Value of Shear Wave Elastography Versus Contrast-Enhanced Sonography for Differentiating Benign and Malignant Superficial Lymphadenopathy Unexplained by Conventional Sonography

Deep learning radiomics of multimodal ultrasound for classifying metastatic cervical lymphadenopathy into primary cancer sites: a feasibility study

PURPOSE

To investigate the feasibility of deep learning radiomics (DLR) based on multimodal ultrasound to differentiate the primary cancer sites of metastatic cervical lymphadenopathy (CLA).

MATERIALS AND METHODS

This study analyzed 280 biopsy-confirmed metastatic CLAs from 280 cancer patients, including 54 from head and neck squamous cell carcinoma (HNSCC), 58 from thyroid cancer (TC), 92 from lung cancer (LC), and 76 from gastrointestinal cancer (GIC). Before biopsy, patients underwent conventional ultrasound (CUS), ultrasound elastography (UE), and contrast-enhanced ultrasound (CEUS). Based on CUS, DLR models using CUS, CUS+UE, CUS+CEUS, and CUS+UE+CEUS data were developed and compared. The best model was integrated with key clinical indicators selected by univariate analysis to achieve the best classification performance.

RESULTS

All DLR models achieved similar performance with respect to classifying four primary tumor sites of metastatic CLA (AUC:0.708~0.755). After integrating key clinical indicators (age, sex, and neck level), the US+UE+CEUS+clinical model yielded the best performance with an overall AUC of 0.822 in the validation cohort, but there was no significance compared with the basal CUS+clinical model (P>0.05), both of which identified metastasis from HNSCC, TC, LC, and GIC with 0.869 and 0.911, 0.838 and 0.916, 0.750 and 0.610, and 0.829 and 0.769, respectively.

CONCLUSION

The ultrasound-based DLR model can be used to classify the primary cancer sites of metastatic CLA, and the CUS combined with clinical indicators is adequate to provide a high discriminatory performance. The addition of the combination of UE and CEUS data is expected to further improve performance.

The Diagnostic Performance of Multiparametric Ultrasound in the Qualitative Assessment of Inconclusive Cervical Lymph Nodes

BACKGROUND

Enlarged cervical lymph nodes (CLNs) can result from infection or malignancies, and a definitive diagnosis requires histological examination. Ultrasound (US) remains the first-line imaging modality for detection, and new US techniques may improve characterization. The aim of our study was to investigate whether the qualitative assessment of multiparametric US (mpUS) can improve diagnostic performance in the differentiation of benign and malignant CLNs.

METHODS

107 CLNs in 105 patients were examined by preoperative mpUS consisting of B-mode US, color-coded duplex sonography (CCDS), shear wave elastography (SWE) and contrast-enhanced US (CEUS). US images were evaluated in consensus by two experienced US operators. Histopathological examination was used as reference standard.

RESULTS

SWE and CEUS combined showed the highest overall diagnostic performance (91% sensitivity, 77% specificity, 87% positive predictive value (PPV), 83% negative predictive value (NPV), 90% accuracy, χ2 (1) = 51.485, p < 0.001) compared to B-mode US and CCDS (87% sensitivity, 44% specificity, 73% PPV, 65% NPV, 73% accuracy χ2 (1) = 12.415, p < 0.001). In terms of individual techniques, SWE had higher specificity than B-mode and CCDS (71% sensitivity, 90% specificity, 92% PPV, 64% NPV, 78% accuracy, χ2 (1) = 36.115, p < 0.001), while qualitative CEUS showed the best diagnostic performance of all investigated US techniques (93% sensitivity, 85% specificity, 91% PPV, 87% NPV, 90% accuracy, χ2 (1) = 13.219, p < 0.001). Perfusion patterns, homogeneity, presence of necrosis, and malignancy differed significantly between malignant and benign CLNs (p < 0.001).

CONCLUSIONS

SWE and CEUS can facilitate the differentiation of inconclusive CLNs when performed to supplement B-mode US and CCDS. MpUS may thus aid the decision between surgery and a watch-and-scan strategy in enlarged CLNs.

Comparison of microvascular flow imaging and contrast-enhanced ultrasound for blood flow analysis of cervical lymph node lesions

OBJECTIVE

To compare the diagnostic value of microvascular flow imaging (MVFI) with that of contrast-enhanced ultrasound (CEUS) for the analysis of blood flow in benign and malignant cervical lymph nodes.

MATERIAL AND METHODS

As a prospective study, 95 cervical enlarged lymph nodes (43 benign and 52 malignant) were observed in 95 patients using conventional ultrasonography (including gray and Color Doppler Flow Imaging), CEUS, and MVFI. Two researchers evaluated vascular parameters of MVFI (vascular distribution, internal vascular features, vascular index) and CEUS (enhancement mode, enhancement type) and compared the diagnostic effects of MVFI and CEUS.All results were compared with pathological findings.

RESULTS

There were significant differences in the vascular distribution and internal vascular features of benign and malignant lymph nodes on MVFI (P < 0.05). The vascular distribution of benign lymph nodes was mainly of the central and avascular types, the internal blood vessels were mostly normal, the vascular distribution of malignant lymph nodes was mainly mixed, the internal vessels were mainly tortuous and displaced. The optimal cut-off value of the benign and malignant lymph node vascular index (VI) was 15.55%, and the area under the receiver operating characteristic curve (AUC) of the VI was 0.876. There were also significant differences in the enhancement mode and types of benign and malignant lymph nodes in CEUS (P < 0.05). The benign lymph nodes showed centrifugal perfusion, and the enhancement types were mostly type I and type II. Most malignant lymph nodes showed centripetal or mixed perfusion, and the enhancement types were usually type III and type IV. The accuracy, sensitivity, and specificity of CEUS in the diagnosis of lymph node lesions were 84.2%, 84.6% and 83.7%, respectively, and the AUC was 0.845. The accuracy, sensitivity, and specificity of MVFI in the diagnosis of lymph node lesions were 85.3%, 84.6%, and 86.0%, respectively, and the AUC was 0.886.

CONCLUSION

Both CEUS and MVFI are valuable in differentiating benign and malignant lesions of lymph nodes and have a similar diagnostic performance; however, MVFI is less invasive and simpler than CEUS. Therefore it is preferred for auxiliary examination of enlarged lymph nodes that are difficult to diagnose by conventional ultrasound.

Evaluating Different Quantitative Shear Wave Parameters of Ultrasound Elastography in the Diagnosis of Lymph Node Malignancies: A Systematic Review and Meta-Analysis

Shear wave elastography (SWE) has shown promise in distinguishing lymph node malignancies. However, the diagnostic accuracies of various SWE parameters that quantify tissue stiffness are yet to be demonstrated. To evaluate the pooled diagnostic accuracy of different SWE parameters for differentiating lymph node malignancies, we conducted a systematic screening of four databases using the PRISMA guidelines. Lymph node biopsy was adopted as the reference standard. E_max (maximum stiffness), E_mean (mean stiffness), E_min (minimum stiffness), and E_sd (standard deviation) SWE parameters were subjected to separate meta-analyses. A sub-group analysis comparing the use of E_max in cervical (including thyroid) and axillary lymph node malignancies was also conducted. Sixteen studies were included in this meta-analysis. E_max and E_sd demonstrated the highest pooled sensitivity (0.78 (95% CI: 0.69-0.87); 0.78 (95% CI: 0.68-0.87)), while E_mean demonstrated the highest pooled specificity (0.93 (95% CI: 0.88-0.98)). From the sub-group analysis, the diagnostic performance did not differ significantly in cervical and axillary LN malignancies. In conclusion, SWE is a promising adjunct imaging technique to conventional ultrasonography in the diagnosis of lymph node malignancy. SWE parameters of E_max and E_sd have been identified as better choices of parameters for screening clinical purposes.

Application of Contrast-Enhanced Ultrasound Combined with Elastic Imaging Technology in Differential Diagnosis of Salivary Gland Tumors

This paper proposes the effect of contrast-enhanced ultrasound combined with real-time elastic imaging technology in the differential diagnosis of salivary gland tumors. 200 patients were selected, including 120 males and 60 females. The age ranged from 9 to 83 years, with an average of 55.4 years. Among the 200 cases, there were 90 cases of single parotid gland on the right, 77 cases of single parotid gland on the left, 2 cases of bilateral (single parotid gland on each side), 2 cases of multiple parotid gland on the right (2 lesions), 1 case of 2 lesions on the left and 1 lesion on the right, and 1 case of multiple parotid gland on the left (4 lesions). 135 cases were located in the superficial lobe (78%) and 38 cases (22%) in the deep lobe of parotid gland. The ARIETTA 70 color Doppler ultrasound diagnostic instrument is used. The equipment is equipped with high-frequency contrast probe, real-time elastic imaging technology, and related software. The results showed that the detection rate of salivary gland tumors by ultrasound was 100% and the diagnostic coincidence rate was 71% (123/173). Ultrasound can not only identify the tumors in and around the parotid gland but also identify the location, size, and internal structure of the tumors. Combined with CDFI, it can make qualitative diagnosis of most benign and malignant salivary gland tumors and provide help for clinical treatment and operation plan. It is proved that contrast-enhanced ultrasound and real-time elastic imaging technology have advantages over gray-scale ultrasound in differentiating benign and malignant superficial enlarged lymph nodes, and the combined use can effectively improve the diagnostic efficiency.

2D-shear wave elastography in the evaluation of suspicious superficial inguinal lymph nodes: Reproducibility and region of interest selection

Purpose

To assess the ability of 2D-Shear wave elastography (2D-SWE) to evaluate its reproducibility, to define the optimal orientation and size of the region of interest (ROI), and to differentiate benign from malignant inguinal lymph nodes (LNs).

Method

Thirty-two suspicious inguinal LNs from 21 patients were evaluated with 2D-SWE. SWE measurements were obtained in two orthogonal planes. To investigate reproducibility, sensitivity and specificity, circular ROIs with a diameter of 1 mm, 2 mm, 3 mm and 5 mm were placed on the cortex of the LNs. Additionally, one freehand ROI was drawn covering majority of the LN. Two observers performed five sets of SWE measurements for each ROI size. All LNs underwent core needle biopsy or were surgically removed.

Results

The 3 mm ROI for Mean-E in axial plane showed high interrater agreement [intraclass correlation coefficient (ICC) 0.899] with the cut-off value of 7.31 kPa resulting in 88.9% sensitivity and 60.9% specificity for differentiating malignant from benign LNs. In benign LNs, mean elasticity of the ROI was lower (7.68 ± 3.82 kPa; range, 3.41–15.40 kPa) compared to the malignant LNs (15.81 ± 10.61 kPa; range, 3.86–36.45 kPa).

Conclusions

The most reproducible way to measure stiffness in inguinal LNs is a 3 mm circular ROI centered on the cortex of the LN in axial plane. Elasticity values were higher in the malignant LNs reflecting the stiffer nature of the metastatic LNs. 2D-SWE offers a noninvasive ultrasonographic tool to assess superficial inguinal lymph nodes with high reproducibility.

Quantitative Multiparametric Ultrasound (mpUS) in the Assessment of Inconclusive Cervical Lymph Nodes

Background: Enlarged cervical lymph nodes (CLN) are preferably examined by ultrasound (US) by using criteria such as size and echogenicity to assess benign and suspicious CLN, which should be histologically evaluated. This study aims to assess the differentiation of malign and benign CLN by using multiparametric US applications (mpUS). Methods: 101 patients received a standardized US protocol prior to surgical intervention using B-mode−US, shear-wave elastography (SWE) and contrast-enhanced ultrasound (CEUS). SWE was assessed by 2D real-time SWE conducting a minimum of five measurements, CEUS parameters were assessed with post-processing perfusion software. Histopathological confirmation served as the gold standard. Results: B-mode−US and SWE analysis of 104 CLN (36 benign, 68 malignant) showed a significant difference between benign and malignant lesions, presenting a larger long axis and higher tissue stiffness (both p < 0.001). Moreover, tissue stiffness assessed by SWE was significantly higher in CLN with regular B-mode−US criteria (Solbiati Index > 2 and short-axis < 1 cm, p < 0.001). No perfusion parameter on CEUS showed a significant differentiation between benign and malignant CLN. Discussion: As the only multiparametric parameter, SWE showed higher tissue stiffness in malignant CLN, also in subgroups with regular B-mode criteria. This fast and easy application may be a promising noninvasive tool to US examination to ameliorate the sonographic differentiation of inconclusive CLN.

Tomoelastography for non-invasive detection of ameloblastoma and metastatic neck lymph nodes

Ameloblastoma is a benign epithelial tumour and the most common odontogenic tumour, accounting for about 18% of cases. We present a patient to illustrate the first use of tomoelastography for quantitatively mapping tissue stiffness (shear wave speed) and fluidity (loss angle of the complex shear modulus) in a metastasised ameloblastoma of the left mandible. Tomoelastography maps clearly depicted the extent of the tumour by abnormally high values of stiffness and fluidity (1.73±0.23 m/s, 1.18±0.08 rad) compared with normal values in the contralateral mandible (1.04±0.09 m/s, 0.93±0.12 rad). Abnormal stiffness also revealed metastatic involvement of the neck lymph nodes (1.30±0.03 m/s vs 0.86±0.01 m/s). Taken together, stiffness and fluidity measured by tomoelastography can sensitively detect the presence and extent of bone tumours and metastatic spread to cervical lymph nodes.

Predictive value of comb-push ultrasound shear elastography for the differentiation of reactive and metastatic axillary lymph nodes: A preliminary investigation

Objectives

To evaluate the predictive performance of comb-push ultrasound shear elastography for the differentiation of reactive and metastatic axillary lymph nodes.

Methods

From June 2014 through September 2018, 114 female volunteers (mean age 58.1±13.3 years; range 28–88 years) with enlarged axillary lymph nodes identified by palpation or clinical imaging were prospectively enrolled in the study. Mean, standard deviation and maximum shear wave elastography parameters from 117 lymph nodes were obtained and compared to fine needle aspiration biopsy results. Mann-Whitney U test and ROC curve analysis were performed.

Results

The axillary lymph nodes were classified as reactive or metastatic based on the fine needle aspiration outcomes. A statistically significant difference between reactive and metastatic axillary lymph nodes was observed based on comb-push ultrasound shear elastography (CUSE) results (p<0.0001) from mean and maximum elasticity values. Mean elasticity showed the best separation with a ROC analysis resulting in 90.5% sensitivity, 94.4% specificity, 0.97 area under the curve, 95% positive predictive value, and 89.5% negative predictive value with a 30.2-kPa threshold.

Conclusions

CUSE provided a quantifiable parameter that can be used for the assessment of enlarged axillary lymph nodes to differentiate between reactive and metastatic processes.

Shear wave elastography in differentiating between benign and malignant cervical lymph nodes in patients with oral carcinoma

OBJECTIVES

To evaluate shear wave elastography in differentiating between benign and malignant cervical lymph nodes in patients with oral carcinoma.

METHODS

77 patients with oral squamous cell carcinoma were examined by B-mode and shear wave elastography with a 14 MHz linear transducer. The integrated shear wave elastography software allowed the operator to place regions of interest of various sizes within the elastography window, and automatically displayed shear elastic modulus data (kPa) for each region of interest. The relationship between size and shear elastic modulus of cervical lymph nodes was assessed by Pearson's rank correlation test. The shear elastic modulus of cervical lymph nodes in benign and malignant were evaluated using the Mann-Whitney U test. The analyses were used with a 5% significance level.

RESULTS

We plotted shear elastic modulus (X) against minimal axial diameter of cervical lymph nodes (Y), and observed a significant correlation [ Y = 0.091 X + 4.648 (R² = 0.603, p = 0.000, N = 77)]. Furthermore, the shear elastic modulus of the malignant cervical lymph nodes (105.9 ± 5.2 kPa) was higher than that of benign (11.9 ± 4.4 kPa, p = 0.000).

CONCLUSIONS

The shear wave elastography is an effective technique for the objectively and quantitatively diagnosis of cervical lymph node metastases of the oral carcinoma.

A Clinical Decision Support System Using Ultrasound Textures and Radiologic Features to Distinguish Metastasis From Tumor-Free Cervical Lymph Nodes in Patients With Papillary Thyroid Carcinoma

OBJECTIVES

This study investigated the potential of a clinical decision support approach for the classification of metastatic and tumor-free cervical lymph nodes (LNs) in papillary thyroid carcinoma on the basis of radiologic and textural analysis through ultrasound (US) imaging.

METHODS

In this research, 170 metastatic and 170 tumor-free LNs were examined by the proposed clinical decision support method. To discover the difference between the groups, US imaging was used for the extraction of radiologic and textural features. The radiologic features in the B-mode scans included the echogenicity, margin, shape, and presence of microcalcification. To extract the textural features, a wavelet transform was applied. A support vector machine classifier was used to classify the LNs.

RESULTS

In the training set data, a combination of radiologic and textural features represented the best performance with sensitivity, specificity, accuracy, and area under the curve (AUC) values of 97.14%, 98.57%, 97.86%, and 0.994, respectively, whereas the classification based on radiologic and textural features alone yielded lower performance, with AUCs of 0.964 and 0.922. On testing the data set, the proposed model could classify the tumor-free and metastatic LNs with an AUC of 0.952, which corresponded to sensitivity, specificity, and accuracy of 93.33%, 96.66%, and 95.00%.

CONCLUSIONS

The clinical decision support method based on textural and radiologic features has the potential to characterize LNs via 2-dimensional US. Therefore, it can be used as a supplementary technique in daily clinical practice to improve radiologists' understanding of conventional US imaging for characterizing LNs.

Differentiation between metastatic and tumour-free cervical lymph nodes in patients with papillary thyroid carcinoma by grey-scale sonographic texture analysis

PURPOSE

Papillary thyroid carcinoma (PTC) is the most common thyroid cancer, and cervical lymph nodes (LNs) are the most common extrathyroid metastatic involvement. Early detection and reliable diagnosis of LNs can lead to improved cure rates and management costs. This study explored the potential of texture analysis for texture-based classification of tumour-free and metastatic cervical LNs of PTC in ultrasound imaging.

MATERIAL AND METHODS

A total of 274 LNs (137 tumour-free and 137 metastatic) were explored using the texture analysis (TA) method. Up to 300 features were extracted for texture analysis in three normalisations (default, 3sigma, and 1-99%). Linear discriminant analysis was employed to transform raw data to lower-dimensional spaces and increase discriminative power. The features were classified by the first nearest neighbour classifier.

RESULTS

Normalisation reflected improvement on the performance of the classifier; hence, the features under 3sigma normalisation schemes through FFPA (fusion Fisher plus the probability of classification error [POE] + average correlation coefficients [ACC]) features indicated high performance in classifying tumour-free and metastatic LNs with a sensitivity of 99.27%, specificity of 98.54%, accuracy of 98.90%, positive predictive value of 98.55%, and negative predictive value of 99.26%. The area under the receiver operating characteristic curve was 0.996.

CONCLUSIONS

TA was determined to be a reliable method with the potential for characterisation. This method can be applied by physicians to differentiate between tumour-free and metastatic LNs in patients with PTC in conventional ultrasound imaging.