Deep Learning (DL) can predict biomarkers directly from digitized cancer
histology in a weakly-supervised setting. Recently, the prediction of
continuous biomarkers through regression-based DL has seen an increasing
interest. Nonetheless, clinical decision making often requires a categorical
outcome. Consequently, we developed a weakly-supervised joint multi-task
Transformer architecture which has been trained and evaluated on four public
patient cohorts for the prediction of two key predictive biomarkers,
microsatellite instability (MSI) and homologous recombination deficiency (HRD),
trained with auxiliary regression tasks related to the tumor microenvironment.
Moreover, we perform a comprehensive benchmark of 16 approaches of task
balancing for weakly-supervised joint multi-task learning in computational
pathology. Using our novel approach, we improve over the state-of-the-art area
under the receiver operating characteristic by +7.7% and +4.1%, as well as
yielding better clustering of latent embeddings by +8% and +5% for the
prediction of MSI and HRD in external cohorts, respectively.

通过弱监督的方式，我们开发了一个联合多任务 Transformer 架构，用于预测肿瘤学领域的两个关键预测生物标志物：微卫星不稳定性和同源重组缺陷，并通过辅助回归任务相关于肿瘤微环境，对此进行了培训和评估。使用我们的新方法，在外部队列中，相对于接收器操作特性下的最佳结果，对于预测微卫星不稳定性和同源重组缺陷，分别提高了 7.7％和 4.1％，同时通过 8％和 5％的更好嵌入聚类获得了更好的结果。

联合多任务学习改进计算机病理学中的弱监督生物标记物预测

Joint multi-task learning improves weakly-supervised biomarker  prediction in computational pathology

We propose a Deep learning-based weak label learning method for analysing
whole slide images (WSIs) of Hematoxylin and Eosin (H&E) stained tumorcells not
requiring pixel-level or tile-level annotations using Self-supervised
pre-training and heterogeneity-aware deep Multiple Instance LEarning
(DeepSMILE). We apply DeepSMILE to the task of Homologous recombination
deficiency (HRD) and microsatellite instability (MSI) prediction. We utilize
contrastive self-supervised learning to pre-train a feature extractor on
histopathology tiles of cancer tissue. Additionally, we use variability-aware
deep multiple instance learning to learn the tile feature aggregation function
while modeling tumor heterogeneity. Compared to state-of-the-art genomic label
classification methods, DeepSMILE improves classification performance for HRD
from $70.43\pm4.10\%$ to $83.79\pm1.25\%$ AUC and MSI from $78.56\pm6.24\%$ to
$90.32\pm3.58\%$ AUC in a multi-center breast and colorectal cancer dataset,
respectively. These improvements suggest we can improve genomic label
classification performance without collecting larger datasets. In the future,
this may reduce the need for expensive genome sequencing techniques, provide
personalized therapy recommendations based on widely available WSIs of cancer
tissue, and improve patient care with quicker treatment decisions - also in
medical centers without access to genome sequencing resources.

提出了 DeepSMILE，一个深度学习弱标签学习方法，用于需要分析 Hematoxylin 和 Eosin 染色的肿瘤细胞的 WSI，无需像素级或瓦片级注释，使用自监督预训练和异质性感知的深度多实例学习进行学习，用于 HRD 和 MSI 预测，将其与最先进的基因组标签分类方法进行比较，DeepSMILE 在多中心乳腺和结直肠癌数据集中提高了 HRD 和 MSI 的分类性能。

DeepSMILE: 自监督异质感知多实例学习用于基于 H&E 全切片图像的 DNA 损伤响应缺陷分类

DeepSMILE: Self-supervised heterogeneity-aware multiple instance  learning for DNA damage response defect classification directly from H&E  whole-slide images