Data Loaders
HoneyBee integrates multiple data modalities for oncology research, including clinical records, pathology imaging, and molecular data. The framework utilizes data loaders to streamline the preprocessing and analysis of these diverse data types.
PDF Reader
The PDF reader in HoneyBee is designed to extract and preprocess text data from medical reports and clinical notes, ensuring the data is ready for analysis.
from honeybee import PDFLoader
pdf_loader = PDFLoader(file_path="path_to_pdf.pdf")
document = pdf_loader.load()
Whole Slide Image Reader
The WSI reader processes histopathology slides, normalizes stain colors, and extracts tissue segments for further analysis.
from honeybee import WSI_Dataloader
wsi_loader = WSI_Dataloader(file_path="path_to_wsi.svs")
wsi = wsi_loader.load()
DICOM Reader
The DICOM reader is essential for handling radiology images, such as CT, MRI, and PET scans, standardizing them for machine learning tasks.
from honeybee import DICOMLoader
dicom_loader = DICOMLoader(file_path="path_to_dicom.dcm")
dicom_data = dicom_loader.load()