lemondan / Focal-liver-lesions-dataset-in-CEUS

We publish our SYSU-CEUS dataset, which consists of three types of FLLs: 186 HCC instances, 109 HEM instances and 58 FNH instances (i.e.,186 malignant instances and 167 benign instances). In this repository, we only upload a small set of data to illustrate. Please contact xdliang328@gmail.com, if you need the full dataset for academic purposes.
12 stars 3 forks source link

SYSU-FLL-CEUS Dataset

We publish our SYSU-CEUS dataset, which consists of three types of FLLs: 186 HCC instances, 109 HEM instances and 58 FNH instances (i.e.,186 malignant instances and 167 benign instances).

This dataset is collected from the First Affiliated Hospital, Sun Yat-sen University. The equipment used was Aplio SSA-770A (Toshiba Medical System).

All these instances with resolution 768*576 were taken from different patients, with large variations in appearance and enhancement patterns (e.g. sizes, contrasts, shapes and locations) of the FLLs. Project website: http://vision.sysu.edu.cn/projects/fllrecog/.

weblink for full dataset: https://drive.google.com/folderview?id=0B5LimsUgYY7ifjRfLUtxb1FRZ2ZXcHN0a0oyeFFUaXdyT2xBMDRpclZES0dTMS1uTXk3VjA&usp=sharing

Please cite our published papers in ISBI and TMI journal if you use this dataset.

Xiaodan Liang and Qingxing Cao and Rui Huang and Liang Lin, Recognizing focal liver lesions in contrast-enhanced ultrasound with discriminatively trained spatio-temporal model, Biomedical Imaging (ISBI), 2014 IEEE 11th International Symposium on, 2014.

Xiaodan Liang, Liang Lin, Qingxing Cao, Rui Huang, Yongtian Wang, “Recognizing Focal Liver Lesions in CEUS with Dynamically Trained Latent Structured Models”. IEEE TRANSACTIONS ON MEDICAL IMAGING (T-MI), 2015