mlsanityData to 7 Oct 2026

Size and Smoothness Aware Adaptive Focal Loss for Small Tumor Segmentation

arXiv 2407.09828 ↗First posted 13 Jul 2024eess.IV cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning has achieved remarkable accuracy in medical image segmentation, particularly for larger structures with well-defined boundaries. However, its effectiveness can be challenged by factors such as irregular object shapes and edges, non-smooth surfaces, small target areas, etc. which complicate the ability of networks to grasp the intricate and diverse nature of anatomical regions. In response to these challenges, we propose an Adaptive Focal Loss (A-FL) that takes both object boundary smoothness and size into account, with the goal to improve segmentation performance in intricate anatomical regions. The proposed A-FL dynamically adjusts itself based on an object's surface smoothness, size, and the class balancing parameter based on the ratio of targeted area and background. We evaluated the performance of the A-FL on the PICAI 2022 and BraTS 2018 datasets. In the PICAI 2022 dataset, the A-FL achieved an Intersection over Union (IoU) score of 0.696 and a Dice Similarity Coefficient (DSC) of 0.769, outperforming the regular Focal Loss (FL) by 5.5% and 5.4% respectively. It also surpassed the best baseline by 2.0% and 1.2%. In the BraTS 2018 dataset, A-FL achieved an IoU score of 0.883 and a DSC score of 0.931. Our ablation experiments also show that the proposed A-FL surpasses conventional losses (this includes Dice Loss, Focal Loss, and their hybrid variants) by large margin in IoU, DSC, and other metrics. The code is available at https://github.com/rakibuliuict/AFL-CIBM.git.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 45 references that are in the map. First posted on arXiv 13 Jul 2024.

Builds on

24 of 45 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  4. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  5. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  6. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
  7. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 823
  8. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  9. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
  10. 2015Holistically-Nested Edge Detectioncited by 590
  11. 20183D MRI brain tumor segmentation using autoencoder regularizationcited by 324
  12. 2019ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed datacited by 260
12 more
  1. 2017Tversky loss function for image segmentation using 3D fully convolutional deep networkscited by 228
  2. 2020A survey of loss functions for semantic segmentationcited by 216
  3. 2018Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentationcited by 180
  4. 2017Deep Extreme Cut: From Extreme Points to Object Segmentationcited by 127
  5. 2024Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directionscited by 97
  6. 20193DRegNet: A Deep Neural Network for 3D Point Registrationcited by 96
  7. 2019AdaptIS: Adaptive Instance Selection Networkcited by 64
  8. 2020The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabelingcited by 64
  9. 2022PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functionscited by 62
  10. 2017Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation using Holistic Convolutional Networkscited by 21
  11. 2024SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentationcited by 18
  12. 2021Deep Learning for fully automatic detection, segmentation, and Gleason Grade estimation of prostate cancer in multiparametric Magnetic Resonance Imagescited by 14

Built on by

Not cited yet.