Interobserver and intermethod variability in data interpretation of breast strain elastography in suspicious breast lesions

Comparison of resistive index and shear-wave elastography in the evaluation of chronic kidney allograft dysfunction

BACKGROUND

Detection of early chronic changes in the kidney allograft is important for timely intervention and long-term survival. Conventional and novel ultrasound-based investigations are being increasingly used for this purpose with variable results.

AIM

To compare the diagnostic performance of resistive index (RI) and shear wave elastography (SWE) in the diagnosis of chronic fibrosing changes of kidney allograft with histopathological results.

METHODS

This is a cross-sectional and comparative study. A total of 154 kidney transplant recipients were included in this study, which was conducted at the Departments of Transplantation and Radiology, Sindh Institute of Urology and Transplan tation, Karachi, Pakistan, from August 2022 to February 2023. All consecutive patients with increased serum creatinine levels and reduced glomerular filtration rate (GFR) after three months of transplantation were enrolled in this study. SWE and RI were performed and the findings of these were evaluated against the kidney allograft biopsy results to determine their diagnostic utility.

RESULTS

The mean age of all patients was 35.32 ± 11.08 years. Among these, 126 (81.8%) were males and 28 (18.2%) were females. The mean serum creatinine in all patients was 2.86 ± 1.68 mg/dL and the mean estimated GFR was 35.38 ± 17.27 mL/min/1.73 m2. Kidney allograft biopsy results showed chronic changes in 55 (37.66%) biopsies. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of SWE for the detection of chronic allograft damage were 93.10%, 96.87%%, 94.73%, and 95.87%, respectively, and the diagnostic accuracy was 95.45%. For RI, the sensitivity, specificity, PPV, and NPV were 76.92%, 83.33%, 70.17%, and 87.62%, respectively, and the diagnostic accuracy was 81.16%.

CONCLUSION

The results from this study show that SWE is more sensitive and specific as compared to RI in the evaluation of chronic allograft damage. It can be of great help during the routine follow-up of kidney transplant recipients for screening and early detection of chronic changes and selecting patients for allograft biopsy.

Development and Validation of a Nomogram for Predicting Breast Malignancy in Male Patients Based on Clinical and Ultrasound Features

OBJECTIVE

This study aimed to construct a nomogram based on clinical and ultrasound (US) features to predict breast malignancy in males.

METHODS

The medical records between August, 2021 and February, 2023 were retrospectively collected from the database. Patients included in this study were randomly divided into training and validation sets in a 7:3 ratio. The models for predicting the risk of malignancy in male patients with breast lesions were virtualized by the nomograms.

RESULTS

Among the 71 enrolled patients, 50 were grouped into the training set, while 21 were grouped into the validation set. After the multivariate analysis was done, pain, BI-RADS category, and elastography score were identified as the predictors for malignancy risk and were selected to generate the nomogram. The C-index was 0.931 for the model. Concordance between predictions and observations was detected by calibration curves and was found to be good in this study. The model achieved a net benefit across all threshold probabilities, which was shown by the decision curve analysis (DCA) curve.

CONCLUSION

We successfully constructed a nomogram to evaluate the risk of breast malignancy in males using clinical and US features, including pain, BI-RADS category, and elastography score, which yielded good predictive performance.

Artificial intelligence-assisted ultrasound image analysis to discriminate early breast cancer in Chinese population: a retrospective, multicentre, cohort study

Background

Early diagnosis of breast cancer has always been a difficult clinical challenge. We developed a deep-learning model EDL-BC to discriminate early breast cancer with ultrasound (US) benign findings. This study aimed to investigate how the EDL-BC model could help radiologists improve the detection rate of early breast cancer while reducing misdiagnosis.

Methods

In this retrospective, multicentre cohort study, we developed an ensemble deep learning model called EDL-BC based on deep convolutional neural networks. The EDL-BC model was trained and internally validated on B-mode and color Doppler US image of 7955 lesions from 6795 patients between January 1, 2015 and December 31, 2021 in the First Affiliated Hospital of Army Medical University (SW), Chongqing, China. The model was assessed by internal and external validations, and outperformed radiologists. The model performance was validated in two independent external validation cohorts included 448 lesions from 391 patients between January 1 to December 31, 2021 in the Tangshan People's Hospital (TS), Chongqing, China, and 245 lesions from 235 patients between January 1 to December 31, 2021 in the Dazu People's Hospital (DZ), Chongqing, China. All lesions in the training and total validation cohort were US benign findings during screening and biopsy-confirmed malignant, benign, and benign with 3-year follow-up records. Six radiologists performed the clinical diagnostic performance of EDL-BC, and six radiologists independently reviewed the retrospective datasets on a web-based rating platform.

Findings

The area under the receiver operating characteristic curve (AUC) of the internal validation cohort and two independent external validation cohorts for EDL-BC was 0.950 (95% confidence interval [CI]: 0.909-0.969), 0.956 (95% [CI]: 0.939-0.971), and 0.907 (95% [CI]: 0.877-0.938), respectively. The sensitivity values were 94.4% (95% [CI]: 72.7%-99.9%), 100% (95% [CI]: 69.2%-100%), and 80% (95% [CI]: 28.4%-99.5%), respectively, at 0.76. The AUC for accurate diagnosis of EDL-BC (0.945 [95% [CI]: 0.933-0.965]) and radiologists with artificial intelligence (AI) assistance (0.899 [95% [CI]: 0.883-0.913]) was significantly higher than that of the radiologists without AI assistance (0.716 [95% [CI]: 0.693-0.738]; p < 0.0001). Furthermore, there were no significant differences between the EDL-BC model and radiologists with AI assistance (p = 0.099).

Interpretation

EDL-BC can identify subtle but informative elements on US images of breast lesions and can significantly improve radiologists' diagnostic performance for identifying patients with early breast cancer and benefiting the clinical practice.

Funding

The National Key R&D Program of China.

Diagnostic Performance of Strain and Shear Wave Elastography for the Response to Neoadjuvant Chemotherapy in Breast Cancer Patients: Systematic Review and Meta-Analysis

OBJECTIVES

To investigate the diagnostic performance of strain and shear wave elastography for the response to neoadjuvant chemotherapy (NAC) in breast cancer patients.

METHODS

Relevant studies were searched in the databases of PubMed, Web of Science and Cochrane Library until October 2021. The diagnostic performance of ultrasonic elastography for the response to NAC were estimated by calculating the area under the curve (AUC) with sensitivity and specificity using Stata 14.0.

RESULTS

A total of 15 studies that comprise 1147 breast cancer patients were included in this meta-analysis. The pooled AUC of strain elastography in diagnosing responses were 0.89 (95% CI = 0.86-0.91) with 87% (95% CI = 75-94%) of sensitivity and 80% (95% CI = 72-84%) of specificity. The pooled AUC of shear wave elastography in diagnosing response were 0.82 (95% CI = 0.78-0.85) with 79% (95% CI = 72-84%) of sensitivity and 81% (95% CI = 71-88%). No publication bias was observed across the studies using Deek's funnel plot.

CONCLUSIONS

Based on current evidence, this meta-analysis confirmed that strain and shear wave elastography exhibited favorable performance for predicting responses to NAC. Strain and shear wave elastography may be a useful, noninvasive method for the assessment of response to NAC in breast cancer patients.