Search Results for author:
Found 8 papers, 5 papers with code
Exploring Intrinsic Properties of Medical Images for Self-Supervised Binary Semantic Segmentation
MedSASS outperforms existing CNN-based self-supervised methods by 3. 83% and matches the performance of ViT-based methods.
Free Form Medical Visual Question Answering in Radiology
We innovatively augment the SLAKE dataset, enabling our model to respond to a more diverse array of questions, not limited to the immediate content of radiology or pathology images.
Shifting to Machine Supervision: Annotation-Efficient Semi and Self-Supervised Learning for Automatic Medical Image Segmentation and Classification
Our study benchmarks these techniques on three distinct medical imaging datasets to evaluate their effectiveness in classification and segmentation tasks.
Enhancing Medical Image Segmentation: Optimizing Cross-Entropy Weights and Post-Processing with Autoencoders
In this paper, we present a deep-learning approach tailored for Medical image segmentation.
Efficient Representation Learning for Healthcare with Cross-Architectural Self-Supervision
We also demonstrate that CASS is considerably more robust to variations in batch size and pretraining epochs, making it a suitable candidate for machine learning in healthcare applications.
Cross-Architectural Positive Pairs improve the effectiveness of Self-Supervised Learning
Existing self-supervised techniques have extreme computational requirements and suffer a substantial drop in performance with a reduction in batch size or pretraining epochs.
A Data-Efficient Deep Learning Framework for Segmentation and Classification of Histopathology Images
The current study of cell architecture of inflammation in histopathology images commonly performed for diagnosis and research purposes excludes a lot of information available on the biopsy slide.
Ranked #1 on
Medical Image Segmentation
on Autoimmune Dataset
CASS: Cross Architectural Self-Supervision for Medical Image Analysis
We also show that CASS is much more robust to changes in batch size and training epochs.
Ranked #1 on
Classification
on Brain Tumor MRI Dataset
