Multi-style conversion for semantic segmentation of lesions in fundus images by adversarial attacks
- URL: http://arxiv.org/abs/2410.13822v1
- Date: Thu, 17 Oct 2024 17:48:17 GMT
- Title: Multi-style conversion for semantic segmentation of lesions in fundus images by adversarial attacks
- Authors: Clément Playout, Renaud Duval, Marie Carole Boucher, Farida Cheriet,
- Abstract summary: This paper introduces a novel method, termed adversarial style conversion, to address the lack of standardization in annotation styles across diverse databases.
By training a single architecture on combined databases, the model spontaneously modifies its segmentation style depending on the input.
Results indicate significant qualitative and quantitative through dataset combination, offering avenues for improved model, uncertainty estimation and continuous generalization.
- Score: 2.123492791776905
- License:
- Abstract: The diagnosis of diabetic retinopathy, which relies on fundus images, faces challenges in achieving transparency and interpretability when using a global classification approach. However, segmentation-based databases are significantly more expensive to acquire and combining them is often problematic. This paper introduces a novel method, termed adversarial style conversion, to address the lack of standardization in annotation styles across diverse databases. By training a single architecture on combined databases, the model spontaneously modifies its segmentation style depending on the input, demonstrating the ability to convert among different labeling styles. The proposed methodology adds a linear probe to detect dataset origin based on encoder features and employs adversarial attacks to condition the model's segmentation style. Results indicate significant qualitative and quantitative through dataset combination, offering avenues for improved model generalization, uncertainty estimation and continuous interpolation between annotation styles. Our approach enables training a segmentation model with diverse databases while controlling and leveraging annotation styles for improved retinopathy diagnosis.
Related papers
- Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View [49.03501451546763]
We identify the importance of implicit correspondences across biological contexts for exploiting domain-invariant pathological composition.
We propose self-adaptive dynamic distillation to secure instance-aware trade-offs across different model constituents.
arXiv Detail & Related papers (2024-07-14T04:41:16Z) - A Classifier-Free Incremental Learning Framework for Scalable Medical Image Segmentation [6.591403935303867]
We introduce a novel segmentation paradigm enabling the segmentation of a variable number of classes within a single classifier-free network.
This network is trained using contrastive learning and produces discriminative feature representations that facilitate straightforward interpretation.
We demonstrate the flexibility of our method in handling varying class numbers within a unified network and its capacity for incremental learning.
arXiv Detail & Related papers (2024-05-25T19:05:07Z) - Cross-Dataset Generalization For Retinal Lesions Segmentation [2.1160877779256126]
This study characterizes several known datasets and compares different techniques that have been proposed to enhance the generalisation performance of a model.
Our results provide insights into how to combine coarsely labelled data with a finely-grained dataset in order to improve the lesions segmentation.
arXiv Detail & Related papers (2024-05-14T05:52:01Z) - Semi-supervised Medical Image Segmentation Method Based on Cross-pseudo
Labeling Leveraging Strong and Weak Data Augmentation Strategies [2.8246591681333024]
This paper proposes a semi-supervised model, DFCPS, which innovatively incorporates the Fixmatch concept.
Cross-pseudo-supervision is introduced, integrating consistency learning with self-training.
Our model consistently exhibits superior performance across all four subdivisions containing different proportions of unlabeled data.
arXiv Detail & Related papers (2024-02-17T13:07:44Z) - Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites:
A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area.
We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions.
We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
arXiv Detail & Related papers (2023-08-31T00:36:10Z) - CellMix: A General Instance Relationship based Method for Data
Augmentation Towards Pathology Image Classification [6.9596321268519326]
In pathology image analysis, obtaining and maintaining high-quality annotated samples is an extremely labor-intensive task.
We propose the CellMix framework, which employs a novel distribution-oriented in-place shuffle approach.
Our experiments in pathology image classification tasks demonstrate state-of-the-art (SOTA) performance on 7 distinct datasets.
arXiv Detail & Related papers (2023-01-27T03:17:35Z) - Simple and Scalable Algorithms for Cluster-Aware Precision Medicine [0.0]
We propose a simple and scalable approach to joint clustering and embedding.
This novel, cluster-aware embedding approach overcomes the complexity and limitations of current joint embedding and clustering methods.
Our approach does not require the user to choose the desired number of clusters, but instead yields interpretable dendrograms of hierarchically clustered embeddings.
arXiv Detail & Related papers (2022-11-29T19:27:26Z) - Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
Several multimodal representation learning approaches have been proposed that jointly represent image and text.
These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining.
We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
arXiv Detail & Related papers (2021-09-24T07:20:13Z) - Learning from Partially Overlapping Labels: Image Segmentation under
Annotation Shift [68.6874404805223]
We propose several strategies for learning from partially overlapping labels in the context of abdominal organ segmentation.
We find that combining a semi-supervised approach with an adaptive cross entropy loss can successfully exploit heterogeneously annotated data.
arXiv Detail & Related papers (2021-07-13T09:22:24Z) - G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for
Biomarker Identification and Disease Classification [49.53651166356737]
We propose a novel deep neural network architecture to integrate imaging and genetics data, as guided by diagnosis, that provides interpretable biomarkers.
We have evaluated our model on a population study of schizophrenia that includes two functional MRI (fMRI) paradigms and Single Nucleotide Polymorphism (SNP) data.
arXiv Detail & Related papers (2021-01-27T19:28:04Z) - Semi-supervised Medical Image Classification with Relation-driven
Self-ensembling Model [71.80319052891817]
We present a relation-driven semi-supervised framework for medical image classification.
It exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations.
Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.
arXiv Detail & Related papers (2020-05-15T06:57:54Z)
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.