Adaptive Evolutionary Optimization of Deep Learning Architectures for Focused Liver Ultrasound Image Segmentation.

Liver ultrasound segmentation is challenging due to low image quality and variability. While deep learning (DL) models have been widely applied for medical segmentation, generic pre-configured models may not meet the specific requirements for targeted areas in liver ultrasound. Quantitative ultrasound (QUS) is emerging as a promising tool for liver fat measurement; however, accurately segmenting regions of interest within liver ultrasound images remains a challenge.

Viral oncogene EBNALP regulates YY1 DNA binding and alters host 3D genome organization.

The Epstein-Barr virus (EBV) nuclear antigen leader protein (EBNALP) is essential for the immortalization of naive B lymphocytes (NBLs). However, the mechanisms remain elusive. To understand EBNALP's role in B-cell transformation, we compare NBLs infected with wild-type EBV and an EBNALP-null mutant EBV using multi-omics techniques.