Fourier Transform Multiple Instance Learning for whole slide image classification [0.03%]
傅里叶变换多实例学习在全片数字化病理图像分类中的应用
Anthony Bilic,Guangyu Sun,Ming Li et al.
Anthony Bilic et al.
Purpose: Whole slide image (WSI) classification relies on multiple instance learning (MIL) with spatial patch features, but current methods struggle to capture global dependencies due to the immense size of WSIs and the l...
Statistical testing of agreement in overlap-based performance between an AI segmentation device and a multi-expert human panel without requiring a reference standard [0.03%]
无需参考标准即可对基于重叠的性能在AI分割设备和多专家小组之间的协议进行统计检验
Tingting Hu,Berkman Sahiner,Shuyue Guan et al.
Tingting Hu et al.
Purpose: Artificial intelligence (AI)-based medical imaging devices often include lesion or organ segmentation capabilities. Existing methods for segmentation performance evaluation compare AI results with an aggregated r...
Improving personalized federated learning to optimize site-specific performance in computer-aided detection/diagnosis [0.03%]
改进个性化联邦学习以优化计算机辅助检测/诊断的特定站点性能
Aiki Yamada,Shouhei Hanaoka,Tomomi Takenaga et al.
Aiki Yamada et al.
Purpose: Personalized federated learning (PFL) has been explored to address data heterogeneity while preserving privacy, and its application in computer-aided detection/diagnosis (CAD) software has been investigated. Ditt...
Benchmarking 3D generative autoencoders for pseudo-healthy reconstruction of brain 18F-fluorodeoxyglucose positron emission tomography [0.03%]
用于构建伪正常脑氟脱氧葡萄糖正电子发射断层扫描图像的三维生成自编码器基准测试
Ravi Hassanaly,Maëlys Solal,Olivier Colliot et al.
Ravi Hassanaly et al.
Purpose: Many deep generative models have been proposed to reconstruct pseudo-healthy images for anomaly detection. Among these models, the variational autoencoder (VAE) has emerged as both simple and efficient. Although ...
Joint CT reconstruction of anatomy and implants using a mixed prior model [0.03%]
基于混合先验模型的联合解剖和植入物CT重建方法
Xiao Jiang,Grace J Gang,J Webster Stayman
Xiao Jiang
Purpose: Medical implants, often made of dense materials, pose significant challenges to accurate computed tomography (CT) reconstruction, especially near implants due to beam hardening and partial-volume artifacts. Moreo...
DABS-MS: deep atlas-based segmentation using the Mumford-Shah functional [0.03%]
基于Mumford-Shah范式的深度图谱引导分割方法
Hannah G Mason,Jack H Noble
Hannah G Mason
Purpose: Cochlear implants (CIs) are neural prosthetics used to treat patients with severe-to-profound hearing loss. Patient-specific modeling of CI stimulation of the auditory nerve fiber (ANF) can help audiologists impr...
Approximating the ideal observer for joint signal detection and estimation tasks by the use of Markov-Chain Monte Carlo with generative adversarial networks [0.03%]
生成对抗网络在马尔可夫链蒙特卡罗方法中的应用及其在联合检测与估计问题中对理想观测者的逼近研究
Dan Li,Kaiyan Li,Weimin Zhou et al.
Dan Li et al.
Purpose: The Bayesian ideal observer (IO) is a special model observer that achieves the best possible performance on tasks that involve signal detection or discrimination. Although IOs are desired for optimizing and asses...
Convolutional neural network model observers discount signal-like anatomical structures during search in virtual digital breast tomosynthesis phantoms [0.03%]
卷积神经网络模型在虚拟数字乳腺体层摄影假体中的搜索过程中忽略类似解剖结构的信号式物体
Aditya Jonnalagadda,Bruno B Barufaldi,Andrew D A Maidment et al.
Aditya Jonnalagadda et al.
Purpose: We aim to assess the perceptual tasks in which convolutional neural networks (CNNs) might be better tools than commonly used linear model observers (LMOs) to evaluate medical image quality. ...
Longitudinal outcome prediction of prostate cancer patients on active surveillance using multiple instance learning [0.03%]
基于多重实例学习的主动监测前列腺癌患者的纵向结果预测
Filip Winzell,Ida Arvidsson,Kalle Åström et al.
Filip Winzell et al.
Purpose: To avoid over-treatment of prostate cancer patients following screening for elevated prostate-specific antigen levels, keeping patients on active surveillance has been suggested as an alternative to radical treat...
Quantification-based explainable artificial intelligence for deep learning decisions: clustering and visualization of quantitative morphometric features in hepatocellular carcinoma discrimination [0.03%]
基于定量化的可解释人工智能的深度学习决策在肝细胞癌鉴别中的聚类和可视化研究
Gen Takagi,Saori Takeyama,Tokiya Abe et al.
Gen Takagi et al.
Purpose: Deep learning (DL) is rapidly advancing in computational pathology, offering high diagnostic accuracy but often functioning as a "black box" with limited interpretability. This lack of transparency hinders its cl...