Co-Learning Feature Fusion Maps From PET-CT Images of Lung Cancer

@article{Kumar2020CoLearningFF,
  title={Co-Learning Feature Fusion Maps From PET-CT Images of Lung Cancer},
  author={Ashnil Kumar and Michael J. Fulham and Dagan Feng and Jinman Kim},
  journal={IEEE Transactions on Medical Imaging},
  year={2020},
  volume={39},
  pages={204-217}
}
The analysis of multi-modality positron emission tomography and computed tomography (PET-CT) images for computer-aided diagnosis applications (e.g., detection and segmentation) requires combining the sensitivity of PET to detect abnormal regions with anatomical localization from CT. [...] Key Method Our CNN first encodes modality-specific features and then uses them to derive a spatially varying fusion map that quantifies the relative importance of each modality’s feature across different spatial locations…Expand
Recurrent feature fusion learning for multi-modality pet-ct tumor segmentation
TLDR
A recurrent fusion network (rfn) is proposed, which consists of multiple recurrent fusion phases to progressively fuse the complementary multi-modality image features with intermediary segmentation results derived at individual recurrent fused phases. Expand
Multimodal Spatial Attention Module for Targeting Multimodal PET-CT Lung Tumor Segmentation
TLDR
A deep learning-based framework in multimodal PET-CT segmentation with a multi-modality spatial attention module (MSAM) is introduced that surpasses the state-of-the-art lung tumor segmentation approach by a margin of 7.6% in Dice similarity coefficient (DSC). Expand
EFNet: evidence fusion network for tumor segmentation from PET-CT volumes
  • Zhaoshuo Diao, Huiyan Jiang, Xian-Hua Han, Yu-Dong Yao, Tianyu Shi
  • Physics, Medicine
  • Physics in medicine and biology
  • 2021
TLDR
The results show that in PET-CT segmentation methods based on FCN, by outputting uncertainty evidence and evidence fusion, the network can be simplified and the segmentation results can be improved. Expand
Improving PET-CT Image Segmentation via Deep Multi-modality Data Augmentation
TLDR
A generative adversarial network (GAN) based augmentation method to synthesized multi- modality data pairs on PET and CT to improve the training of multi-modality segmentation method and demonstrates that the synthesized images generated by the method can be used to augment the training data for PET-CT segmentation. Expand
Unsupervised Positron Emission Tomography Tumor Segmentation via GAN based Adversarial Auto-Encoder
TLDR
A convolutional adversarial auto-encoder is introduced to learn a latent space which models normal (disease-free) variations of PET images, and then to compute a residual map that identifies where the PET image differs from this manifold due to anomalies, i.e., tumors. Expand
Automatic Segmentation of Head and Neck Tumors and Nodal Metastases in PET-CT scans
TLDR
An automatic segmentation of Head and Neck tumors and nodal metastases from FDG-PET and CT images using a fully-convolutional network trained on PET-CT images using ground truth ROIs that were manually delineated by radiation oncologists for 202 patients is proposed. Expand
Using deep learning techniques in medical imaging: a systematic review of applications on CT and PET
TLDR
A survey of the use of DL architectures in computer-assisted imaging contexts, attending two different image modalities: the actively studied computed tomography and the under-studied positron emission tomography, as well as the combination of both modalities, which has been an important landmark in several decisions related to numerous diseases. Expand
Deep learning in Nuclear Medicine—focus on CNN-based approaches for PET/CT and PET/MR: where do we stand?
Introduction In recent years, machine learning algorithms have led to innovative tools for medical imaging analysis. The purpose of the present review was to summarize the literature on theExpand
Combining CNN and Hybrid Active Contours for Head and Neck Tumor Segmentation in CT and PET images
TLDR
This short paper introduces a multi-channel 3D U-Net to segment the tumor with the concatenated PET and CT images and estimates the segmentation uncertainty by model ensembles and defines a segmentation quality score to select the cases with high uncertainties. Expand
A Comprehensive Review of Computer-Aided Diagnosis of Pulmonary Nodules Based on Computed Tomography Scans
TLDR
A comprehensive review of the application and development of CAD systems is presented, covering public datasets of lung CT scans, commonly used evaluation metrics and various medical competitions, and the advantages of CNNs over traditional image processing methods are summarized. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 87 REFERENCES
3D fully convolutional networks for co-segmentation of tumors on PET-CT images
TLDR
A novel approach for the segmentation of lung tumors that combines the powerful fully convolutional networks (FCN) based semantic segmentation framework (3D-UNet) and the graph cut based co-segmentation model is proposed. Expand
Tumor co-segmentation in PET/CT using multi-modality fully convolutional neural network.
TLDR
This study proposed a novel multi-modality segmentation method based on a 3D fully convolutional neural network (FCN), which is capable of taking account of both PET and CT information simultaneously for tumor segmentation and achieved significantly performance gain over CNN-based methods and traditional methods. Expand
Deep learning for variational multimodality tumor segmentation in PET/CT
TLDR
The proposed novel deep learning based variational method successfully fused the complementary information in PET/CT, and outperformed two existing deep learning-based multimodality segmentation methods and other multi-modality segmentsation methods using traditional fusion strategies (without deep learning). Expand
Optimal Co-Segmentation of Tumor in PET-CT Images With Context Information
TLDR
A novel method for the co-segmentation of the tumor in both PET and CT images, which makes use of advantages from each modality: the functionality information from PET and the anatomical structure information from CT. Expand
PET/CT: form and function.
TLDR
This review will describe some of the most recent technologic developments in PET/CT instrumentation and the clinical indications for which combined PET/ CT has been shown to be more useful than PET and CT performed separately. Expand
Multi-stage Thresholded Region Classification for Whole-Body PET-CT Lymphoma Studies
TLDR
A new method to automatically separate NEURs in thresholded PET images is proposed to group thresholded regions of the same structure with spatial and texture based clustering; the approach had better accuracy when compared to conventional methods. Expand
Thoracic cavity definition for 3D PET/CT analysis and visualization
TLDR
An automatic method for thoracic cavity segmentation from 3D CT scans is presented and how the method facilitates 3D ROI localization and visualization in patient multimodal imaging studies is demonstrated. Expand
Automated detection of pulmonary nodules in PET/CT images: Ensemble false-positive reduction using a convolutional neural network technique.
TLDR
An improved FP-reduction scheme using CNN technique has been developed for the detection of pulmonary nodules in PET/CT images by means of convolutional neural networks (CNNs) and results indicate that the method may be useful in the computer-aided detection ofmonary nodules using PET/ CT images. Expand
Simultaneous cosegmentation of tumors in PET‐CT images using deep fully convolutional networks
TLDR
The proposed DFCN cosegmentation shows promise for further integration with quantitative multimodality imaging tools in clinical trials and outperforms the deep learning method using either PET or CT alone. Expand
Globally Optimal Tumor Segmentation in PET-CT Images: A Graph-Based Co-segmentation Method
TLDR
The method simulates the clinical practice of delineating tumor simultaneously using both PET and CT, and is able to concurrently segment tumor from both modalities, achieving globally optimal solutions in low-order polynomial time by a single maximum flow computation. Expand
...
1
2
3
4
5
...