On the Effective Transfer Learning Strategy for Medical Image Analysis in Deep Learning

Wen, Yang; Chen, Leiting; Zhou, Chuan; Deng, Yu; Zeng, Huiru; Xi, Shuo; Guo, Rui

doi:10.1109/bibm49941.2020.9313593

Cited by 3 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several experimental studies have investigated the transfer learning performance in medical image analysis. In [6], advantages and disadvantages of several transfer learning strategies for medical image segmentation tasks are explored, such as which component of a CNN model is better to transfer. Weatheritt et al [7] analyze the impacts of different choices of data pre-processing methods, tasks, and amount of data used on the final transfer performance.…”

Section: Introductionmentioning

confidence: 99%

Finding the Most Transferable Tasks for Brain Image Segmentation

Tan

Yang

et al. 2022

2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

View full text Add to dashboard Cite

Although many studies have successfully applied transfer learning to medical image segmentation, very few of them have investigated the selection strategy when multiple source tasks are available for transfer. In this paper, we propose a prior knowledge guided and transferability based framework to select the best source tasks among a collection of brain image segmentation tasks, to improve the transfer learning performance on the given target task. The framework consists of modality analysis, RoI (region of interest) analysis, and transferability estimation, such that the source task selection can be refined step by step. Specifically, we adapt the state-of-the-art analytical transferability estimation metrics to medical image segmentation tasks and further show that their performance can be significantly boosted by filtering candidate source tasks based on modality and RoI characteristics. Our experiments on brain matter, brain tumor, and white matter hyperintensities segmentation datasets reveal that transferring from different tasks under the same modality is often more successful than transferring from the same task under different modalities. Furthermore, within the same modality, transferring from the source task that has stronger RoI shape similarity with the target task can significantly improve the final transfer performance. And such similarity can be captured using the Structural Similarity index in the label space.

show abstract

Section: Introductionmentioning

confidence: 99%