Reducing the Model Variance of a Rectal Cancer Segmentation Network

@article{Lee2019ReducingTM,
  title={Reducing the Model Variance of a Rectal Cancer Segmentation Network},
  author={Joohyun Lee and Ji Eun Oh and Min Ju Kim and Bo Yun Hur and Dae Kyung Sohn},
  journal={IEEE Access},
  year={2019},
  volume={7},
  pages={182725-182733}
}
In preoperative imaging, the demarcation of rectal cancer with magnetic resonance images provides an important basis for cancer staging and treatment planning. [] Key Method Moreover, we propose a method to perform a bias-variance analysis within an arbitrary region-of-interest (ROI) of a segmentation network, which we applied to assess the efficacy of our approaches in reducing model variance.

Figures and Tables from this paper

Automatic segmentation of rectal tumor on diffusion‐weighted images by deep learning with U‐Net

Volumetric U-Net can automatically segment rectal tumor region on DWI images of locally advanced rectal cancer.

Moving from 2D to 3D: Volumetric Medical Image Classification for Rectal Cancer Staging

A volumetric convolutional neural network to accurately discriminate T2 from T3 stage rectal cancer with rectal MR volumes is presented and it is believed this method can be extended to other volume analysis tasks.

Deep learning-based automatic delineation of anal cancer gross tumour volume: a multimodality comparison of CT, PET and MRI.

CNNs provided high-quality automatic GTV delineations for both single and multimodality image input, indicating that deep learning may prove a versatile tool for target volume delineation in future patients with ASCC.

A Diversified Supervised based U-shape Colorectal Lesion Segmentor with Meaningful Feature Supplement and Multi-Level Residual Attention Mechanism

The proposed model outperforms other state-of-the-art techniques for colorectal lesion segmentation on CT images, achieving Dice scores of 0.733 and dramatically decreasing Hausdorff distance to 17.62.

A review of medical image data augmentation techniques for deep learning applications

A systematic review of the literature where data augmentation was utilised on medical images to train a deep learning model aims to give an insight to these techniques and confidence in the validity of the models produced.

Diagnosis of rectal cancer based on the Xception-MS network

The experimental results show that the proposed deep-learning-based Xception-MS diagnostic model is superior to the existing classification models, can effectively and automatically classify ultrasound images of rectal cancer, and can better assist doctors in the diagnosis ofrectal cancer.

Imaging of colorectal nodal disease

MSBC-Net: Automatic Rectal Cancer Segmentation from MR Scans

The comprehensive results show that the proposed MSBC-Net outperforms state-of-the-art methods with a dice similarity coefficient (DSC) of 0.801 (95\% CI, 0.791-0.811), which can be well extended to other medical image segmentation tasks with high potential clinical applicability.

References

SHOWING 1-10 OF 68 REFERENCES

Deep Learning for Fully-Automated Localization and Segmentation of Rectal Cancer on Multiparametric MR

It is demonstrated that deep learning can perform accurate localization and segmentation of rectal cancer in MR imaging in the majority of patients.

Knowledge-Aided Convolutional Neural Network for Small Organ Segmentation

Experimental results demonstrate that the proposed method outperforms cutting-edge deep learning approaches, traditional forest-based approaches, and multi-atlas approaches in the segmentation of small organs.

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.

V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation

The proposed method, named V-NAS, consistently outperforms other state-of-the-arts on the segmentation tasks of both normal organ and abnormal organs and can be well generalized to other datasets, which demonstrates the robustness and practical use of the proposed method.

Preprocessing MRI Images of Colorectal Cancer

The research work focuses on the various preprocessing techniques such as noise removal techniques and image enhancement techniques and the optimal method is determined for generating a noise-free edgesharp intensity enhanced MRI images of colon and rectum cancer, paving for precision diagnosis.

A survey on deep learning in medical image analysis

Learning normalized inputs for iterative estimation in medical image segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Deep Learning for Fully-Automated Localization and Segmentation of Rectal Cancer on Multiparametric MR

It is demonstrated that deep learning can perform accurate localization and segmentation of rectal cancer in MR imaging in the majority of patients.

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.
...