10 citations · 17 across the 4 of their papers we have counts for
4 papers
SonoSAMTrack -- Segment and Track Anything on Ultrasound Images
Hariharan Ravishankar, Rohan Patil, Vikram Melapudi +5
In this paper, we present SonoSAMTrack - that combines a promptable foundational model for segmenting objects of interest on ultrasound images called SonoSAM, with a state-of-the a…
Towards Continuous Domain adaptation for Healthcare
Rahul Venkataramani, Hariharan Ravishankar, Saihareesh Anamandra
Deep learning algorithms have demonstrated tremendous success on challenging medical imaging problems. However, post-deployment, these algorithms are susceptible to data distributi…
Understanding the Mechanisms of Deep Transfer Learning for Medical Images
Hariharan Ravishankar, Prasad Sudhakar, Rahul Venkataramani +4
The ability to automatically learn task specific feature representations has led to a huge success of deep learning methods. When large training data is scarce, such as in medical…
Filter sharing: Efficient learning of parameters for volumetric convolutions
Rahul Venkataramani, Sheshadri Thiruvenkadam, Prasad Sudhakar +2
Typical convolutional neural networks (CNNs) have several millions of parameters and require a large amount of annotated data to train them. In medical applications where training…