MedNNS: Supernet-Based Medical Task-Adaptive Neural Network Search
Mecharbat, Lotfi Abdelkrim Almakky, Ibrahim Takáč, Martin Yaqub, Mohammad K.
Mecharbat, Lotfi Abdelkrim
Almakky, Ibrahim
Takáč, Martin
Yaqub, Mohammad K.
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2026
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Deep learning (DL) has achieved remarkable progress in the field of medical imaging. However, adapting DL models to medical tasks remains a significant challenge, primarily due to two key factors: (1) architecture selection, as different tasks necessitate specialized model designs, and (2) weight initialization, which directly impacts the convergence speed and final performance of the models. Although transfer learning from ImageNet is a widely adopted strategy, its effectiveness is constrained by the substantial differences between natural and medical images. To address these challenges, we introduce Medical Neural Network Search (MedNNS), the first Neural Network Search framework for medical imaging applications. MedNNS jointly optimizes architecture selection and weight initialization by constructing a meta-space that encodes datasets and models based on how well they perform together. We build this space using a Supernetwork-based approach, expanding the model zoo size by 51×times over previous state-of-the-art (SOTA) methods. Moreover, we introduce rank loss and Fréchet Inception Distance (FID) loss into the construction of the space to capture inter-model and inter-dataset relationships, thereby achieving more accurate alignment in the meta-space. Experimental results across multiple datasets demonstrate that MedNNS significantly outperforms both ImageNet pretrained DL models and SOTA Neural Architecture Search (NAS) methods, achieving an average accuracy improvement of 1.7% across datasets while converging substantially faster. The code and the processed meta-space is available at https://github.com/BioMedIA-MBZUAI/MedNNS.
Citation
L. A. Mecharbat, I. Almakky, M. Takac, and M. Yaqub, “MedNNS: Supernet-Based Medical Task-Adaptive Neural Network Search,” Lecture Notes in Computer Science, vol. 15965 LNCS, pp. 448–458, 2026, doi: 10.1007/978-3-032-04978-0_43/TABLES/2
Source
Lecture Notes in Computer Science
Conference
28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
Keywords
Meta Learning, Neural Network Search, Supernetworks
Subjects
Source
28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
Publisher
Springer Nature