2 citations · 3 across the 10 of their papers we have counts for
11 papers
Rethinking AI in Medical Imaging: Assumptions, Reality, and Reframing; Towards Physician-Centered Agentic Reasoning
Arman Rahmim, Nourhan Bayasi, Xiaoxiao Li +2
Medical imaging has served as primary proving ground for clinical AI, yet a decade of intense research has not translated into proportionate bedside impact. We argue that this gap…
Representation-Level Adversarial Regularization for Clinically Aligned Multitask Thyroid Ultrasound Assessment
Dina Salama, Mohamed Mahmoud, Nourhan Bayasi +2
Thyroid ultrasound is the first-line exam for assessing thyroid nodules and determining whether biopsy is warranted. In routine reporting, radiologists produce two coupled outputs:…
Multi-Kernel Gated Decoder Adapters for Robust Multi-Task Thyroid Ultrasound under Cross-Center Shift
Maziar Sabouri, Nourhan Bayasi, Arman Rahmim
Thyroid ultrasound (US) automation couples two competing requirements: global, geometry-driven reasoning for nodule delineation and local, texture-driven reasoning for malignancy r…
LesionGen: A Concept-Guided Diffusion Model for Dermatology Image Synthesis
Jamil Fayyad, Nourhan Bayasi, Ziyang Yu +1
Deep learning models for skin disease classification require large, diverse, and well-annotated datasets. However, such resources are often limited due to privacy concerns, high an…
Foundation Models as Class-Incremental Learners for Dermatological Image Classification
Mohamed Elkhayat, Mohamed Mahmoud, Jamil Fayyad +1
Class-Incremental Learning (CIL) aims to learn new classes over time without forgetting previously acquired knowledge. The emergence of foundation models (FM) pretrained on large d…
Conformal-in-the-Loop for Learning with Imbalanced Noisy Data
John Brandon Graham-Knight, Jamil Fayyad, Nourhan Bayasi +2
Class imbalance and label noise are pervasive in large-scale datasets, yet much of machine learning research assumes well-labeled, balanced data, which rarely reflects real world c…
Debiasify: Self-Distillation for Unsupervised Bias Mitigation
Nourhan Bayasi, Jamil Fayyad, Ghassan Hamarneh +2
Simplicity bias poses a significant challenge in neural networks, often leading models to favor simpler solutions and inadvertently learn decision rules influenced by spurious corr…
BiasPruner: Debiased Continual Learning for Medical Image Classification
Nourhan Bayasi, Jamil Fayyad, Alceu Bissoto +2
Continual Learning (CL) is crucial for enabling networks to dynamically adapt as they learn new tasks sequentially, accommodating new data and classes without catastrophic forgetti…
AViT: Adapting Vision Transformers for Small Skin Lesion Segmentation Datasets
Siyi Du, Nourhan Bayasi, Ghassan Hamarneh +1
Skin lesion segmentation (SLS) plays an important role in skin lesion analysis. Vision transformers (ViTs) are considered an auspicious solution for SLS, but they require more trai…
MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets
Siyi Du, Nourhan Bayasi, Ghassan Hamarneh +1
Despite its clinical utility, medical image segmentation (MIS) remains a daunting task due to images' inherent complexity and variability. Vision transformers (ViTs) have recently…
FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning
Siyi Du, Ben Hers, Nourhan Bayasi +2
Deep learning models have achieved great success in automating skin lesion diagnosis. However, the ethnic disparity in these models' predictions, where lesions on darker skin types…