arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.07052cs.CV
收藏

用于光学相干断层扫描中高度近视筛查的可调节鲁棒Transformer

Adjustable Robust Transformer for High Myopia Screening in Optical Coherence Tomography

School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院);The First Affiliated Hospital of Nanjing Medical University(南京医科大学第一附属医院)

Xiao Ma, Zetian Zhang, Zexuan Ji, Kun Huang, Na Su, Songtao Yuan, Qiang Chen

AI总结:

针对高度近视筛查中匹配图像数据稀缺、定义标准不一及阈值处数据混淆的问题,提出基于视觉Transformer的ARTran模型,通过APE、ACE和SST提升特征提取能力、条件适配性与鲁棒性,经实验验证有效可靠。

摘要:

近视是眼球过度拉长导致的视力损伤症状。图像数据是研究高度近视和病理性近视的关键材料。球镜等效度数与眼轴长度的测量是识别高度近视的金标准,但与之匹配的可用图像数据十分稀缺。此外,不同研究对高度近视的定义标准存在差异,因此自动化筛查工作中的样本纳入需要对可解释性进行恰当评估。本研究提出了一种名为可调节鲁棒Transformer(adjustable robust transformer, ARTran)的模型,用于光学相干断层扫描(optical coherence tomography, OCT)数据的高度近视筛查。我们基于视觉Transformer,提出各向异性块嵌入(anisotropic patch embedding, APE)以捕捉更具区分度的高度近视特征。为使模型在可变筛查条件下有效工作,我们提出可调节类别嵌入(adjustable class embedding, ACE)来替代固定类别标记,通过改变输出来适配不同条件。考虑到数据在高度近视与低度近视阈值处的混淆问题,我们引入标签噪声学习策略,并提出偏移子空间转移矩阵(shifted subspace transition matrix, SST)以增强模型的鲁棒性。此外,结合上述提出的两种结构,该模型能够为不确定性评估提供依据。实验结果证明了所提方法的有效性与可靠性。代码可在以下链接获取:https://github.com/maxiao0234/ARTran。

英文摘要:

Myopia is a manifestation of visual impairment caused by an excessively elongated eyeball. Image data is critical material for studying high myopia and pathological myopia. Measurements of spherical equivalent and axial length are the gold standards for identifying high myopia, but the available image data for matching them is scarce. In addition, the criteria for defining high myopia vary from study to study, and therefore the inclusion of samples in automated screening efforts requires an appropriate assessment of interpretability. In this work, we propose a model called adjustable robust transformer (ARTran) for high myopia screening of optical coherence tomography (OCT) data. Based on vision transformer, we propose anisotropic patch embedding (APE) to capture more discriminative features of high myopia. To make the model effective under variable screening conditions, we propose an adjustable class embedding (ACE) to replace the fixed class token, which changes the output to adapt to different conditions. Considering the confusion of the data at high myopia and low myopia threshold, we introduce the label noise learning strategy and propose a shifted subspace transition matrix (SST) to enhance the robustness of the model. Besides, combining the two structures proposed above, the model can provide evidence for uncertainty evaluation. The experimental results demonstrate the effectiveness and reliability of the proposed method. Code is available at: https://github.com/maxiao0234/ARTran.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑