Photoacoustic Imaging Radiomics to Identify Breast Cancer in BI-RADS 4 or 5 Lesions.

OBJECTIVES: To develop a nomogram based on photoacoustic imaging (PAI) radiomics and BI-RADs to identify breast cancer (BC) in BI-RADS 4 or 5 lesions detected by ultrasound (US). METHODS: In this retrospective study, 119 females with 119 breast lesions at US and PAI examination were included (January 2022 to December 2022). Patients were divided into the training set (n = 83) or testing set (n = 36) to develop a nomogram to identify BC in BI-RADS 4 or 5 lesions. Relevant factors at clinic, BI-RADS category, and PAI were reviewed. Univariate and multivariate regression was used to evaluate factors for associations with BC. To evaluate the diagnostic performance of nomogram, the area under the curve (AUC) of receiver operating characteristic curve, accuracy, specificity and sensitivity was employed. RESULTS: The nomogram that included BI-RADS category and PAI radiomics score demonstrated a high AUC of 0.925 (95%CI: 0.8467-0.9712) in the training set and 0.926 (95%CI: 0.846-1.000) in the test set. The nomogram also showed significantly better discrimination than the radiomics score (P = .048) or BI-RADS category (P = .009) in the training set. These significant differences were demonstrated in the testing set, outperform the radiomics score (P = .038) and BI-RADS category (P = .013). CONCLUSIONS: The nomogram developed with BI-RADS and PAI radiomics score can effectively identify BC in BI-RADS 4 or 5 lesions. This technique has the potential to further improve early diagnostic accuracy for BC.

Diagnostic Performance of Deep Learning in Video-Based Ultrasonography for Breast Cancer: A Retrospective Multicentre Study.

OBJECTIVE: Although ultrasound is a common tool for breast cancer screening, its accuracy is often operator-dependent. In this study, we proposed a new automated deep-learning framework that extracts video-based ultrasound data for breast cancer screening. METHODS: Our framework incorporates DenseNet121, MobileNet, and Xception as backbones for both video- and image-based models. We used data from 3907 patients to train and evaluate the models, which were tested using video- and image-based methods, as well as reader studies with human experts. RESULTS: This study evaluated 3907 female patients aged 22 to 86 years. The results indicated that the MobileNet video model achieved an AUROC of 0.961 in prospective data testing, surpassing the DenseNet121 video model. In real-world data testing, it demonstrated an accuracy of 92.59%, outperforming both the DenseNet121 and Xception video models, and exceeding the 76.00% to 85.60% accuracy range of human experts. Additionally, the MobileNet video model exceeded the performance of image models and other video models across all evaluation metrics, including accuracy, sensitivity, specificity, F1 score, and AUC. Its exceptional performance, particularly suitable for resource-limited clinical settings, demonstrates its potential for clinical application in breast cancer screening. CONCLUSIONS: The level of expertise reached by the video models was greater than that achieved by image-based models. We have developed an artificial intelligence framework based on videos that may be able to aid breast cancer diagnosis and alleviate the shortage of experienced experts.

Assessment of Oxygen Saturation in Breast Lesions Using Photoacoustic Imaging: Correlation With Benign and Malignant Disease.

BACKGROUND: Hypoxia is a hallmark of breast cancer (BC). Photoacoustic (PA) imaging, based on the use of laser-generated ultrasound (US), can detect oxygen saturation (So2) in the tissues of breast lesion patients. PURPOSE: To measure the oxygenation status of tissue in and on both sides of the lesion in breast lesion participants using a multimodal Photoacoustic/ultrasound (PA/US) imaging system and to determine the correlation between So2 measured by PA imaging and benign or malignant disease. MATERIALS AND METHODS: Multimodal PA/US imaging and gray-scale US (GSUS) of breast lesion was performed in consecutive breast lesion participants imaged in the US Outpatient Clinic between 2022 and 2023. Dual-wavelength PA imaging was used to measure the So2 value inside the lesion and on both sides of the tissue, and to distinguish benign from malignant lesions based on the So2 value. The ability of So2 to distinguish benign from malignant breast lesions was evaluated by the receiver operating characteristic curve (ROC) and the De-Long test. RESULTS: A total of 120 breast lesion participants (median age, 42.5 years) were included in the study. The malignant lesions exhibited lower So2 levels compared to benign lesions (malignant: 71.30%; benign: 83.81%; P < .01). Moreover, PA/US imaging demonstrates superior diagnostic results compared to GSUS, with an area under the curve (AUC) of 0.89 versus 0.70, sensitivity of 89.58% versus 85.42%, and specificity of 86.11% versus 55.56% at the So2 cut-off value of 78.85 (P < .001). The false positive rate in GSUS reduced by 30.75%, and the false negative rate diminished by 4.16% with PA /US diagnosis. Finally, the So2 on both sides tissues of malignant lesions are lower than that of benign lesions (P < .01). CONCLUSION: PA imaging allows for the assessment of So2 within the lesions of breast lesion patients, thereby facilitating a superior distinction between benign and malignant lesions.

Sonography-based multimodal information platform for identifying the surgical pathology of ductal carcinoma in situ.

BACKGROUND: The risk of ductal carcinoma in situ (DCIS) identified by biopsy often increases during surgery. Therefore, confirming the DCIS grade preoperatively is necessary for clinical decision-making. PURPOSE: To train a three-classification deep learning (DL) model based on ultrasound (US), combining clinical data, mammography (MG), US, and core needle biopsy (CNB) pathology to predict low-grade DCIS, intermediate-to-high-grade DCIS, and upstaged DCIS. MATERIALS AND METHODS: Data of 733 patients with 754 DCIS cases confirmed by biopsy were retrospectively collected from May 2013 to June 2022 (N1), and other data (N2) were confirmed by biopsy as low-grade DCIS. The lesions were randomly divided into training (n=471), validation (n=142), and test (n = 141) sets to establish the DCIS-Net. Information on the DCIS-Net, clinical (age and sign), US (size, calcifications, type, breast imaging reporting and data system [BI-RADS]), MG (microcalcifications, BI-RADS), and CNB pathology (nuclear grade, architectural features, and immunohistochemistry) were collected. Logistic regression and random forest analyses were conducted to develop Multimodal DCIS-Net to calculate the specificity, sensitivity, accuracy, receiver operating characteristic curve, and area under the curve (AUC). RESULTS: In the test set of N1, the accuracy and AUC of the multimodal DCIS-Net were 0.752-0.766 and 0.859-0.907 in the three-classification task, respectively. The accuracy and AUC for discriminating DCIS from upstaged DCIS were 0.751-0.780 and 0.829-0.861, respectively. In the test set of N2, the accuracy and AUC of discriminating low-grade DCIS from upstaged low-grade DCIS were 0.769-0.987 and 0.818-0.939, respectively. DL was ranked from one to five in the importance of features in the multimodal-DCIS-Net. CONCLUSION: By developing the DCIS-Net and integrating it with multimodal information, diagnosing low-grade DCIS, intermediate-to high-grade DCIS, and upstaged DCIS is possible. It can also be used to distinguish DCIS from upstaged DCIS and low-grade DCIS from upstaged low-grade DCIS, which could pave the way for the DCIS clinical workflow.

Development and validation of nomograms using photoacoustic imaging and 2D ultrasound to predict breast nodule benignity and malignancy.

BACKGROUND: The application of photoacoustic imaging (PAI), utilizing laser-induced ultrasound, shows potential in assessing blood oxygenation in breast nodules. However, its effectiveness in distinguishing between malignant and benign nodules remains insufficiently explored. PURPOSE: This study aims to develop nomogram models for predicting the benign or malignant nature of breast nodules using PAI. METHOD: A prospective cohort study enrolled 369 breast nodules, subjecting them to PAI and ultrasound examination. The training and testing cohorts were randomly divided into two cohorts in a ratio of 3:1. Based on the source of the variables, three models were developed, Model 1: photoacoustic-BIRADS+BMI + blood oxygenation, Model 2: BIRADS+Shape+Intranodal blood (Doppler) + BMI, Model 3: photoacoustic-BIRADS+BIRADS+ Shape+Intranodal blood (Doppler) + BMI + blood oxygenation. Risk factors were identified through logistic regression, resulting in the creation of three predictive models. These models were evaluated using calibration curves, subject receiver operating characteristic (ROC), and decision curve analysis. RESULTS: The area under the ROC curve for the training cohort was 0.91 (95% confidence interval, 95% CI: 0.88-0.95), 0.92 (95% CI: 0.89-0.95), and 0.97 (95% CI: 0.96-0.99) for Models 1-3, and the ROC curve for the testing cohort was 0.95 (95% CI: 0.91-0.98), 0.89 (95% CI: 0.83-0.96), and 0.97 (95% CI: 0.95-0.99) for Models 1-3. CONCLUSIONS: The calibration curves demonstrate that the model's predictions agree with the actual values. Decision curve analysis suggests a good clinical application.

A validation of an entropy-based artificial intelligence for ultrasound data in breast tumors.

BACKGROUND: The application of artificial intelligence (AI) in the ultrasound (US) diagnosis of breast cancer (BCa) is increasingly prevalent. However, the impact of US-probe frequencies on the diagnostic efficacy of AI models has not been clearly established. OBJECTIVES: To explore the impact of using US-video of variable frequencies on the diagnostic efficacy of AI in breast US screening. METHODS: This study utilized different frequency US-probes (L14: frequency range: 3.0-14.0 MHz, central frequency 9 MHz, L9: frequency range: 2.5-9.0 MHz, central frequency 6.5 MHz and L13: frequency range: 3.6-13.5 MHz, central frequency 8 MHz, L7: frequency range: 3-7 MHz, central frequency 4.0 MHz, linear arrays) to collect breast-video and applied an entropy-based deep learning approach for evaluation. We analyzed the average two-dimensional image entropy (2-DIE) of these videos and the performance of AI models in processing videos from these different frequencies to assess how probe frequency affects AI diagnostic performance. RESULTS: The study found that in testing set 1, L9 was higher than L14 in average 2-DIE; in testing set 2, L13 was higher in average 2-DIE than L7. The diagnostic efficacy of US-data, utilized in AI model analysis, varied across different frequencies (AUC: L9 > L14: 0.849 vs. 0.784; L13 > L7: 0.920 vs. 0.887). CONCLUSION: This study indicate that US-data acquired using probes with varying frequencies exhibit diverse average 2-DIE values, and datasets characterized by higher average 2-DIE demonstrate enhanced diagnostic outcomes in AI-driven BCa diagnosis. Unlike other studies, our research emphasizes the importance of US-probe frequency selection on AI model diagnostic performance, rather than focusing solely on the AI algorithms themselves. These insights offer a new perspective for early BCa screening and diagnosis and are of significant for future choices of US equipment and optimization of AI algorithms.

The research on artificial intelligence-assisted breast diagnosis often relies on static images or dynamic videos obtained from ultrasound probes with different frequencies. However, the effect of frequency-induced image variations on the diagnostic performance of artificial intelligence models remains unclear. In this study, we aimed to explore the impact of using ultrasound images with variable frequencies on AI's diagnostic efficacy in breast ultrasound screening. Our approach involved employing a video and entropy-based feature breast network to compare the diagnostic efficiency and average two-dimensional image entropy of the L14 (frequency range: 3.0-14.0 MHz, central frequency 9 MHz), L9 (frequency range: 2.5-9.0 MHz, central frequency 6.5 MHz) linear array probe and L13 (frequency range: 3.6-13.5 MHz, central frequency 8 MHz), and L7 (frequency range: 3-7 MHz, central frequency 4.0 MHz) linear array probes. The results revealed that the diagnostic efficiency of AI models differed based on the frequency of the ultrasound probe. It is noteworthy that ultrasound images acquired with different frequency probes exhibit different average two-dimensional image entropy, while higher average two-dimensional image entropy positively affect the diagnostic performance of the AI model. We concluded that a dataset with higher average two-dimensional image entropy is associated with superior diagnostic efficacy for AI-based breast diagnosis. These findings contribute to a better understanding of how ultrasound image variations impact AI-assisted breast diagnosis, potentially leading to improved breast cancer screening outcomes.

An artificial intelligence model based on transrectal ultrasound images of biopsy needle tract tissues to differentiate prostate cancer.

PURPOSE: We aimed to develop an artificial intelligence (AI) model based on transrectal ultrasonography (TRUS) images of biopsy needle tract (BNT) tissues for predicting prostate cancer (PCa) and to compare the PCa diagnostic performance of the radiologist model and clinical model. METHODS: A total of 1696 2D prostate TRUS images were involved from 142 patients between July 2021 and May 2022. The ResNet50 network model was utilized to train classification models with different input methods: original image (Whole model), BNT (Needle model), and combined image [Feature Pyramid Networks (FPN) model]. The training set, validation set, and test set were randomly assigned, then randomized 5-fold cross-validation between the training set and validation set was performed. The diagnostic effectiveness of AI models and image combination was accessed by an independent testing set. Then, the optimal AI model and image combination were selected to compare the diagnostic efficacy with that of senior radiologists and the clinical model. RESULTS: In the test set, the area under the curve, specificity, and sensitivity of the FPN model were 0.934, 0.966, and 0.829, respectively; the diagnostic efficacy was improved compared with the Whole and Needle models, with statistically significant differences (P < 0.05), and was better than that of senior radiologists (area under the curve: 0.667). The FPN model detected more PCa compared with senior physicians (82.9% vs. 55.8%), with a 61.3% decrease in the false-positive rate and a 23.2% increase in overall accuracy (0.887 vs. 0.655). CONCLUSION: The proposed FPN model can offer a new method for prostate tissue classification, improve the diagnostic performance, and may be a helpful tool to guide prostate biopsy.

The effect of image resolution on convolutional neural networks in breast ultrasound.

Purpose: The objective of this research was to investigate the efficacy of various parameter combinations of Convolutional Neural Networks (CNNs) models, namely MobileNet and DenseNet121, and different input image resolutions (REZs) ranging from 64×64 to 512×512 pixels, for diagnosing breast cancer. Materials and methods: During the period of June 2015 to November 2020, two hospitals were involved in the collection of two-dimensional ultrasound breast images for this retrospective multicenter study. The diagnostic performance of the computer models MobileNet and DenseNet 121 was compared at different resolutions. Results: The results showed that MobileNet had the best breast cancer diagnosis performance at 320×320pixel REZ and DenseNet121 had the best breast cancer diagnosis performance at 448×448pixel REZ. Conclusion: Our study reveals a significant correlation between image resolution and breast cancer diagnosis accuracy. Through the comparison of MobileNet and DenseNet121, it is highlighted that lightweight neural networks (LW-CNNs) can achieve model performance similar to or even slightly better than large neural networks models (HW-CNNs) in ultrasound images, and LW-CNNs' prediction time per image is lower.

Artificial intelligence for non-mass breast lesions detection and classification on ultrasound images: a comparative study.

BACKGROUND: This retrospective study aims to validate the effectiveness of artificial intelligence (AI) to detect and classify non-mass breast lesions (NMLs) on ultrasound (US) images. METHODS: A total of 228 patients with NMLs and 596 volunteers without breast lesions on US images were enrolled in the study from January 2020 to December 2022. The pathological results served as the gold standard for NMLs. Two AI models were developed to accurately detect and classify NMLs on US images, including DenseNet121_448 and MobileNet_448. To evaluate and compare the diagnostic performance of AI models, the area under the curve (AUC), accuracy, specificity and sensitivity was employed. RESULTS: A total of 228 NMLs patients confirmed by postoperative pathology with 870 US images and 596 volunteers with 1003 US images were enrolled. In the detection experiment, the MobileNet_448 achieved the good performance in the testing set, with the AUC, accuracy, sensitivity, and specificity were 0.999 (95%CI: 0.997-1.000),96.5%,96.9% and 96.1%, respectively. It was no statistically significant compared to DenseNet121_448. In the classification experiment, the MobileNet_448 model achieved the highest diagnostic performance in the testing set, with the AUC, accuracy, sensitivity, and specificity were 0.837 (95%CI: 0.990-1.000), 70.5%, 80.3% and 74.6%, respectively. CONCLUSIONS: This study suggests that the AI models, particularly MobileNet_448, can effectively detect and classify NMLs in US images. This technique has the potential to improve early diagnostic accuracy for NMLs.

Knockdown of TXNDC5 alleviates CCL4-induced hepatic fibrosis in mice by enhancing endoplasmic reticulum stress.

BACKGROUND: Hepatic fibrosis is a common pathological process in many chronic liver diseases. TXNDC5 has been shown to be involved in the progression of renal and pulmonary fibrosis. However, the role of TXNDC5 in hepatic fibrosis is unknown. The purpose of this study is to explore the role and mechanism of TXNDC5 in hepatic fibrosis. METHODS: We used TGF-ß1 to activate LX-2 cells and reduced TXNDC5 expression by short hairpin RNA. Cell viability was assessed by CCK-8 assay. Cell apoptosis was analyzed by flow cytometry or Tunel assay. The fibrosis-related proteins and endoplasmic reticulum stress (ERs)-related proteins were measured by western blot. ELISA was performed to detect COL1AL levels and MMP2/9 activities in cell medium. A mouse model of hepatic fibrosis was constructed by intraperitoneal injection of CCL4. HE and Masson staining were performed to assess fibrosis in mouse liver tissue. RESULTS: The results show that TXNDC5 was up-regulated in activated LX-2 cells and CCL4-induced hepatic fibrosis mice. Knockdown of TXNDC5 inhibited the viability of activated LX-2 cells and the production of collagen COL1A1. Knockdown of TXNDC5 promoted apoptosis of activated LX-2 cells. Mechanically, inhibition of TXNDC5 enhanced ERs, and the ERs inhibitor 4-Phenylbutyric acid (4-PBA) reversed the effect of TXNDC5 on activated LX-2 cells. More importantly, knockdown of TXNDC5 alleviated CCl4-induced hepatic fibrosis in mice. CONCLUSIONS: Knockdown of TXNDC5 may reduce hepatic fibrosis by regulating ERs, and targeting TXNDC5 seems to be a candidate treatment for hepatic fibrosis.

A new xAI framework with feature explainability for tumors decision-making in Ultrasound data: comparing with Grad-CAM.

BACKGROUND AND OBJECTIVE: The value of implementing artificial intelligence (AI) on ultrasound screening for thyroid cancer has been acknowledged, with numerous early studies confirming AI might help physicians acquire more accurate diagnoses. However, the black box nature of AI's decision-making process makes it difficult for users to grasp the foundation of AI's predictions. Furthermore, explainability is not only related to AI performance, but also responsibility and risk in medical diagnosis. In this paper, we offer Explainer, an intrinsically explainable framework that can categorize images and create heatmaps highlighting the regions on which its prediction is based. METHODS: A dataset of 19341 thyroid ultrasound images with pathological results and physician-annotated TI-RADS features is used to train and test the robustness of the proposed framework. Then we conducted a benign-malignant classification study to determine whether physicians perform better with the assistance of an explainer than they do alone or with Gradient-weighted Class Activation Mapping (Grad-CAM). RESULTS: Reader studies show that the Explainer can achieve a more accurate diagnosis while explaining heatmaps, and that physicians' performances are improved when assisted by the Explainer. Case study results confirm that the Explainer is capable of locating more reasonable and feature-related regions than the Grad-CAM. CONCLUSIONS: The Explainer offers physicians a tool to understand the basis of AI predictions and evaluate their reliability, which has the potential to unbox the "black box" of medical imaging AI.

Development and validation of a nomogram for discriminating between benign and malignant breast masses by conventional ultrasound and dual-mode elastography: a multicenter study.

Background: This study developed and validated an ultrasound nomogram based on conventional ultrasound and dual-mode elastography to differentiate breast masses. Methods: The data of 234 patients were collected before they underwent breast mass puncture or surgery at 4 different centers between 2016 and 2021. Patients were divided into 5 datasets: internal validation and development sets from the same hospital, and external validation sets from the 3 other hospitals. In the development cohort, age and 294 different ultrasound and elastography features were obtained from ultrasound images. Univariate logistic regression and least absolute shrinkage and selection operator (LASSO) regression were used for data reduction and visualization. Multivariable logistic regression analysis was used to develop the prediction model and ultrasound nomogram. Receiver operating characteristic (ROC) curve analysis, calibration curves, integrated discrimination improvement, and the net reclassification index were used to evaluate nomogram performance; decision curve analysis (DCA) and clinical impact curves were used to estimate clinical usefulness. Results: In the development cohort, margin, posterior features, shape, vascularity, (the mean shear wave elastography value of 1.5 mm surrounding tissues in a breast mass) divided by (the mean shear wave elastography value of the breast mass)-shell mean/A mean1.5(E), (the ratio of strain elastography of adipose tissue near a breast mass) divided by [the ratio of strain elastography of (the breast mass adds the 1.5 mm surrounding tissues in the breast mass)]-B/A'1.5 were selected as predictors in multivariable logistic regression analysis, comprising Model 1. Among the 5 cohorts, Model 1 performed best, with areas under the curve (AUC) of 0.92, 0.84, 0.87, 0.93, and 0.89, respectively. The AUCs were 0.90, 0.82, 0.83, 0.91, and 0.85, respectively, in Model 2 (margin + posterior features + shape + vascularity) and 0.80, 0.76, 0.77, 0.87, and 0.80, respectively, in Model 3 [shell mean/A mean1.5(E) + B/A'1.5]. Conclusions: Our ultrasound nomograms facilitate exposure to the features and visualization of breast cancer. Shell mean/A mean1.5(E), B/A'1.5 integrated with margin, posterior features, shape, and vascularity are superior at identifying breast cancer, and are worthy of further clinical investigation.

Feasibility of using AI to auto-catch responsible frames in ultrasound screening for breast cancer diagnosis.

The research of AI-assisted breast diagnosis has primarily been based on static images. It is unclear whether it represents the best diagnosis image.To explore the method of capturing complementary responsible frames from breast ultrasound screening by using artificial intelligence. We used feature entropy breast network (FEBrNet) to select responsible frames from breast ultrasound screenings and compared the diagnostic performance of AI models based on FEBrNet-recommended frames, physician-selected frames, 5-frame interval-selected frames, all frames of video, as well as that of ultrasound and mammography specialists. The AUROC of AI model based on FEBrNet-recommended frames outperformed other frame set based AI models, as well as ultrasound and mammography physicians, indicating that FEBrNet can reach level of medical specialists in frame selection.FEBrNet model can extract video responsible frames for breast nodule diagnosis, whose performance is equivalent to the doctors selected responsible frames.

A Comparative Study of Multiple Deep Learning Models Based on Multi-Input Resolution for Breast Ultrasound Images.

Purpose: The purpose of this study was to explore the performance of different parameter combinations of deep learning (DL) models (Xception, DenseNet121, MobileNet, ResNet50 and EfficientNetB0) and input image resolutions (REZs) (224 × 224, 320 × 320 and 488 × 488 pixels) for breast cancer diagnosis. Methods: This multicenter study retrospectively studied gray-scale ultrasound breast images enrolled from two Chinese hospitals. The data are divided into training, validation, internal testing and external testing set. Three-hundreds images were randomly selected for the physician-AI comparison. The Wilcoxon test was used to compare the diagnose error of physicians and models under P=0.05 and 0.10 significance level. The specificity, sensitivity, accuracy, area under the curve (AUC) were used as primary evaluation metrics. Results: A total of 13,684 images of 3447 female patients are finally included. In external test the 224 and 320 REZ achieve the best performance in MobileNet and EfficientNetB0 respectively (AUC: 0.893 and 0.907). Meanwhile, 448 REZ achieve the best performance in Xception, DenseNet121 and ResNet50 (AUC: 0.900, 0.883 and 0.871 respectively). In physician-AI test set, the 320 REZ for EfficientNetB0 (AUC: 0.896, P < 0.1) is better than senior physicians. Besides, the 224 REZ for MobileNet (AUC: 0.878, P < 0.1), 448 REZ for Xception (AUC: 0.895, P < 0.1) are better than junior physicians. While the 448 REZ for DenseNet121 (AUC: 0.880, P < 0.05) and ResNet50 (AUC: 0.838, P < 0.05) are only better than entry physicians. Conclusion: Based on the gray-scale ultrasound breast images, we obtained the best DL combination which was better than the physicians.

Assessment of elastographic Q-analysis score combined with Prostate Imaging-Reporting and Data System (PI-RADS) based on transrectal ultrasound (TRUS)/multi-parameter magnetic resonance imaging (MP-MRI) fusion-guided biopsy in differentiating benign and malignant prostate.

Background: Magnetic resonance imaging (MRI) has advantages in the diagnosis of prostate diseases, but there is also overdiagnosis. We compensate for this with fusion imaging and elastography. In this study, we want to evaluate Elastographic Q-analysis score (EQS) combined with Prostate Imaging Reporting and Data System (PI-RADS), based on transrectal ultrasound (TRUS)/multi-parameter magnetic resonance imaging (MP-MRI) fusion biopsy in differentiating benign and malignant prostate lesions. Methods: A total of 296 patients with 318 prostate lesions who underwent TRUS/MP-MRI fusion biopsy between October 2017 and October 2019 were retrospectively analysed. The performance of the EQS was evaluated on the sites of the suspicious areas of MP-MRI. The cut-off value of EQS was obtained according to receiver operating characteristic (ROC) curve, which was used to upgrade and downgrade the PI-RADS scores. The area under the curve (AUC), integrated discrimination improvement, and decision curve analysis were used to assess the new PI-RADS performance. Results: In total, 318 MP-MRI suspicious prostate lesions (94 malignant vs. 224 benign lesions). The EQS optimal threshold was 1.85, and the AUC was 0.816. All cases were constructed three models by using 1.85 as the cut-off value: upgrade-PI-RADS, downgrade-PI-RADS and complex-PI-RADS. The AUC of PI-RADS, upgrade-PI-RADS, downgrade-PI-RADS and complex-PI-RADS were 0.869, 0.867, 0.872 and 0.873 respectively. The diagnostic coincidence rate of PI-RADS was increased from 0.667 to 0.874 by using strain elastography, among which the diagnostic rate of prostate cancer was increased from 0.557 to 0.806, and the diagnostic rate of non-prostate cancer was increased from 0.775 to 0.967. The integrated discrimination improvement indicated that downgrade-PI-RADS had a better diagnostic capability (P<0.05). The net benefit of all models, which downgrade-PI-RADS can maximize the net benefit value of patients by decision curve analysis. Conclusions: The combination of PI-RADS and EQS with TRUS/MP-MRI fusion, particularly downgrade-PI-RADS, can reduce unnecessary biopsy procedures and prevent overdiagnosis.

S-Thyroid Computer-Aided Diagnosis Ultrasound System of Thyroid Nodules: Correlation Between Transverse and Longitudinal Planes.

Introduction: We compare the differences in the diagnostic results of S-thyroid, a computer-aided diagnosis (CAD) software, based on two mutually perpendicular planes. Methods: Initially, 149 thyroid nodules confirmed by surgical pathology were enrolled in our study. CAD in our study was based on the ACR TI-RADS lexicon. t test, rank-sum test, and Chi-square test were used. The interclass correlation coefficient and Cohen's kappa were used to explore the correlation between CAD features. Receiver operating characteristic was plotted for different combinations of CAD features. Results: The patient's age, transverse diameter, longitudinal diameter, shape, margin, echogenicity, echogenic foci, composition, TI-RADS classification, and risk probability of nodules in the transverse and longitudinal planes were related to thyroid cancer (p < 0.05). The AUC (95%CI) of TI-RADS classification in the transverse plane of CAD is better than that of the longitudinal plane [0.90 (0.84-0.95) vs. 0.83 (0.77-0.90), p = 0.04]. The AUC (95%CI) of risk probability of nodules in the transverse planes shows no difference from that in the longitudinal plane statistically [0.90 (0.85-0.95) vs. 0.88 (0.82-0.94), p = 0.52]. The AUC (95% CI), specificity, sensitivity, and accuracy [TI-RADS classification (transverse plane) + TI-RADS classification (longitudinal plane) + risk (transverse plane) + risk (longitudinal plane)] are 0.93 (0.89-0.97), 86.15%, 90.48%, and 88.59%, respectively. Conclusion: The diagnosis of thyroid cancer in the CAD transverse plane was superior to that in the CAD longitudinal plane when using the TI-RADS classification, but there was no difference in the diagnosis between the two planes when using risk. However, the combination of CAD transverse and longitudinal planes had the best diagnostic ability.

Knockdown of ARL5B Induces Mitochondrial-mediated Apoptosis and Inhibits Glycolysis in Breast Cancer Cells by Activating MDA5 Signaling.

AIM: Mitochondria are essential for energy metabolism in the tumor microenvironment and the survival of cancer cells. BACKGROUND: ADP-ribosylation factor-like GTPase 5b (ARL5B) has been found to be associated with mitochondrial dysfunction and breast cancer (BC) progression, but the underlying mechanism needs to be further understood. OBJECTIVE: We investigated the effects of ARL5B on the apoptosis and glycolysis of breast cancer cells and its underlying mechanisms. METHODS: Quantitative reverse transcription-PCR (qRT-PCR) and western blot assays were used to detect the expression of ARL5B in breast cancer tissues and cells. An ARL5B loss-of-function assay was performed to verify its role in BC development. RESULTS: ARL5B was upregulated in breast cancer tissues and cell lines. ARL5B knockdown induced apoptosis and activated the mitochondrial pathway in breast cancer cells. Interestingly, the inhibition of ARL5B repressed the aerobic glycolysis of breast cancer cells. The role of ARL5B in breast cancer cells was exerted by mediating the activation of viral RNA sensor MDA5-evoked signaling. Silencing ARL5B triggered MDA5 signaling by upregulating the key proteins involved in the MDA5 pathway. Importantly, MDA5 silencing reversed the effects of ARL5B knockdown on mitochondrial-mediated apoptosis and glycolysis, whereas poly (I:C), as a ligand for MDA5, further enhanced ARL5B knockdown- facilitated mitochondrial apoptosis and the inhibition of glycolysis. CONCLUSION: The knockdown of ARL5B activated MDA5 signaling and thus led to the enhanced mitochondrial- mediated apoptosis and glycolysis inhibition in breast cancer cells. Our study suggested that ARL5B might be a potential therapy target for BC.

The significance of dual-mode elastography in the diagnosis of breast lesions by physicians with different levels of experience.

BACKGROUND: This study aimed to assess the diagnostic value of dual-mode elastography for benign and malignant breast lesions and determine whether this technique can improve the diagnostic ability of physicians with different levels of experience. METHODS: One hundred and eighty-three breast lesions were analyzed retrospectively, and the following values were calculated for the lesions with various shells: shear modulus (G), Young's modulus (E), shear wave velocity (Cs), and strain ratio (SR). A random forest algorithm was used to select the optimal modes for elastography. A receiver operating characteristic curve was used to assess the diagnostic efficacy for benign and malignant breast lesions. Sensitivity and specificity values were calculated to evaluate any improvements in the diagnostic efficacy of physicians with different levels of experience (junior, intermediate-level, and senior) in the evaluation of malignant breast lesions using dual-mode elastography. RESULTS: The best-performing mode of shear wave elastography (SWE) in the diagnosis of breast lesions was the A'min 1.0 (Cs) mode (minimum shear wave velocity of the area of interest and 1.0 mm around the area of interest), and the best-performing mode of strain elastography (SE) was the B/A' 0.5 (ratio of fat to the elasticity of the area of interest and 0.5 mm around the area of interest). When the two methods were used in series, results showed high specificity (98%), positive likelihood ratio (PLR) (21.2), and positive predictive value (PPV) (95%). Series means that if SE and SWE were malignant, the result in series was malignant, and that if either SE or SWE was benign, the result in series was benign. When the methods were used in parallel, the results showed high sensitivity (91%), negative likelihood ratio (NLR) (0.15), and negative predictive value (NPV) (89%). Parallel means that if SE and SWE were benign, the result in parallel was benign, and that if either SE or SWE was malignant, the result in parallel was malignant. When conventional ultrasound was combined with dual-mode elastography, the intermediate-level and junior physicians' diagnoses of breast lesions showed a higher sensitivity, specificity, and area under the curve than conventional ultrasound diagnosis alone. CONCLUSIONS: Dual-mode elastography is effective in the diagnosis of breast lesions. The sensitivity and specificity values in this study show that diagnoses made by junior and intermediate-level physicians improve when dual-mode elastography is used, although diagnoses made by senior physicians do not improve significantly.

Development and validation of a nomogram based on multiparametric magnetic resonance imaging and elastography-derived data for the stratification of patients with prostate cancer.

BACKGROUND: This study sought to develop and validate a nomogram combining the elastographic Q-analysis score (EQS), the Prostate Imaging Reporting and Data System (PI-RADS) score, and clinical parameters for the stratification of patients with prostate cancer (PCa). METHODS: A retrospective study was conducted of 375 patients with 375 lesions who underwent volume-navigation transrectal ultrasound (TRUS) and multiparametric magnetic resonance imaging (MP-MRI)-fusion targeted biopsies between April 2017 and January 2020. Based on a multivariate logistic regression model, a nomogram was created to assess any PCa and high-risk PCa [Gleason score (GS) ≥4+3] using data from patients diagnosed between April 2017 and June 2019 (n=271), and was validated in patients diagnosed after July 2019 (n=104). The nomogram's performance was evaluated based on its discrimination, calibration, and clinical usefulness. RESULTS: The areas under the curve (AUCs) of the nomogram for predicting any PCa and high-risk PCa were 0.949 [95% confidence interval (CI), 0.921 to 0.978] and 0.936 (95% CI, 0.906 to 0.965), respectively, in the training cohort, and 0.946 (95% CI, 0.894 to 0.997) and 0.971 (95% CI, 0.9331 to 1), respectively, in the validation cohort. The nomogram was well calibrated, and no significant difference was found between the predicted and observed probabilities. A decision curve analysis (DCA) for the nomogram with and without the EQS showed that the threshold probability of for any PCa was <67%. CONCLUSIONS: The nomogram that combined elastography-derived and MP-MRI data was more clinically useful than the model based on PI-RADS and clinical parameters alone. Our nomogram could aid urologists to make decisions and avoid unnecessary biopsies.

Development and validation of a nomogram for predicting prostate cancer in men with prostate-specific antigen grey zone based on retrospective analysis of clinical and multi-parameter magnetic resonance imaging/transrectal ultrasound fusion-derived data.

BACKGROUND: Urologists face a dilemma when deciding whether prostate biopsy is required for patients with prostate-specific antigen (PSA) levels in the grey zone (4 to 10 ng/mL). METHODS: We retrospectively analyzed data from consecutive patients with PSA levels in grey zone, who underwent targeted multiparametric magnetic resonance imaging (MP-MRI)/transrectal ultrasound (TRUS) fusion biopsy with elastography between November 2017 and December 2019 in our hospital. The patientse data including age, PSA, fPSA (free PSA), fPSA/PSA, PSA density (PSAD), prostate volume, elastography Q-analysis score (EQS), and prostate imaging-reporting and data system (PI-RADS) score were collected. The nomogram was built using logistic regression and the final cohort of patients was randomly divided into a training cohort (70%) and a validation cohort (30%) by R software. The models were evaluated by receiver operating characteristic curve (ROC) analysis and calibration curve analysis. The nomogram was constructed from the best model. RESULTS: The final study cohort consisted of 155 patients (training cohort, 109 patients; validation cohort, 46 patients) with PSA in the grey zone, of which 36 patients were pathologically diagnosed with PCa. The EQS model, -EQS model, +EQS model were built. The +EQS model that consisted of fPSA/PSA, EQS, and PI-RADS score had the best PCa diagnostic accuracy (development and validation, 0.783 and 0.781) and probability score (development and validation, 0.939 vs. 0.622). The new nomogram based on this model was constructed, in which fPSA/PSA ratio had the largest impact, followed by PI-RADS and EQS. CONCLUSIONS: Elastography and pre-biopsy MP-MRI has clinical significance for patients with PSA in the grey zone. The new nomogram, which is based on pre biopsy data including serological analysis, PI-RADS score, and EQS, can be helpful for clinical decision-making to avoid unnecessary biopsy.