mlsanityData to 7 Oct 2026

Adaptive Bidirectional Task Interaction for Joint Segmentation and Classification of Breast Ultrasound

arXiv 2603.01295 ↗First posted 1 Mar 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Joint lesion segmentation and tissue classification in breast ultrasound are usually trained with a shared encoder, so the two branches stop exchanging information once their decoders separate. That is exactly where boundary detail and semantic evidence are most complementary. The proposed method restores this exchange during decoding and, because its value differs between images, lets the network decide per image how much to keep. A Task Interaction Module (TIM) at each of four decoder levels passes pooled boundary context into the classification representation and modulates decoder channels with class-conditioned priors. An Adaptive Interaction Weighting (AIW) unit then blends interacted and original features with a coefficient computed for each image and level. On BUSI the model reaches 74.19% IoU and 90.60% accuracy, and on BUSI-WHU 86.40% IoU and 95.00% accuracy, ahead of encoder-sharing multi-task, transformer segmentation and decoder-interaction baselines evaluated under the same protocol. The ablation shows that multi-scale context and cross-task exchange are not independent: applied separately they contribute 4.00 points of IoU in total, applied together 6.76. Adding the adaptive blend to task interaction alone raises AUC from 94.41% to 97.31%, indicating that the blend acts primarily on the classification branch. Code: https://github.com/C-loud-Nine/Adaptive-Task-Interaction-BUS.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 27 references that are in the map. First posted on arXiv 1 Mar 2026.

Builds on

16 of 27 references.

References · 16

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  6. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  7. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  8. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  9. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  10. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  11. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  12. 2018A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentationcited by 171
4 more
  1. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  2. 2021MISSFormer: An Effective Medical Image Segmentation Transformercited by 103
  3. 2022DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learningcited by 25
  4. 2021Vision Transformer for Classification of Breast Ultrasound Imagescited by 21

Built on by

Not cited yet.