A5010728835- Advanced Radiotherapy Techniques
- Biomedical Text Mining and Ontologies
- AI in cancer detection
- Hepatocellular Carcinoma Treatment and Prognosis
- Radiomics and Machine Learning in Medical Imaging
- Prostate Cancer Treatment and Research
- Topic Modeling
- Radiation Dose and Imaging
- Prostate Cancer Diagnosis and Treatment
- Cancer Genomics and Diagnostics
- Machine Learning in Healthcare
- Gastric Cancer Management and Outcomes
- Frailty in Older Adults
- Nutrition and Health in Aging
- Digital Radiography and Breast Imaging
- Brain Metastases and Treatment
- Advances in Oncology and Radiotherapy
- Economic and Financial Impacts of Cancer
- Cancer survivorship and care
- Lung Cancer Diagnosis and Treatment
- Lung Cancer Treatments and Mutations
- Pancreatic and Hepatic Oncology Research
- Colorectal and Anal Carcinomas
- Management of metastatic bone disease
- Medical Imaging Techniques and Applications
University of British Columbia
2022-2025
Kelowna General Hospital
2025
Many Natural Language Processing (NLP) methods achieve greater performance when the input text is preprocessed to remove extraneous or unnecessary text. A technique known as segmentation can facilitate this step by isolating key sections from a document. Give that transformer models-such Bidirectional Encoder Representations Transformers (BERT)-have demonstrated state-of-the-art on many NLP tasks, it desirable leverage such models for segmentation. However, are typically limited only 512...
PURPOSE Breast cancer relapses are rarely collected by registries because of logistical and financial constraints. Hence, we investigated natural language processing (NLP), enhanced with state-of-the-art deep learning transformer tools large models, to automate relapse identification in the text computed tomography (CT) reports. METHODS We analyzed follow-up CT reports from patients diagnosed breast between January 1, 2005, December 31, 2014. The were curated annotated for presence or...
e13591 Background: Relapse is a major concern for oncologists and breast cancer survivors that necessitates additional treatment often leads to mortality. Cancer registries routinely track mortality, but few monitor relapse because of logistical challenges prohibitive costs. In this context, Natural Language Processing (NLP) promising tool. Merging artificial intelligence with linguistics, NLP can rapidly analyze vast volumes text in electronic health records. This capability particularly...
PURPOSE Population-based cancer registries (PBCRs) collect data on all new diagnoses in a defined population. Data are sourced from pathology reports, and the PBCRs rely manual rule-based solutions. This study presents state-of-the-art natural language processing (NLP) pipeline, built by fine-tuning pretrained models (LMs). The pipeline is deployed at British Columbia Cancer Registry (BCCR) to detect reportable tumors population-based feed of electronic pathology. METHODS We fine-tune two...