Gallbladder Ultrasound Video (GBUSV) Dataset

Figure: Sample ultrasound video sequences.


GBUSV is a un-annotated dataset consisting of ultrasound videos of of patients with either of a malignant or a non-malignant gallbladder. The ultrasound videos were obtained from patients referred to the radiology department of PGIMER, Chandigarh (a high-input hospital in Northern India) for abdominal ultrasound examinations of suspected gallbladder pathologies. Patients were at fasting of at least 6 hours. A 1-5 MHz curved array transducer (C-1-5D, Logiq S8, GE Healthcare) was used. The scanning intended to include the entire gallbladder and the lesion or pathology. The length of the video sequences varies from 43 to 888 frames. The dataset consists of 32 malignant and 32 non-malignant videos containing a total of 12,251 and 3,549 frames, respectively. The video frames are cropped from the center to anonymize the patient information and annotations. The processed frame sizes are of size 360x480 pixels.


The images of the video sequences are un-annotated and suitable for unsupervised learning tasks. We provide the high-level categorization for each video whether it's malignant or non-malignant.

Download Dataset

To obtain the dataset, please fill and sign this License Agreement, and send it to Dr. Pankaj Gupta and Dr. Chetan Arora.
After duly verifying the License Agreement, we will mail the dataset download link to you.
Note: We will only accept requests from permanent employees/ faculty of the requesting institute. We will ignore all requests from students. Student Researchers must ask their Supervisor/ Head of the Department to fill out and send the agreement to us.

BibTeX (Citation)

If you use GBUSV for your research, then please cite our paper using the following BibTeX.
  title={Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos with Hard Negative Mining},
  author={Basu, Soumen and Singla, Somanshu and Gupta, Mayank and Rana, Pratyaksha and Gupta, Pankaj and Arora, Chetan},
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},

Credits: Template of this webpage from here.