CAN3D: Fast 3D Medical Image Segmentation via Compact Context Aggregation

• URL: http://arxiv.org/abs/2109.05443v1
• Date: Sun, 12 Sep 2021 06:27:59 GMT
• Title: CAN3D: Fast 3D Medical Image Segmentation via Compact Context Aggregation
• Authors: Wei Dai, Boyeong Woo, Siyu Liu, Matthew Marques, Craig B. Engstrom, Peter B. Greer, Stuart Crozier, Jason A. Dowling and Shekhar S. Chandras
• Abstract summary: We present a compact convolutional neural network with a shallow memory footprint to efficiently reduce the number of model parameters required for state-of-art performance. The proposed network can maintain data integrity by directly processing large full-size 3D input volumes with no patches required.
• Score: 6.188937569449575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Direct automatic segmentation of objects from 3D medical imaging, such as magnetic resonance (MR) imaging, is challenging as it often involves accurately identifying a number of individual objects with complex geometries within a large volume under investigation. To address these challenges, most deep learning approaches typically enhance their learning capability by substantially increasing the complexity or the number of trainable parameters within their models. Consequently, these models generally require long inference time on standard workstations operating clinical MR systems and are restricted to high-performance computing hardware due to their large memory requirement. Further, to fit 3D dataset through these large models using limited computer memory, trade-off techniques such as patch-wise training are often used which sacrifice the fine-scale geometric information from input images which could be clinically significant for diagnostic purposes. To address these challenges, we present a compact convolutional neural network with a shallow memory footprint to efficiently reduce the number of model parameters required for state-of-art performance. This is critical for practical employment as most clinical environments only have low-end hardware with limited computing power and memory. The proposed network can maintain data integrity by directly processing large full-size 3D input volumes with no patches required and significantly reduces the computational time required for both training and inference. We also propose a novel loss function with extra shape constraint to improve the accuracy for imbalanced classes in 3D MR images.

Related papers

• Efficient Slice Anomaly Detection Network for 3D Brain MRI Volume [2.3633885460047765]
  Current anomaly detection methods excel with benchmark industrial data but struggle with medical data due to varying definitions of 'normal' and 'abnormal' We propose a framework called Simple Slice-based Network (SimpleSliceNet), which utilizes a model pre-trained on ImageNet and fine-tuned on a separate MRI dataset as a 2D slice feature extractor to reduce computational cost.
  arXiv  Detail & Related papers  (2024-08-28T17:20:56Z)
• Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimes [2.8498944632323755]
  We propose an end-to-end hybrid architecture for medical image segmentation. We use Hamiltonian Variational Autoencoders (HVAE) and a discriminative regularization to improve the quality of generated images. Our architecture operates on a slice-by-slice basis to segment 3D volumes, capitilizing on the richly augmented dataset.
  arXiv  Detail & Related papers  (2024-06-17T15:42:08Z)
• Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain [48.440691680864745]
  We introduce a new neural network architecture, termed LoGoNet, with a tailored self-supervised learning (SSL) method. LoGoNet integrates a novel feature extractor within a U-shaped architecture, leveraging Large Kernel Attention (LKA) and a dual encoding strategy. 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)
• Leveraging Frequency Domain Learning in 3D Vessel Segmentation [50.54833091336862]
  In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models. We show that our novel network achieves remarkable dice performance (84.37% on ASACA500 and 80.32% on ImageCAS) in tubular vessel segmentation tasks.
  arXiv  Detail & Related papers  (2024-01-11T19:07:58Z)
• Random resistive memory-based deep extreme point learning machine for unified visual processing [67.51600474104171]
  We propose a novel hardware-software co-design, random resistive memory-based deep extreme point learning machine (DEPLM) Our co-design system achieves huge energy efficiency improvements and training cost reduction when compared to conventional systems.
  arXiv  Detail & Related papers  (2023-12-14T09:46:16Z)
• 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)
• GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction [50.248694764703714]
  Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction. These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based regularization. We propose Greedy LEarning for Accelerated MRI reconstruction, an efficient training strategy for high-dimensional imaging settings.
  arXiv  Detail & Related papers  (2022-07-18T06:01:29Z)
• Memory Efficient Invertible Neural Networks for 3D Photoacoustic Imaging [1.0312968200748118]
  Photoacoustic imaging (PAI) can image high-resolution structures of clinical interest. Iterative physical model based approaches reduce artifacts but require time consuming PDE solves. We propose using invertible neural networks (INNs) to alleviate memory pressure.
  arXiv  Detail & Related papers  (2022-04-24T18:37:18Z)
• Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN [52.851990439671475]
  We propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation.
  arXiv  Detail & Related papers  (2020-08-05T02:33:04Z)
• Organ Segmentation From Full-size CT Images Using Memory-Efficient FCN [10.411340412305849]
  In medical image segmentation tasks, subvolume cropping has become a common preprocessing. We present a memory-efficient fully convolutional network (FCN) incorporated with several memory-optimized techniques.
  arXiv  Detail & Related papers  (2020-03-24T07:12:45Z)

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.