Training robust deep learning models for medical imaging tasks with spectral decoupling

• URL: http://arxiv.org/abs/2103.17171v1
• Date: Wed, 31 Mar 2021 15:47:01 GMT
• Title: Training robust deep learning models for medical imaging tasks with spectral decoupling
• Authors: Joona Pohjonen, Carolin St\"urenberg, Antti Rannikko, Tuomas Mirtti, Esa Pitk\"anen
• Abstract summary: Spectral decoupling allows training neural networks on datasets with strong spurious correlations. Networks trained with spectral decoupling increase the accuracy by 10 percentage points over weight decay on the dataset from a different centre. Our results show that spectral decoupling allows training generalisable and robust neural networks to be used across multiple centres.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks show impressive performance in medical imaging tasks. However, many current networks generalise poorly to data unseen during training, for example data generated by different centres. Such behaviour can be caused by networks overfitting easy-to-learn, or statistically dominant, features while disregarding other potentially informative features. Moreover, dominant features can lead to learning spurious correlations. For instance, indistinguishable differences in the sharpness of the images from two different scanners can degrade the performance of the network significantly. To address these challenges, we evaluate the utility of spectral decoupling in the context of medical image analysis. Spectral decoupling encourages the neural network to learn more features by simply regularising the networks' unnormalized prediction scores with an L2 penalty. Simulation experiments show that spectral decoupling allows training neural networks on datasets with strong spurious correlations. Networks trained without spectral decoupling do not learn the original task and appear to make false predictions based on the spurious correlations. Spectral decoupling also significantly increases networks' robustness for data distribution shifts. To validate our findings, we train networks with and without spectral decoupling to detect prostate cancer on haematoxylin and eosin stained whole slide images. The networks are then evaluated with data scanned in the same centre with two different scanners, and data from a different centre. Networks trained with spectral decoupling increase the accuracy by 10 percentage points over weight decay on the dataset from a different centre. Our results show that spectral decoupling allows training generalisable and robust neural networks to be used across multiple centres, and recommend its use in future medical imaging tasks.

Related papers

• LMBF-Net: A Lightweight Multipath Bidirectional Focal Attention Network for Multifeatures Segmentation [15.091476025563528]
  Retinal diseases can cause irreversible vision loss in both eyes if not diagnosed and treated early. Current deep learning techniques for segmenting retinal images with many labels and attributes have poor detection accuracy and generalisability. This paper presents a multipath convolutional neural network for multifeature segmentation.
  arXiv  Detail & Related papers  (2024-07-03T07:37:09Z)
• Slicer Networks [8.43960865813102]
  We propose the Slicer Network, a novel architecture for medical image analysis. The Slicer Network strategically refines and upsamples feature maps via a splatting-blurring-slicing process. Experiments across different medical imaging applications have verified the Slicer Network's improved accuracy and efficiency.
  arXiv  Detail & Related papers  (2024-01-18T09:50:26Z)
• Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy [55.014926694758195]
  Entropy and mutual information in neural networks provide rich information on the learning process. We leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. We show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data.
  arXiv  Detail & Related papers  (2023-12-04T01:32:42Z)
• Are Deep Learning Classification Results Obtained on CT Scans Fair and Interpretable? [0.0]
  Most lung nodule classification papers using deep learning randomly shuffle data and split it into training, validation, and test sets. In contrast, deep neural networks trained with strict patient-level separation maintain their accuracy rates even when new patient images are tested. Heat-map visualizations of the activations of the deep neural networks trained with strict patient-level separation indicate a higher degree of focus on the relevant nodules.
  arXiv  Detail & Related papers  (2023-09-22T05:57:25Z)
• Data-Efficient Vision Transformers for Multi-Label Disease Classification on Chest Radiographs [55.78588835407174]
  Vision Transformers (ViTs) have not been applied to this task despite their high classification performance on generic images. ViTs do not rely on convolutions but on patch-based self-attention and in contrast to CNNs, no prior knowledge of local connectivity is present. Our results show that while the performance between ViTs and CNNs is on par with a small benefit for ViTs, DeiTs outperform the former if a reasonably large data set is available for training.
  arXiv  Detail & Related papers  (2022-08-17T09:07:45Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Correlation between image quality metrics of magnetic resonance images and the neural network segmentation accuracy [0.0]
  In this study, we investigated the correlation between the image quality metrics of MR images with the neural network segmentation accuracy. The difference in the segmentation accuracy between models based on the random training inputs with IQM based training inputs shed light on the role of image quality metrics on segmentation accuracy.
  arXiv  Detail & Related papers  (2021-11-01T17:02:34Z)
• HistoTransfer: Understanding Transfer Learning for Histopathology [9.231495418218813]
  We compare the performance of features extracted from networks trained on ImageNet and histopathology data. We investigate if features learned using more complex networks lead to gain in performance.
  arXiv  Detail & Related papers  (2021-06-13T18:55:23Z)
• Leveraging Sparse Linear Layers for Debuggable Deep Networks [86.94586860037049]
  We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. The resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks.
  arXiv  Detail & Related papers  (2021-05-11T08:15:25Z)
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization [59.5104563755095]
  We introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a representative feature space through variational encoding.
  arXiv  Detail & Related papers  (2020-09-27T12:30:30Z)
• Curriculum By Smoothing [52.08553521577014]
  Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. We propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data.
  arXiv  Detail & Related papers  (2020-03-03T07:27:44Z)

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.