First U-Net Layers Contain More Domain Specific Information Than The Last Ones

by   Boris Shirokikh, et al.

MRI scans appearance significantly depends on scanning protocols and, consequently, the data-collection institution. These variations between clinical sites result in dramatic drops of CNN segmentation quality on unseen domains. Many of the recently proposed MRI domain adaptation methods operate with the last CNN layers to suppress domain shift. At the same time, the core manifestation of MRI variability is a considerable diversity of image intensities. We hypothesize that these differences can be eliminated by modifying the first layers rather than the last ones. To validate this simple idea, we conducted a set of experiments with brain MRI scans from six domains. Our results demonstrate that 1) domain-shift may deteriorate the quality even for a simple brain extraction segmentation task (surface Dice Score drops from 0.85-0.89 even to 0.09); 2) fine-tuning of the first layers significantly outperforms fine-tuning of the last layers in almost all supervised domain adaptation setups. Moreover, fine-tuning of the first layers is a better strategy than fine-tuning of the whole network, if the amount of annotated data from the new domain is strictly limited.


page 8

page 13

page 14


Gradual Fine-Tuning for Low-Resource Domain Adaptation

Fine-tuning is known to improve NLP models by adapting an initial model ...

Anatomy of Domain Shift Impact on U-Net Layers in MRI Segmentation

Domain Adaptation (DA) methods are widely used in medical image segmenta...

SynthSeg: Domain Randomisation for Segmentation of Brain MRI Scans of any Contrast and Resolution

Despite advances in data augmentation and transfer learning, convolution...

Unsupervised Domain Adaptation with Adapter

Unsupervised domain adaptation (UDA) with pre-trained language models (P...

Growing a Brain: Fine-Tuning by Increasing Model Capacity

CNNs have made an undeniable impact on computer vision through the abili...

Improving Span Representation for Domain-adapted Coreference Resolution

Recent work has shown fine-tuning neural coreference models can produce ...

Accurate Prostate Cancer Detection and Segmentation on Biparametric MRI using Non-local Mask R-CNN with Histopathological Ground Truth

Purpose: We aimed to develop deep machine learning (DL) models to improv...