A5100403237- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Treatments and Mutations
- Colorectal Cancer Treatments and Studies
- Image Retrieval and Classification Techniques
- Gastrointestinal Tumor Research and Treatment
- Generative Adversarial Networks and Image Synthesis
- Colorectal Cancer Screening and Detection
- Cancer Research and Treatments
- Natural Language Processing Techniques
- Risk and Safety Analysis
- Machine Learning in Bioinformatics
- Advanced Image Fusion Techniques
- Metastasis and carcinoma case studies
- Machine Learning and Data Classification
- Pneumonia and Respiratory Infections
- Brain Tumor Detection and Classification
- Gene expression and cancer classification
- Lung Cancer Diagnosis and Treatment
- Meningioma and schwannoma management
- Robotics and Sensor-Based Localization
- RNA modifications and cancer
- Sarcoma Diagnosis and Treatment
- Melanoma and MAPK Pathways
- Resilience and Mental Health
Shanxi Medical University
2011-2024
Shanxi Academy of Medical Sciences
2015-2024
University of Jinan
2012-2024
University of Houston
2024
Houston Methodist
2019-2024
Methodist Hospital
2023
Shandong Jianzhu University
2023
Tongji Hospital
2022
Huazhong University of Science and Technology
2022
Peking University
2021
Thymic epithelial tumors (TETs) are a relatively rare type of thoracic tumor, accounting for less than 1% all tumors. The incidence TETs is about 3.93/10000 in China, slightly higher that European and American countries. For resectable TETs, complete surgical resection recommended. Radiotherapy or chemotherapy may be used as postoperative adjuvant treatment. Treatment advanced, unresectable consist mainly radiotherapy chemotherapy, but there lack standard first- second-line treatment...
Predicting the recurrence risk of lung cancer is critical for appropriate adjuvant therapy patients after surgical resection. However, traditional circulating tumor cell (CTC) detection or next generation sequencing-based methods are usually expensive and time-inefficient, which urges need more efficient computational models. In this study, we have established a convolutional neural network (CNN) framework called DeepLRHE to predict through analyzing histopathology images. consists few steps...
The Breast Imaging Reporting and Data System (BI-RADS) lexicon was developed to standardize mammographic reporting assess cancer risk facilitate the decision biopsy. Because of substantial interobserver variability in application BI-RADS lexicon, biopsy varies greatly results overdiagnosis excessive biopsies. false-positive rate from mammograms is estimated be 7% approximately 10% overall, but within 4 category, it greater than 70%. Therefore, we Cancer Risk Calculator (BRISK) target a...
Nuclear instance segmentation is a challenging task due to large number of touching and overlapping nuclei in pathological images. Existing methods cannot effectively recognize the accurate boundary owing neglecting relationship between pixels (e.g., direction information). In this paper, we propose novel Centripetal Direction Net-work (CDNet) for nuclear segmentation. Specifically, define centripetal feature as class adjacent directions pointing center rep-resent spatial within nucleus....
The rearranged during transfection (RET) gene is one of the receptor tyrosine kinases and cell-surface molecules responsible for transmitting signals that regulate cell growth differentiation. In non-small lung cancer (NSCLC), RET fusion a rare driver alteration associated with poor prognosis. Fortunately, two selective inhibitors (sRETi), namely pralsetinib selpercatinib, have been approved treating NSCLC due to their remarkable efficacy safety profiles. These shown ability overcome...
Gene fusions can drive tumor development for multiple types of cancer. Currently, many drugs targeting gene are being approved clinical application. At present, tyrosine receptor kinase (TRK) inhibitors neurotrophic (NTRK) among the first "tumor agnostic" pan-cancer use. Representative TRK inhibitors, including larotrectinib and entrectinib, have shown high efficacy same time, several second-generation designed to overcome first-generation drug resistance undergoing development. Due rarity...
The aim of the present study was to investigate mutation status c-Kit gene (KIT) and PDGFRA in patients with a gastrointestinal stromal tumor (GIST). In total, 93 GIST were included study, which polymerase chain reaction amplification sequencing used detect sequences exons 9, 11, 13 17 KIT 12 18 PDGFRA. mutations detected 64 cases (68.82%), exon 11 56 (60.22%), three (3.23%) one case (1.08%) shown have 17. most common deletion, accounted for 55.36% (31/56) cases, followed by point observed...
Abstract The study aimed to explore predictors of Mycoplasma pneumoniae pneumonia (MPP) in adults and develop a nomogram predictive model order identify high-risk patients early. We retrospectively analysed the clinical data total 337 adult with community-acquired (CAP) divided them into MPP non-MPP groups according whether they were infected MP. Univariate multivariate logistic regression analyses used screen independent developed model. Receiver operating characteristic (ROC) curve,...
Breast cancer is a pervasive global health concern among women. Leveraging multimodal data from enterprise patient databases-including Picture Archiving and Communication Systems (PACS) Electronic Health Records (EHRs)-holds promise for improving risk assessment. This study introduces deep-learning model leveraging mammogram datasets to evaluate breast risk. Our approach integrates frozen large-scale pretrained vision-language models, showcasing superior performance stability compared...
Digital pathology images are treated as the "gold standard" for diagnosis of colorectal lesions, especially colon cancer. Real-time, objective and accurate inspection results will assist clinicians to choose symptomatic treatment in a timely manner, which is great significance clinical medicine. However, Manual methods suffers from long cycle serious reliance on subjective interpretation. It also challenging task existing computer-aided obtain models that both interpretable. Models exhibit...
This study aimed to investigate the association of mRNA expression echinoderm microtubule-associated protein-like 4 (EML4)-anaplastic lymphoma kinase (ALK) fusion gene with that thymidylate synthase (TYMS) in non-small cell lung cancer (NSCLC) tissues. Quantitative polymerase chain reaction was used detect EML4-ALK and TYMS 257 cases NSCLC. The positive rate 4.28% NSCLC tissues (11/257), higher nonsmokers than smokers (P<0.05); detected 63.42% (163/257) cases. An detected; a low level...
The present study aimed to investigate the association between epidermal growth factor receptor (EGFR) gene mutations and excision repair cross-complementing protein 1 (ERCC1) ribonucleotide reductase subunit M1 (RRM1) mRNA expression in non-small cell lung cancer (NSCLC) tissue. quantitative polymerase chain reaction was used detect EGFR mutations, ERCC1 RRM1 257 cases of NSCLC. In NSCLC samples mutation rate 49.03% (126/257). higher females non-smoking patients (P<0.05). High observed...
Flight data recorded by Quick Access Recorder (QAR) can accurately reflect aircraft's flight conditions and pilot's operations. By analyzing the relationship between parameter operations, risk analysis of operations is carried out to provide guidance for pilots' training. For specific types exceedances, this paper employs an model constructed interval partition Markov method analyze potential dangers The results help reduce incidence exceedances improve safety.
Abstract Introduction: BI-RADS category 4 is associated with a wide variability in probability of malignancy, ranging from 2 to 95% while biopsy-derived positive predictive value (PPV3) for this category’s lesions remains low at 21.1% the US. A major fallout these facts that we have way very high false rate leading too many unnecessary biopsies and their costs emotional burden. We improved our in-house intelligent-augmented Breast cancer RISK calculator (iBRISK), an integrated deep learning...