Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans

• URL: http://arxiv.org/abs/2001.01330v4
• Date: Thu, 6 Apr 2023 09:01:41 GMT
• Title: Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans
• Authors: Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Nicolae Verga
• Abstract summary: We propose an approach for the single-image super-resolution of 3D CT or MRI scans. Our method is based on deep convolutional neural networks (CNNs) composed of 10 convolutional layers. We evaluate our method in the context of 2D and 3D super-resolution of CT and MRI scans from two databases.
• Score: 25.089517950882527
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: CT scanners that are commonly-used in hospitals nowadays produce low-resolution images, up to 512 pixels in size. One pixel in the image corresponds to a one millimeter piece of tissue. In order to accurately segment tumors and make treatment plans, doctors need CT scans of higher resolution. The same problem appears in MRI. In this paper, we propose an approach for the single-image super-resolution of 3D CT or MRI scans. Our method is based on deep convolutional neural networks (CNNs) composed of 10 convolutional layers and an intermediate upscaling layer that is placed after the first 6 convolutional layers. Our first CNN, which increases the resolution on two axes (width and height), is followed by a second CNN, which increases the resolution on the third axis (depth). Different from other methods, we compute the loss with respect to the ground-truth high-resolution output right after the upscaling layer, in addition to computing the loss after the last convolutional layer. The intermediate loss forces our network to produce a better output, closer to the ground-truth. A widely-used approach to obtain sharp results is to add Gaussian blur using a fixed standard deviation. In order to avoid overfitting to a fixed standard deviation, we apply Gaussian smoothing with various standard deviations, unlike other approaches. We evaluate our method in the context of 2D and 3D super-resolution of CT and MRI scans from two databases, comparing it to relevant related works from the literature and baselines based on various interpolation schemes, using 2x and 4x scaling factors. The empirical results show that our approach attains superior results to all other methods. Moreover, our human annotation study reveals that both doctors and regular annotators chose our method in favor of Lanczos interpolation in 97.55% cases for 2x upscaling factor and in 96.69% cases for 4x upscaling factor.

Related papers

• Resolution-Independent Neural Operators for Multi-Rate Sparse-View CT [67.14700058302016]
  Deep learning methods achieve high-fidelity reconstructions but often overfit to a fixed acquisition setup.<n>We propose Computed Tomography neural Operator (CTO), a unified CT reconstruction framework that extends to continuous function space.<n>CTO enables consistent multi-sampling-rate and cross-resolution performance, with on average >4dB PSNR gain over CNNs.
  arXiv  Detail & Related papers  (2025-12-13T08:31:46Z)
• Learning from spatially inhomogenous data: resolution-adaptive convolutions for multiple sclerosis lesion segmentation [32.93762295714261]
  In MRI, differences in between vendors, hospitals and sequences can yield highly inhomogeneous imaging data.<n>For clinical applications, algorithms must be trained to handle data with various voxel resolutions.<n>We present a network architecture designed to be able to learn directly from spatially heterogeneous data, without resampling.
  arXiv  Detail & Related papers  (2025-03-26T14:07:52Z)
• ECLARE: Efficient cross-planar learning for anisotropic resolution enhancement [3.854399264296032]
  In clinical imaging, magnetic resonance (MR) image volumes are often acquired as stacks of 2D slices, permitting decreased scan times, improved signal-to-noise ratio, and image contrasts unique to 2D MR pulse sequences. While this is sufficient for clinical evaluation, automated algorithms designed for 3D analysis perform sub-optimally on 2D-acquired scans, especially those with thick slices and gaps between slices. Super-resolution (SR) methods aim to address this problem, but previous methods do not address all of the following: slice profile shape estimation, slice gap, domain shift, and non-integer / arbitrary
  arXiv  Detail & Related papers  (2025-03-14T18:24:35Z)
• Deep learning network to correct axial and coronal eye motion in 3D OCT retinal imaging [65.47834983591957]
  We propose deep learning based neural networks to correct axial and coronal motion artifacts in OCT based on a single scan. The experimental result shows that the proposed method can effectively correct motion artifacts and achieve smaller error than other methods.
  arXiv  Detail & Related papers  (2023-05-27T03:55:19Z)
• Moving from 2D to 3D: volumetric medical image classification for rectal cancer staging [62.346649719614]
  preoperative discrimination between T2 and T3 stages is arguably both the most challenging and clinically significant task for rectal cancer treatment. We present a volumetric convolutional neural network to accurately discriminate T2 from T3 stage rectal cancer with rectal MR volumes.
  arXiv  Detail & Related papers  (2022-09-13T07:10:14Z)
• CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation [56.622832383316215]
  We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans. Our approach is based on cycle-consistent generative adversarial convolutional transformers, for short, CyTran. Our empirical results show that CyTran outperforms all competing methods.
  arXiv  Detail & Related papers  (2021-10-12T23:25:03Z)
• Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation [13.477290490742224]
  Super-resolution in medical imaging aims to increase the resolution of images but is conventionally trained on features from low resolution datasets. Here we propose a semi-supervised multi-task generative adversarial network (Gemini-GAN) that performs joint super-resolution of the images and their labels. Our proposed approach is extensively evaluated on two transnational multi-ethnic populations of 1,331 and 205 adults respectively.
  arXiv  Detail & Related papers  (2021-07-16T15:42:39Z)
• 3D Convolutional Neural Networks for Stalled Brain Capillary Detection [72.21315180830733]
  Brain vasculature dysfunctions such as stalled blood flow in cerebral capillaries are associated with cognitive decline and pathogenesis in Alzheimer's disease. Here, we describe a deep learning-based approach for automatic detection of stalled capillaries in brain images based on 3D convolutional neural networks. In this setting, our approach outperformed other methods and demonstrated state-of-the-art results, achieving 0.85 Matthews correlation coefficient, 85% sensitivity, and 99.3% specificity.
  arXiv  Detail & Related papers  (2021-04-04T20:30:14Z)
• Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast [4.987889348212769]
  We present SynthSR, a method to train a CNN that receives one or more thick-slice scans with different contrast, resolution and orientation. The presented method does not require any preprocessing, e.g., stripping or bias field correction.
  arXiv  Detail & Related papers  (2020-12-24T17:29:53Z)
• Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices [48.85784310158493]
  We propose a Modified Pseudo-3D Feature Pyramid Network (MP3D FPN) to efficiently extract 3D context enhanced 2D features for universal lesion detection in CT slices. With the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset. The proposed 3D pre-trained weights can potentially be used to boost the performance of other 3D medical image analysis tasks.
  arXiv  Detail & Related papers  (2020-12-16T07:11:16Z)
• Convolutional 3D to 2D Patch Conversion for Pixel-wise Glioma Segmentation in MRI Scans [22.60715394470069]
  We devise a novel pixel-wise segmentation framework through a convolutional 3D to 2D MR patch conversion model. In our architecture, both local inter-slice and global intra-slice features are jointly exploited to predict class label of the central voxel in a given patch.
  arXiv  Detail & Related papers  (2020-10-20T20:42:52Z)
• Uniformizing Techniques to Process CT scans with 3D CNNs for Tuberculosis Prediction [5.270882613122642]
  A common approach to medical image analysis on volumetric data uses deep 2D convolutional neural networks (CNNs) dealing with the individual slices independently in 2D CNNs deliberately discards the depth information which results in poor performance for the intended task. We evaluate a set of volume uniformizing methods to address the aforementioned issues. We report 73% area under curve (AUC) and binary classification accuracy (ACC) of 67.5% on the test set beating all methods which leveraged only image information.
  arXiv  Detail & Related papers  (2020-07-26T21:53:47Z)
• Cephalometric Landmark Regression with Convolutional Neural Networks on 3D Computed Tomography Data [68.8204255655161]
  Cephalometric analysis performed on lateral radiographs doesn't fully exploit the structure of 3D objects due to projection onto the lateral plane. We present a series of experiments with state of the art 3D convolutional neural network (CNN) based methods for keypoint regression. For the first time, we extensively evaluate the described methods and demonstrate their effectiveness in the estimation of Frankfort Horizontal and cephalometric points locations.
  arXiv  Detail & Related papers  (2020-07-20T12:45:38Z)
• HRINet: Alternative Supervision Network for High-resolution CT image Interpolation [3.7966959476339035]
  We propose a novel network, High Resolution Interpolation Network (HRINet), aiming at producing high-resolution CT images. We combine the idea of ACAI and GANs, and propose a novel idea of alternative supervision method by applying supervised and unsupervised training. Our experiments show the great improvement on 256 2 and 5122 images quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2020-02-11T15:09:42Z)

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.