A Neural Ordinary Differential Equation Model for Visualizing Deep Neural Network Behaviors in Multi-Parametric MRI based Glioma Segmentation

• URL: http://arxiv.org/abs/2203.00628v1
• Date: Tue, 1 Mar 2022 17:16:41 GMT
• Title: A Neural Ordinary Differential Equation Model for Visualizing Deep Neural Network Behaviors in Multi-Parametric MRI based Glioma Segmentation
• Authors: Zhenyu Yang, Zongsheng Hu, Hangjie Ji, Kyle Lafata, Scott Floyd, Fang-Fang Yin, Chunhao Wang
• Abstract summary: We develop a neural ordinary differential equation (ODE) model for visualizing deep neural network (DNN) during multi-parametric MRI (mp-MRI) based glioma segmentation. All neural ODE models successfully illustrated image dynamics as expected.
• Score: 3.1435638364138105
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Purpose: To develop a neural ordinary differential equation (ODE) model for visualizing deep neural network (DNN) behavior during multi-parametric MRI (mp-MRI) based glioma segmentation as a method to enhance deep learning explainability. Methods: By hypothesizing that deep feature extraction can be modeled as a spatiotemporally continuous process, we designed a novel deep learning model, neural ODE, in which deep feature extraction was governed by an ODE without explicit expression. The dynamics of 1) MR images after interactions with DNN and 2) segmentation formation can be visualized after solving ODE. An accumulative contribution curve (ACC) was designed to quantitatively evaluate the utilization of each MRI by DNN towards the final segmentation results. The proposed neural ODE model was demonstrated using 369 glioma patients with a 4-modality mp-MRI protocol: T1, contrast-enhanced T1 (T1-Ce), T2, and FLAIR. Three neural ODE models were trained to segment enhancing tumor (ET), tumor core (TC), and whole tumor (WT). The key MR modalities with significant utilization by DNN were identified based on ACC analysis. Segmentation results by DNN using only the key MR modalities were compared to the ones using all 4 MR modalities. Results: All neural ODE models successfully illustrated image dynamics as expected. ACC analysis identified T1-Ce as the only key modality in ET and TC segmentations, while both FLAIR and T2 were key modalities in WT segmentation. Compared to the U-Net results using all 4 MR modalities, Dice coefficient of ET (0.784->0.775), TC (0.760->0.758), and WT (0.841->0.837) using the key modalities only had minimal differences without significance. Conclusion: The neural ODE model offers a new tool for optimizing the deep learning model inputs with enhanced explainability. The presented methodology can be generalized to other medical image-related deep learning applications.

Related papers

• Comparative Study of Probabilistic Atlas and Deep Learning Approaches for Automatic Brain Tissue Segmentation from MRI Using N4 Bias Field Correction and Anisotropic Diffusion Pre-processing Techniques [0.0]
  This study provides a comparative analysis of various segmentation models, including Probabilistic ATLAS, U-Net, nnU-Net, and LinkNet. Our results demonstrate that the 3D nnU-Net model outperforms others, achieving the highest mean Dice Coefficient score (0.937 + 0.012) The findings highlight the superiority of nnU-Net models in brain tissue segmentation, particularly when combined with N4 Bias Field Correction and Anisotropic Diffusion pre-processing techniques.
  arXiv  Detail & Related papers  (2024-11-08T10:07:03Z)
• NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation [55.51412454263856]
  This paper proposes to directly modulate the generation process of diffusion models using fMRI signals. By training with about 67,000 fMRI-image pairs from various individuals, our model enjoys superior fMRI-to-image decoding capacity.
  arXiv  Detail & Related papers  (2024-03-27T02:42:52Z)
• DeepThalamus: A novel deep learning method for automatic segmentation of brain thalamic nuclei from multimodal ultra-high resolution MRI [32.73124984242397]
  We have designed and implemented a multimodal volumetric deep neural network for the segmentation of thalamic nuclei at ultra-high resolution (0.125 mm3) A database of semiautomatically segmented thalamic nuclei was created using ultra-high resolution T1, T2 and White Matter nulled (WMn) images. A novel Deep learning based strategy was designed to obtain the automatic segmentations and trained to improve its robustness and accuaracy.
  arXiv  Detail & Related papers  (2024-01-15T14:59:56Z)
• A Radiomics-Incorporated Deep Ensemble Learning Model for Multi-Parametric MRI-based Glioma Segmentation [5.890417404600585]
  We developed a deep ensemble learning model with a radiomics spatial encoding execution for improved glioma segmentation accuracy. This model was developed using 369 glioma patients with a 4-modality mp-MRI protocol: T1, contrast-enhanced T1 (T1-Ce), T2, and FLAIR.
  arXiv  Detail & Related papers  (2023-03-19T02:16:55Z)
• Modality-Agnostic Variational Compression of Implicit Neural Representations [96.35492043867104]
  We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR) Bridging the gap between latent coding and sparsity, we obtain compact latent representations non-linearly mapped to a soft gating mechanism. After obtaining a dataset of such latent representations, we directly optimise the rate/distortion trade-off in a modality-agnostic space using neural compression.
  arXiv  Detail & Related papers  (2023-01-23T15:22:42Z)
• Deep Convolutional Neural Networks for Molecular Subtyping of Gliomas Using Magnetic Resonance Imaging [24.418025043887678]
  A DCNN model was developed for the prediction of the five glioma subtypes based on a hierarchical classification paradigm. The predictive performance was evaluated via the area under the curve (AUC) from the receiver operating characteristic analysis. The results showed that the developed DCNN model can predict glioma subtypes with promising performance, given sufficient, non-ill-balanced training data.
  arXiv  Detail & Related papers  (2022-03-10T14:46:20Z)
• A multi-stage machine learning model on diagnosis of esophageal manometry [50.591267188664666]
  The framework includes deep-learning models at the swallow-level stage and feature-based machine learning models at the study-level stage. This is the first artificial-intelligence-style model to automatically predict CC diagnosis of HRM study from raw multi-swallow data.
  arXiv  Detail & Related papers  (2021-06-25T20:09:23Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• M2Net: Multi-modal Multi-channel Network for Overall Survival Time Prediction of Brain Tumor Patients [151.4352001822956]
  Early and accurate prediction of overall survival (OS) time can help to obtain better treatment planning for brain tumor patients. Existing prediction methods rely on radiomic features at the local lesion area of a magnetic resonance (MR) volume. We propose an end-to-end OS time prediction model; namely, Multi-modal Multi-channel Network (M2Net)
  arXiv  Detail & Related papers  (2020-06-01T05:21:37Z)
• Stochasticity in Neural ODEs: An Empirical Study [68.8204255655161]
  Regularization of neural networks (e.g. dropout) is a widespread technique in deep learning that allows for better generalization. We show that data augmentation during the training improves the performance of both deterministic and versions of the same model. However, the improvements obtained by the data augmentation completely eliminate the empirical regularization gains, making the performance of neural ODE and neural SDE negligible.
  arXiv  Detail & Related papers  (2020-02-22T22:12:56Z)
• Deep Learning Estimation of Multi-Tissue Constrained Spherical Deconvolution with Limited Single Shell DW-MRI [2.903217519429591]
  Deep learning can be used to estimate the information content captured by 8th order constrained spherical deconvolution (CSD) We examine two network architectures: Sequential network of fully connected dense layers with a residual block in the middle (ResDNN), and Patch based convolutional neural network with a residual block (ResCNN) The fiber orientation distribution function (fODF) can be recovered with high correlation as compared to the ground truth of MT-CST, which was derived from the multi-shell DW-MRI acquisitions.
  arXiv  Detail & Related papers  (2020-02-20T15:59:03Z)

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.