Background: In the post-Z0011 era, sentinel lymph node (SLN) status and metastatic burden determine whether axillary management entails conservative sentinel lymph node biopsy (SLNB) or radical axillary lymph node dissection (ALND) in breast cancer patients. However, SLN status and metastatic burden cannot be evaluated preoperatively in clinical practice. This study explored the predictive value of contrastenhanced ultrasound (CEUS) patterns of SLN to assess the nodal status and metastatic burden in early breast cancer patients.Methods: A retrospective study was conducted on 88 consecutive patients who were diagnosed with clinical T1-2N0 breast cancer between December 2020 and November 2021 at the Lanzhou University Second Hospital and scheduled for SLNB. Preoperative CEUS was performed to confirm the location and enhancement pattern of the SLN, and the conventional ultrasonic characteristics of the primary breast lesions and SLN were recorded. Intraoperative localized SLN and postoperative pathological results were used as the gold standard for comparison with preoperative ultrasound findings.Results: CEUS successfully identified at least 1 SLN in 88 patients, with a total of 118 SLNs identified in the entire cohort. Univariate analysis showed that lesion size, blood flow grade, SLN longitudinal diameter, cortical thickness, and enhancement pattern were significant predictive features of SLN metastasis. Further multiple regression analysis indicated that the enhancement pattern of the SLN was an independent risk factor for SLN metastasis, with a sensitivity and a specificity of 84.2% (32/38) and 80.0% (40/50), respectively. Meanwhile, the SLN enhancement pattern could predict the lymph node metastasis burden (P<0.001). In patients presenting with a type I (homogeneous enhancement) or type II (heterogeneous enhancement) SLN, 91.5% (65/71) had ≤2 positive SLNs, whereas in patients with a type III (no enhancement) SLN, 70.6% (12/17) had >2 metastatic nodes. Conclusions:The contrast-enhanced pattern of the SLN is an independent risk factor for SLN status.Patients presenting with a type I or type II SLN enhanced pattern are unlikely to have high-burden metastases detected at their final surgical treatment and omission of ALND may be appropriate.
Ultrasound (US) imaging is part of conventional medical imaging in clinical practice that is low-cost, non-ionizing, portable and capable of real-time image acquisition and display. However, in certain cases, US has limited sensitivity and specificity in differentiating between malignant and benign lesions. Ultrasound-based radiomics, as a new branch of radiomics, can provide additional features such as heterogeneity of lesions that are invisible to the naked eye, alone or in combination with demographic, histological, genomic or proteomic data, thereby improving the accuracy of US in diagnosis of disease. This article provides an introduction to ultrasound-based radiomics, covering its workflow, the application of machine learning, and current research status. Current limitations of radiomics, such as consistency of image acquisition, parameter variations, and difficulty in calibrating quantitative methods in ultrasound, will also be covered.
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.
Background: Sentinel lymph node biopsy (SLNB), as a common method for axillary staging of early breast cancer, has gradually attracted people’s attention to the false-negative rate and postoperative complications. The aim of the study is to investigate the clinical value of preoperative contrast-enhanced ultrasound (CEUS) for intraoperative SLNB in early breast cancer patients. Methods: A total of 201 patients scheduled for SLNB from September 2018 to April 2021 were collected consecutively. Preoperative CEUS was used to identify sentinel lymph nodes (SLN) and lymphatic drainage in breast cancer patients. Results: The SLN identification rate of CEUS was 93.0% (187/201) and four lymphatic drainage patterns were found: single LC to single SLN (70.0%), multiple LCs to single SLN (8.0%), single LC to multiple SLNs (10.2%), and multiple LCs to multiple SLNs (11.8%). The Sen, Spe, PPV, NPV, AUC of CEUS, US and CEUS + US in diagnosis of SLNs were 82.7%, 80.4%, 73.8%, 87.4%, 0.815; 70.7%, 77.7%, 68.0%, 79.8%, 0.742; and 86.7%, 77.7%, 72.2%, 89.7%, 0.822, respectively. There was no statistically significant difference between the diagnostic performance of CEUS and CEUS + US (p = 0.630). Conclusions: CEUS can be used to preoperatively assess the lymphatic drainage patterns and the status of the SLNs in early breast cancer to assist precision intraoperative SLNB.
Objectives Tumor‐infiltrating lymphocytes (TILs) have emerged as an efficient biomarker predicting treatment response and prognosis of breast cancer (BC). This study aimed to evaluate the association between conventional ultrasound and contrast‐enhanced ultrasound (CEUS) imaging features with TIL levels in invasive BC patients. Methods We retrospectively included 267 women with invasive BC who had undergone conventional ultrasound and CEUS. Patients were divided into low (≤10%) and high (>10%) TIL groups. Conventional ultrasound and CEUS features were analyzed by two sonographers. The associations between the TIL levels and imaging features were evaluated. Results Of the 267 patients, 122 with high TILs and 145 with low TIL levels. High TIL tumors were more likely to have a circumscribed margin, oval or round shape, and enhanced posterior echoes on ultrasonography (p < 0.05). In contrast, low TIL tumors were more likely to have an irregular shape, un‐circumscribed, indistinct and spiculated margin (p < 0.05). In CEUS, high TIL tumors showed a more regular shape, clearer margin, more homogeneous enhancement and higher peak intensity (PI) value (p < 0.05). Logistic analysis indicated that shape, posterior features, PI, and enhanced homogeneity were independent predictors for high TIL tumors. The model combined the four independent predictors have a moderate performance in predicting high TIL tumors with AUC 0.79, sensitivity 0.72, and specificity 0.78. Conclusions Conventional ultrasound and CEUS features were associated with TIL levels in invasive BC. Consequently, the results suggested that preoperative conventional ultrasound and CEUS may be a useful noninvasive imaging biomarker for individualized treatment decisions.
OBJECTIVE: Since the ACOSOG Z0011 trial, the clinical examination of axillary lymph node-negative early breast cancer patients (cT1-2N0) can be used to predict the burden of axillary lymph nodes (ALNs) by axillary ultrasound (AUS). To improving diagnosis of axillary lymph node metastasis (ALNM), we assessed the value of combining clinicopathological, conventional ultrasound, SWE features in the cT1-2N0 breast cancer patients. METHODS: Retrospective analysis of 285 patients with cT1-2N0 breast cancer who underwent preoperative ultrasound examination of the lesion and axillary, with shear wave elastography (SWE) of the lesions. According to the postoperative pathological results, they were divided into ≤2 metastatic ALNs group (low nodal burden, LNB) and > 2 metastatic ALNs group (high nodal burden, HNB). Binary logistic regression analysis was used to screen independent risk factors and establish prediction models. The best cut-off value of continuous variables is determined by the receiver operating characteristic curve, and the performance of the prediction model is evaluated. RESULTS: Presence of lymphovascular invasion (OR = 7.966, P = 0.010), tumor size (OR = 2.485, P = 0.019), Emean of intratumor (OR = 0.939, P = 0.002) and cortical thickness of lymph node (OR = 9.277, P < 0.001) were independent risk predictors for HNB of cT1-2N0 Group. The predictive model of combined method had better performance in predicting HNB of cT1-2N0 compared with models based on SWE and conventional ultrasound alone (area under the curve: 0.824 vs 0.658, P < 0.001; 0.824 vs 0.789, P = 0.035). CONCLUSIONS: The predictive models of combined method obtained from significant clinicopathological and ultrasonographic features can potentially improve the diagnosis and individual treatment of ALNM in patients with cT1-2N0 breast cancer.
Objectives The aim of this study was to compare the value of the AI‐SONIC ultrasound‐assisted diagnosis system versus contrast‐enhanced ultrasound (CEUS) for differential diagnosis of thyroid nodules in diffuse and non‐diffuse backgrounds. Methods A total of 555 thyroid nodules with pathologically confirmed diagnosis were included in this retrospective study. The diagnostic efficacies of AI‐SONIC and CEUS for differentiating benign from malignant nodules in diffuse and non‐diffuse backgrounds were evaluated, with pathological diagnosis as the gold standard. Results The agreement between AI‐SONIC diagnosis and pathological diagnosis was moderate in diffuse backgrounds (κ = 0.417) and almost perfect in non‐diffuse backgrounds (κ = 0.81). The agreement between CEUS diagnosis and pathological diagnosis was substantial in diffuse backgrounds (κ = 0.684) and moderate in non‐diffuse backgrounds (κ = 0.407). In diffuse backgrounds, AI‐SONIC had slightly higher sensitivity (95.7 vs 89.4%, P = .375), but CEUS had significantly higher specificity (80.0 vs 40.0%, P = .008). In non‐diffuse background, AI‐SONIC had significantly higher sensitivity (96.2 vs 73.4%, P < .001), specificity (82.9 vs 71.2%, P = .007), and negative predictive value (90.3 vs 53.3%, P < .001). Conclusion In non‐diffuse backgrounds, AI‐SONIC is superior to CEUS for differentiating malignant from benign thyroid nodules. In diffuse backgrounds, AI‐SONIC could be useful for screening of cases to detect suspicious nodules requiring further examination by CEUS.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.