MedNNS: Supernet-based Medical Task-Adaptive Neural Network Search

• URL: http://arxiv.org/abs/2504.15865v2
• Date: Wed, 23 Apr 2025 05:28:18 GMT
• Title: MedNNS: Supernet-based Medical Task-Adaptive Neural Network Search
• Authors: Lotfi Abdelkrim Mecharbat, Ibrahim Almakky, Martin Takac, Mohammad Yaqub,
• Abstract summary: We introduce Medical Neural Network Search (MedNNS), the first Neural Network Search framework for medical imaging applications.<n>We build a meta-space that encodes datasets and models based on how well they perform together.<n>We show that MedNNS significantly outperforms both ImageNet pre-trained DL models and SOTA Neural Architecture Search (NAS) methods.
• Score: 0.8812173669205372
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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 51x times over previous state-of-the-art (SOTA) methods. Moreover, we introduce rank loss and Fr\'echet 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 pre-trained 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.

Related papers

• Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image Retrieval [0.37478492878307323]
  Content-based medical image retrieval (CBMIR) depends on image features, which can be extracted automatically or semi-automatically.<n>In this study, we used several pre-trained feature extractors from well-known pre-trained convolutional neural networks (CNNs) and pre-trained foundation models.<n>Our results show that, overall, for the 2D datasets, foundation models deliver superior performance by a large margin compared to CNNs.<n>Our findings confirm that while using larger image sizes (especially for 2D datasets) yields slightly better performance, competitive CBMIR performance can still be achieved even with smaller image
  arXiv  Detail & Related papers  (2024-09-14T13:07:30Z)
• A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism [58.855741970337675]
  Neural architecture search (NAS) enables re-searchers to automatically explore vast search spaces and find efficient neural networks. NAS suffers from a key bottleneck, i.e., numerous architectures need to be evaluated during the search process. We propose the SMEM-NAS, a pairwise com-parison relation-assisted multi-objective evolutionary algorithm based on a multi-population mechanism.
  arXiv  Detail & Related papers  (2024-07-22T12:46:22Z)
• LiteNeXt: A Novel Lightweight ConvMixer-based Model with Self-embedding Representation Parallel for Medical Image Segmentation [2.0901574458380403]
  We propose a new lightweight but efficient model, namely LiteNeXt, for medical image segmentation.<n>The model is trained from scratch with small amount of parameters (0.71M) and Giga Floating Point Operations Per Second (0.42).<n>Experiments on public datasets including Data Science Bowls, GlaS, ISIC2018, PH2, Sunnybrook, and Lung X-ray data show promising results.
  arXiv  Detail & Related papers  (2024-04-04T01:59:19Z)
• Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain [46.44049019428938]
  We introduce a new neural network architecture, termed LoGoNet, with a tailored self-supervised learning (SSL) method.<n>LoGoNet integrates a novel feature extractor within a U-shaped architecture, leveraging Large Kernel Attention (LKA) and a dual encoding strategy.<n>We propose a novel SSL method tailored for 3D images to compensate for the lack of large labeled datasets.
  arXiv  Detail & Related papers  (2024-02-09T05:06:58Z)
• Predicting Infant Brain Connectivity with Federated Multi-Trajectory GNNs using Scarce Data [54.55126643084341]
  Existing deep learning solutions suffer from three major limitations. We introduce FedGmTE-Net++, a federated graph-based multi-trajectory evolution network. Using the power of federation, we aggregate local learnings among diverse hospitals with limited datasets.
  arXiv  Detail & Related papers  (2024-01-01T10:20:01Z)
• Connecting the Dots: Graph Neural Network Powered Ensemble and Classification of Medical Images [0.0]
  Deep learning for medical imaging is limited due to the requirement for large amounts of training data. We employ the Image Foresting Transform to optimally segment images into superpixels. These superpixels are subsequently transformed into graph-structured data, enabling the proficient extraction of features and modeling of relationships.
  arXiv  Detail & Related papers  (2023-11-13T13:20:54Z)
• DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs [53.82853297675979]
  1-bit convolutional neural networks (CNNs) with binary weights and activations show their potential for resource-limited embedded devices. One natural approach is to use 1-bit CNNs to reduce the computation and memory cost of NAS. We introduce Discrepant Child-Parent Neural Architecture Search (DCP-NAS) to efficiently search 1-bit CNNs.
  arXiv  Detail & Related papers  (2023-06-27T11:28:29Z)
• LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching [59.01894976615714]
  We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
  arXiv  Detail & Related papers  (2023-06-20T22:21:34Z)
• Recurrence With Correlation Network for Medical Image Registration [66.63200823918429]
  We present Recurrence with Correlation Network (RWCNet), a medical image registration network with multi-scale features and a cost volume layer. We demonstrate that these architectural features improve medical image registration accuracy in two image registration datasets.
  arXiv  Detail & Related papers  (2023-02-05T02:41:46Z)
• InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images [53.4351366246531]
  We construct a novel interpretable dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded. We analyze the CT values among different tissues, and merge the prior observations into a prior network for our InDuDoNet+, which significantly improve its generalization performance.
  arXiv  Detail & Related papers  (2021-12-23T15:52:37Z)
• Two layer Ensemble of Deep Learning Models for Medical Image Segmentation [0.2699900017799093]
  We propose a two-layer ensemble of deep learning models for the segmentation of medical images. The prediction for each training image pixel made by each model in the first layer is used as the augmented data of the training image. The prediction of the second layer is then combined by using a weights-based scheme in which each model contributes differently to the combined result.
  arXiv  Detail & Related papers  (2021-04-10T16:52:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.