Estimating concept difficulty with cross entropy.

Image structures are segmented automatically using deep learning (DL) for analysis and processing. The three most popular base loss functions are cross entropy (crossE), intersect-over-the-union (IoU), and dice. Which should be used, is it useful to consider simple variations, such as modifying formula coefficients? How do characteristics of different image structures influence scores? Taking three different medical image segmentation problems (segmentation of organs in magnetic resonance images (MRI), liver in computer tomography images (CT) and diabetic retinopathy lesions in eye fundus images (EFI)), we quantify loss functions and variations, as well as segmentation scores of different targets. We first describe the limitations of metrics, since loss is a metric, then we describe and test alternatives. Experimentally, we observed that DeeplabV3 outperforms UNet and fully convolutional network (FCN) in all datasets. Dice scored 1 to 6 percentage points (pp) higher than cross entropy over all datasets, IoU improved 0 to 3 pp. Varying formula coefficients improved scores, but the best choices depend on the dataset: compared to crossE, different false positive vs. false negative weights improved MRI by 12 pp, and assigning zero weight to background improved EFI by 6 pp. Multiclass segmentation scored higher than n-uniclass segmentation in MRI by 8 pp. EFI lesions score low compared to more constant structures (e.g., optic disk or even organs), but loss modifications improve those scores significantly 6 to 9 pp. Our conclusions are that dice is best, it is worth assigning 0 weight to class background and to test different weights on false positives and false negatives.

Download Full-text

Hybrid cross entropy—cuckoo search algorithm for solving optimal power flow with renewable generators and controllable loads

Optimal Control Applications and Methods ◽

10.1002/oca.2759 ◽

2021 ◽

Author(s):

Jigar Sarda ◽

Kartik Pandya ◽

Kwang Y. Lee

Keyword(s):

Power Flow ◽

Optimal Power Flow ◽

Search Algorithm ◽

Cuckoo Search ◽

Cuckoo Search Algorithm ◽

Cross Entropy ◽

Optimal Power ◽

Hybrid Cross

Download Full-text

A Densely Connected Network Based on U-Net for Medical Image Segmentation

ACM Transactions on Multimedia Computing Communications and Applications ◽

10.1145/3446618 ◽

2021 ◽

Vol 17 (3) ◽

pp. 1-14

Author(s):

Zhenzhen Yang ◽

Pengfei Xu ◽

Yongpeng Yang ◽

Bing-Kun Bao

Keyword(s):

Feature Extraction ◽

Image Segmentation ◽

Loss Function ◽

Network Architecture ◽

Medical Image ◽

Medical Image Segmentation ◽

Cross Entropy ◽

Loss Functions ◽

Feature Maps ◽

Different Levels

The U-Net has become the most popular structure in medical image segmentation in recent years. Although its performance for medical image segmentation is outstanding, a large number of experiments demonstrate that the classical U-Net network architecture seems to be insufficient when the size of segmentation targets changes and the imbalance happens between target and background in different forms of segmentation. To improve the U-Net network architecture, we develop a new architecture named densely connected U-Net (DenseUNet) network in this article. The proposed DenseUNet network adopts a dense block to improve the feature extraction capability and employs a multi-feature fuse block fusing feature maps of different levels to increase the accuracy of feature extraction. In addition, in view of the advantages of the cross entropy and the dice loss functions, a new loss function for the DenseUNet network is proposed to deal with the imbalance between target and background. Finally, we test the proposed DenseUNet network and compared it with the multi-resolutional U-Net (MultiResUNet) and the classic U-Net networks on three different datasets. The experimental results show that the DenseUNet network has significantly performances compared with the MultiResUNet and the classic U-Net networks.

Download Full-text