Corpus ID: 235193542

Optimizing Operating Points for High Performance Lesion Detection and Segmentation Using Lesion Size Reweighting

@article{Nichyporuk2021OptimizingOP,
  title={Optimizing Operating Points for High Performance Lesion Detection and Segmentation Using Lesion Size Reweighting},
  author={Brennan Nichyporuk and Justin Szeto and Douglas L. Arnold and Tal Arbel},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.12978}
}
There are many clinical contexts which require accurate detection and segmentation of all focal pathologies (e.g. lesions, tumours) in patient images. In cases where there are a mix of small and large lesions, standard binary cross entropy loss will result in better segmentation of large lesions at the expense of missing small ones. Adjusting the operating point to accurately detect all lesions generally leads to oversegmentation of large lesions. In this work, we propose a novel reweighing… Expand

Figures from this paper

References

SHOWING 1-5 OF 5 REFERENCES
Universal Loss Reweighting to Balance Lesion Size Inequality in 3D Medical Image Segmentation
TLDR
A loss reweighting approach to increase the ability of the network to detect small lesions and shows that inverse weighting considerably increases the detection quality, while preserves the delineation quality on a state-of-the-art level. Expand
Lesion Detection, Segmentation and Prediction in Multiple Sclerosis Clinical Trials
TLDR
A series of fully-automatic, probabilistic machine learning frameworks to detect and segment all lesions in patient MRI, and show their accuracy and robustness in large multi-center, multi-scanner, clinical trial datasets are presented. Expand
Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation
TLDR
A 3D MS lesion segmentation CNN is developed, augmented to provide four different voxel-based uncertainty measures based on Monte Carlo (MC) dropout, and empirical evidence suggests that uncertainty measures consistently allow us to choose superior operating points compared only using the network’s sigmoid output as a probability. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
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. Expand
Focal Loss for Dense Object Detection
TLDR
This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. Expand