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

To SMOTE, or not to SMOTE?

List of awesome things around semantic segmentation 🎉

Code for "Diffusion is All You Need for Learning on Surfaces"

FluidNet re-written with ATen tensor lib

EmoTag helps you train emotion detection model for Chinese audios

This is an official PyTorch implementation of Task-Adaptive Neural Network Search with Meta-Contrastive Learning (NeurIPS 2021, Spotlight).

Face uncertainty quantification or estimation using PyTorch.

Architecture Patterns with Python (TDD, DDD, EDM)

Intelligent Video Analytics toolkit based on different inference backends.

Open source Python module for computer vision

i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery

Tiny-NewsRec: Efﬁcient and Effective PLM-based News Recommendation

This is the repository of the NeurIPS 2021 paper "Curriculum Disentangled Recommendation withNoisy Multi-feedback"

Efficient Online Bayesian Inference for Neural Bandits

Code for paper "Document-Level Argument Extraction by Conditional Generation". NAACL 21'

Crawl & visualize ICLR papers and reviews

Codes for our paper The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders published to EMNLP 2021.

Sarus implementation of classical ML models. The models are implemented using the Keras API of tensorflow 2. Vizualization are implemented and can be seen in tensorboard.

TextBPN Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection