Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentation

@article{Taghanaki2019ComboLH,
  title={Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentation},
  author={Saeid Asgari Taghanaki and Y. Zheng and S. Zhou and B. Georgescu and P. Sharma and Daguang Xu and D. Comaniciu and G. Hamarneh},
  journal={Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society},
  year={2019},
  volume={75},
  pages={
          24-33
        }
}
  • Saeid Asgari Taghanaki, Y. Zheng, +5 authors G. Hamarneh
  • Published 2019
  • Computer Science, Medicine
  • Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
  • Simultaneous segmentation of multiple organs from different medical imaging modalities is a crucial task as it can be utilized for computer-aided diagnosis, computer-assisted surgery, and therapy planning. Thanks to the recent advances in deep learning, several deep neural networks for medical image segmentation have been introduced successfully for this purpose. In this paper, we focus on learning a deep multi-organ segmentation network that labels voxels. In particular, we examine the… CONTINUE READING
    18 Citations
    Marginal loss and exclusion loss for partially supervised multi-organ segmentation
    • 3
    • PDF
    Medical Image Segmentation Using Deep Learning: A Survey
    Improved Inference via Deep Input Transfer
    • 4
    • PDF
    Matthews Correlation Coefficient Loss for Deep Convolutional Networks: Application to Skin Lesion Segmentation
    Penalizing small errors using an Adaptive Logarithmic Loss
    • 2
    • PDF
    WCE Polyp Detection with Triplet based Embeddings
    Deep semantic segmentation of natural and medical images: a review
    • 31
    • PDF
    Deep Learning in Radiation Oncology Treatment Planning for Prostate Cancer: A Systematic Review
    • 1
    • Highly Influenced
    • PDF
    Myocardial Infarction Segmentation From Late Gadolinium Enhancement MRI By Neural Networks and Prior Information

    References

    SHOWING 1-10 OF 61 REFERENCES
    Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
    • 457
    • Highly Influential
    • PDF
    V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
    • 2,277
    • PDF
    Automatic Liver Segmentation Using an Adversarial Image-to-Image Network
    • 79
    • PDF
    Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets
    • 88
    Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound
    • 173
    • PDF
    Fully convolutional neural networks improve abdominal organ segmentation
    • 17
    Deep Convolutional Encoder Networks for Multiple Sclerosis Lesion Segmentation
    • 88
    • PDF
    U-Net: Convolutional Networks for Biomedical Image Segmentation
    • 16,867
    • PDF