# 3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes

arXiv: https://arxiv.org/abs/1809.00076 · HTML: https://mlsanity.com/paper/1809.00076/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2018.

## Built on by (most cited first, 30 of 42)

- [(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network](https://mlsanity.com/paper/2102.04530/) (2021)
- [Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation](https://mlsanity.com/paper/2102.04525/) (2021)
- [Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2110.08762/) (2021)
- [Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation](https://mlsanity.com/paper/2102.10365/) (2021)
- [Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook](https://mlsanity.com/paper/2312.05391/) (2023)
- [Directional Connectivity-based Segmentation of Medical Images](https://mlsanity.com/paper/2304.00145/) (2023)
- [Calibrating the Dice loss to handle neural network overconfidence for biomedical image segmentation](https://mlsanity.com/paper/2111.00528/) (2021)
- [Unknown Object Segmentation from Stereo Images](https://mlsanity.com/paper/2103.06796/) (2021)
- [A Generalized Surface Loss for Reducing the Hausdorff Distance in Medical Imaging Segmentation](https://mlsanity.com/paper/2302.03868/) (2023)
- [M2SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation](https://mlsanity.com/paper/2303.10894/) (2023)
- [Tilted Cross Entropy (TCE): Promoting Fairness in Semantic Segmentation](https://mlsanity.com/paper/2103.14051/) (2021)
- [Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses](https://mlsanity.com/paper/2104.08717/) (2021)
- [Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss](https://mlsanity.com/paper/2102.01897/) (2021)
- [MetaSSL: A General Heterogeneous Loss for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2509.01144/) (2025)
- [Automatic Segmentation of Gross Target Volume of Nasopharynx Cancer using Ensemble of Multiscale Deep Neural Networks with Spatial Attention](https://mlsanity.com/paper/2101.11254/) (2021)
- [A Data-Adaptive Loss Function for Incomplete Data and Incremental Learning in Semantic Image Segmentation](https://mlsanity.com/paper/2104.11020/) (2021)
- [3D Segmentation with Fully Trainable Gabor Kernels and Pearson's Correlation Coefficient](https://mlsanity.com/paper/2201.03644/) (2022)
- [Distribution-aware Margin Calibration for Semantic Segmentation in Images](https://mlsanity.com/paper/2112.11554/) (2021)
- [Shape-Sensitive Loss for Catheter and Guidewire Segmentation](https://mlsanity.com/paper/2311.11205/) (2023)
- [SemSegLoss: A python package of loss functions for semantic segmentation](https://mlsanity.com/paper/2106.05844/) (2021)
- [Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift](https://mlsanity.com/paper/2210.01891/) (2022)
- [Towards more precise automatic analysis: a comprehensive survey of deep learning-based multi-organ segmentation](https://mlsanity.com/paper/2303.00232/) (2023)
- [FNOSeg3D: Resolution-Robust 3D Image Segmentation with Fourier Neural Operator](https://mlsanity.com/paper/2310.03872/) (2023)
- [Inter- and intra-uncertainty based feature aggregation model for semi-supervised histopathology image segmentation](https://mlsanity.com/paper/2403.12767/) (2024)
- [R2U3D: Recurrent Residual 3D U-Net for Lung Segmentation](https://mlsanity.com/paper/2105.02290/) (2021)
- [HartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation](https://mlsanity.com/paper/2310.04466/) (2023)
- [Next Generation Loss Function for Image Classification](https://mlsanity.com/paper/2404.12948/) (2024)
- [Pixel-wise Modulated Dice Loss for Medical Image Segmentation](https://mlsanity.com/paper/2506.15744/) (2025)
- [HNOSeg-XS: Extremely Small Hartley Neural Operator for Efficient and Resolution-Robust 3D Image Segmentation](https://mlsanity.com/paper/2507.08205/) (2025)
- [Multiview and Multiclass Image Segmentation using Deep Learning in Fetal Echocardiography](https://mlsanity.com/paper/2103.12245/) (2021)

## Abstract (arXiv)

With the introduction of fully convolutional neural networks, deep learning has raised the benchmark for medical image segmentation on both speed and accuracy, and different networks have been proposed for 2D and 3D segmentation with promising results. Nevertheless, most networks only handle relatively small numbers of labels (<10), and there are very limited works on handling highly unbalanced object sizes especially in 3D segmentation. In this paper, we propose a network architecture and the corresponding loss function which improve segmentation of very small structures. By combining skip connections and deep supervision with respect to the computational feasibility of 3D segmentation, we propose a fast converging and computationally efficient network architecture for accurate segmentation. Furthermore, inspired by the concept of focal loss, we propose an exponential logarithmic loss which balances the labels not only by their relative sizes but also by their segmentation difficulties. We achieve an average Dice coefficient of 82% on brain segmentation with 20 labels, with the ratio of the smallest to largest object sizes as 0.14%. Less than 100 epochs are required to reach such accuracy, and segmenting a 128x128x128 volume only takes around 0.4 s.