The human liver exhibits variable characteristics and anatomical information, which is often ambiguous in radiological images. Machine learning can be of great assistance in automatically segmenting the liver in radiological images, which can be further processed for computer-aided diagnosis. Magnetic resonance imaging (MRI) is preferred by clinicians for liver pathology diagnosis over volumetric abdominal computerized tomography (CT) scans, due to their superior representation of soft tissues. The convenience of Hounsfield unit (HoU) based preprocessing in CT scans is not available in MRI, making automatic segmentation challenging for MR images. This study investigates multiple state-of-the-art segmentation networks for liver segmentation from volumetric MRI images. Here, T1-weighted (in-phase) scans are investigated using expert-labeled liver masks from a public dataset of 20 patients (647 MR slices) from the Combined Healthy Abdominal Organ Segmentation grant challenge (CHAOS). The reason for using T1-weighted images is that it demonstrates brighter fat content, thus providing enhanced images for the segmentation task. Twenty-four different state-of-the-art segmentation networks with varying depths of dense, residual, and inception encoder and decoder backbones were investigated for the task. A novel cascaded network is proposed to segment axial liver slices. The proposed framework outperforms existing approaches reported in the literature for the liver segmentation task (on the same test set) with a dice similarity coefficient (DSC) score and intersect over union (IoU) of $95.15\%$ and $92.10\%$, respectively.

This study focuses on artificial intelligence-driven classification of glioma and Ki-67 leveling using T2w-FLAIR MRI, exploring the association of Ki-67 biomarkers with deep learning (DL) features through explainable artificial intelligence (XAI) and SHapley Additive exPlanations (SHAP). This IRB-approved study included 101 patients with glioma brain tumor acquired MR images with the T2W-FLAIR sequence. We extracted DL bottleneck features using ResNet50 from glioma MR images. Principal component analysis (PCA) was deployed for dimensionality reduction. XAI was used to identify potential features. The XGBosst classified the histologic grades of the glioma and the level of Ki-67. We integrated potential DL features with patient demographics (age and sex) and Ki-67 biomarkers, utilizing SHAP to determine the model's essential features and interactions. Glioma grade classification and Ki-67 level predictions achieved overall accuracies of 0.94 and 0.91, respectively. It achieved precision scores of 0.92, 0.94, and 0.96 for glioma grades 2, 3, and 4, and 0.88, 0.94, and 0.97 for Ki-67 levels (low: 5%≤Ki-6720%). Corresponding F1-scores were 0.95, 0.88, and 0.96 for glioma grades and 0.92, 0.93, and 0.87 for Ki-67 levels. SHAP analysis further highlighted a strong association between bottleneck DL features and Ki-67 biomarkers, demonstrating their potential to differentiate glioma grades and Ki-67 levels while offering valuable insights into glioma aggressiveness. This study demonstrates the precise classification of glioma grades and the prediction of Ki-67 levels to underscore the potential of AI-driven MRI analysis to enhance clinical decision-making in glioma management.

Understanding SARS-CoV-2 human protein-protein interactions (PPIs) and the host response to infection is essential for developing effective COVID-19 antivirals. However, how the ancestral virus and its variants remodel virus-host protein assemblies in various organ-specific cells and bodily fluids remains unclear. Here, we conduct 639 affinity-purifications by tagging and expressing 28 SARS-CoV-2 and spike proteins from the ancestral virus and four variants in eight cell lines representing five mammalian organs and the immune system. Using mass spectrometry (MS), we identify both known and previously unreported SARS-CoV-2-human PPIs, highlighting similarities and differences across organ- or immune-derived cell lines and virus strains. Besides verifying the cell- and variant-specific PPIs, co-fractionation-MS analysis of COVID-19 patients’ saliva confirm host PPI changes between SARS-CoV-2 strains. We discover that the NSP3 papain-like protease, a secreted protein, binds fibrinogen to induce abnormal blood clotting and interferon-induced proteins to evade host innate immune responses. Leveraging deep learning, we design peptide inhibitors that successfully blocked SARS-CoV-2 and variant replication in human liver cells, reversing virus-induced PPI alterations. Together, these findings provide molecular insights into SARS-CoV-2 biology, uncover reorganized viral-host protein assemblies during infection, and identify potential host therapeutic targets and inhibitors for developing antivirals against SARS-CoV-2 strains.

Aims: This study aimed to isolate and genomically characterise a lytic bacteriophage targeting multidrug-resistant and extensively drug-resistant Klebsiella pneumoniae strains from hospital sewage in Dhaka, Bangladesh. Methods and Results: A lytic bacteriophage, designated MFS, was isolated using the double-layer agar method and propagated against clinical K. pneumoniae isolates. The phage genome was sequenced using the Oxford Nanopore MinION platform. Phage MFS had a linear genome of 48,780 bp with a GC content of 52.02%. Genomic analysis identified genes associated with DNA replication, DNA packaging, phage structure, and host lysis, including putative holin, endolysin, and spanin genes. No known antimicrobial resistance, virulence, or lysogeny-associated genes were detected in the in silico screening. Conclusions: Our findings support further investigation of sewage-derived bacteriophages as potential antibacterial candidates against MDR/XDR clinical K. pneumoniae. However, additional phenotypic, safety, and in vivo validation is required before therapeutic application.