Diagnostic Performance of Superb Microvascular Imaging in Differentiating Benign and Malignant Axillary Lymph Nodes.

ABSTRACT: The aim was to evaluate the effectiveness of superb microvascular imaging (SMI) in axillary lymph nodes (LNs).Benign and malignant LNs diagnosed via histopathological examination constituted the study subgroups. In addition to grayscale findings for morphological evaluation, vascular patterns and appearance of internal vessels were analyzed by both power Doppler ultrasound (PDUS) and SMI. The number of vascular branches was counted, and a vascularity index (VI) was calculated by SMI.Fifty-two LNs with suspicious findings in terms of metastasis (33 malignant and 19 benign) were evaluated. Diagnostic accuracy according to vascular patterns was 82% for PDUS and 92% for SMI. In the presence of asymmetric cortical thickening, there was a significant difference between benign and malignant LNs in the number of vascular branches of both thin and thick cortical sides ( P < 0.01). Mean VI was significantly higher in the malignant group ( P < 0.05). In differentiating malignancy, when a cutoff VI value was set to 9%, sensitivity was 69.7%, and specificity was 63.2%.Evaluating the vascularity of axillary LNs by SMI is a useful tool in determining the potential of axillary metastasis, especially in the absence of typical sonographic findings. Superb microvascular imaging can beneficially be used to select the most suspicious LN and suspicious area of the LN to sample.

Comparison and ensemble of 2D and 3D approaches for COVID-19 detection in CT images.

Detecting COVID-19 in computed tomography (CT) or radiography images has been proposed as a supplement to the RT-PCR test. We compare slice-based (2D) and volume-based (3D) approaches to this problem and propose a deep learning ensemble, called IST-CovNet, combining the best 2D and 3D systems with novel preprocessing and attention modules and the use of a bidirectional Long Short-Term Memory model for combining slice-level decisions. The proposed ensemble obtains 90.80% accuracy and 0.95 AUC score overall on the newly collected IST-C dataset in detecting COVID-19 among normal controls and other types of lung pathologies; and 93.69% accuracy and 0.99 AUC score on the publicly available MosMedData dataset that consists of COVID-19 scans and normal controls only. The system also obtains state-of-art results (90.16% accuracy and 0.94 AUC) on the COVID-CT-MD dataset which is only used for testing. The system is deployed at Istanbul University Cerrahpasa School of Medicine where it is used to automatically screen CT scans of patients, while waiting for RT-PCR tests or radiologist evaluation.