Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images

• URL: http://arxiv.org/abs/2308.07688v5
• Date: Thu, 8 Feb 2024 09:06:00 GMT
• Title: Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images
• Authors: Soroosh Tayebi Arasteh, Leo Misera, Jakob Nikolas Kather, Daniel Truhn, Sven Nebelung
• Abstract summary: Self-supervised learning (SSL) can be applied to chest radiographs to learn robust features. We tested our approach on over 800,000 chest radiographs from six large global datasets.
• Score: 1.883452979588382
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Pre-training datasets, like ImageNet, have become the gold standard in medical image analysis. However, the emergence of self-supervised learning (SSL), which leverages unlabeled data to learn robust features, presents an opportunity to bypass the intensive labeling process. In this study, we explored if SSL for pre-training on non-medical images can be applied to chest radiographs and how it compares to supervised pre-training on non-medical images and on medical images. We utilized a vision transformer and initialized its weights based on (i) SSL pre-training on natural images (DINOv2), (ii) SL pre-training on natural images (ImageNet dataset), and (iii) SL pre-training on chest radiographs from the MIMIC-CXR database. We tested our approach on over 800,000 chest radiographs from six large global datasets, diagnosing more than 20 different imaging findings. Our SSL pre-training on curated images not only outperformed ImageNet-based pre-training (P<0.001 for all datasets) but, in certain cases, also exceeded SL on the MIMIC-CXR dataset. Our findings suggest that selecting the right pre-training strategy, especially with SSL, can be pivotal for improving artificial intelligence (AI)'s diagnostic accuracy in medical imaging. By demonstrating the promise of SSL in chest radiograph analysis, we underline a transformative shift towards more efficient and accurate AI models in medical imaging.

Related papers

• Self-supervised learning for skin cancer diagnosis with limited training data [0.196629787330046]
  Self-supervised learning (SSL) is an alternative to the standard supervised pre-training on ImageNet data for scenarios with limited training data. We find that minimal further SSL pre-training on task-specific data can be as effective as large-scale SSL pre-training on ImageNet for medical image classification tasks with limited labelled data.
  arXiv  Detail & Related papers  (2024-01-01T08:11:38Z)
• Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training [51.16994853817024]
  This work focuses on designing an effective pre-training framework for 3D radiology images. We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations. The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-07-31T17:59:42Z)
• 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)
• Performance of GAN-based augmentation for deep learning COVID-19 image classification [57.1795052451257]
  The biggest challenge in the application of deep learning to the medical domain is the availability of training data. Data augmentation is a typical methodology used in machine learning when confronted with a limited data set. In this work, a StyleGAN2-ADA model of Generative Adversarial Networks is trained on the limited COVID-19 chest X-ray image set.
  arXiv  Detail & Related papers  (2023-04-18T15:39:58Z)
• Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime [70.04389979779195]
  This paper explores training medical vision-language models (VLMs) where the visual and language inputs are embedded into a common space. We explore several candidate methods to improve low-data performance, including adapting generic pre-trained models to novel image and text domains. Using text-to-image retrieval as a benchmark, we evaluate the performance of these methods with variable sized training datasets of paired chest X-rays and radiological reports.
  arXiv  Detail & Related papers  (2023-03-30T18:20:00Z)
• Exploring Self-Supervised Representation Learning For Low-Resource Medical Image Analysis [2.458658951393896]
  We investigate the applicability of self-supervised learning algorithms on small-scale medical imaging datasets. In-domain low-resource SSL pre-training can yield competitive performance to transfer learning from large-scale datasets.
  arXiv  Detail & Related papers  (2023-03-03T22:26:17Z)
• Self-Supervised Curricular Deep Learning for Chest X-Ray Image Classification [1.6631602844999727]
  Self-Supervised Learning pretraining outperforms models trained from scratch or pretrained on ImageNet. Top-performing SSLpretrained models show a higher degree of attention in the lung regions.
  arXiv  Detail & Related papers  (2023-01-25T16:45:13Z)
• PCRLv2: A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image Analysis [56.63327669853693]
  We propose to incorporate the task of pixel restoration for explicitly encoding more pixel-level information into high-level semantics. We also address the preservation of scale information, a powerful tool in aiding image understanding. The proposed unified SSL framework surpasses its self-supervised counterparts on various tasks.
  arXiv  Detail & Related papers  (2023-01-02T17:47:27Z)
• Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning [10.631361618707214]
  Well-annotated medical datasets enable deep neural networks (DNNs) to gain strong power in extracting lesion-related features. Model pre-training based on ImageNet is a common practice to gain better generalization when the data amount is limited. In this work, we pre-trains on ultrasound (US) domains instead of ImageNet to reduce the domain gap in medical US applications.
  arXiv  Detail & Related papers  (2022-12-08T06:24:08Z)
• SB-SSL: Slice-Based Self-Supervised Transformers for Knee Abnormality Classification from MRI [5.199134881541244]
  We propose a slice-based self-supervised deep learning framework (SBSSL) for classifying abnormality using knee MRI scans. For a limited number of cases (1000), our proposed framework is capable to identify anterior cruciate ligament tear with an accuracy of 89.17% and an AUC of 0.954.
  arXiv  Detail & Related papers  (2022-08-29T23:08:41Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)

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.