Shear-wave elastography predicts T-restaging and pathologic complete response of rectal cancer post neoadjuvant chemoradiotherapy.

PURPOSE: To investigate the value of shear-wave elastography (SWE) in assessing the response to neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer. METHODS: In this study, 455 participants with locally advanced rectal cancer who underwent nCRT at our hospital between September 2021 and December 2022 were prospectively enrolled. The participants were randomly divided into training and test cohorts in a 3:2 ratio. Clinical baseline data, endorectal ultrasound examination data, and SWE measurements were collected for all participants. Logistic regression models were used to predict whether rectal cancer after nCRT had a low T staging (ypT 0-2 stage, Model A) and pathological complete response (pCR) (Model B). Paired Chi-square tests were used to compare the diagnostic performances of the radiologists to those of Models A and B. RESULTS: In total, 256 participants were included. The area under the receiver operating characteristic curve of Models A and B in the test cohort were 0.94 (0.87, 1.00) and 0.88 (0.80, 0.97), respectively. The optimal diagnostic thresholds for Models A and B were 14.9 kPa for peritumoral mesangial Emean and 15.2 kPa for tumor Emean, respectively. The diagnostic performance of the radiologists was significantly lower than that of Models A and B, respectively (p < 0.05). CONCLUSION: SWE can be used as a feasible method to evaluate the treatment response of nCRT for locally advanced rectal cancer.

Deep Learning-Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging.

PURPOSE: To develop a deep neural network system for the automatic segmentation and risk stratification prediction of gastrointestinal stromal tumors (GISTs). METHODS: A total of 980 ultrasound (US) images from 245 GIST patients were retrospectively collected. These images were randomly divided (6:2:2) into a training set, a validation set, and an internal test set. Additionally, 188 US images from 47 prospective GIST patients were collected to evaluate the segmentation and diagnostic performance of the model. Five deep learning-based segmentation networks, namely, UNet, FCN, DeepLabV3+, Swin Transformer, and SegNeXt, were employed, along with the ResNet 18 classification network, to select the most suitable network combination. The performance of the segmentation models was evaluated using metrics such as the intersection over union (IoU), Dice similarity coefficient (DSC), recall, and precision. The classification performance was assessed based on accuracy and the area under the receiver operating characteristic curve (AUROC). RESULTS: Among the compared models, SegNeXt-ResNet18 exhibited the best segmentation and classification performance. On the internal test set, the proposed model achieved IoU, DSC, precision, and recall values of 82.1, 90.2, 91.7, and 88.8%, respectively. The accuracy and AUC for GIST risk prediction were 87.4 and 92.0%, respectively. On the external test set, the segmentation models exhibited IoU, DSC, precision, and recall values of 81.0, 89.5, 92.8, and 86.4%, respectively. The accuracy and AUC for GIST risk prediction were 86.7 and 92.5%, respectively. CONCLUSION: This two-stage SegNeXt-ResNet18 model achieves automatic segmentation and risk stratification prediction for GISTs and demonstrates excellent segmentation and classification performance.

A Preoperative Prediction Model for Lymph Node Metastasis in Patients with Gastric Cancer Using a Machine Learning-based Ultrasomics Approach.

OBJECTIVE: This study aimed to develop an ultrasomics model for predicting lymph node metastasis preoperative in patients with gastric cancer (GC). METHODS: This study enrolled GC patients who underwent preoperative ultrasound examination. Manual segmentation of the region of interest (ROI) was performed by an experienced radiologist to extract radiomics features using the Pyradiomics software. The Z-score algorithm was used for feature normalization, followed by the Wilcoxon test to identify the most informative features. Linear prediction models were constructed using the least absolute shrinkage and selection operator (LASSO). The performance of the ultrasomics model was evaluated using the area under curve (AUC), sensitivity, specificity, and the corresponding 95% confidence intervals (CIs). RESULTS: A total of 464 GC patients (mean age: 60.4 years ±11.3 [SD]; 328 men [70.7%]) were analyzed, of whom 291 had lymph node metastasis. The patients were randomly assigned to either the training (n=324) or test (n=140) sets, using a 7:3 ratio. An ultrasomics model that consisted of 19 radiomics features was developed using Wilcoxon and LASSO algorithms in the training set. Our ultrasomics model showed moderate performance for lymph node metastasis prediction in both the training (AUC: 0.802, 95%CI: 0.752-0.851, P<0.001) and test sets (AUC: 0.802, 95%CI: 0.724-0.879, P<0.001). The calibration curve analysis indicated good agreement between the predicted probabilities of ultrasomics and actual lymph node metastasis status. CONCLUSION: Our study highlights the potential of a machine learning-based ultrasomics model in predicting lymph node metastasis in GC patients, offering implications for personalized therapy approaches.

Ultrasound-based radiomics-clinical nomogram for noninvasive prediction of residual cancer burden grading in breast cancer.

PURPOSE: To assess the predictive value of an ultrasound-based radiomics-clinical nomogram for grading residual cancer burden (RCB) in breast cancer patients. METHODS: This retrospective study of breast cancer patients who underwent neoadjuvant therapy (NAC) and ultrasound scanning between November 2020 and July 2023. First, a radiomics model was established based on ultrasound images. Subsequently, multivariate LR (logistic regression) analysis incorporating both radiomic scores and clinical factors was performed to construct a nomogram. Finally, Receiver operating characteristics (ROC) curve analysis and decision curve analysis (DCA) were employed to evaluate and validate the diagnostic accuracy and effectiveness of the nomogram. RESULTS: A total of 1122 patients were included in this study. Among them, 427 patients exhibited a favorable response to NAC chemotherapy, while 695 patients demonstrated a poor response to NAC therapy. The radiomics model achieved an AUC value of 0.84 in the training cohort and 0.83 in the validation cohort. The ultrasound-based radiomics-clinical nomogram achieved an AUC value of 0.90 in the training cohort and 0.91 in the validation cohort. CONCLUSIONS: Ultrasound-based radiomics-clinical nomogram can accurately predict the effectiveness of NAC therapy by predicting RCB grading in breast cancer patients.

Application of contrast-enhanced ultrasound in diagnosis and grading of bladder urothelial carcinoma.

PURPOSE: To explore the application of contrast-enhanced ultrasound (CEUS) for the diagnosis and grading of bladder urothelial carcinoma (BUC). METHODS: The results of a two-dimensional ultrasound, color Doppler ultrasound and CEUS, were analyzed in 173 bladder lesion cases. The ultrasound and surgical pathology results were compared, and their diagnostic efficacy was analyzed. RESULTS: There were statistically significant differences between BUC and benign lesions in terms of color blood flow distribution intensity and CEUS enhancement intensity (both P < 0.05). The area under the time-intensity curve (AUC), rising slope, and peak intensity of BUC were significantly higher than those of benign lesions (all P < 0.05). The H/T (height H / basal width T)value of 0.63 was the critical value for distinguishing high- and low-grade BUC, had a diagnostic sensitivity of 80.0% and a specificity of 60.0%. CONCLUSION: The combination of CEUS and TIC can help improve the diagnostic accuracy of BUC. There is a statistically significant difference between high- and low-grade BUC in contrast enhancement intensity (P < 0.05); The decrease of H/T value indicates the possible increase of the BUC grade.

Predictive Model of CK7 Expression in Patients With Clear Cell Renal Cell Carcinoma by Combined Multimodal Ultrasound Diagnostic Techniques: A Retrospective Study.

OBJECTIVE: The aim of the work described here was to develop and validate a predictive model for cytokeratin 7 (CK7) expression in clear cell renal cell carcinoma (ccRCC) patients by combining multimodal ultrasound diagnostic techniques. METHODS: This retrospective study enrolled 157 surgically confirmed ccRCC patients. All patients underwent pre-operative multimodal ultrasound diagnostic examinations, including B-mode ultrasound (US), color Doppler flow imaging (CDFI) and contrast-enhanced ultrasound (CEUS). The patients were randomly divided into a training group (103 cases) and a testing group (54 cases). Univariate and multivariate logistic regression analyses were performed in the training group to identify independent indicators associated with CK7 positivity. These indicators were included in the predictive model. Receiver operating characteristic (ROC) curves and calibration curves were used to evaluate the model's discriminative ability and accuracy. Decision curve analysis (DCA) and nomogram visualization were used to assess the clinical utility of the predictive model. RESULTS: Univariate logistic regression analysis revealed that US and CDFI observations were not correlated with CK7 expression and could not predict it. Multivariate logistic regression analysis identified age (odds ratio [OR] = 0.953, 95% confidence interval [CI]: 0.909-0.999), wash-in pattern (OR = 0.180, 95% CI: 0.063-0.513) and enhancement homogeneity (OR = 11.610, 95% CI: 1.394-96.675) as independent factors related to CK7 positivity in ccRCC. Incorporating these variables into the predictive model resulted in areas under the receiver operating characteristic curve of 0.812 (95% CI: 0.711-0.913) for the training group and 0.792 (95% CI: 0.667-0.924) for the testing group. The calibration curve and DCA revealed that the model had good accuracy and clinical utility of the model. CONCLUSION: The combination of multimodal ultrasound diagnostic techniques in constructing a predictive model for CK7 expression in ccRCC patients has significant predictive value.

Associations between contrast-enhanced ultrasound features and WHO/ISUP grade of clear cell renal cell carcinoma: a retrospective study.

BACKGROUND: Clear cell renal cell carcinoma (CCRCC) comprises 70%-80% of RCCs. The World Health Organization/International Society of Urology Pathology (WHO/ISUP) classification is the most important prognostic factor for CCRCC. By evaluating the variations of tumor microvascular density, contrast-enhanced ultrasound (CEUS) can noninvasively predict the WHO/ISUP grade of CCRCC, and provide the appropriate treatment plan before clinical operation. METHODS: In this study, we used CEUS features to analyze 116 CCRCC cases and assess the value of correlation between each indicator and CCRCC WHO/ISUP grading. RESULTS: When compared to high-grade (WHO/ISUP grade III/IV) tumors, low-grade (WHO/ISUP grade I/II) tumors had reduced relative peak intensity (ΔPI) (P = 0.021), relative area under the curve (ΔAUC) (P = 0.019). However, the frequency of incomplete pseudocapsule (P = 0.021) was significantly higher in high-grade tumors. A cut-off value of mean diameter > 5.5 cm, ΔPI > 304 × 10-3, ΔAUC > 350 × 10-3 allowed identification of high-grade tumors with an area under the curve (AUC) of 74.6%, 71.7%, 70.7%, respectively (95% confidence interval). CONCLUSIONS: The features of CEUS are effective for differentiating high-grade tumors from low-grade tumors, thus CEUS can be considered an acceptable method for the preoperative assessment of tumor grade.

Predicting the risk stratification of gastrointestinal stromal tumors using machine learning-based ultrasound radiomics.

PURPOSE: This study aimed to use conventional ultrasound features, ultrasound radiomics, and machine learning algorithms to establish a predictive model to assess the risk of post-surgical recurrence of gastrointestinal stromal tumors (GISTs). METHODS: This retrospective analysis included 230 patients with pathologically diagnosed GISTs. Radiomic features were extracted from manually annotated images. Radiomic features plus conventional ultrasound features were selected using the SelectKbest analysis of variance and stratified tenfold cross-validation recursive elimination methods. Finally, five different machine learning algorithms (logistic regression [LR], support vector machine [SVM], random forest [RF], extreme gradient boosting [XGBoost], and multilayer perceptron [MLP]) were established to predict risk stratification of GISTs. The predictive performance of the established model was mainly evaluated based on the area under the receiver operating characteristic (ROC) curve (AUC) and accuracy, whereas the predictive performance of the optimal machine learning algorithm and a radiologist's subjective assessment were compared using McNemar's test. RESULTS: Seven radiomics features and one conventional ultrasound feature were selected to construct the machine learning models for GIST risk classification. The mentioned five machine learning models were able to predict the malignant potential of GISTs. LR and SVM outperformed other classifiers on the test set, with LR achieving an accuracy of 0.852 (AUC, 0.881; sensitivity, 0.871; specificity, 0.826) and SVM achieving an accuracy of 0.852 (AUC, 0.879; sensitivity, 0.839; specificity, 0.870), and proved significantly better than the radiologist (accuracy, 0.691; sensitivity, 0.645; specificity, 0.813). CONCLUSION: Machine learning-based ultrasound radiomics features are able to noninvasively predict the biological risk of GISTs.

A nomogram incorporating clinical, conventional ultrasound and shear wave elastography findings for distinguishing pleomorphic adenoma from Warthin's tumor of the major salivary glands.

OBJECTIVE: Pre-operative differentiation between pleomorphic adenoma (PA) and Warthin's tumor (WT) of the major salivary glands is crucial for treatment decisions. The purpose of this study was to develop and validate a nomogram incorporating clinical, conventional ultrasound (CUS) and shear wave elastography (SWE) features to differentiate PA from WT. METHODS: A total of 113 patients with histological diagnosis of PA or WT of the major salivary glands treated at Fujian Medical University Union Hospital were enrolled in training cohort (n = 75; PA = 41, WT = 34) and validation cohort (n = 38; PA = 22, WT = 16). The least absolute shrinkage and selection operator (LASSO) regression algorithm was used for screening the most optimal clinical, CUS, and SWE features. Different models, including the nomogram model, clinic-CUS (Clin+CUS) and SWE model, were built using logistic regression. The performance levels of the models were evaluated and validated on the training and validation cohorts, and then compared among the three models. RESULTS: The nomogram incorporating the clinical, CUS and SWE features showed favorable predictive value for differentiating PA from WT, with the area under the curves (AUCs) of 0.947 and 0.903 for the training cohort and validation cohort, respectively. Decision curve analysis showed that the nomogram model outperformed the Clin+CUS model and SWE model in terms of clinical usefulness. CONCLUSIONS: The nomogram had good performance in distinguishing major salivary PA from WT and held potential for optimizing the clinical decision-making process.

Contrast-Enhanced Ultrasound Imaging: Novel Method for the Evaluation of Chronic Alcohol-Induced Testicular Damage.

OBJECTIVE: The goals of this study were to determine whether contrast-enhanced ultrasound (CEUS) imaging could be used for assessment of chronic alcohol-induced testicular damage (CAITD) and to explore the relationships between the laboratory and pathological findings of CAITD and the quantitative parameters of CEUS. METHODS: Thirty-six rabbits were randomly divided into a chronic ethanol exposure (CEE) group and negative control (NC) group, which were further randomly divided into six groups with equal numbers of rabbits by period of exposure (30 d, 60 d, 90 d). All rabbits underwent conventional US and CEUS imaging at the end of the induction period. Blood and histological specimens were collected for laboratory and pathological examination. RESULTS: The peak intensity (PI) and area under the curve (AUC) for the CEUS parameters decreased as CAITD progressed (p < 0.05). Both PI and AUC were positively correlated with the Johnsen score (r= 0.945 and 0.898, respectively, all p values <0.001) and the mean epithelium thickness of the seminiferous tubule (METST) (r= 0.927 and 0.881, respectively, all p values <0.001) of the testis, and negatively correlated with the serum levels of endothelin-1 (ET-1) (r = -0.940 and -0.899, respectively, all p values <0.001) and nitric oxide (NO) (r = -0.894 and -0.954, respectively, all p values <0.001), as well as the testicular tissue content of malondialdehyde (MDA) (r = -0.894 and -0.945, respectively, all p values <0.001). CONCLUSION: CEUS imaging can be used for monitoring organ perfusion of the testis to quantify the development of CAITD.

Use of a Convolutional Neural Network to Predict the Malignant Potential of Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Images: Visualization of the Focus of the Prediction Model.

OBJECTIVE: We established a deep convolutional neural network (CNN) model based on ultrasound images (US-CNN) for predicting the malignant potential of gastrointestinal stromal tumors (GISTs). METHODS: A total of 980 ultrasound images from 245 pathology-confirmed GIST patients after surgical operation were retrospectively collected and divided into a low (very-low-risk, low-risk) and a high (medium-risk, high-risk) malignant potential group. Eight pre-trained CNN models were used to extract the features. The CNN model with the highest accuracy in the test set was selected. The model's performance was evaluated by calculating accuracy, sensitivity, specificity, positive-predictive value (PPV), negative-predictive value (NPV) and the F1 score. Three radiologists with different experience levels also predicted the malignant potential of GISTs in the same test set. US-CNN and human assessments were compared. Subsequently, gradient-weighted class activation diagrams (Grad-CAMs) were used to visualize the model's final classification decisions. RESULTS: Among the eight transfer learning-based CNNs, ResNet18 performed best. The accuracy, sensitivity, specificity, PPV, NPV and F1 score were 0.88, 0.86, 0.89, 0.82, 0.92 and 0.90, respectively, which were significantly better than those achieved by radiologists (resident doctor: 0.66, 0.55, 0.79, 0.74, 0.62 and 0.69; attending doctor: 0.68, 0.59, 0.78, 0.70, 0.69 and 0.73; professor: 0.69, 0.63, 0.72, 0.51, 0.80 and 0.76). Model interpretation with Grad-CAMs revealed that the activated areas mainly focused on cystic necrosis and margins. CONCLUSION: The US-CNN model predicts GIST malignant potential well, which can assist in clinical treatment decision-making.

CUSS-Net: A Cascaded Unsupervised-Based Strategy and Supervised Network for Biomedical Image Diagnosis and Segmentation.

Biomedical image segmentation and classification are critical components in a computer-aided diagnosis system. However, various deep convolutional neural networks are trained by a single task, ignoring the potential contribution of mutually performing multiple tasks. In this paper, we propose a cascaded unsupervised-based strategy to boost the supervised CNN framework for automated white blood cell (WBC) and skin lesion segmentation and classification, called CUSS-Net. Our proposed CUSS-Net consists of an unsupervised-based strategy (US) module, an enhanced segmentation network named E-SegNet, and a mask-guided classification network called MG-ClsNet. On the one hand, the proposed US module produces coarse masks that provide a prior localization map for the proposed E-SegNet to enhance it in locating and segmenting a target object accurately. On the other hand, the enhanced coarse masks predicted by the proposed E-SegNet are then fed into the proposed MG-ClsNet for accurate classification. Moreover, a novel cascaded dense inception module is presented to capture more high-level information. Meanwhile, we adopt a hybrid loss by combining a dice loss and a cross-entropy loss to alleviate the imbalance training problem. We evaluate our proposed CUSS-Net on three public medical image datasets. Experiments show that our proposed CUSS-Net outperforms representative state-of-the-art approaches.

Ultrasound-based deep learning in the establishment of a breast lesion risk stratification system: a multicenter study.

OBJECTIVES: To establish a breast lesion risk stratification system using ultrasound images to predict breast malignancy and assess Breast Imaging Reporting and Data System (BI-RADS) categories simultaneously. METHODS: This multicenter study prospectively collected a dataset of ultrasound images for 5012 patients at thirty-two hospitals from December 2018 to December 2020. A deep learning (DL) model was developed to conduct binary categorization (benign and malignant) and BI-RADS categories (2, 3, 4a, 4b, 4c, and 5) simultaneously. The training set of 4212 patients and the internal test set of 416 patients were from thirty hospitals. The remaining two hospitals with 384 patients were used as an external test set. Three experienced radiologists performed a reader study on 324 patients randomly selected from the test sets. We compared the performance of the DL model with that of three radiologists and the consensus of the three radiologists. RESULTS: In the external test set, the DL model achieved areas under the receiver operating characteristic curve (AUCs) of 0.980 and 0.945 for the binary categorization and six-way categorizations, respectively. In the reader study set, the DL BI-RADS categories achieved a similar AUC (0.901 vs. 0.933, p = 0.0632), sensitivity (90.98% vs. 95.90%, p = 0.1094), and accuracy (83.33% vs. 79.01%, p = 0.0541), but higher specificity (78.71% vs. 68.81%, p = 0.0012) than those of the consensus of the three radiologists. CONCLUSIONS: The DL model performed well in distinguishing benign from malignant breast lesions and yielded outcomes similar to experienced radiologists. This indicates the potential applicability of the DL model in clinical diagnosis. KEY POINTS: • The DL model can achieve binary categorization for benign and malignant breast lesions and six-way BI-RADS categorizations for categories 2, 3, 4a, 4b, 4c, and 5, simultaneously. • The DL model showed acceptable agreement with radiologists for the classification of breast lesions. • The DL model performed well in distinguishing benign from malignant breast lesions and had promise in helping reduce unnecessary biopsies of BI-RADS 4a lesions.

A Super-resolution Guided Network for Improving Automated Thyroid Nodule Segmentation.

BACKGROUND AND OBJECTIVE: A thyroid nodule is an abnormal lump that grows in the thyroid gland, which is the early symptom of thyroid cancer. In order to diagnose and treat thyroid cancer at the earliest stage, it is desired to characterize the nodule accurately. Ultrasound thyroid nodules segmentation is a challenging task due to the speckle noise, intensity heterogeneity, low contrast and low resolution. In this paper, we propose a novel framework to improve the accuracy of thyroid nodules segmentation. METHODS: Different from previous work, a super-resolution reconstruction network is firstly constructed to upscale the resolution of the input ultrasound image. After that, our proposed N-shape network is utilized to perform the segmentation task. The guidance of super-resolution reconstruction network can make the high-frequency information of the input thyroid ultrasound image richer and more comprehensive than the original image. Our N-shape network consists of several atrous spatial pyramid pooling blocks, a multi-scale input layer, a U-shape convolutional network with attention blocks and a proposed parallel atrous convolution(PAC) module. These modules are conducive to capture context information at multiple scales so that semantic features can be fully utilized for lesion segmentation. Especially, our proposed PAC module is beneficial to further improve the segmentation by extracting high-level semantic features from different receptive fields. We use the UTNI-2021 dataset for model training, validating and testing. RESULTS: The experimental results show that our proposed method achieve a Dice value of 91.9%, a mIoU value of 87.0%, a Precision value of 88.0%, a Recall value 83.7% and a F1-score value of 84.3%, which outperforms most state-of-the-art methods. CONCLUSIONS: Our method achieves the best performance on the UTNI-2021 dataset and provides a new way of ultrasound image segmentation. We believe that our method can provide doctors with reliable auxiliary diagnosis information in clinical practice.

Corrigendum: N-Net: A novel dense fully convolutional neural network for thyroid nodule segmentation.

[This corrects the article DOI: 10.3389/fnins.2022.872601.].

N-Net: A novel dense fully convolutional neural network for thyroid nodule segmentation.

Medical image segmentation is an essential component of computer-aided diagnosis (CAD) systems. Thyroid nodule segmentation using ultrasound images is a necessary step for the early diagnosis of thyroid diseases. An encoder-decoder based deep convolutional neural network (DCNN), like U-Net architecture and its variants, has been extensively used to deal with medical image segmentation tasks. In this article, we propose a novel N-shape dense fully convolutional neural network for medical image segmentation, referred to as N-Net. The proposed framework is composed of three major components: a multi-scale input layer, an attention guidance module, and an innovative stackable dilated convolution (SDC) block. First, we apply the multi-scale input layer to construct an image pyramid, which achieves multi-level receiver field sizes and obtains rich feature representation. After that, the U-shape convolutional network is employed as the backbone structure. Moreover, we use the attention guidance module to filter the features before several skip connections, which can transfer structural information from previous feature maps to the following layers. This module can also remove noise and reduce the negative impact of the background. Finally, we propose a stackable dilated convolution (SDC) block, which is able to capture deep semantic features that may be lost in bilinear upsampling. We have evaluated the proposed N-Net framework on a thyroid nodule ultrasound image dataset (called the TNUI-2021 dataset) and the DDTI publicly available dataset. The experimental results show that our N-Net model outperforms several state-of-the-art methods in the thyroid nodule segmentation tasks.

Deep learning based on ultrasound images assists breast lesion diagnosis in China: a multicenter diagnostic study.

BACKGROUND: Studies on deep learning (DL)-based models in breast ultrasound (US) remain at the early stage due to a lack of large datasets for training and independent test sets for verification. We aimed to develop a DL model for differentiating benign from malignant breast lesions on US using a large multicenter dataset and explore the model's ability to assist the radiologists. METHODS: A total of 14,043 US images from 5012 women were prospectively collected from 32 hospitals. To develop the DL model, the patients from 30 hospitals were randomly divided into a training cohort (n = 4149) and an internal test cohort (n = 466). The remaining 2 hospitals (n = 397) were used as the external test cohorts (ETC). We compared the model with the prospective Breast Imaging Reporting and Data System assessment and five radiologists. We also explored the model's ability to assist the radiologists using two different methods. RESULTS: The model demonstrated excellent diagnostic performance with the ETC, with a high area under the receiver operating characteristic curve (AUC, 0.913), sensitivity (88.84%), specificity (83.77%), and accuracy (86.40%). In the comparison set, the AUC was similar to that of the expert (p = 0.5629) and one experienced radiologist (p = 0.2112) and significantly higher than that of three inexperienced radiologists (p < 0.01). After model assistance, the accuracies and specificities of the radiologists were substantially improved without loss in sensitivities. CONCLUSIONS: The DL model yielded satisfactory predictions in distinguishing benign from malignant breast lesions. The model showed the potential value in improving the diagnosis of breast lesions by radiologists.

A Multi-Scale Densely Connected Convolutional Neural Network for Automated Thyroid Nodule Classification.

Automated thyroid nodule classification in ultrasound images is an important way to detect thyroid nodules and to make a more accurate diagnosis. In this paper, we propose a novel deep convolutional neural network (CNN) model, called n-ClsNet, for thyroid nodule classification. Our model consists of a multi-scale classification layer, multiple skip blocks, and a hybrid atrous convolution (HAC) block. The multi-scale classification layer first obtains multi-scale feature maps in order to make full use of image features. After that, each skip-block propagates information at different scales to learn multi-scale features for image classification. Finally, the HAC block is used to replace the downpooling layer so that the spatial information can be fully learned. We have evaluated our n-ClsNet model on the TNUI-2021 dataset. The proposed n-ClsNet achieves an average accuracy (ACC) score of 93.8% in the thyroid nodule classification task, which outperforms several representative state-of-the-art classification methods.

The Ultrasonographic Characteristics of Focal Fibrocystic Change of the Breast and Analysis of Misdiagnosis.

INTRODUCTION: To investigate ultrasonographic features and analyze causes of misdiagnosis of focal fibrocystic change (FC) of the breast. MATERIALS AND METHODS: The ultrasonographic features of 95 women (104 lesions) with postoperatively pathologically confirmed focal FC (Group 1) were retrospectively analyzed and compared with those of 105 women (107 lesions) with ductal carcinoma in situ (DCIS) (Group 2), and 164 women (177 lesions) with invasive ductal carcinoma (IDC) (Group 3). RESULTS: There were significant differences in 12 features among groups. The sizes and distributions of cystic changes among the groups were significantly different. In group 1, the incidence of cystic changes was 75%(78/104), and the main manifestation was scattered cystic changes (88.5%, 69/78) and microcapsules (81.8%, 63/78). Among focal FC lesions, 36.5% were preoperative BI-RADS classifications 4b-5 (30.8% 4b and 4c). Lesions misdiagnosed as malignant showed solid or cystic solid mixed echoes, and 70.2% of group 1 were irregularly shaped, and 63.5% had unclear edges. In group 1, 5 cases had "hyperechoic halo," 11.5% (12/104) appeared echo attenuation behind the mass, and 21 cases appeared punctate hyperechoic. CONCLUSION: FC frequently exhibits low heterogeneity, scattered microcapsules with posterior enhancement, "pit-like" or "grid-like" changes, posterior enhancement, rare hyperechoic halo, calcification, and lack of blood supply. Certain focal FC are irregularly shaped with unclear edges, with malignant signs such as crab feet and burr, hyperechoic halo, and calcification, which ultrasound BI-RADS classification may easily misdiagnose as malignant. Local magnification function should be considered, and the internal structure should be carefully observed to prevent misdiagnosis.