wentaozhu/deep-mil-for-whole-mammogram-classification

Stars
113
Rank 310,115 (Top 7 %)
Language
Python
License
MIT License
Created over 7 years ago
Updated over 6 years ago

wentaozhu/deep-mil-for-whole-mammogram-classification

wentaozhu

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Zhu, Wentao, Qi Lou, Yeeleng Scott Vang, and Xiaohui Xie. "Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification." MICCAI 2017.

deep-mil-for-whole-mammogram-classification

The code is based on keras with theano backend.

Please cite our paper

Zhu, Wentao, Qi Lou, Yeeleng Scott Vang, and Xiaohui Xie. "Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification." MICCAI 2017.

Preprocessed InBreast dataset can be downloaded from https://drive.google.com/drive/folders/0B-7-8LLwONIZZm1pQWdyak5Od28?usp=sharing or https://pan.baidu.com/s/1eMep77riQrXqg9oU5uPAHw. If you use the preprocessed dataset, you do not need to download the original InBreast dataset.

For label processing, please read inbreast.py readlabel() function. For converting dicom to pickle file, please read readdicom() function in the inbreast.py.

For original InBreast dataset (.dicom files), please contact http://medicalresearch.inescporto.pt/breastresearch/index.php/Get_INbreast_Database .

run_cnn_k_new.py is used for alex net. run_cnn_k_mil_new.py is used for max pooling based deep mil. run_cnn_k_mysparsemil_new.py is used for sparse deep mil. run_cnn_k_mymil_new.py is used for label assignment based deep mil. Here we finetuned weights from max pooling based deep mil.

_test is used for test.

Our code is based on conv-keras and keras. If you use current version of keras, you need to revised the code a little bit for adaption. I will update a repo. for current keras.

If you have any questions, please contact with me [email protected].

DeepLung

WACV18 paper "DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification"

Jupyter Notebook

AnatomyNet-for-anatomical-segmentation

AnatomyNet: Deep 3D Squeeze-and-excitation U-Nets for fast and fully automated whole-volume anatomical segmentation

AutoShot

AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection - CVPR NAS 2023

adversarial-deep-structural-networks

ISBI2018: Adversarial Deep Structural Networks for Mammographic Mass Segmentation https://arxiv.org/abs/1612.05970

protein-cascade-cnn-lstm

Implementation of IJCAI15 cascade cnn and LSTM for protein secondary structure prediction

speechnas

SpeechNAS-Better-Trade-off-between-Latency-and-Accuracy-for-Large-Scale-Speaker-Verification

Hierarchical-ELM-Network

IJCNN 2015 Hierarchical extreme learning machine for unsupervised representation learning

recurrent-attention-for-QA-SQUAD-based-on-keras

recurrent attention based on keras. Question Answering SQUAD dataset

DeepEM-for-Weakly-Supervised-Detection

MICCAI18 DeepEM: Deep 3D ConvNets with EM for Weakly Supervised Pulmonary Nodule Detection

Jupyter Notebook

constrained-extreme-learning-machine

constrained extreme learning machine, IJCNN 2014

rna_protein_binding

deep multi-instance learning for rna protein binding prediction

inbreast

Extreme-support-vector-regression

The code is used for the Pattern Recognition Letters paper "Robust regression with extreme support vectors". There are kernel based ESVR and conventional ESVR respectively. Please cite it as "Zhu, Wentao, Jun Miao, and Laiyun Qing. "Robust regression with extreme support vectors." Pattern Recognition Letters 45 (2014): 205-210."

lamp-automated-model-parallelism

MICCAI20 Early Accepted "LAMP: Large Deep Nets with Automated Model Parallelism for Image Segmentation"

AI_Reading_List

My everyday reading list about healthcare, AI, machine learning, deep learning, startup

CTnoddetector

SLAM

Deep-trans-layer-unsupervised-network

deep trans-layer PCA network and deep trans-layer denoising auto encoder network