Deep Learning-Based Computer-Aided Diagnosis System for Localization and Diagnosis of Metastatic Lymph Nodes on Ultrasound: A Pilot Study

Deep learning-based computer-aided diagnosis system for the automatic detection and classification of lateral cervical lymph nodes on original ultrasound images of papillary thyroid carcinoma: a prospective diagnostic study

PURPOSE

This study aims to develop a deep learning-based computer-aided diagnosis (CAD) system for the automatic detection and classification of lateral cervical lymph nodes (LNs) on original ultrasound images of papillary thyroid carcinoma (PTC) patients.

METHODS

A retrospective data set of 1801 cervical LN ultrasound images from 1675 patients with PTC and a prospective test set including 185 images from 160 patients were collected. Four different deep leaning models were trained and validated in the retrospective data set. The best model was selected for CAD system development and compared with three sonographers in the retrospective and prospective test sets.

RESULTS

The Deformable Detection Transformer (DETR) model showed the highest diagnostic efficacy, with a mean average precision score of 86.3% in the retrospective test set, and was therefore used in constructing the CAD system. The detection performance of the CAD system was superior to the junior sonographer and intermediate sonographer with accuracies of 86.3% and 92.4% in the retrospective and prospective test sets, respectively. The classification performance of the CAD system was better than all sonographers with the areas under the curve (AUCs) of 94.4% and 95.2% in the retrospective and prospective test sets, respectively.

CONCLUSIONS

This study developed a Deformable DETR model-based CAD system for automatically detecting and classifying lateral cervical LNs on original ultrasound images, which showed excellent diagnostic efficacy and clinical utility. It can be an important tool for assisting sonographers in the diagnosis process.

Ultrasound-Base Radiomics for Discerning Lymph Node Metastasis in Thyroid Cancer: A Systematic Review and Meta-analysis

PURPOSE

Ultrasound is the imaging modality of choice for preoperative diagnosis of lymph node metastasis (LNM) in thyroid cancer (TC), yet its efficacy remains suboptimal. As radiomics gains traction in tumor diagnosis, its integration with ultrasound for LNM differentiation in TC has emerged, but its diagnostic merit is debated. This study assesses the accuracy of ultrasound-integrated radiomics in preoperatively diagnosing LNM in TC.

METHODS

Literatures were searched in PubMed, Embase, Cochrane, and Web of Science until July 11, 2023. Quality of the studies was assessed by the radiomics quality score (RQS). A meta-analysis was executed using a bivariate mixed effects model, with a subgroup analysis based on modeling variables (clinical features, radiomics features, or their combination).

RESULTS

Among 27 articles (16,410 TC patients, 6356 with LNM), the average RQS was 16.5 (SD:5.47). Sensitivity of the models based on clinical features, radiomics features, and radiomics features plus clinical features were 0.64, 0.76 and 0.69. Specificities were 0.77, 0.78 and 0.82. SROC values were 0.76, 0.84 and 0.81.

CONCLUSION

Ultrasound-based radiomics effectively evaluates LNM in TC preoperatively. Adding clinical features does not notably enhance the model's performance. Some radiomics studies showed high bias, possibly due to the absence of standard application guidelines.

Application of deep-learning to the automatic segmentation and classification of lateral lymph nodes on ultrasound images of papillary thyroid carcinoma

PURPOSE

It is crucial to preoperatively diagnose lateral cervical lymph node (LN) metastases (LNMs) in papillary thyroid carcinoma (PTC) patients. This study aims to develop deep-learning models for the automatic segmentation and classification of LNM on original ultrasound images.

METHODS

This study included 1000 lateral cervical LN ultrasound images (consisting of 512 benign and 558 metastatic LNs) collected from 728 patients at the Chongqing General Hospital between March 2022 and July 2023. Three instance segmentation models (MaskRCNN, SOLO and Mask2Former) were constructed to segment and classify ultrasound images of lateral cervical LNs by recognizing each object individually and in a pixel-by-pixel manner. The segmentation and classification results of the three models were compared with an experienced sonographer in the test set.

RESULTS

Upon completion of a 200-epoch learning cycle, the loss among the three unique models became negligible. To evaluate the performance of the deep-learning models, the intersection over union threshold was set at 0.75. The mean average precision scores for MaskRCNN, SOLO and Mask2Former were 88.8%, 86.7% and 89.5%, respectively. The segmentation accuracies of the MaskRCNN, SOLO, Mask2Former models and sonographer were 85.6%, 88.0%, 89.5% and 82.3%, respectively. The classification AUCs of the MaskRCNN, SOLO, Mask2Former models and sonographer were 0.886, 0.869, 0.90.2 and 0.852 in the test set, respectively.

CONCLUSIONS

The deep learning models could automatically segment and classify lateral cervical LNs with an AUC of 0.92. This approach may serve as a promising tool to assist sonographers in diagnosing lateral cervical LNMs among patients with PTC.

Prediction of cervical lymph node metastasis in differentiated thyroid cancer based on radiomics models

OBJECTIVE

The accurate clinical diagnosis of cervical lymph node metastasis plays an important role in the treatment of differentiated thyroid cancer (DTC). This study aimed to explore and summarize a more objective approach to detect cervical malignant lymph node metastasis of DTC via radiomics models.

METHODS

PubMed, Web of Science, MEDLINE, EMBASE, and Cochrane databases were searched for all eligible studies. Articles using radiomics models based on ultrasound, computed tomography, or magnetic resonance imaging to assess cervical lymph node metastasis preoperatively were included. Characteristics and diagnostic accuracy measures were extracted. Bias and applicability judgments were evaluated by the revised QUADAS-2 tool. The estimates were pooled using a random-effects model. Additionally, the leave-one-out method was conducted to assess the heterogeneity.

RESULTS

Twenty-nine radiomics studies with 6160 validation set patients were included in the qualitative analysis, and 11 studies with 3863 validation set patients were included in the meta-analysis. Four of them had an external independent validation set. The studies were heterogeneous, and a significant risk of bias was found in 29 studies. Meta-analysis showed that the pooled sensitivity and specificity for preoperative prediction of lymph node metastasis via US-based radiomics were 0.81 (95% CI, 0.73-0.86) and 0.87 (95% CI, 0.83-0.91), respectively.

CONCLUSIONS

Although radiomics-based models for cervical lymphatic metastasis in DTC have been demonstrated to have moderate diagnostic capabilities, broader data, standardized radiomics features, robust feature selection, and model exploitation are still needed in the future.

ADVANCES IN KNOWLEDGE

The radiomics models showed great potential in detecting malignant lymph nodes in thyroid cancer.

Deep learning-assisted ultrasonic diagnosis of cervical lymph node metastasis of thyroid cancer: a retrospective study of 3059 patients

Objective

This study aimed to develop a deep learning system to identify and differentiate the metastatic cervical lymph nodes (CLNs) of thyroid cancer.

Methods

From January 2014 to December 2020, 3059 consecutive patients with suspected with metastatic CLNs of thyroid cancer were retrospectively enrolled in this study. All CLNs were confirmed by fine needle aspiration. The patients were randomly divided into the training (1228 benign and 1284 metastatic CLNs) and test (307 benign and 240 metastatic CLNs) groups. Grayscale ultrasonic images were used to develop and test the performance of the Y-Net deep learning model. We used the Y-Net network model to segment and differentiate the lymph nodes. The Dice coefficient was used to evaluate the segmentation efficiency. Sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were used to evaluate the classification efficiency.

Results

In the test set, the median Dice coefficient was 0.832. The sensitivity, specificity, accuracy, PPV, and NPV were 57.25%, 87.08%, 72.03%, 81.87%, and 66.67%, respectively. We also used the Y-Net classified branch to evaluate the classification efficiency of the LNs ultrasonic images. The classification branch model had sensitivity, specificity, accuracy, PPV, and NPV of 84.78%, 80.23%, 82.45%, 79.35%, and 85.61%, respectively. For the original ultrasonic reports, the sensitivity, specificity, accuracy, PPV, and NPV were 95.14%, 34.3%, 64.66%, 59.02%, 87.71%, respectively. The Y-Net model yielded better accuracy than the original ultrasonic reports.

Conclusion

The Y-Net model can be useful in assisting sonographers to improve the accuracy of the classification of ultrasound images of metastatic CLNs.

Metastatic Lymph Node Detection on Ultrasound Images Using YOLOv7 in Patients with Head and Neck Squamous Cell Carcinoma

Ultrasonography is the preferred modality for detailed evaluation of enlarged lymph nodes (LNs) identified on computed tomography and/or magnetic resonance imaging, owing to its high spatial resolution. However, the diagnostic performance of ultrasonography depends on the examiner's expertise. To support the ultrasonographic diagnosis, we developed YOLOv7-based deep learning models for metastatic LN detection on ultrasonography and compared their detection performance with that of highly experienced radiologists and less experienced residents. We enrolled 462 B- and D-mode ultrasound images of 261 metastatic and 279 non-metastatic histopathologically confirmed LNs from 126 patients with head and neck squamous cell carcinoma. The YOLOv7-based B- and D-mode models were optimized using B- and D-mode training and validation images and their detection performance for metastatic LNs was evaluated using B- and D-mode testing images, respectively. The D-mode model's performance was comparable to that of radiologists and superior to that of residents' reading of D-mode images, whereas the B-mode model's performance was higher than that of residents but lower than that of radiologists on B-mode images. Thus, YOLOv7-based B- and D-mode models can assist less experienced residents in ultrasonographic diagnoses. The D-mode model could raise the diagnostic performance of residents to the same level as experienced radiologists.

Deep learning predicts cervical lymph node metastasis in clinically node-negative papillary thyroid carcinoma

OBJECTIVES

Precise determination of cervical lymph node metastasis (CLNM) involvement in patients with early-stage thyroid cancer is fairly significant for identifying appropriate cervical treatment options. However, it is almost impossible to directly judge lymph node metastasis based on the imaging information of early-stage thyroid cancer patients with clinically negative lymph nodes.

METHODS

Preoperative US images (BMUS and CDFI) of 1031 clinically node negative PTC patients definitively diagnosed on pathology from two independent hospitals were divided into training set, validation set, internal test set, and external test set. An ensemble deep learning model based on ResNet-50 was built integrating clinical variables, BMUS, and CDFI images using a bagging classifier to predict metastasis of CLN. The final ensemble model performance was compared with expert interpretation.

RESULTS

The ensemble deep convolutional neural network (DCNN) achieved high performance in predicting CLNM in the test sets examined, with area under the curve values of 0.86 (95% CI 0.78-0.94) for the internal test set and 0.77 (95% CI 0.68-0.87) for the external test set. Compared to all radiologists averaged, the ensemble DCNN model also exhibited improved performance in making predictions. For the external validation set, accuracy was 0.72 versus 0.59 (p = 0.074), sensitivity was 0.75 versus 0.58 (p = 0.039), and specificity was 0.69 versus 0.60 (p = 0.078).

CONCLUSIONS

Deep learning can non-invasive predict CLNM for clinically node-negative PTC using conventional US imaging of thyroid cancer nodules and clinical variables in a multi-institutional dataset with superior accuracy, sensitivity, and specificity comparable to experts.

CRITICAL RELEVANCE STATEMENT

Deep learning efficiently predicts CLNM for clinically node-negative PTC based on US images and clinical variables in an advantageous manner.

KEY POINTS

• A deep learning-based ensemble algorithm for predicting CLNM in PTC was developed. • Ultrasound AI analysis combined with clinical data has advantages in predicting CLNM. • Compared to all experts averaged, the DCNN model achieved higher test performance.

A novel wavelet-transform-based convolution classification network for cervical lymph node metastasis of papillary thyroid carcinoma in ultrasound images

Preoperative assessment of cervical lymph nodes metastasis (CLNM) for accurate qualitative and locating diagnosis is important for choosing the best treatment option for patients with papillary thyroid cancer. Non-destructive, non-invasive ultrasound is currently the imaging method of choice for lymph node metastatic assessment. For lymph node characteristics and ultrasound images, this paper proposes a multitasking network framework for diagnosing metastatic lymph nodes in ultrasound images, in which localization module not only provides information on the location of lymph nodes to focus on the peripheral and self regions of lymph nodes, but also provides structural features of lymph nodes for subsequent classification module. In the classification module, we design a novel wavelet-transform-based convolution network. Wavelet transform is introduced into the deep learning convolution module to analyze ultrasound images in both spatial and frequency domains, which effectively enriches the feature information and improves the classification performance of the model without increasing the model parameters. We collected 510 patient data (N = 1376) from Shanghai Sixth People's Hospital regarding ultrasound lymph nodes in the neck, as well as used three publicly available ultrasound datasets, including SCUI2020 (N = 2914), DDTI (N = 480), and BUSI (N = 780). Compared to the optimal two-stage model, our model has improved its accuracy and AUC indexes by 5.83% and 4%, which outperforms the two-stage architectures and also surpasses the latest classification networks.

Deep Learning-Based Evaluation of Ultrasound Images for Benign Skin Tumors

In this study, a combined convolutional neural network for the diagnosis of three benign skin tumors was designed, and its effectiveness was verified through quantitative and statistical analysis. To this end, 698 sonographic images were taken and diagnosed at the Department of Dermatology at Severance Hospital in Seoul, Korea, between 10 November 2017 and 17 January 2020. Through an empirical process, a convolutional neural network combining two structures, which consist of a residual structure and an attention-gated structure, was designed. Five-fold cross-validation was applied, and the train set for each fold was augmented by the Fast AutoAugment technique. As a result of training, for three benign skin tumors, an average accuracy of 95.87%, an average sensitivity of 90.10%, and an average specificity of 96.23% were derived. Also, through statistical analysis using a class activation map and physicians' findings, it was found that the judgment criteria of physicians and the trained combined convolutional neural network were similar. This study suggests that the model designed and trained in this study can be a diagnostic aid to assist physicians and enable more efficient and accurate diagnoses.

Diagnostic Value of Artificial Intelligence-Assistant Diagnostic System Combined With Contrast-Enhanced Ultrasound in Thyroid TI-RADS 4 Nodules

OBJECTIVES

This study evaluated the diagnostic value of artificial intelligence-assistant diagnostic system combined with contrast-enhanced ultrasound in The American College of Radiology Thyroid Imaging, Reporting and Data System (ACR TI-RADS) 4 category thyroid nodules.

METHODS

Thyroid nodules that were evaluated as ACR TI-RADS 4 by conventional ultrasound were selected, all of which had pathological or fine needle aspiration (FNA) results. All nodules were examined by contrast-enhanced ultrasound (CEUS) and artificial intelligence (AI) analysis. The sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of AI, CEUS and their combined diagnosis were compared; Analyzed and compared the diagnostic efficiency of AI, CEUS and their combined diagnosis.

RESULTS

A total of 148 thyroid nodules were included in 140 patients, including 58 malignant nodules and 89 benign nodules. The sensitivity of combined diagnosis was significantly higher than that of AI or CEUS alone (P < .05). The NPV of AI, CEUS and combined diagnosis were statistically significant (P < .05). There was no significant difference in the diagnostic efficacy between AI and CEUS (P > .05), but there was a significant difference in NPV between AI and combined diagnosis (P < .05). The AUC of the combined diagnosis was 0.859, which was higher than that of AI, CEUS alone.

CONCLUSIONS

AI has a high diagnostic efficiency, which was helpful for radiologists to make rapid assessment. AI combined CEUS can significantly improve the diagnostic sensitivity and NPV, which was beneficial for the early detection of malignant nodules.

Artificial intelligence in thyroid ultrasound

Artificial intelligence (AI), particularly deep learning (DL) algorithms, has demonstrated remarkable progress in image-recognition tasks, enabling the automatic quantitative assessment of complex medical images with increased accuracy and efficiency. AI is widely used and is becoming increasingly popular in the field of ultrasound. The rising incidence of thyroid cancer and the workload of physicians have driven the need to utilize AI to efficiently process thyroid ultrasound images. Therefore, leveraging AI in thyroid cancer ultrasound screening and diagnosis cannot only help radiologists achieve more accurate and efficient imaging diagnosis but also reduce their workload. In this paper, we aim to present a comprehensive overview of the technical knowledge of AI with a focus on traditional machine learning (ML) algorithms and DL algorithms. We will also discuss their clinical applications in the ultrasound imaging of thyroid diseases, particularly in differentiating between benign and malignant nodules and predicting cervical lymph node metastasis in thyroid cancer. Finally, we will conclude that AI technology holds great promise for improving the accuracy of thyroid disease ultrasound diagnosis and discuss the potential prospects of AI in this field.

Fine-Needle Aspiration Biopsy Evaluation-Oriented Thyroid Carcinoma Auxiliary Diagnosis

OBJECTIVE

Thyroid carcinoma is one of the most common diseases with an increasing incidence worldwide in recent years. In clinical diagnosis, medical practitioners normally take a preliminary thyroid nodule grading so that highly suspected thyroid nodules can be taken into the fine-needle aspiration (FNA) biopsy to evaluate the malignancy. However, subjective misinterpretations might lead to ambiguous risk stratification of thyroid nodules and unnecessary FNA biopsy.

METHODS

We propose a thyroid carcinoma auxiliary diagnosis method for fine-needle aspiration biopsy evaluation. Through integration of several deep learning models into a multibranch network for thyroid nodule risk stratification in the Thyroid Imaging Reporting and Data System (TIRADS) with pathological features and cascading of a discriminator, our proposed method provides an intelligent auxiliary diagnosis to assist medical practitioners in determining the necessity for further FNA.

DISCUSSION

Experimental results revealed that not only was the rate at which nodules are falsely diagnosed as malignant nodules effectively reduced, which avoids the unnecessary high cost and pain of aspiration biopsy, but also previously missing detected cases were identified with high possibility. By comparing the physicians' diagnosis alone with machine-assisted diagnosis, physicians' diagnostic performance improved with the aid of our proposed method, illustrating that our model can be very helpful in clinical practice.

CONCLUSION

Our proposed method might help medical practitioners avoid subjective interpretations and inter-observer variability. For patients, reliable diagnosis is provided and unnecessary painful diagnostics can be avoided. In other superficial organs such as metastatic lymph nodes and salivary gland tumors, the proposed method might also provide a reliable auxiliary diagnosis for risk stratification.

Extreme gradient boosting model to assess risk of central cervical lymph node metastasis in patients with papillary thyroid carcinoma: Individual prediction using SHapley Additive exPlanations

BACKGROUND AND OBJECTIVES

Central cervical lymph node metastasis (CLNM) is considered a risk factor for recurrence in patients with papillary thyroid carcinoma (PTC). Traditional machine learning models suffered from "black-box" problems, which could not exactly explain the interactive effects of the risk factors. We aimed to develop an eXtreme Gradient Boosting (XGBoost) model to assess CLNM, including positive and negative effects.

METHODS

1,122 patients with PTC admitted at Tianjin First Central Hospital from 2016 to 2020 were retrospectively selected. They were randomly divided into the training and test datasets with an 8:2 ratio. 108 patients with PTC admitted at Binzhou Medical University Hospital in 2020 served as the validation dataset. The XGBoost model was used to assess CLNM. The 10-fold cross-validation was utilized for model selection, and the metric used to evaluate classification performance was the average area under the curve (AUC) of 10-fold cross-validation. Interpretation and transparency of the "black-box" problem were performed. SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanation (LIME) were used to ensure the stability and reliability of the model.

RESULTS

The XGBoost model based on ultrasound and dual-energy computed tomography images of the solitary primary lesion had an excellent performance for assessing CLNM, with average AUCs of 0.918, 0.903, and 0.881 in the training, test, and validation datasets, respectively. SHAP plots showed the influence of each parameter on the XGBoost model, including positive (i.e., capsular invasion, diameter, iodine concentration in the venous phase, and calcification) and negative (i.e., sex and age) impacts. For all cases, the capsular invasion prediction weight was the highest; for individual cases, different predictors were assigned different weights. Moreover, the performance of the XGBoost model was better than classical machine-learning models.

CONCLUSIONS

This study developed and validated an XGBoost model for assessing CLNM in patients with PTC. The ability to visually interpret the positive and negative effects made the XGBoost model an effective tool for guiding clinical treatment.

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.

Early detection of suspicious lymph nodes in differentiated thyroid cancer

BACKGROUND

Early identification of cervical lymph node (LN) metastases cervical lymph node metastases (CLNM) is crucial in the management of differentiated thyroid cancer differentiated thyroid cancer (DTC) as it influences the indication and the extent of surgery with an impact on the recurrence risk and overall survival. The present review focused on novel sensitive and specific diagnostic techniques, by searching through online databases like MEDLINE and Scopus up to February 2022.

AREAS COVERED

The techniques identified included contrast-enhanced ultrasound (CEUS), dosage of fragment 21-1 of cytokeratin 19 (CYFRA 21-1) in lymph node fine needle aspiration washout, sentinel LN biopsy (SNB), and artificial intelligence (AI) - deep learning applied to ultrasonography and computed tomography. These methods displayed widely varying sensitivity and specificity results, ranging from approximately 60-100%. This variability is mainly due to the operator's experience because of the great complexity of execution of these new techniques, which require a long-learning curve.

EXPERT OPINION

Despite the appearance of many candidate methods to improve the detection of metastatic lymph nodes, none seem to be clearly superior to the tools currently used in clinical practice and FNA-Tg measurement remains the more accurate tool to detect neck recurrences and CLNM from DTC.

Deep learning radiomics of dual-modality ultrasound images for hierarchical diagnosis of unexplained cervical lymphadenopathy

BACKGROUND

Accurate diagnosis of unexplained cervical lymphadenopathy (CLA) using medical images heavily relies on the experience of radiologists, which is even worse for CLA patients in underdeveloped countries and regions, because of lack of expertise and reliable medical history. This study aimed to develop a deep learning (DL) radiomics model based on B-mode and color Doppler ultrasound images for assisting radiologists to improve their diagnoses of the etiology of unexplained CLA.

METHODS

Patients with unexplained CLA who received ultrasound examinations from three hospitals located in underdeveloped areas of China were retrospectively enrolled. They were all pathologically confirmed with reactive hyperplasia, tuberculous lymphadenitis, lymphoma, or metastatic carcinoma. By mimicking the diagnosis logic of radiologists, three DL sub-models were developed to achieve the primary diagnosis of benign and malignant, the secondary diagnosis of reactive hyperplasia and tuberculous lymphadenitis in benign candidates, and of lymphoma and metastatic carcinoma in malignant candidates, respectively. Then, a CLA hierarchical diagnostic model (CLA-HDM) integrating all sub-models was proposed to classify the specific etiology of each unexplained CLA. The assistant effectiveness of CLA-HDM was assessed by comparing six radiologists between without and with using the DL-based classification and heatmap guidance.

RESULTS

A total of 763 patients with unexplained CLA were enrolled and were split into the training cohort (n=395), internal testing cohort (n=171), and external testing cohorts 1 (n=105) and 2 (n=92). The CLA-HDM for diagnosing four common etiologies of unexplained CLA achieved AUCs of 0.873 (95% CI: 0.838-0.908), 0.837 (95% CI: 0.789-0.889), and 0.840 (95% CI: 0.789-0.898) in the three testing cohorts, respectively, which was systematically more accurate than all the participating radiologists. With its assistance, the accuracy, sensitivity, and specificity of six radiologists with different levels of experience were generally improved, reducing the false-negative rate of 2.2-10% and the false-positive rate of 0.7-3.1%.

CONCLUSIONS

Multi-cohort testing demonstrated our DL model integrating dual-modality ultrasound images achieved accurate diagnosis of unexplained CLA. With its assistance, the gap between radiologists with different levels of experience was narrowed, which is potentially of great significance for benefiting CLA patients in underdeveloped countries and regions worldwide.

Predictions for Three-Month Postoperative Vocal Recovery after Thyroid Surgery from Spectrograms with Deep Neural Network

Despite the lack of findings in laryngeal endoscopy, it is common for patients to undergo vocal problems after thyroid surgery. This study aimed to predict the recovery of the patient's voice after 3 months from preoperative and postoperative voice spectrograms. We retrospectively collected voice and the GRBAS score from 114 patients undergoing surgery with thyroid cancer. The data for each patient were taken from three points in time: preoperative, and 2 weeks and 3 months postoperative. Using the pretrained model to predict GRBAS as the backbone, the preoperative and 2-weeks-postoperative voice spectrogram were trained for the EfficientNet architecture deep-learning model with long short-term memory (LSTM) to predict the voice at 3 months postoperation. The correlation analysis of the predicted results for the grade, breathiness, and asthenia scores were 0.741, 0.766, and 0.433, respectively. Based on the scaled prediction results, the area under the receiver operating characteristic curve for the binarized grade, breathiness, and asthenia were 0.894, 0.918, and 0.735, respectively. In the follow-up test results for 12 patients after 6 months, the average of the AUC values for the five scores was 0.822. This study showed the feasibility of predicting vocal recovery after 3 months using the spectrogram. We expect this model could be used to relieve patients' psychological anxiety and encourage them to actively participate in speech rehabilitation.

Automated classification of cervical lymph-node-level from ultrasound using Depthwise Separable Convolutional Swin Transformer

There are few studies on cervical ultrasound lymph-node-level classification which is very important for qualitative diagnosis and surgical treatment of diseases. Currently, ultrasound examination relies on the subjective experience of physicians to judge the level of the cervical lymph nodes, which is easily misclassified. Unlike other automated diagnostic tasks, lymph-node-level classification needs to focus on global structural information. Besides, there is a large range of sternocleidomastoid muscles in levels II, III and IV, which leads to small inter-class differences in these levels, so it also needs to focus on key local areas to extract strong distinguishable features. In this paper, we propose the Depthwise Separable Convolutional Swin Transformer, introducing the deepwise separable convolution branch into the self-attention mechanism to capture discriminative local features. Meanwhile, to address the problem of data imbalance, a new loss function is proposed to improve the performance of the classification network. In addition, for the ultrasound data collected by different devices, low contrast and blurring problems of ultrasound imaging, a unified pre-processing algorithm is designed. The model was validated on 1146 cases of cervical ultrasound lymph node collected from the Sixth People's Hospital of Shanghai. The average accuracy precision, sensitivity, specificity, and F1 value of the model for the valid dataset after five-fold cross-validation were 80.65%, 80.68%, 78.73%, 95.99% and 79.42%, respectively. It has been verified by visualization methods that the Region of Interest (ROI) of the model is similar or consistent with the observed region of the experts.

A Local and Global Feature Disentangled Network: Toward Classification of Benign-Malignant Thyroid Nodules From Ultrasound Image

Thyroid nodules are one of the most common nodular lesions. The incidence of thyroid cancer has increased rapidly in the past three decades and is one of the cancers with the highest incidence. As a non-invasive imaging modality, ultrasonography can identify benign and malignant thyroid nodules, and it can be used for large-scale screening. In this study, inspired by the domain knowledge of sonographers when diagnosing ultrasound images, a local and global feature disentangled network (LoGo-Net) is proposed to classify benign and malignant thyroid nodules. This model imitates the dual-pathway structure of human vision and establishes a new feature extraction method to improve the recognition performance of nodules. We use the tissue-anatomy disentangled (TAD) block to connect the dual pathways, which decouples the cues of local and global features based on the self-attention mechanism. To verify the effectiveness of the model, we constructed a large-scale dataset and conducted extensive experiments. The results show that our method achieves an accuracy of 89.33%, which has the potential to be used in the clinical practice of doctors, including early cancer screening procedures in remote or resource-poor areas.

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.

Deep multimodal learning for lymph node metastasis prediction of primary thyroid cancer

Objective. The incidence of primary thyroid cancer has risen steadily over the past decades because of overdiagnosis and overtreatment through the improvement in imaging techniques for screening, especially in ultrasound examination. Metastatic status of lymph nodes is important for staging the type of primary thyroid cancer. Deep learning algorithms based on ultrasound images were thus developed to assist radiologists on the diagnosis of lymph node metastasis. The objective of this study is to integrate more clinical context (e.g., health records and various image modalities) into, and explore more interpretable patterns discovered by, deep learning algorithms for the prediction of lymph node metastasis in primary thyroid cancer patients.Approach. A deep multimodal learning network was developed in this study with a novel index proposed to compare the contribution of different modalities when making the predictions.Main results. The proposed multimodal network achieved an average F1 score of 0.888 and an average area under the receiver operating characteristic curve (AUC) value of 0.973 in two independent validation sets, and the performance was significantly better than that of three single-modality deep learning networks. Moreover, among three modalities used in this study, the deep multimodal learning network relied generally more on image modalities than the data modality of clinic records when making the predictions.Significance. Our work is beneficial to prospective clinic trials of radiologists on the diagnosis of lymph node metastasis in primary thyroid cancer, and will better help them understand how the predictions are made in deep multimodal learning algorithms.

Risk factors and diagnostic prediction models for papillary thyroid carcinoma

Thyroid nodules (TNs) represent a common scenario. More accurate pre-operative diagnosis of malignancy has become an overriding concern. This study incorporated demographic, serological, ultrasound, and biopsy data and aimed to compare a new diagnostic prediction model based on Back Propagation Neural Network (BPNN) with multivariate logistic regression model, to guide the decision of surgery. Records of 2,090 patients with TNs who underwent thyroid surgery were retrospectively reviewed. Multivariate logistic regression analysis indicated that Bethesda category (OR=1.90, P<0.001), TIRADS (OR=2.55, P<0.001), age (OR=0.97, P=0.002), nodule size (OR=0.53, P<0.001), and serum levels of Tg (OR=0.994, P=0.004) and HDL-C (OR=0.23, P=0.001) were statistically significant independent differentiators for patients with PTC and benign nodules. Both BPNN and regression models showed good accuracy in differentiating PTC from benign nodules (area under the curve [AUC], 0.948 and 0.924, respectively). Notably, the BPNN model showed a higher specificity (88.3% vs. 73.9%) and negative predictive value (83.7% vs. 45.8%) than the regression model, while the sensitivity (93.1% vs. 93.9%) was similar between two models. Stratified analysis based on Bethesda indeterminate cytology categories showed similar findings. Therefore, BPNN and regression models based on a combination of demographic, serological, ultrasound, and biopsy data, all of which were readily available in routine clinical practice, might help guide the decision of surgery for TNs.

A comparative analysis of eight machine learning models for the prediction of lateral lymph node metastasis in patients with papillary thyroid carcinoma

BACKGROUND

Lateral lymph node metastasis (LLNM) is a contributor for poor prognosis in papillary thyroid cancer (PTC). We aimed to develop and validate machine learning (ML) algorithms-based models for predicting the risk of LLNM in these patients.

METHODS

This is retrospective study comprising 1236 patients who underwent initial thyroid resection at our institution between January 2019 and March 2022. All patients were randomly split into the training dataset (70%) and the validation dataset (30%). Eight ML algorithms, including the Logistic Regression, Gradient Boosting Machine, Extreme Gradient Boosting, Random Forest (RF), Decision Tree, Neural Network, Support Vector Machine and Bayesian Network were used to evaluate the risk of LLNM. The performance of ML models was evaluated by the area under curve (AUC), sensitivity, specificity, and decision curve analysis.

RESULTS

Among the eight ML algorithms, RF had the highest AUC (0.975), with sensitivity and specificity of 0.903 and 0.959, respectively. It was therefore used to develop as prediction model. The diagnostic performance of RF algorithm was dependent on the following nine top-rank variables: central lymph node ratio, size, central lymph node metastasis, number of foci, location, body mass index, aspect ratio, sex and extrathyroidal extension.

CONCLUSION

By combining clinical and sonographic characteristics, ML algorithms can achieve acceptable prediction of LLNM, of which the RF model performs best. ML algorithms can help clinicians to identify the risk probability of LLNM in PTC patients.

LASSO-based machine learning models for the prediction of central lymph node metastasis in clinically negative patients with papillary thyroid carcinoma

BACKGROUND

The presence of central lymph node metastasis (CLNM) is crucial for surgical decision-making in clinical N0 (cN0) papillary thyroid carcinoma (PTC) patients. We aimed to develop and validate machine learning (ML) algorithms-based models for predicting the risk of CLNM in cN0 patients.

METHODS

A total of 1099 PTC patients with cN0 central neck from July 2019 to March 2022 at our institution were retrospectively analyzed. All patients were randomly split into the training dataset (70%) and the validation dataset (30%). Eight ML algorithms, including the Logistic Regression, Gradient Boosting Machine, Extreme Gradient Boosting (XGB), Random Forest (RF), Decision Tree, Neural Network, Support Vector Machine and Bayesian Network were used to evaluate the risk of CLNM. The performance of ML models was evaluated by the area under curve (AUC), sensitivity, specificity, and decision curve analysis (DCA).

RESULTS

We firstly used the LASSO Logistic regression method to select the most relevant factors for predicting CLNM. The AUC of XGB was slightly higher than RF (0.907 and 0.902, respectively). According to DCA, RF model significantly outperformed XGB model at most threshold points and was therefore used to develop the predictive model. The diagnostic performance of RF algorithm was dependent on the following nine top-rank variables: size, margin, extrathyroidal extension, sex, echogenic foci, shape, number, lateral lymph node metastasis and chronic lymphocytic thyroiditis.

CONCLUSION

By incorporating clinicopathological and sonographic characteristics, we developed ML-based models, suggesting that this non-invasive method can be applied to facilitate individualized prediction of occult CLNM in cN0 central neck PTC patients.

Machine Learning Applications for Head and Neck Imaging

The head and neck (HN) consists of a large number of vital anatomic structures within a compact area. Imaging plays a central role in the diagnosis and management of major disorders affecting the HN. This article reviews the recent applications of machine learning (ML) in HN imaging with a focus on deep learning approaches. It categorizes ML applications in HN imaging into deep learning and traditional ML applications and provides examples of each category. It also discusses the main challenges facing the successful deployment of ML-based applications in the clinical setting and provides suggestions for addressing these challenges.

A Comparative Analysis of Six Machine Learning Models Based on Ultrasound to Distinguish the Possibility of Central Cervical Lymph Node Metastasis in Patients With Papillary Thyroid Carcinoma

Current approaches to predict central cervical lymph node metastasis (CLNM) in patients with papillary thyroid carcinoma (PTC) have failed to identify patients who would benefit from preventive treatment. Machine learning has offered the opportunity to improve accuracy by comparing the different algorithms. We assessed which machine learning algorithm can best improve CLNM prediction. This retrospective study used routine ultrasound data of 1,364 PTC patients. Six machine learning algorithms were compared to predict the possibility of CLNM. Predictive accuracy was assessed by sensitivity, specificity, positive predictive value, negative predictive value, and the area under the curve (AUC). The patients were randomly split into the training (70%), validation (15%), and test (15%) data sets. Random forest (RF) led to the best diagnostic model in the test cohort (AUC 0.731 ± 0.036, 95% confidence interval: 0.664–0.791). The diagnostic performance of the RF algorithm was most dependent on the following five top-rank features: extrathyroidal extension (27.597), age (17.275), T stage (15.058), shape (13.474), and multifocality (12.929). In conclusion, this study demonstrated promise for integrating machine learning methods into clinical decision-making processes, though these would need to be tested prospectively.

Deep Learning Based on ACR TI-RADS Can Improve the Differential Diagnosis of Thyroid Nodules

Objective

The purpose of this study was to improve the differentiation between malignant and benign thyroid nodules using deep learning (DL) in category 4 and 5 based on the Thyroid Imaging Reporting and Data System (TI-RADS, TR) from the American College of Radiology (ACR).

Design and Methods

From June 2, 2017 to April 23, 2019, 2082 thyroid ultrasound images from 1396 consecutive patients with confirmed pathology were retrospectively collected, of which 1289 nodules were category 4 (TR4) and 793 nodules were category 5 (TR5). Ninety percent of the B-mode ultrasound images were applied for training and validation, and the residual 10% and an independent external dataset for testing purpose by three different deep learning algorithms.

Results

In the independent test set, the DL algorithm of best performance got an AUC of 0.904, 0.845, 0.829 in TR4, TR5, and TR4&5, respectively. The sensitivity and specificity of the optimal model was 0.829, 0.831 on TR4, 0.846, 0.778 on TR5, 0.790, 0.779 on TR4&5, versus the radiologists of 0.686 (P=0.108), 0.766 (P=0.101), 0.677 (P=0.211), 0.750 (P=0.128), and 0.680 (P=0.023), 0.761 (P=0.530), respectively.

Conclusions

The study demonstrated that DL could improve the differentiation of malignant from benign thyroid nodules and had significant potential for clinical application on TR4 and TR5.

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.

Artificial Intelligence for Personalized Medicine in Thyroid Cancer: Current Status and Future Perspectives

Thyroid cancers (TC) have increasingly been detected following advances in diagnostic methods. Risk stratification guided by refined information becomes a crucial step toward the goal of personalized medicine. The diagnosis of TC mainly relies on imaging analysis, but visual examination may not reveal much information and not enable comprehensive analysis. Artificial intelligence (AI) is a technology used to extract and quantify key image information by simulating complex human functions. This latent, precise information contributes to stratify TC on the distinct risk and drives tailored management to transit from the surface (population-based) to a point (individual-based). In this review, we started with several challenges regarding personalized care in TC, for example, inconsistent rating ability of ultrasound physicians, uncertainty in cytopathological diagnosis, difficulty in discriminating follicular neoplasms, and inaccurate prognostication. We then analyzed and summarized the advances of AI to extract and analyze morphological, textural, and molecular features to reveal the ground truth of TC. Consequently, their combination with AI technology will make individual medical strategies possible.

Artificial intelligence performance in detecting tumor metastasis from medical radiology imaging: A systematic review and meta-analysis

BACKGROUND

Early diagnosis of tumor metastasis is crucial for clinical treatment. Artificial intelligence (AI) has shown great promise in the field of medicine. We therefore aimed to evaluate the diagnostic accuracy of AI algorithms in detecting tumor metastasis using medical radiology imaging.

METHODS

We searched PubMed and Web of Science for studies published from January 1, 1997, to January 30, 2020. Studies evaluating an AI model for the diagnosis of tumor metastasis from medical images were included. We excluded studies that used histopathology images or medical wave-form data and those focused on the region segmentation of interest. Studies providing enough information to construct contingency tables were included in a meta-analysis.

FINDINGS

We identified 2620 studies, of which 69 were included. Among them, 34 studies were included in a meta-analysis with a pooled sensitivity of 82% (95% CI 79-84%), specificity of 84% (82-87%) and AUC of 0·90 (0·87-0·92). Analysis for different AI algorithms showed a pooled sensitivity of 87% (83-90%) for machine learning and 86% (82-89%) for deep learning, and a pooled specificity of 89% (82-93%) for machine learning, and 87% (82-91%) for deep learning.

INTERPRETATION

AI algorithms may be used for the diagnosis of tumor metastasis using medical radiology imaging with equivalent or even better performance to health-care professionals, in terms of sensitivity and specificity. At the same time, rigorous reporting standards with external validation and comparison to health-care professionals are urgently needed for AI application in the medical field.

FUNDING

College students' innovative entrepreneurial training plan program .

Applications of machine learning and deep learning to thyroid imaging: where do we stand?

Ultrasonography (US) is the primary diagnostic tool used to assess the risk of malignancy and to inform decision-making regarding the use of fine-needle aspiration (FNA) and postFNA management in patients with thyroid nodules. However, since US image interpretation is operator-dependent and interobserver variability is moderate to substantial, unnecessary FNA and/or diagnostic surgery are common in practice. Artificial intelligence (AI)-based computeraided diagnosis (CAD) systems have been introduced to help with the accurate and consistent interpretation of US features, ultimately leading to a decrease in unnecessary FNA. This review provides a developmental overview of the AI-based CAD systems currently used for thyroid nodules and describes the future developmental directions of these systems for the personalized and optimized management of thyroid nodules.

Using ultrasound features and radiomics analysis to predict lymph node metastasis in patients with thyroid cancer

Background

Lymph node metastasis (LNM) is an important factor for thyroid cancer patients’ treatment and prognosis. The aim of this study was to explore the clinical value of ultrasound features and radiomics analysis in predicting LNM in thyroid cancer patients before surgery.

Methods

The characteristics of ultrasound images of 150 thyroid nodules were retrospectively analysed. All nodules were confirmed as thyroid cancer. Among the assessed patients, only one hundred and twenty-six patients underwent lymph node dissection. All patients underwent an ultrasound examination before surgery. In the radiomic analysis, the area of interest was identified from selected ultrasound images by using ITK-SNAP software. The radiomic features were extracted by using Ultrosomics software. Then, the data were classified into a training set and a validation set. Hypothetical tests and bagging were used to build the model. The diagnostic performance of different ultrasound features was assessed, a radiomic analysis was conducted, and a receiver operating characteristic (ROC) curve analysis was performed to explore the diagnostic accuracy.

Results

Regarding the prediction of LNM, the ROC curves showed that the area under the curve (AUC) values of an irregular shape and microcalcification were 0.591 (P = 0.059) and 0.629 (P = 0.007), respectively. In the radiomics analysis, in the training set, the AUC value of LNM was 0.759, with a sensitivity of 0.90 and a specificity of 0.860. In the verification set, the AUC was 0.803, with a sensitivity of 0.727 and a specificity of 0.800.

Conclusions

Microcalcification and an irregular shape are predictors of LNM in thyroid carcinoma patients. In addition, radiomics analysis has promising value in screening meaningful ultrasound features in thyroid cancer patients with LNM. Therefore, the prediction of LNM based on ultrasound features and radiomic features is useful for making appropriate decisions regarding surgery and interventions before thyroid carcinoma surgery.

Performance of deep learning to detect mastoiditis using multiple conventional radiographs of mastoid

Objectives

This study aimed to compare the diagnostic performance of deep learning algorithm trained by single view (anterior-posterior (AP) or lateral view) with that trained by multiple views (both views together) in diagnosis of mastoiditis on mastoid series and compare the diagnostic performance between the algorithm and radiologists.

Methods

Total 9,988 mastoid series (AP and lateral views) were classified as normal or abnormal (mastoiditis) based on radiographic findings. Among them 792 image sets with temporal bone CT were classified as the gold standard test set and remaining sets were randomly divided into training (n = 8,276) and validation (n = 920) sets by 9:1 for developing a deep learning algorithm. Temporal (n = 294) and geographic (n = 308) external test sets were also collected. Diagnostic performance of deep learning algorithm trained by single view was compared with that trained by multiple views. Diagnostic performance of the algorithm and two radiologists was assessed. Inter-observer agreement between the algorithm and radiologists and between two radiologists was calculated.

Results

Area under the receiver operating characteristic curves of algorithm using multiple views (0.971, 0.978, and 0.965 for gold standard, temporal, and geographic external test sets, respectively) showed higher values than those using single view (0.964/0.953, 0.952/0.961, and 0.961/0.942 for AP view/lateral view of gold standard, temporal external, and geographic external test sets, respectively) in all test sets. The algorithm showed statistically significant higher specificity compared with radiologists (p = 0.018 and 0.012). There was substantial agreement between the algorithm and two radiologists and between two radiologists (κ = 0.79, 0.8, and 0.76).

Conclusion

The deep learning algorithm trained by multiple views showed better performance than that trained by single view. The diagnostic performance of the algorithm for detecting mastoiditis on mastoid series was similar to or higher than that of radiologists.

Visual Interpretability in Computer-Assisted Diagnosis of Thyroid Nodules Using Ultrasound Images

BACKGROUND The number of studies on deep learning in artificial intelligence (AI)-assisted diagnosis of thyroid nodules is increasing. However, it is difficult to explain what the models actually learn in artificial intelligence-assisted medical research. Our aim is to investigate the visual interpretability of the computer-assisted diagnosis of malignant and benign thyroid nodules using ultrasound images. MATERIAL AND METHODS We designed and implemented 2 experiments to test whether our proposed model learned to interpret the ultrasound features used by ultrasound experts to diagnose thyroid nodules. First, in an anteroposterior/transverse (A/T) ratio experiment, multiple models were trained by changing the A/T ratio of the original nodules, and their classification, accuracy, sensitivity, and specificity were tested. Second, in a visualization experiment, class activation mapping used global average pooling and a fully connected layer to visualize the neural network to show the most important features. We also examined the importance of data preprocessing. RESULTS The A/T ratio experiment showed that after changing the A/T ratio of the nodules, the accuracy of the neural network model was reduced by 9.24-30.45%, indicating that our neural network model learned the A/T ratio information of the nodules. The visual experiment results showed that the nodule margins had a strong influence on the prediction of the neural network. CONCLUSIONS This study was an active exploration of interpretability in the deep learning classification of thyroid nodules. It demonstrated the neural network-visualized model focused on irregular nodule margins and the A/T ratio to classify thyroid nodules.

Deep Learning Radiomics Based on Contrast-Enhanced Ultrasound Might Optimize Curative Treatments for Very-Early or Early-Stage Hepatocellular Carcinoma Patients

BACKGROUND

We aimed to evaluate the performance of a deep learning (DL)-based Radiomics strategy designed for analyzing contrast-enhanced ultrasound (CEUS) to not only predict the progression-free survival (PFS) of radiofrequency ablation (RFA) and surgical resection (SR) but also optimize the treatment selection between them for patients with very-early or early-stage hepatocellular carcinoma (HCC).

METHODS

We retrospectively enrolled 419 patients examined by CEUS within 1 week before receiving RFA or SR (RFA: 214, SR: 205) from January 2008 to 2016. Two Radiomics signatures were constructed by the Radiomics model R-RFA and R-SR to stratify PFS of different treatment groups. Then, RFA and SR nomograms were built by incorporating Radiomics signatures and significant clinical variables to achieve individualized 2-year PFS prediction. Finally, we applied both Radiomics models and both nomograms to each enrolled patient to investigate whether there were space for treatment optimization and how much prognostic improvement could be expected.

RESULTS

R-RFA and R-SR showed remarkable discrimination (C-index: 0.726 for RFA, 0.741 for SR). RFA and SR nomograms provided good 2-year PFS prediction accuracy and good calibrations. We identified 17.3% RFA patients and 27.3% SR patients should swap their treatment, so their average probability of 2-year PFS would increase 12 and 15%, respectively.

CONCLUSIONS

The proposed Radiomics models and nomograms achieved accurate preoperative prediction of PFS for RFA and SR, and they could facilitate the optimized treatment selection between them for patients with very-early or early-stage HCC.

Risk model and risk stratification to preoperatively predict central lymph node metastasis in papillary thyroid carcinoma

Background

The central lymph node is the most common involvement for papillary thyroid carcinoma (PTC), which is correlated to recurrence and survival. But it is difficult to accurately evaluate lymph node prior to an operation. This retrospective study was designed to develop a risk model and risk stratification to preoperatively predict central lymph node metastasis (CLNM) in PTC and validate this model.

Methods

A series of 1,714 initial treatment PTC patients were enrolled. Among these patients, 1,001 patients were used to develop a predictive model and establish a stratification scoring system. This was validated through the remaining 713 patients.

Results

The multivariate analysis revealed that CLNM and lateral lymph node metastasis (LLNM) in ultrasound (US), tumor size, gender, capsule invasion in US, microcalcification and age were significant independent predictors for CLNM. The area under the curve (AUC) of the model was 0.778. Furthermore, the cutoff value to predict CLNM was 8 points, and the sensitivity and specificity were 77% and 65%, respectively. In the scoring system for CLNM, a score of ≤8, 8-18 and >18 were defined as low, intermediate and high risk, respectively. The risk of CLNM was approximately 30%, 60% and 80%, corresponding to the stratification. When validated, the model predicted the risk of CLNM with an AUC of 0.811, a sensitivity and specificity of 83% and 63%, respectively.

Conclusions

This study presented a predictive model to preoperatively assess the risk of CLNM in PTC. The predictive model performed well, but needed to be prospectively validated in external center.

Radiomics signature for prediction of lateral lymph node metastasis in conventional papillary thyroid carcinoma

Purpose

Preoperative neck ultrasound (US) for lateral cervical lymph nodes is recommended for all patients undergoing thyroidectomy for thyroid malignancy, but it is operator dependent. We aimed to develop a radiomics signature using US images of the primary tumor to preoperatively predict lateral lymph node metastasis (LNM) in patients with conventional papillary thyroid carcinoma (cPTC).

Methods

Four hundred consecutive cPTC patients from January 2004 to February 2006 were enrolled as the training cohort, and 368 consecutive cPTC patients from March 2006 to February 2007 served as the validation cohort. A radiomics signature, which consisted of 14 selected features, was generated by the least absolute shrinkage and selection operator (LASSO) regression model in the training cohort. The discriminating performance of the radiomics signature was assessed in the validation cohort with the area under the receiver operating characteristic curve (AUC).

Results

The radiomics signature was significantly associated with lateral cervical lymph node status (p < 0.001). The AUC of its performance in discriminating metastatic and non-metastatic lateral cervical lymph nodes was 0.710 (95% CI: 0.649–0.770) in the training cohort and was 0.621 (95% CI: 0.560–0.682) in the validation cohort.

Conclusions

The present study showed that US radiomic features of the primary tumor were associated with lateral cervical lymph node status. Although their discriminatory performance was slightly lower in the validation cohort, our study shows that US radiomic features of the primary tumor alone have the potential to predict lateral LNM.

The Diagnostic Efficiency of Ultrasound Computer-Aided Diagnosis in Differentiating Thyroid Nodules: A Systematic Review and Narrative Synthesis

Computer-aided diagnosis (CAD) techniques have emerged to complement qualitative assessment in the diagnosis of benign and malignant thyroid nodules. The aim of this review was to summarize the current evidence on the diagnostic performance of various ultrasound CAD in characterizing thyroid nodules. PUBMED, EMBASE and Cochrane databases were searched for studies published until August 2019. The Quality Assessment of Studies of Diagnostic Accuracy included in Systematic Review 2 (QUADAS-2) tool was used to assess the methodological quality of the studies. Reported diagnostic performance data were analyzed and discussed. Fourteen studies with 2232 patients and 2675 thyroid nodules met the inclusion criteria. The study quality based on QUADAS-2 assessment was moderate. At best performance, grey scale CAD had a sensitivity of 96.7% while Doppler CAD was 90%. Combined techniques of qualitative grey scale features and Doppler CAD assessment resulted in overall increased sensitivity (92%) and optimal specificity (85.1%). The experience of the CAD user, nodule size and the thyroid malignancy risk stratification system used for interpretation were the main potential factors affecting diagnostic performance outcomes. The diagnostic performance of CAD of thyroid ultrasound is comparable to that of qualitative visual assessment; however, combined techniques have the potential for better optimized diagnostic accuracy.

Effectiveness evaluation of computer-aided diagnosis system for the diagnosis of thyroid nodules on ultrasound: A systematic review and meta-analysis

BACKGROUND

More and more automated efficient ultrasound image analysis techniques, such as ultrasound-based computer-aided diagnosis system (CAD), were developed to obtain accurate, reproducible, and more objective diagnosis results for thyroid nodules. So far, whether the diagnostic performance of existing CAD systems can reach the diagnostic level of experienced radiologists is still controversial. The aim of the meta-analysis was to evaluate the accuracy of CAD for thyroid nodules' diagnosis by reviewing current literatures and summarizing the research status.

METHODS

A detailed literature search on PubMed, Embase, and Cochrane Libraries for articles published until December 2018 was carried out. The diagnostic performances of CAD systems vs radiologist were evaluated by meta-analysis. We determined the sensitivity and the specificity across studies, calculated positive and negative likelihood ratios and constructed summary receiver-operating characteristic (SROC) curves. Meta-analysis of studies was performed using a mixed-effect, hierarchical logistic regression model.

RESULTS

Five studies with 536 patients and 723 thyroid nodules were included in this meta-analysis. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio (DOR) for CAD system were 0.87 (95% confidence interval [CI], 0.73-0.94), 0.79 (95% CI 0.63-0.89), 4.1 (95% CI 2.5-6.9), 0.17 (95% CI 0.09-0.32), and 25 (95% CI 15-42), respectively. The SROC curve indicated that the area under the curve was 0.90 (95% CI 0.87-0.92). The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and DOR for experienced radiologists were 0.82 (95% CI 0.69-0.91), 0.83 (95% CI 0.76-0.89), 4.9 (95% CI 3.4-7.0), 0.22 (95% CI 0.12-0.38), and 23 (95% CI 11-46), respectively. The SROC curve indicated that the area under the curve was 0.96 (95% CI 0.94-0.97).

CONCLUSION

The sensitivity of the CAD system in the diagnosis of thyroid nodules was similar to that of experienced radiologists. However, the CAD system had lower specificity and DOR than experienced radiologists. The CAD system may play the potential role as a decision-making assistant alongside radiologists in the thyroid nodules' diagnosis. Future technical improvements would be helpful to increase the accuracy as well as diagnostic efficiency.

Application of deep learning to the diagnosis of cervical lymph node metastasis from thyroid cancer with CT

PURPOSE

To develop a deep learning-based computer-aided diagnosis (CAD) system for use in the CT diagnosis of cervical lymph node metastasis (LNM) in patients with thyroid cancer.

METHODS

A total of 995 axial CT images that included benign (n = 647) and malignant (n = 348) lymph nodes were collected from 202 patients with thyroid cancer who underwent CT for surgical planning between July 2017 and January 2018. The datasets were randomly split into training (79.0%), validation (10.5%), and test (10.5%) datasets. Eight deep convolutional neural network (CNN) models were used to classify the images into metastatic or benign lymph nodes. Pretrained networks were used on the ImageNet and the best-performing algorithm was selected. Class-specific discriminative regions were visualized with attention heatmap using a global average pooling method.

RESULTS

The area under the ROC curve (AUROC) for the tested algorithms ranged from 0.909 to 0.953. The sensitivity, specificity, and accuracy of the best-performing algorithm were all 90.4%, respectively. Attention heatmap highlighted important subregions for further clinical review.

CONCLUSION

A deep learning-based CAD system could accurately classify cervical LNM in patients with thyroid cancer on preoperative CT with an AUROC of 0.953. Whether this approach has clinical utility will require evaluation in a clinical setting.

KEY POINTS

• A deep learning-based CAD system could accurately classify cervical lymph node metastasis. The AUROC for the eight tested algorithms ranged from 0.909 to 0.953. • Of the eight models, the ResNet50 algorithm was the best-performing model for the validation dataset with 0.953 AUROC. The sensitivity, specificity, and accuracy of the ResNet50 model were all 90.4%, respectively, in the test dataset. • Based on its high accuracy of 90.4%, we consider that this model may be useful in a clinical setting to detect LNM on preoperative CT in patients with thyroid cancer.