FAIMED 3D

use fastai to quickly train fully three-dimensional models on radiological data

Classification

from faimed3d.all import *

Load data in various medical formats (DICOM, NIfTI, NRRD) or even videos as simple as in fastai.

d = pd.read_csv('../data/radiopaedia_cases.csv')
dls = ImageDataLoaders3D.from_df(d,
                                 item_tfms = Resize3D((20, 112, 112)),
                                 batch_tfms = aug_transforms_3d(), 
                                 bs = 2, val_bs = 2)

Faimed3d provides multiple model architectures, pretrained on the UCF101 dataset for action recoginiton, which can be used for transfer learning.

Model	3-fold accuracy	duration/epoch	model size
efficientnet b0	92.5 %	9M:35S	48.8 MB
efficientnet b1	90.1 %	13M:20S	80.5 MB
resnet 18	87.6 %	6M:57S	339.1 MB
resnet 50	94.8 %	12M:16S	561.2 MB
resnet 101	96.0 %	17M:20S	1,030 MB

# slow
learn = cnn_learner_3d(dls, efficientnet_b0)

# slow
learn.lr_find()

SuggestedLRs(lr_min=0.014454397559165954, lr_steep=6.309573450380412e-07)

Click here for a more in-depth classification example.

Segmentation

dls = SegmentationDataLoaders3D.from_df(d,
                                 item_tfms = Resize3D((20, 112, 112)),
                                 batch_tfms = aug_transforms_3d(), 
                                 bs = 2, val_bs = 2)

All models in faimed3d can be used as a backbone for U-Nets, even with pre-trained weights.

# slow
learn = unet_learner_3d(dls, efficientnet_b0, n_out = 2)

# slow 
learn.lr_find()

SuggestedLRs(lr_min=0.33113112449646, lr_steep=0.10000000149011612)

Click here for a more in-depth segmentation example.

Extension to fastai for volumetric medical data

Related tags

Overview

FAIMED 3D

Classification

Segmentation

Owner

Keno

OpenMMLab Image and Video Editing Toolbox

A DeepStack custom model for detecting common objects in dark/night images and videos.

Supervised Contrastive Learning for Downstream Optimized Sequence Representations

Offline Multi-Agent Reinforcement Learning Implementations: Solving Overcooked Game with Data-Driven Method

This repository contains demos I made with the Transformers library by HuggingFace.

Pairwise model for commonlit competition

Anomaly Localization in Model Gradients Under Backdoor Attacks Against Federated Learning

Hand Gesture Volume Control | Open CV | Computer Vision

(ICCV'21) Official PyTorch implementation of Relational Embedding for Few-Shot Classification

A Python framework for conversational search

Implementation of several Bayesian multi-target tracking algorithms, including Poisson multi-Bernoulli mixture filters for sets of targets and sets of trajectories. The repository also includes the GOSPA metric and a metric for sets of trajectories to evaluate performance.

DziriBERT: a Pre-trained Language Model for the Algerian Dialect

Augmented Traffic Control: A tool to simulate network conditions

House-GAN++: Generative Adversarial Layout Refinement Network towards Intelligent Computational Agent for Professional Architects

Learning to Communicate with Deep Multi-Agent Reinforcement Learning in PyTorch

Record radiologists' eye gaze when they are labeling images.

[CVPR2021] Look before you leap: learning landmark features for one-stage visual grounding.

Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter

A port of muP to JAX/Haiku

PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training”