REFUGE2 Challenge: Treasure for Multi-Domain Learning in Glaucoma Assessment

Fang, Huihui; Li, Fēi; Fu, Huazhu; Sun, Xu; Cao, Xia; Son, Jaemin; Yu, Shuang; Zhang, Menglu; Yuan, Chenglang; Lei, Baiying; Zhao, Benjian; Xu, X. X.; Li, Shaohua; Fumero, Francisco; Sigut, J.; Almubarak, Haidar; Bazi, Yakoub; Guo, Yuanhao; Zhou, Yating; Baid, Ujjwal; Innani, Shubham; Guo, Ting; Yang, Jie; Orlando, José Ignacio; Bogunović, Hrvoje; Zhang, Xiulan; Xu, Yuanfu

doi:10.48550/arxiv.2202.08994

Cited by 7 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conduct the experiments on three different medical tasks with different image modalities, which are optic-cup segmentation from fundus images, brain tumor segmentation from MRI images, and thyroid nodule segmentation from ultrasound images. The experiments of glaucoma, thyroid cancer and melanoma diagnosis are conducted on REFUGE-2 dataset [14], BraTs-2021 dataset [15] and DDTI dataset [16], which contain 1200, 2000, 8046 samples, respectively. The datasets are publicly available with both segmentation and diagnosis labels.…”

Section: Experiments a Datasetmentioning

confidence: 99%

MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model

Wu¹,

Fang²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Diffusion probabilistic model (DPM) recently becomes one of the hottest topic in computer vision. Its image generation application such as Imagen, Latent Diffusion Models and Stable Diffusion have shown impressive generation capabilities, which aroused extensive discussion in the community. Many recent studies also found it is useful in many other vision tasks, like image deblurring, super-resolution and anomaly detection. Inspired by the success of DPM, we propose the first DPM based model toward general medical image segmentation tasks, which we named MedSegDiff. In order to enhance the step-wise regional attention in DPM for the medical image segmentation, we propose dynamic conditional encoding, which establishes the state-adaptive conditions for each sampling step. We further propose Feature Frequency Parser (FF-Parser), to eliminate the negative effect of high-frequency noise component in this process. We verify MedSegDiff on three medical segmentation tasks with different image modalities, which are optic cup segmentation over fundus images, brain tumor segmentation over MRI images and thyroid nodule segmentation over ultrasound images. The experimental results show that MedSegDiff outperforms stateof-the-art (SOTA) methods with considerable performance gap, indicating the generalization and effectiveness of the proposed model.

show abstract

Section: Experiments a Datasetmentioning

confidence: 99%

MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model

Wu¹,

Fang²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Melanoma is predicted from dermoscopic images and is assisted by skin lesions segmentation. The experiments of glaucoma, thyroid cancer and melanoma diagnosis are conducted on REFUGE-2 dataset [8], TNMIX dataset [13,27] and ISIC dataset [15], which contain 1200, 8046, 1600 samples, respectively. The datasets are publicly available with both segmentation and diagnosis labels.…”

Section: Diagnosis Tasksmentioning

confidence: 99%

SeATrans: Learning Segmentation-Assisted diagnosis model via Transforme

Wu¹,

Fang²,

Shang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Clinically, the accurate annotation of lesions/tissues can significantly facilitate the disease diagnosis. For example, the segmentation of optic disc/cup (OD/OC) on fundus image would facilitate the glaucoma diagnosis, the segmentation of skin lesions on dermoscopic images is helpful to the melanoma diagnosis, etc. With the advancement of deep learning techniques, a wide range of methods proved the lesions/tissues segmentation can also facilitate the automated disease diagnosis models. However, existing methods are limited in the sense that they can only capture static regional correlations in the images. Inspired by the global and dynamic nature of Vision Transformer, in this paper, we propose Segmentation-Assisted diagnosis Transformer (SeATrans) to transfer the segmentation knowledge to the disease diagnosis network. Specifically, we first propose an asymmetric multi-scale interaction strategy to correlate each single low-level diagnosis feature with multi-scale segmentation features. Then, an effective strategy called SeA-block is adopted to vitalize diagnosis feature via correlated segmentation features. To model the segmentation-diagnosis interaction, SeA-block first embeds the diagnosis feature based on the segmentation information via the encoder, and then transfers the embedding back to the diagnosis feature space by a decoder. Experimental results demonstrate that SeATrans surpasses a wide range of state-of-the-art (SOTA) segmentation-assisted diagnosis methods on several disease diagnosis tasks.

show abstract

“…Thus, fusing the multi-rater segmentation in different ways will also differently affect the diagnosis performance. In order to quantitatively analyze these affects on the diagnosis, we perform a preliminary experiment with a OD/OC segmentation setting on the REFUGE-2 benchmark (Fang et al (2022)).…”

Section: Motivationmentioning

confidence: 99%

Calibrate the inter-observer segmentation uncertainty via diagnosis-first principle

Wu¹,

Fang²,

Xiong³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

On the medical images, many of the tissues/lesions may be ambiguous. That is why the medical segmentation is typically annotated by a group of clinical experts to mitigate the personal bias. However, this clinical routine also brings new challenges to the application of machine learning algorithms. Without a definite ground-truth, it will be difficult to train and evaluate the deep learning models. When the annotations are collected from different graders, a common choice is majority vote, e.g., taking the average of multiple labels. However such a strategy ignores the difference between the grader expertness. In this paper, we consider the task of predicting the segmentation with the calibrated inter-observer uncertainty. We note that in clinical practice, the medical image segmentation is usually used to assist the disease diagnosis. Inspired by this observation, we propose diagnosis-first principle, which is to take disease diagnosis as the criterion to calibrate the inter-observer segmentation uncertainty. Following this idea, a framework named Diagnosis First segmentation Framework (DiFF) is proposed to estimate diagnosis-first segmentation from the raw images. Specifically, DiFF will first learn to fuse the multi-rater segmentation labels to a single ground-truth which could maximize the disease diagnosis performance. We dubbed the fused ground-truth as Diagnosis First Ground-truth (DF-GT). Then, we further propose Take and Give

show abstract

REFUGE2 Challenge: Treasure for Multi-Domain Learning in Glaucoma Assessment

Cited by 7 publications

References 0 publications

MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model

MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model

SeATrans: Learning Segmentation-Assisted diagnosis model via Transforme

Calibrate the inter-observer segmentation uncertainty via diagnosis-first principle

Contact Info

Product

Resources

About