Zare Samira, Vo Huy Q, Altini Nicola, Bevilacqua Vitoantonio, Rossini Michele, Pesce Francesco, Gesualdo Loreto, Turkevi-Nagy Sándor, Becker Jan Ulrich, Mohan Chandra, Van Nguyen Hien
Department of Electrical and Computer Engineering, University of Houston, Houston, Texas.
Electronic and Information Engineering Department, Polytechnic University of Bari, Bari, Italy.
Kidney360. 2025 Mar 1;6(3):441-450. doi: 10.34067/KID.0000000668. Epub 2025 Mar 3.
Permutation-invariant cascaded attentional set operator (PICASO) is a versatile set operator that uses Transformers to dynamically aggregate histopathologic features from a set of glomerular crops. For detecting active crescent in patients with IgA nephropathy on internal and external validation sets, PICASO achieved an area under the receiver-operating characteristic curve of 0.99 and 0.96, respectively. In the case-level classification of antibody-mediated rejection in kidney transplants, PICASO performed well, with an area under the receiver-operating characteristic curves of 0.97.
The advent of digital nephropathology offers the potential to integrate deep learning algorithms into the diagnostic workflow. We introduce permutation-invariant cascaded attentional set operator (PICASO), a novel permutation-invariant set operator to dynamically aggregate histopathologic features from instances. We applied PICASO to two nephropathology scenarios: detecting active crescent lesions in sets of glomerular crops with IgA nephropathy (IgAN) and case-level classification for antibody-mediated rejection (AMR) in kidney transplant.
PICASO is a Transformer-based set operator that aggregates features from sets of instances to make predictions. It uses initial histopathologic vectors as a static memory component and continuously updates them on the basis of input embeddings. For active crescent detection in patients with IgAN, we obtained 6206 periodic acid–Schiff–stained glomerular crops (5792 no active crescent, 414 active crescent) from three different health institutes. For the AMR classification, we have 1655 periodic acid–Schiff–stained glomerular crops (769 AMR and 886 non-AMR images) from 89 biopsies. The performance of PICASO as a set operator was compared with other set operators, such as DeepSet, Set Transformer, DeepSet++, and Set Transformer++, using metrics including area under the receiver-operating characteristic curve (AUROC), area under the precision-recall curves, recall, and accuracy.
PICASO achieved superior performance in detecting active crescent in patients with IgAN, with an AUROC of 0.99 (95% confidence interval [CI], 0.98 to 0.99) on internal validation and 0.96 (95% CI, 0.95 to 0.98) on external validation, significantly outperforming other set operators ( < 0.001). It also attained the highest AUROC of 0.97 (95% CI, 0.90 to 1.0, = 0.02) for case-level AMR classification. The area under the precision-recall curve, recall, and accuracy scores were also higher when using PICASO, and it significantly outperformed baselines ( < 0.001).
PICASO can potentially advance nephropathology by improving performance through dynamic feature aggregation.
排列不变级联注意力集算子（PICASO）是一种通用的集算子，它使用Transformer动态聚合一组肾小球切片的组织病理学特征。在内部和外部验证集上检测IgA肾病患者的活动性新月体时，PICASO的受试者操作特征曲线下面积分别达到0.99和0.96。在肾移植抗体介导排斥反应的病例水平分类中，PICASO表现良好，受试者操作特征曲线下面积为0.97。
数字肾病理学的出现为将深度学习算法整合到诊断工作流程中提供了可能性。我们引入了排列不变级联注意力集算子（PICASO），这是一种新型的排列不变集算子，用于动态聚合实例的组织病理学特征。我们将PICASO应用于两种肾病理学场景：检测IgA肾病（IgAN）肾小球切片中的活动性新月体病变以及肾移植中抗体介导排斥反应（AMR）的病例水平分类。
PICASO是一种基于Transformer的集算子，它聚合实例集的特征以进行预测。它使用初始组织病理学向量作为静态记忆组件，并根据输入嵌入不断更新它们。对于IgAN患者的活动性新月体检测，我们从三个不同的健康机构获得了6206张过碘酸 - 希夫染色的肾小球切片（5792张无活动性新月体，414张有活动性新月体）。对于AMR分类，我们有来自89例活检的1655张过碘酸 - 希夫染色的肾小球切片（769张AMR和886张非AMR图像）。使用受试者操作特征曲线下面积（AUROC）、精确召回率曲线下面积、召回率和准确率等指标，将PICASO作为集算子的性能与其他集算子（如DeepSet、Set Transformer、DeepSet++和Set Transformer++）进行比较。
PICASO在检测IgAN患者的活动性新月体方面表现出色，内部验证时AUROC为0.99（95%置信区间[CI]，0.98至0.99），外部验证时为0.96（95%CI，0.95至0.98），显著优于其他集算子（<0.001）。在病例水平的AMR分类中，它还获得了最高的AUROC为0.97（95%CI，0.90至1.0，P = 0.02）。使用PICASO时，精确召回率曲线下面积、召回率和准确率得分也更高，并且它显著优于基线（<0.001）。
PICASO通过动态特征聚合提高性能，有可能推动肾病理学的发展。
