-0.854 (95% CI: 0.658-0.934) for the three radiologists. The AUC for breast cancer classification is 0.875 (95% CI: 0.804-0.947) for the TNet model and 0.698-0.777 (95% CI: 0.593-0.872) for the radiologists, indicating the model's potential in classifying both breast and thyroid cancers with a higher level of accuracy than that of radiologists.

Update on ACR TI-RADS: Successes, Challenges, and Future Directions, From the AJR Special Series on Radiology Reporting and Data Systems

The American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) is an ultrasound-based risk stratification system (RSS) for thyroid nodules that was released in 2017. Since publication, research has shown that ACR TI-RADS has a higher specificity than other RSSs and reduces the number of unnecessary biopsies of benign nodules compared with other systems by 19.9-46.5%. The risk of missing significant cancers using ACR TI-RADS is mitigated by the follow-up recommendations for nodules that do not meet criteria for biopsy. In practice, after a nodule's ultrasound features have been enumerated, the ACR TI-RADS points-based approach leads to clear management recommendations. Practices seeking to implement ACR TI-RADS must engage their radiologists in understanding how the system addresses the problems of thyroid cancer overdiagnosis and unnecessary surgeries by reducing unnecessary biopsies. This review compares ACR TI-RADS to other RSSs and explores key clinical questions faced by practices considering its implementation. We also address the challenge of reducing interobserver variability in assigning ultrasound features. Finally, we highlight emerging imaging techniques and recognize the ongoing international effort to develop a system that harmonizes multiple RSSs, including ACR TI-RADS.

Deep learning-based computer-aided diagnosis in screening breast ultrasound to reduce false-positive diagnoses

A major limitation of screening breast ultrasound (US) is a substantial number of false-positive biopsy. This study aimed to develop a deep learning-based computer-aided diagnosis (DL-CAD)-based diagnostic model to improve the differential diagnosis of screening US-detected breast masses and reduce false-positive diagnoses. In this multicenter retrospective study, a diagnostic model was developed based on US images combined with information obtained from the DL-CAD software for patients with breast masses detected using screening US; the data were obtained from two hospitals (development set: 299 imaging studies in 2015). Quantitative morphologic features were obtained from the DL-CAD software, and the clinical findings were collected. Multivariable logistic regression analysis was performed to establish a DL-CAD-based nomogram, and the model was externally validated using data collected from 164 imaging studies conducted between 2018 and 2019 at another hospital. Among the quantitative morphologic features extracted from DL-CAD, a higher irregular shape score (P = .018) and lower parallel orientation score (P = .007) were associated with malignancy. The nomogram incorporating the DL-CAD-based quantitative features, radiologists' Breast Imaging Reporting and Data Systems (BI-RADS) final assessment (P = .014), and patient age (P < .001) exhibited good discrimination in both the development and validation cohorts (area under the receiver operating characteristic curve, 0.89 and 0.87). Compared with the radiologists' BI-RADS final assessment, the DL-CAD-based nomogram lowered the false-positive rate (68% vs. 31%, P < .001 in the development cohort; 97% vs. 45% P < .001 in the validation cohort) without affecting the sensitivity (98% vs. 93%, P = .317 in the development cohort; each 100% in the validation cohort). In conclusion, the proposed model showed good performance for differentiating screening US-detected breast masses, thus demonstrating a potential to reduce unnecessary biopsies.

Computer-Aided Diagnostic System for Thyroid Nodules on Ultrasonography: Diagnostic Performance Based on the Thyroid Imaging Reporting and Data System Classification and Dichotomous Outcomes

BACKGROUND AND PURPOSE

Artificial intelligence-based computer-aided diagnostic systems have been introduced for thyroid cancer diagnosis. Our aim was to compare the diagnostic performance of a commercially available computer-aided diagnostic system and radiologist-based assessment for the detection of thyroid cancer based on the Thyroid Imaging Reporting and Data Systems (TIRADS) and dichotomous outcomes.

MATERIALS AND METHODS

In total, 372 consecutive patients with 454 thyroid nodules were enrolled. The computer-aided diagnostic system was set up to render a possible diagnosis in 2 formats, the Korean Society of Thyroid Radiology (K)-TIRADS and the American Thyroid Association (ATA)-TIRADS-classifications, and dichotomous outcomes (possibly benign or possibly malignant).

RESULTS

The diagnostic sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the computer-aided diagnostic system for thyroid cancer were, respectively, 97.6%, 21.6%, 42.0%, 93.9%, and 49.6% for K-TIRADS; 94.6%, 29.6%, 43.9%, 90.4%, and 53.5% for ATA-TIRADS; and 81.4%, 81.9%, 72.3%, 88.3%, and 81.7% for dichotomous outcomes. The sensitivities of the computer-aided diagnostic system did not differ significantly from those of the radiologist (all P > .05); the specificities and accuracies were significantly lower than those of the radiologist (all P < .001). Unnecessary fine-needle aspiration rates were lower for the dichotomous outcome characterizations, particularly for those performed by the radiologist. The interobserver agreement for the description of K-TIRADS and ATA-TIRADS classifications was fair-to-moderate, but the dichotomous outcomes were in substantial agreement.

CONCLUSIONS

The diagnostic performance of the computer-aided diagnostic system varies in terms of TIRADS classification and dichotomous outcomes and relative to radiologist-based assessments. Clinicians should know about the strengths and weaknesses associated with the diagnosis of thyroid cancer using computer-aided diagnostic systems.

Combining radiomics with ultrasound-based risk stratification systems for thyroid nodules: an approach for improving performance

OBJECTIVES

To develop a radiomics score using ultrasound images to predict thyroid malignancy and to investigate its potential as a complementary tool to improve the performance of risk stratification systems.

METHODS

We retrospectively included consecutive patients who underwent fine-needle aspiration (FNA) for thyroid nodules that were cytopathologically diagnosed as benign or malignant. Nodules were randomly assigned to a training and test set (8:2 ratio). A radiomics score was developed from the training set, and cutoff values based on the maximum Youden index (Rad_maxY) and for 5%, 10%, and 20% predicted malignancy risk (Rad_5%, Rad_10%, Rad_20%, respectively) were applied to the test set. The performances of the American College of Radiology (ACR) and the American Thyroid Association (ATA) guidelines were compared with the combined performances of the guidelines and radiomics score with interpretations from expert and nonexpert readers.

RESULTS

A total of 1624 thyroid nodules from 1609 patients (mean age, 50.1 years [range, 18-90 years]) were included. The radiomics score yielded an AUC of 0.85 (95% CI: 0.83, 0.87) in the training set and 0.75 (95% CI: 0.69, 0.81) in the test set (Rad_maxY). When the radiomics score was combined with the ACR or ATA guidelines (Rad_5%), all readers showed increased specificity, accuracy, and PPV and decreased unnecessary FNA rates (all p < .05), with no difference in sensitivity (p > .05).

CONCLUSION

Radiomics help predict thyroid malignancy and improve specificity, accuracy, PPV, and unnecessary FNA rate while maintaining the sensitivity of the ACR and ATA guidelines for both expert and nonexpert readers.

KEY POINTS

• The radiomics score yielded an AUC of 0.85 and 0.75 in the training and test set, respectively. • For all readers, combining a 5% predicted malignancy risk cutoff for the radiomics score with the ACR and ATA guidelines significantly increased specificity, accuracy, and PPV and decreased unnecessary FNA rates, with no decrease in sensitivity. • Radiomics can help predict malignancy in thyroid nodules in combination with risk stratification systems, by improving specificity, accuracy, and PPV and unnecessary FNA rates while maintaining sensitivity for both expert and nonexpert readers.

Use of artificial intelligence and machine learning for estimating malignancy risk of thyroid nodules

PURPOSE OF REVIEW

Current methods for thyroid nodule risk stratification are subjective, and artificial intelligence algorithms have been used to overcome this shortcoming. In this review, we summarize recent developments in the application of artificial intelligence algorithms for estimating the risks of malignancy in a thyroid nodule.

RECENT FINDINGS

Artificial intelligence have been used to predict malignancy in thyroid nodules using ultrasound images, cytopathology images, and molecular markers. Recent clinical trials have shown that artificial intelligence model's performance matched that of experienced radiologists and pathologists. Explainable artificial intelligence models are being developed to avoid the black box problem. Risk stratification algorithms using artificial intelligence for thyroid nodules are now commercially available in many countries.

SUMMARY

Artificial intelligence models could become a useful tool in a thyroidolgist's armamentarium as a decision support tool. Increased adoption of this emerging technology will depend upon increased awareness of the potential benefits and pitfalls in using artificial intelligence.

Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency

In this review of the most recent applications of deep learning to ultrasound imaging, the architectures of deep learning networks are briefly explained for the medical imaging applications of classification, detection, segmentation, and generation. Ultrasonography applications for image processing and diagnosis are then reviewed and summarized, along with some representative imaging studies of the breast, thyroid, heart, kidney, liver, and fetal head. Efforts towards workflow enhancement are also reviewed, with an emphasis on view recognition, scanning guide, image quality assessment, and quantification and measurement. Finally some future prospects are presented regarding image quality enhancement, diagnostic support, and improvements in workflow efficiency, along with remarks on hurdles, benefits, and necessary collaborations.

S-Detect Software vs. EU-TIRADS Classification: A Dual-Center Validation of Diagnostic Performance in Differentiation of Thyroid Nodules

Computer-aided diagnosis (CAD) and other risk stratification systems may improve ultrasound image interpretation. This prospective study aimed to compare the diagnostic performance of CAD and the European Thyroid Imaging Reporting and Data System (EU-TIRADS) classification applied by physicians with S-Detect 2 software CAD based on Korean Thyroid Imaging Reporting and Data System (K-TIRADS) and combinations of both methods (MODELs 1 to 5). In all, 133 nodules from 88 patients referred to thyroidectomy with available histopathology or with unambiguous results of cytology were included. The S-Detect system, EU-TIRADS, and mixed MODELs 1–5 for the diagnosis of thyroid cancer showed a sensitivity of 89.4%, 90.9%, 84.9%, 95.5%, 93.9%, 78.9% and 93.9%; a specificity of 80.6%, 61.2%, 88.1%, 53.7%, 73.1%, 89.6% and 80.6%; a positive predictive value of 81.9%, 69.8%, 87.5%, 67%, 77.5%, 88.1% and 82.7%; a negative predictive value of 88.5%, 87.2%, 85.5%, 92.3%, 92.5%, 81.1% and 93.1%; and an accuracy of 85%, 75.9%, 86.5%, 74.4%, 83.5%, 84.2%, and 87.2%, respectively. Comparison showed superiority of the similar MODELs 1 and 5 over other mixed models as well as EU-TIRADS and S-Detect used alone (p-value < 0.05). S-Detect software is characterized with high sensitivity and good specificity, whereas EU-TIRADS has high sensitivity, but rather low specificity. The best diagnostic performance in malignant thyroid nodule (TN) risk stratification was obtained for the combined model of S-Detect (“possibly malignant” nodule) and simultaneously obtaining 4 or 5 points (MODEL 1) or exactly 5 points (MODEL 5) on the EU-TIRADS scale.