A5008005754- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- Cancer Genomics and Diagnostics
- Ferroptosis and cancer prognosis
- Cancer-related molecular mechanisms research
- Genomics and Phylogenetic Studies
- RNA modifications and cancer
- AI in cancer detection
- Multiple Myeloma Research and Treatments
- Environmental DNA in Biodiversity Studies
- vaccines and immunoinformatics approaches
- Molecular Biology Techniques and Applications
- RNA Research and Splicing
- Hematological disorders and diagnostics
- Musculoskeletal synovial abnormalities and treatments
- Hepatocellular Carcinoma Treatment and Prognosis
- Protein purification and stability
- Monoclonal and Polyclonal Antibodies Research
- Endometrial and Cervical Cancer Treatments
- Advanced biosensing and bioanalysis techniques
- Cancer Immunotherapy and Biomarkers
- Protein Degradation and Inhibitors
Nanjing University of Information Science and Technology
2023-2025
State Key Laboratory of Digital Medical Engineering
2019-2023
DKFZ-ZMBH Alliance
2023
German Cancer Research Center
2022-2023
Southeast University
2019-2023
Heidelberg University
2022
In multiple myeloma and its precursor stages, plasma cell infiltration (PCI) cytogenetic aberrations are important for staging, risk stratification, response assessment. However, invasive bone marrow (BM) biopsies cannot be performed frequently multifocally to assess the spatially heterogenous tumor tissue. Therefore, goal of this study was establish an automated framework predict local BM biopsy results from magnetic resonance imaging (MRI).This retrospective multicentric used data center 1...
Abstract Motivation Endometrial cancer is a prevalent gynecological malignancy that requires accurate identification of its molecular subtypes for effective diagnosis and treatment. Four with different clinical outcomes have been identified: POLE mutation, mismatch repair deficient, p53 abnormal, no specific profile. However, determining these typically relies on expensive gene sequencing. To overcome this limitation, we propose novel method utilizes hematoxylin eosin-stained whole slide...
Extrachromosomal circular DNA (eccDNA) has emerged as a potential biomarker for disease due to its stable closed structure. However, the diagnostic utility of eccDNA remains underexplored. In this study, we demonstrate that characteristics associated with genomic repetitive elements change in breast cancer patient tissues and plasma. These changes can serve signatures accurate classification. We profiled annotated repeat across genome plasma, aggregating each element superfamily subfamily...
Hepatocellular carcinoma (HCC) is one of the most prevalent malignancies worldwide, and pronounced intra- inter-tumor heterogeneity restricts clinical benefits. Dissecting molecular in HCC commonly explored by endoscopic biopsy or surgical forceps, but invasive tissue sampling possible complications limit broadeer adoption. The radiomics framework a promising non-invasive strategy for tumor decoding, linkage between immuno-oncological characteristics worth further in-depth study. In this...
The recent development of artificial intelligence (AI) technologies coupled with medical imaging data has gained considerable attention, and offers a non-invasive approach for cancer diagnosis prognosis. In this context, improved breast (BC) molecular characteristics assessment models are foreseen to enable personalized strategies better clinical outcomes compared existing screening strategies. And it is promising developing hormone receptors (HR) subtypes BC patients from dynamic...
Abstract Reconstructing the full-length sequence of extrachromosomal circular DNA (eccDNA) from short sequencing reads has proved challenging given similarity eccDNAs and their corresponding linear DNAs. Previous methods were unable to achieve high-throughput detection eccDNAs. Herein, a novel algorithm was developed, called Full-Length eccDNA Detection (FLED), reconstruct based on strategy that combined rolling circle amplification nanopore long-reads technology. Seven human epithelial...
To investigate reliable associations between dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) features and gene expression characteristics in breast cancer (BC) to develop validate classifiers for predicting PAM50 subtypes prognosis from DCE-MRI non-invasively. Two radiogenomics cohorts with paired RNA-sequencing (RNA-seq) data were collected local public databases divided into discovery (n = 174) validation 72). Six external datasets 1,443) used prognostic validation....
Background: Breast cancer (BC) is a highly heterogeneous cancer. The interaction between immune system and BC complex, widespread yet unclear. In this study, we aimed to reveal the heterogeneity of host systemic response understand possible mechanisms that may drive using transcriptomic data from peripheral blood mononuclear cells (PBMCs). Methods: Transcriptome-wide gene expressions PBMCs in 33 patients were generated by RNA sequencing. An unsupervised clustering algorithm was employed...
Background: This study aimed to reveal the heterogeneity of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) breast cancer (BC) and identify its prognosis values molecular characteristics. Methods: Two radiogenomics cohorts (n = 246) were collected tumor regions segmented semi-automatically. A total 174 radiomics features extracted, subtypes identified validated by unsupervised analysis. gene-profile-based classifier was developed predict subtypes. The prognostic differences...
Abstract Accurate prediction of mutation effects on antibody-antigen interactions is critical for antibody engineering and drug design. In this study, we present abCAN, a practical novel attention network designed to predict changes in binding affinity caused by mutations. abCAN requires only the pre-mutant complex structure information perform its predictions. introduces an innovative approach, Progressive Encoding, which progressively integrates structural, residue-level, sequential...
Background: To investigate the relationship between dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomic features and expression activity of hallmark pathways to develop prediction models pathway-level heterogeneity for breast cancer (BC) patients. Methods: Two radiogenomic cohorts were analyzed (n = 246). Tumor regions segmented semiautomatically, 174 extracted. Gene set enrichment analysis (GSEA) gene variation (GSVA) performed identify significant imaging-pathway...
Abstract Reconstructing the full-length sequence of extrachromosomal circular DNA (eccDNA) from short sequencing reads has proved challenging given similarity eccDNAs and their corresponding linear DNAs. Previous methods were unable to achieve high-throughput detection eccDNAs. Here we describe a new strategy that combined rolling circle amplification (RCA) nanopore long-reads technology generate We further developed novel algorithm, called Full-Length eccDNA Detection (FLED), reconstruct...
Zielsetzung Das Multiple Myelom zeigt eine ausgeprägte räumliche Heterogenität bzgl. Tumorlastverteilung und Genetik. Regelmäßige multifokale Knochenmarksbiopsien sind jedoch nicht durchführbar. Ziel der Arbeit war es, Algorithmen zu etablieren, die automatisch lokale Knochenmarks-Biopsieergebnisse aus dem MRT prädizieren können.