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

A library of extension and helper modules for Python's data analysis and machine learning libraries.

Pytorch implementation of "ARM: Any-Time Super-Resolution Method"

The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".

Robust, modular and efficient implementation of advanced Hamiltonian Monte Carlo algorithms

[CVPR'21] FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space

OpenMMLab Image Classification Toolbox and Benchmark

Monocular Depth Estimation - Weighted-average prediction from multiple pre-trained depth estimation models

Learned Initializations for Optimizing Coordinate-Based Neural Representations

Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval (NeurIPS'21)

Next-gen Rowhammer fuzzer that uses non-uniform, frequency-based patterns.

SplineConv implementation for Paddle.

Implementation of Continuous Sparsification, a method for pruning and ticket search in deep networks

PyTorch implementation of SMODICE: Versatile Offline Imitation Learning via State Occupancy Matching

novel deep learning research works with PaddlePaddle

The pure and clear PyTorch Distributed Training Framework.

The implemention of Video Depth Estimation by Fusing Flow-to-Depth Proposals

fklearn: Functional Machine Learning

Faune proche - Retrieval of Faune-France data near a google maps location

Release of SPLASH: Dataset for semantic parse correction with natural language feedback in the context of text-to-SQL parsing

Speech Recognition using DeepSpeech2.