DiffSeg: Diffusion-Based Weakly Supervised Segmentation for Fibrosis
A novel diffusion-based method for weakly supervised semantic segmentation, achieving SOTA performance on fibrotic lung disease using only image-level labels and eliminating the need for pixel-level annotations.
Auto Lung Anatomy Segmentation
Trained and Evaluated CNNs-based Segmentation Model for automated lung region segmentation.
Explainable AI - Controlable Image Generation
Investigated the intermediate latent spaces in generative AI StyleGAN and Diffusion models for controlable image generation.
Evaluating Generative AI: GAN-Based Models
Evaluated cutting-edge GANs-based AI and their applications. Explored advancements in GAN architectures and their practical implementations across various domains