# A Data-Adaptive Loss Function for Incomplete Data and Incremental Learning in Semantic Image Segmentation

arXiv: https://arxiv.org/abs/2104.11020 · HTML: https://mlsanity.com/paper/2104.11020/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 22 Apr 2021.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentation](https://mlsanity.com/paper/1805.02798/) (2018)
- [No New-Net](https://mlsanity.com/paper/1809.10483/) (2018)
- [3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes](https://mlsanity.com/paper/1809.00076/) (2018)
- [Semi-Supervised Multi-Organ Segmentation via Deep Multi-Planar Co-Training](https://mlsanity.com/paper/1804.02586/) (2018)
- [TuNet: End-to-end Hierarchical Brain Tumor Segmentation using Cascaded Networks](https://mlsanity.com/paper/1910.05338/) (2019)
- [Multi-Decoder Networks with Multi-Denoising Inputs for Tumor Segmentation](https://mlsanity.com/paper/2012.03684/) (2020)
- [A 2D dilated residual U-Net for multi-organ segmentation in thoracic CT](https://mlsanity.com/paper/1905.07710/) (2019)
- [Evaluation of Multi-Slice Inputs to Convolutional Neural Networks for Medical Image Segmentation](https://mlsanity.com/paper/1912.09287/) (2019)

## Built on by (most cited first, 5 of 5)

- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application](https://mlsanity.com/paper/2310.14277/) (2023)
- [Domain-incremental Cardiac Image Segmentation with Style-oriented Replay and Domain-sensitive Feature Whitening](https://mlsanity.com/paper/2211.04862/) (2022)
- [A Unified Framework for Tabular Generative Modeling: Loss Functions, Benchmarks, and Improved Multi-objective Bayesian Optimization Approaches](https://mlsanity.com/paper/2405.16971/) (2024)
- [Using Synthetic Images to Augment Small Medical Image Datasets](https://mlsanity.com/paper/2503.00962/) (2025)

## Abstract (arXiv)

In the last years, deep learning has dramatically improved the performances in a variety of medical image analysis applications. Among different types of deep learning models, convolutional neural networks have been among the most successful and they have been used in many applications in medical imaging. Training deep convolutional neural networks often requires large amounts of image data to generalize well to new unseen images. It is often time-consuming and expensive to collect large amounts of data in the medical image domain due to expensive imaging systems, and the need for experts to manually make ground truth annotations. A potential problem arises if new structures are added when a decision support system is already deployed and in use. Since the field of radiation therapy is constantly developing, the new structures would also have to be covered by the decision support system. In the present work, we propose a novel loss function, that adapts to the available data in order to utilize all available data, even when some have missing annotations. We demonstrate that the proposed loss function also works well in an incremental learning setting, where it can automatically incorporate new structures as they appear. Experiments on a large in-house data set show that the proposed method performs on par with baseline models, while greatly reducing the training time.