Purpose: Necrosis quantification in the neoadjuvant setting using pathology slide review is the most important validated prognostic marker in conventional osteosarcoma. Herein, we explored three deep learning strategies on histology samples to predict outcome for OSA in the neoadjuvant setting. Experimental Design: Our study relies on a training cohort from New York University (New York, NY) and an external cohort from Charles university (Prague, Czechia). We trained and validated the performance of a supervised approach that integrates neural network predictions of necrosis/tumor content, and compared predicted overall survival (OS) using Kaplan-Meier curves. Furthermore, we explored morphology-based supervised and self-supervised approaches to determine whether intrinsic histomorphological features could serve as a potential marker for OS in the setting of neoadjuvant. Results: Excellent correlation between the trained network and the pathologists was obtained for the quantification of necrosis content (R2=0.899, r=0.949, p < 0.0001). OS prediction cutoffs were consistent between pathologists and the neural network (22% and 30% of necrosis, respectively). Morphology-based supervised approach predicted OS with p-value=0.0028, HR=2.43 [1.10-5.38]. The self-supervised approach corroborated the findings with clusters enriched in necrosis, fibroblastic stroma, and osteoblastic morphology associating with better OS (lg2HR; -2.366; -1.164; -1.175; 95% CI=[-2.996; -0.514]). Viable/partially viable tumor and fat necrosis were associated with worse OS (lg2HR;1.287;0.822;0.828; 95% CI=[0.38-1.974]). Conclusions: Neural networks can be used to automatically estimate the necrosis to tumor ratio, a quantitative metric predictive of survival. Furthermore, we identified alternate histomorphological biomarkers specific to the necrotic and tumor regions themselves which can be used as predictors.

中文翻译：

---

用于新辅助和转移情况下骨肉瘤生存预测的定量和基于形态学的深度卷积神经网络方法。


目的： 使用病理切片回顾在新辅助情况下进行坏死量化是传统骨肉瘤中最重要的经过验证的预后标志物。在此，我们探索了三种组织学样本的深度学习策略，以预测新辅助治疗中 OSA 的结局。实验设计： 我们的研究依赖于纽约大学（纽约州纽约市）的培训队列和查尔斯大学（捷克布拉格）的外部队列。我们训练并验证了集成坏死/肿瘤含量的神经网络预测的监督方法的性能，并使用 Kaplan-Meier 曲线比较了预测的总生存期 （OS）。此外，我们探索了基于形态学的监督和自我监督方法，以确定内在组织形态学特征是否可以作为新辅助治疗情况下 OS 的潜在标志物。结果：在坏死内容的定量方面，训练网络与病理学家之间获得了极好的相关性 （R2=0.899，r=0.949，p < 0.0001）。病理学家和神经网络之间的 OS 预测临界值是一致的 （分别为 22% 和 30% 的坏死）。基于形态学的监督方法预测 OS p-value=0.0028，HR=2.43 [1.10-5.38]。自我监督方法证实了这一发现，富含坏死、成纤维细胞基质和成骨细胞形态的簇与更好的 OS 相关 （lg2HR; -2.366; -1.164; -1.175;95% CI=[-2.996; -0.514]）。活/部分活的肿瘤和脂肪坏死与较差的 OS 相关 （lg2HR;1.287;0.822;0.828;95% CI =[0.38-1.974]）。结论： 神经网络可用于自动估计坏死与肿瘤的比率，这是一种预测生存率的定量指标。 此外，我们确定了特定于坏死和肿瘤区域本身的替代组织形态学生物标志物，这些生物标志物可用作预测因子。