Impact of loss function in Deep Learning methods for accurate retinal vessel segmentation

• URL: http://arxiv.org/abs/2206.00536v1
• Date: Wed, 1 Jun 2022 14:47:18 GMT
• Title: Impact of loss function in Deep Learning methods for accurate retinal vessel segmentation
• Authors: Daniela Herrera and Gilberto Ochoa-Ruiz and Miguel Gonzalez-Mendoza and Christian Mata
• Abstract summary: We compare Binary Cross Entropy, Dice, Tversky, and Combo loss using the deep learning architectures (i.e. U-Net, Attention U-Net, and Nested UNet) with the DRIVE dataset. The results showed that there is a significant difference in the selection of loss function.
• Score: 1.1470070927586016
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The retinal vessel network studied through fundus images contributes to the diagnosis of multiple diseases not only found in the eye. The segmentation of this system may help the specialized task of analyzing these images by assisting in the quantification of morphological characteristics. Due to its relevance, several Deep Learning-based architectures have been tested for tackling this problem automatically. However, the impact of loss function selection on the segmentation of the intricate retinal blood vessel system hasn't been systematically evaluated. In this work, we present the comparison of the loss functions Binary Cross Entropy, Dice, Tversky, and Combo loss using the deep learning architectures (i.e. U-Net, Attention U-Net, and Nested UNet) with the DRIVE dataset. Their performance is assessed using four metrics: the AUC, the mean squared error, the dice score, and the Hausdorff distance. The models were trained with the same number of parameters and epochs. Using dice score and AUC, the best combination was SA-UNet with Combo loss, which had an average of 0.9442 and 0.809 respectively. The best average of Hausdorff distance and mean square error were obtained using the Nested U-Net with the Dice loss function, which had an average of 6.32 and 0.0241 respectively. The results showed that there is a significant difference in the selection of loss function

Related papers

• Cross-dataset domain adaptation for the classification COVID-19 using chest computed tomography images [0.6798775532273751]
  COVID19-DANet is based on pre-trained CNN backbone for feature extraction. It is tested under four cross-dataset scenarios using the SARS-CoV-2-CT and COVID19-CT datasets.
  arXiv  Detail & Related papers  (2023-11-14T20:36:34Z)
• FS-Net: Full Scale Network and Adaptive Threshold for Improving Extraction of Micro-Retinal Vessel Structures [4.776514178760067]
  We propose a full-scale micro-vessel extraction mechanism based on an encoder-decoder neural network architecture. The proposed solution has been evaluated using the DRIVE, CHASE-DB1, and STARE datasets.
  arXiv  Detail & Related papers  (2023-11-14T10:32:17Z)
• Class Anchor Margin Loss for Content-Based Image Retrieval [97.81742911657497]
  We propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimize for the L2 metric without the need of generating pairs. We evaluate the proposed objective in the context of few-shot and full-set training on the CBIR task, by using both convolutional and transformer architectures.
  arXiv  Detail & Related papers  (2023-06-01T12:53:10Z)
• A Generalized Surface Loss for Reducing the Hausdorff Distance in Medical Imaging Segmentation [1.2289361708127877]
  We propose a novel loss function to minimize Hausdorff-based metrics with more desirable numerical properties than current methods. Our loss function outperforms other losses when tested on the LiTS and BraTS datasets using the state-of-the-art nnUNet architecture.
  arXiv  Detail & Related papers  (2023-02-08T04:01:42Z)
• Adaptation to CT Reconstruction Kernels by Enforcing Cross-domain Feature Maps Consistency [0.06117371161379209]
  We show a decrease in the COVID-19 segmentation quality of the model trained on the smooth and tested on the sharp reconstruction kernels. We propose the unsupervised adaptation method, called F-Consistency, that outperforms the previous approaches.
  arXiv  Detail & Related papers  (2022-03-28T10:00:03Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Binary segmentation of medical images using implicit spline representations and deep learning [1.5293427903448025]
  We propose a novel approach to image segmentation based on combining implicit spline representations with deep convolutional neural networks. For our best network, we achieve an average volumetric test Dice score of almost 92%, which reaches the state of the art for this congenital heart disease dataset.
  arXiv  Detail & Related papers  (2021-02-25T10:04:25Z)
• Topological obstructions in neural networks learning [67.8848058842671]
  We study global properties of the loss gradient function flow. We use topological data analysis of the loss function and its Morse complex to relate local behavior along gradient trajectories with global properties of the loss surface.
  arXiv  Detail & Related papers  (2020-12-31T18:53:25Z)
• An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
  We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem. We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
  arXiv  Detail & Related papers  (2020-12-06T18:55:07Z)
• DONet: Dual Objective Networks for Skin Lesion Segmentation [77.9806410198298]
  We propose a simple yet effective framework, named Dual Objective Networks (DONet), to improve the skin lesion segmentation. Our DONet adopts two symmetric decoders to produce different predictions for approaching different objectives. To address the challenge of large variety of lesion scales and shapes in dermoscopic images, we additionally propose a recurrent context encoding module (RCEM)
  arXiv  Detail & Related papers  (2020-08-19T06:02:46Z)
• clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation [57.20783326661043]
  We introduce a novel similarity measure termed centerlineDice (short clDice) We theoretically prove that clDice guarantees topology preservation up to homotopy equivalence for binary 2D and 3D segmentation. We benchmark the soft-clDice loss on five public datasets, including vessels, roads and neurons (2D and 3D)
  arXiv  Detail & Related papers  (2020-03-16T16:27:49Z)

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.