How Reliable Are Out-of-Distribution Generalization Methods for Medical
Image Segmentation?
- URL: http://arxiv.org/abs/2109.01668v1
- Date: Fri, 3 Sep 2021 10:15:44 GMT
- Title: How Reliable Are Out-of-Distribution Generalization Methods for Medical
Image Segmentation?
- Authors: Antoine Sanner, Camila Gonzalez, Anirban Mukhopadhyay
- Abstract summary: We evaluate OoD Generalization solutions for the problem of hippocampus segmentation in MR data using both fully- and semi-supervised training.
Only the V-REx loss stands out as it remains easy to tune, while it outperforms a standard U-Net in most cases.
- Score: 0.46023882211671957
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The recent achievements of Deep Learning rely on the test data being similar
in distribution to the training data. In an ideal case, Deep Learning models
would achieve Out-of-Distribution (OoD) Generalization, i.e. reliably make
predictions on out-of-distribution data. Yet in practice, models usually fail
to generalize well when facing a shift in distribution. Several methods were
thereby designed to improve the robustness of the features learned by a model
through Regularization- or Domain-Prediction-based schemes. Segmenting medical
images such as MRIs of the hippocampus is essential for the diagnosis and
treatment of neuropsychiatric disorders. But these brain images often suffer
from distribution shift due to the patient's age and various pathologies
affecting the shape of the organ. In this work, we evaluate OoD Generalization
solutions for the problem of hippocampus segmentation in MR data using both
fully- and semi-supervised training. We find that no method performs reliably
in all experiments. Only the V-REx loss stands out as it remains easy to tune,
while it outperforms a standard U-Net in most cases.
Related papers
- Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images [68.42215385041114]
This paper introduces a novel lightweight multi-level adaptation and comparison framework to repurpose the CLIP model for medical anomaly detection.
Our approach integrates multiple residual adapters into the pre-trained visual encoder, enabling a stepwise enhancement of visual features across different levels.
Our experiments on medical anomaly detection benchmarks demonstrate that our method significantly surpasses current state-of-the-art models.
arXiv Detail & Related papers (2024-03-19T09:28:19Z) - DGM-DR: Domain Generalization with Mutual Information Regularized
Diabetic Retinopathy Classification [40.35834579068518]
Domain shift between training and testing data presents a significant challenge for training general deep learning models.
We introduce a DG method that re-establishes the model objective function as a pretrained model to the medical imaging field.
Our proposed method consistently outperforms the previous state-of-the-art by a margin of 5.25% in average accuracy and a lower standard deviation.
arXiv Detail & Related papers (2023-09-18T11:17:13Z) - The effect of data augmentation and 3D-CNN depth on Alzheimer's Disease
detection [51.697248252191265]
This work summarizes and strictly observes best practices regarding data handling, experimental design, and model evaluation.
We focus on Alzheimer's Disease (AD) detection, which serves as a paradigmatic example of challenging problem in healthcare.
Within this framework, we train predictive 15 models, considering three different data augmentation strategies and five distinct 3D CNN architectures.
arXiv Detail & Related papers (2023-09-13T10:40:41Z) - Diffusion Models for Counterfactual Generation and Anomaly Detection in
Brain Images [59.85702949046042]
We present a weakly supervised method to generate a healthy version of a diseased image and then use it to obtain a pixel-wise anomaly map.
We employ a diffusion model trained on healthy samples and combine Denoising Diffusion Probabilistic Model (DDPM) and Denoising Implicit Model (DDIM) at each step of the sampling process.
We verify that when our method is applied to healthy samples, the input images are reconstructed without significant modifications.
arXiv Detail & Related papers (2023-08-03T21:56:50Z) - Understanding the Tricks of Deep Learning in Medical Image Segmentation:
Challenges and Future Directions [66.40971096248946]
In this paper, we collect a series of MedISeg tricks for different model implementation phases.
We experimentally explore the effectiveness of these tricks on consistent baselines.
We also open-sourced a strong MedISeg repository, where each component has the advantage of plug-and-play.
arXiv Detail & Related papers (2022-09-21T12:30:05Z) - PCA: Semi-supervised Segmentation with Patch Confidence Adversarial
Training [52.895952593202054]
We propose a new semi-supervised adversarial method called Patch Confidence Adrial Training (PCA) for medical image segmentation.
PCA learns the pixel structure and context information in each patch to get enough gradient feedback, which aids the discriminator in convergent to an optimal state.
Our method outperforms the state-of-the-art semi-supervised methods, which demonstrates its effectiveness for medical image segmentation.
arXiv Detail & Related papers (2022-07-24T07:45:47Z) - Practical Challenges in Differentially-Private Federated Survival
Analysis of Medical Data [57.19441629270029]
In this paper, we take advantage of the inherent properties of neural networks to federate the process of training of survival analysis models.
In the realistic setting of small medical datasets and only a few data centers, this noise makes it harder for the models to converge.
We propose DPFed-post which adds a post-processing stage to the private federated learning scheme.
arXiv Detail & Related papers (2022-02-08T10:03:24Z) - Distributionally Robust Segmentation of Abnormal Fetal Brain 3D MRI [5.463018151091638]
We show that state-of-the-art deep learning pipeline nnU-Net has difficulties to generalize to unseen abnormal cases.
We propose to train a deep neural network to minimize a percentile of the distribution of per-volume loss over the dataset.
We validated our approach using a dataset of 368 fetal brain T2w MRIs.
arXiv Detail & Related papers (2021-08-09T17:00:21Z) - About Explicit Variance Minimization: Training Neural Networks for
Medical Imaging With Limited Data Annotations [2.3204178451683264]
Variance Aware Training (VAT) method exploits this property by introducing the variance error into the model loss function.
We validate VAT on three medical imaging datasets from diverse domains and various learning objectives.
arXiv Detail & Related papers (2021-05-28T21:34:04Z) - Cross-Domain Segmentation with Adversarial Loss and Covariate Shift for
Biomedical Imaging [2.1204495827342438]
This manuscript aims to implement a novel model that can learn robust representations from cross-domain data by encapsulating distinct and shared patterns from different modalities.
The tests on CT and MRI liver data acquired in routine clinical trials show that the proposed model outperforms all other baseline with a large margin.
arXiv Detail & Related papers (2020-06-08T07:35:55Z) - Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A
Comparative Study [43.26668942258135]
New approaches in the field of Unsupervised Anomaly Detection (UAD) in brain MRI.
Main principle behind these works is to learn a model of normal anatomy by learning to compress and recover healthy data.
concept is of great interest to the medical image analysis community as it i) relieves from the need of vast amounts of manually segmented training data.
arXiv Detail & Related papers (2020-04-07T11:12:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.