sanchezcarlosjr / breast-cancer-toolkit Goto Github PK

View Code? Open in Web Editor NEW

The repository provides code for running inference with different breast cancer models, links for downloading the trained model checkpoints, and example notebooks on how work with a DICOM pipeline.

License: MIT License

Python 85.67% Jupyter Notebook 3.89% Dockerfile 10.43%

breast-cancer-toolkit's Introduction

BCT

Machine learning toolkit designed to support data scientists in breast cancer detection, classification and analysis.

Installation

Install the package with:

pip install breast-cancer-toolkit

Usage as CLI

Convert the DCM files into TIFF format recursively with the same basename.

parallel bct convert {} {.}.tiff ::: **/*.dcm

Usage as library

Models

Remove background with instance segmentation

Model	Training data	Resolution	# of samples seen	IoU	Accuracy

Data sources

Source	Argument	Type	Notes
image	'image.jpg'	str or Path	Single image file. Format supported: jgp, png, dcm, tiff
URL	'https://ultralytics.com/images/bus.jpg'	str	URL to an image.
screenshot	'screen'	str	Capture a screenshot.
PIL	Image.open('im.jpg')	PIL.Image	HWC format with RGB channels.
OpenCV	cv2.imread('im.jpg')	np.ndarray	HWC format with BGR channels `uint8 (0-255)`.
numpy	np.zeros((640,1280,3))	np.ndarray	HWC format with BGR channels `uint8 (0-255)`.
torch	torch.zeros(16,3,320,640)	torch.Tensor	BCHW format with RGB channels `float32 (0.0-1.0)`.
CSV, json, xlsx	'sources.csv'	str or Path	CSV file containing paths to images, videos, or directories.
video	'video.mp4'	str or Path	Video file in formats like MP4, AVI, etc.
directory	'path/'	str or Path	Path to a directory containing images or videos.
glob	'path/*.jpg'	str	Glob pattern to match multiple files. Use the `*` character as a wildcard.
YouTube	'https://youtu.be/LNwODJXcvt4'	str	URL to a YouTube video.
stream	'rtsp://example.com/media.mp4'	str	URL for streaming protocols such as RTSP, RTMP, TCP, or an IP address.
multi-stream	'list.streams'	str or Path	*.streams text file with one stream URL per row, i.e. 8 streams will run at batch-size 8.