A nomogram based on conventional and contrast-enhanced ultrasound radiomics for the noninvasively prediction of axillary lymph node metastasis in breast cancer patients.

Background: This study aimed to investigate whether quantitative radiomics features extracted from conventional ultrasound (CUS) and contrast-enhanced ultrasound (CEUS) of primary breast lesions can help noninvasively predict axillary lymph nodes metastasis (ALNM) in breast cancer patients. Method: A total of 111 breast cancer patients with 111 breast lesions were prospectively enrolled. All the included patients received presurgical CUS screening and CEUS examination and were randomly assigned to the training and validation sets at a ratio of 7:3 (n = 78 versus 33). Radiomics features were respectively extracted based on CUS and CEUS using the PyRadiomics package. The max-relevance and min-redundancy (MRMR) and least absolute shrinkage and selection operator (LASSO) analyses were used for feature selection and radiomics score calculation in the training set. The variance inflation factor (VIF) was performed to check the multicollinearity among selected predictors. The best performing model was selected to develop a nomogram using binary logistic regression analysis. The calibration and clinical utility of the nomogram were assessed. Results: The model combining CUS reported ALN status, CUS radiomics score (CUS-radscore) and CEUS radiomics score (CEUS-radscore) exhibited the best performance. The areas under the curves (AUC) of our proposed nomogram in the training and external validation sets were 0.845 [95% confidence interval (CI), 0.739-0.950] and 0.901 (95% CI, 0.758-1). The calibration curves and decision curve analysis (DCA) demonstrated the nomogram's robust consistency and clinical utility. Conclusions: The established nomogram is a promising prediction tool for noninvasive prediction of ALN status. The radiomics features based on CUS and CEUS can help improve the predictive performance.

A prospective study on using shear wave elastography to predict the ypT0 stage of rectal cancer after neoadjuvant therapy: a new support for the watch-and-wait approach?

Introduction: The diagnostic accuracy of traditional imaging examination in predicting ypT stage of rectal cancer after neoadjuvant therapy is significantly reduced, which would affect patients' subsequent treatment choices. This study aimed to investigate the use of endorectal shear wave elastography (SWE) for diagnosing ypT0 stage of rectal cancer after neoadjuvant chemoradiotherapy (nCRT). Methods: Sixty patients with rectal cancer were prospectively recruited in this study. Data on endorectal ultrasound (ERUS) and SWE parameters were collected before nCRT and 6-8 weeks after nCRT. Postoperative pathological results were the gold standard for evaluating the diagnostic accuracy of SWE and ERUS in predicting the ypT0 stage of rectal cancer after nCRT. Receiver operating characteristic (ROC) curve analysis was used to determine the cut-off values of the SWE parameters that best corresponded to the ypT0 stage and analyze the sensitivity, specificity, and accuracy. Results: The diagnostic accuracies of using ERUS to predict the ypT and ypT0 stages of rectal cancer after nCRT were 58.1% (18/31) and 64.3% (9/14), respectively. The ROC curve was constructed with the lesion's Emean, Emean corrected (EC), Emean difference (ED), Emean corrected differencede (ECD), Emean descendding rate (EDR) and Emean corrected descendding rate (ECDR) values after nCRT, the cut-off values of diagnosing the ypT0 stage were 64.40 kPa, 55.45 kPa, 72.55 kPa, 73.75 kPa, 50.15%, and 55.93%, respectively; the area under the curve (AUC) for diagnosing the ypT0 stage was 0.924, 0.933, 0.748, 0.729, 0.857 and 0.861, respectively. The EC value showed the best diagnostic performance. Conclusion: SWE could improve the accuracy of conventional ERUS in diagnosing the ypT0 stage of rectal cancer after nCRT. It is expected to become a new method to help predict pathological complete responses in clinical practice and provide new evidence for the watch-and-wait approach.

Progress in research on ultrasound radiomics for predicting the prognosis of breast cancer.

Breast cancer is the most common malignant tumor and the leading cause of cancer-related deaths in women worldwide. Effective means of predicting the prognosis of breast cancer are very helpful in guiding treatment and improving patients' survival. Features extracted by radiomics reflect the genetic and molecular characteristics of a tumor and are related to its biological behavior and the patient's prognosis. Thus, radiomics provides a new approach to noninvasive assessment of breast cancer prognosis. Ultrasound is one of the commonest clinical means of examining breast cancer. In recent years, some results of research into ultrasound radiomics for diagnosing breast cancer, predicting lymph node status, treatment response, recurrence and survival times, and other aspects, have been published. In this article, we review the current research status and technical challenges of ultrasound radiomics for predicting breast cancer prognosis. We aim to provide a reference for radiomics researchers, promote the development of ultrasound radiomics, and advance its clinical application.

HER-2 Expression in Colorectal Cancer and Its Correlation with Immune Cell Infiltration.

BACKGROUND: This study aimed to investigate the effect of increased HER-2 expression on tumor-infiltrating lymphocytes (TILs) and determine its impact on the prognosis of colorectal cancer (CRC) patients; Methods: HER-2, CD4, CD8, CD19, LY6G, CD56, CD68, CD11b, and EpCam expression in CRC tissues and adjacent paracancerous tissues were assessed using multiplex fluorescence immunohistochemical staining. The correlation between HER-2 expression and the number of TILs in CRC tissues was analyzed. Kaplan-Meier and Cox proportional hazards models were used to analyze survival outcomes; Results: The expression of HER-2 in tumor tissues was higher than that in paracancerous tissues (1.31 ± 0.45 vs. 0.86 ± 0.20, p < 0.05). Additionally, there was an increase in the numbers of CD4+, CD8+, CD19+, and CD68+ cells in CRC tissues (14.11 ± 1.10 vs. 3.40 ± 0.18, p < 0.005; 0.16 ± 0.12 vs. 0.04 ± 0.04, p < 0.005; 0.71 ± 0.46 vs. 0.25 ± 0.13, p < 0.0005; 0.27 ± 0.24 vs. 0.03 ± 0.11, p < 0.05). An increase in HER-2 expression was positively correlated with an increase in CD4, CD8, and CD19 (p < 0.0001). In HER-2-positive CRC tissues, CD68 expression was increased (0.80 ± 0.55 vs. 0.25 ± 0.22, p < 0.05). In HER-2-upregulated CRC tissues, CD4, CD8, CD19, CD68, CD11b, Ly6G, and CD56 expressions were elevated (0.70 ± 0.37 vs. 0.32 ± 0.17, p = 0.03; 0.22 ± 0.13 vs. 0.09 ± 0.06, p = 0.03; 0.31 ± 0.19 vs. 0.12 ± 0.08, p = 0.02; 1.05 ± 0.62 vs. 0.43 ± 0.21, p < 0.01; 1.34 ± 0.81 vs. 0.53 ± 0.23, p < 0.01; 0.50 ± 0.31 vs. 0.19 ± 0.10, p < 0.01; 1.26 ± 0.74 vs. 0.52 ± 0.24, p < 0.01). Furthermore, increased HER-2 expression was an independent risk factor for recurrence-free survival (RFS) in patients (p < 0.01, HR = 3.421); Conclusions: The increased expression of HER-2 and its relationship with immune cells will provide new insights for immunotherapy in CRC patients.

Conventional ultrasound and contrast-enhanced ultrasound radiomics in breast cancer and molecular subtype diagnosis.

Objectives: This study aimed to explore the value of conventional ultrasound (CUS) and contrast-enhanced ultrasound (CEUS) radiomics to diagnose breast cancer and predict its molecular subtype. Method: A total of 170 lesions (121 malignant, 49 benign) were selected from March 2019 to January 2022. Malignant lesions were further divided into six categories of molecular subtype: (non-)Luminal A, (non-)Luminal B, (non-)human epidermal growth factor receptor 2 (HER2) overexpression, (non-)triple-negative breast cancer (TNBC), hormone receptor (HR) positivity/negativity, and HER2 positivity/negativity. Participants were examined using CUS and CEUS before surgery. Regions of interest images were manually segmented. The pyradiomics toolkit and the maximum relevance minimum redundancy algorithm were utilized to extract and select features, multivariate logistic regression models of CUS, CEUS, and CUS combined with CEUS radiomics were then constructed and evaluated by fivefold cross-validation. Results: The accuracy of the CUS combined with CEUS model was superior to CUS model (85.4% vs. 81.3%, p<0.01). The accuracy of the CUS radiomics model in predicting the six categories of breast cancer is 68.2% (82/120), 69.3% (83/120), 83.7% (100/120), 86.7% (104/120), 73.5% (88/120), and 70.8% (85/120), respectively. In predicting breast cancer of Luminal A, HER2 overexpression, HR-positivity, and HER2 positivity, CEUS video improved the predictive performance of CUS radiomics model [accuracy=70.2% (84/120), 84.0% (101/120), 74.5% (89/120), and 72.5% (87/120), p<0.01]. Conclusion: CUS radiomics has the potential to diagnose breast cancer and predict its molecular subtype. Moreover, CEUS video has auxiliary predictive value for CUS radiomics.

The diagnostic value of contrast-enhanced ultrasonography in breast ductal abnormalities.

BACKGROUND: Ductal lesions are an important, often overlooked, and poorly understood issue in breast imaging, which have a risk of underlying malignancy ranging from 5 to 23%. Ultrasonography (US), which has largely replaced galactography or ductography, has become an important imaging method to assess patients with ductal lesions. However, it is difficult to distinguish benign from malignant ductal abnormalities only by ultrasonography, most of which are recommended to be at least in subcategory 4A; these require biopsy according to the ACR BI-RADS®atlas 5th Edition-breast ultrasound. Contrast-enhanced ultrasound (CEUS) has been shown to be valuable for differentiating benign from malignant tumors, but its value is unclear in breast ductal lesions. Therefore, the purposes of this study were to explore the characteristics of malignant ductal abnormalities on US and CEUS imaging and the diagnostic value of CEUS in breast ductal abnormalities. METHODS: Overall, 82 patients with 82 suspicious ductal lesions were recruited for this prospective study. They were divided into benign and malignant groups according to the pathological results. Morphologic features and quantitative parameters of US and CEUS were analyzed by comparison and multivariate logistic regression to determine the independent risk factors. The diagnostic performance was assessed by receiver operating characteristic (ROC) curve analysis. RESULTS: Shape, margin, inner echo, size, microcalcification and blood flow classification on US, wash-in time, enhancement intensity, enhancement mode, enhancement scope, blood perfusion defects, peripheral high enhancement and boundary on CEUS were identified as features correlated with malignant ductal lesions. However, multivariate logistic regression showed that only microcalcification (OR = 8.96, P = 0.047) and enhancement scope (enlarged, OR = 27.42, P = 0.018) were independent risk factors for predicting malignant ductal lesions. The sensitivity, specificity, positive predictive value, negative predictive value, accuracy and area under the ROC curve of microcalcifications combined with an enlarged enhancement scope were 0.895, 0.886, 0.872, 0.907, 0.890, and 0.92, respectively. CONCLUSIONS: Microcalcification and enlarged enhancement scope are independent factors for predicting malignant ductal lesions. The combined diagnosis can greatly improve the diagnostic performance, indicating that CEUS can be useful in the differentiation of benign and malignant lesions to formulate more appropriate management for ductal lesions.

Contrast-enhanced ultrasound imaging for intestinal lymphoma.

BACKGROUND: Intestinal lymphoma is a rare tumor. Contrast-enhanced ultrasound (CEUS) findings of intestinal lymphoma have not been reported previously, and the relationship between CEUS and clinicopathological features and prognostic factors is still unknown. AIM: To describe the B-mode US and CEUS features of intestinal lymphoma and investigate the correlation of CEUS and histopathological features. METHODS: This was a single-center retrospective study. Eighteen patients with histologically confirmed intestinal lymphoma underwent B-mode US and CEUS examinations between October 2016 and November 2019. We summarized the features of B-mode US and CUES imaging of intestinal lymphoma and compared the frequency of tumor necrosis in intestinal lymphomas with reference to different pathological subtypes (aggressive or indolent) and clinical stage (early or advanced). The time-intensity curve parameters of CEUS were also compared between patients with normal and elevated serum lactate dehydrogenase. RESULTS: In B-mode imaging, four patterns were observed in intestinal lymphoma: Mass type (12/18, 66.7%), infiltration type (1/18, 5.6%), mesentery type (4/18, 22.2%) and mixed type (1/18, 5.6%). All cases were hypoechoic and no cystic areas were detected. On CEUS, most cases (17/18, 94.4%) showed arterial hyperechoic enhancement. All cases showed arterial enhancement followed by venous wash out. A relatively high rate of tumor necrosis (11/18, 61.1%) was observed in this study. Tumor necrosis on CEUS was more frequent in aggressive subtypes (10/13, 76.9%) than in indolent subtypes (1/5, 20.0%) (P = 0.047). There were no correlations between tumor necrosis and lesion size and Ann Arbor stage. There was no significant difference in time-intensity curve parameters between normal and elevated lactate dehydrogenase groups. CONCLUSION: B-mode US and CEUS findings of intestinal lymphoma are characteristic. We observed a high rate of tumor necrosis, which appeared more frequently in aggressive pathological subtypes of intestinal lymphoma.

Domain Knowledge Powered Deep Learning for Breast Cancer Diagnosis Based on Contrast-Enhanced Ultrasound Videos.

In recent years, deep learning has been widely used in breast cancer diagnosis, and many high-performance models have emerged. However, most of the existing deep learning models are mainly based on static breast ultrasound (US) images. In actual diagnostic process, contrast-enhanced ultrasound (CEUS) is a commonly used technique by radiologists. Compared with static breast US images, CEUS videos can provide more detailed blood supply information of tumors, and therefore can help radiologists make a more accurate diagnosis. In this paper, we propose a novel diagnosis model based on CEUS videos. The backbone of the model is a 3D convolutional neural network. More specifically, we notice that radiologists generally follow two specific patterns when browsing CEUS videos. One pattern is that they focus on specific time slots, and the other is that they pay attention to the differences between the CEUS frames and the corresponding US images. To incorporate these two patterns into our deep learning model, we design a domain-knowledge-guided temporal attention module and a channel attention module. We validate our model on our Breast-CEUS dataset composed of 221 cases. The result shows that our model can achieve a sensitivity of 97.2% and an accuracy of 86.3%. In particular, the incorporation of domain knowledge leads to a 3.5% improvement in sensitivity and a 6.0% improvement in specificity. Finally, we also prove the validity of two domain knowledge modules in the 3D convolutional neural network (C3D) and the 3D ResNet (R3D).

Comparison of sonographic characteristics of primary thyroid lymphoma and anaplastic thyroid carcinoma.

BACKGROUND: Although primary thyroid lymphoma (PTL) and anaplastic thyroid carcinoma (ATC) both account for a rare portion of the morbidity of all thyroid malignancies, the therapeutic methods and prognosis for these two diseases are different. The purpose of this study was to investigate the sonographic characteristics of PTL and ATC and to compare the sonographic findings of PTL and ATC. METHODS: The study included 42 patients with histopathologically proven PTL (n=27) and ATC (n=15). The Clinical characteristics and sonographic findings were retrospectively reviewed and compared between the two groups. RESULTS: The mean age of patients with ATC was not significantly different from that in patients with PTL (P=0.601). The female-to-male ratio of patients with ATC was significantly lower than that of patients with PTL (P=0.029). Both PTL and ATC commonly present as a relatively large, solid mass on sonography with compressive symptoms, in which hoarseness was seen more frequently in ATC group (66.7%) than in PTL group (14.8%) (P=0.001). There is no significant difference in thyroid size, nodular size, margin, shape, echo texture, echogenicity, cystic change, vascularity and local invasion on sonography between ATC and PTL groups. Echogenic strands, markedly hypoechoic and enhanced posterior echo were seen more frequently in PTL group (92.6%, 92.6%, and 85.2%, respectively) than those in ATC group (6.7%, 60.0%, and 33.3%, respectively) (P<0.05), and calcification was seen more frequently in ATC group (80.0%) than in PTL group (0%) (P<0.001). Three ultrasound patterns were observed for PTL including diffuse type (25.9%), nodular type (48.2%) and mixed type (25.9%), while all ATC cases presented with nodular type (100.0%). Associated Hashimoto's thyroiditis occurred more frequently in PTL group (59.3%) than in ATC group (20.0%) (P=0.023). CONCLUSIONS: Certain sonographic features as a markedly hypoechogenicity, the presence of an enhanced posterior echo and linear echogenic strands, lack of calcification and associated Hashimoto's thyroiditis were valuable for distinguishing PTL from ATC. In contrast, heterogeneous echogenicity, uncircumscribed margin, irregular shape, and vascular pattern were not specific features for differential diagnosis.