Interactive image diagnosis using test-time backpropagation from the auxiliary task
Abstract
Multi-task deep learning has been developed to ensure explainability in computer-aided diagnosis (CAD) systems. These systems simultaneously predict interpretable characteristics of findings in auxiliary tasks to help radiologists assess the reliability of the diagnostic prediction. However, the CAD's opinion would not be referred to when the auxiliary task prediction deviates from the radiologist's expectation. To further leverage CAD's knowledge in the above situation, we proposed a multi-task gradient assist (MGA) method that brings interactivity to multi-task models without additional training. MGA allows radiologists to give feedback to the CAD and ask for additional diagnostic suggestions. Using two datasets of mammography and CT, we show that MGA successfully improves diagnostic accuracy upon feedback on various auxiliary tasks. Compared to an existing method using forward propagation only, MGA performs more robustly and can be combined to further improve accuracy. Our method paves a promising way for integrating artificial intelligence into image diagnosis.
Versions
Related
- A native signed incoherent photonic matrix core on thin-film lithium niobate supporting in situ backpropagation
- Quantum neural network equipped with backpropagation on a qudit processor
- Compass in the Mirror: Quantum Backpropagation with the Hopf Ansatz
- Unifying Physical Backpropagation
- Thermodynamic volumes of extended black hole thermodynamics with auxiliary gauge fields
BibTeX
@misc{shimaya2026interactive,
title = {{Interactive image diagnosis using test-time backpropagation from the auxiliary task}},
author = {Takuro Shimaya},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32396},
eprint = {2610.32396},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32396},
}
RIS
TY - UNPB
TI - Interactive image diagnosis using test-time backpropagation from the auxiliary task
AU - Takuro Shimaya
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.32396
UR - https://arxiv.org/abs/2610.32396
AB - Multi-task deep learning has been developed to ensure explainability in computer-aided diagnosis (CAD) systems. These systems simultaneously predict interpretable characteristics of findings in auxiliary tasks to help radiologists assess the reliability of the diagnostic prediction. However, the CAD's opinion would not be referred to when the auxiliary task prediction deviates from the radiologist's expectation. To further leverage CAD's knowledge in the above situation, we proposed a multi-task gradient assist (MGA) method that brings interactivity to multi-task models without additional training. MGA allows radiologists to give feedback to the CAD and ask for additional diagnostic suggestions. Using two datasets of mammography and CT, we show that MGA successfully improves diagnostic accuracy upon feedback on various auxiliary tasks. Compared to an existing method using forward propagation only, MGA performs more robustly and can be combined to further improve accuracy. Our method paves a promising way for integrating artificial intelligence into image diagnosis.
ER -