[论文解读] Plexus Convolutional Neural Network (PlexusNet): A novel neural network architecture for histologic image analysis

Okyaz Eminağa, Mahmoud Abbas+6 more|arXiv (Cornell University)|Aug 23, 2019

AI in cancer detection被引用 4

一句话总结

PlexusNet 是一种新颖的轻量化卷积神经网络架构，专为组织学图像分析而设计，在显著减少参数量的同时实现了最先进的分类性能。其在校准性和临床实用性方面优于更大的模型，在前列腺癌检测中AUC达0.963，在乳腺癌转移检测中AUC达0.978，参数量最多仅为ResNet18的1/200。

ABSTRACT

Different convolutional neural network (CNN) models have been tested for their application in histological image analyses. However, these models are prone to overfitting due to their large parameter capacity, requiring more data or valuable computational resources for model training. Given these limitations, we introduced a novel architecture (termed PlexusNet). We utilized 310 Hematoxylin and Eosin stained (H&E) annotated histological images of prostate cancer cases from TCGA-PRAD and Stanford University and 398 H&E whole slides images from the Camelyon 2016 challenge. PlexusNet-architecture -derived models were compared to models derived from several existing "state of the art" architectures. We measured discrimination accuracy, calibration, and clinical utility. An ablation study was conducted to study the effect of each component of PlexusNet on model performance. A well-fitted PlexusNet-based model delivered comparable classification performance (AUC: 0.963) in distinguishing prostate cancer from healthy tissues, although it was at least 23 times smaller, had a better model calibration and clinical utility than the comparison models. A separate smaller PlexusNet model accurately detected slides with breast cancer metastases (AUC: 0.978); it helped reduce the slide number to examine by 43.8% without consequences, although its parameter capacity was 200 times smaller than ResNet18. We found that the partitioning of the development set influences the model calibration for all models. However, with PlexusNet architecture, we could achieve comparable well-calibrated models trained on different partitions. In conclusion, PlexusNet represents a novel model architecture for histological image analysis that achieves classification performance comparable to other models while providing orders-of-magnitude parameter reduction.

研究动机与目标

• 通过设计更小、更高效的神经网络架构，解决组织学图像分析中过拟合和高计算需求的问题。
• 与现有最先进模型相比，提升模型的校准性能和临床实用性。
• 评估数据划分对模型校准的影响，并确保在不同训练划分下具有鲁棒性。
• 在全切片图像分析中，以极低的参数容量实现高分类准确率。
• 通过减少需要人工审阅的切片数量，实现在不损失诊断准确率的前提下高效筛查。

提出的方法

• 提出了一种新型神经网络架构PlexusNet，采用分层的多尺度特征聚合机制，在参数更少的情况下增强表征能力。
• 采用分块训练策略，研究训练集划分对模型校准和泛化能力的影响。
• 设计了PlexusNet的紧凑变体，适用于低资源环境，优化了推理效率和参数效率。
• 在两个数据集上训练和评估模型：来自TCGA-PRAD和斯坦福的310张H&E染色前列腺癌切片，以及来自Camelyon 2016挑战赛的398张全切片。
• 通过消融研究隔离每个架构组件对整体性能的贡献。
• 使用AUC、校准指标和临床实用性评分，将PlexusNet与ResNet18等成熟架构进行比较。

实验结果

研究问题

• RQ1 更小的神经网络架构是否能在组织学图像分析中实现与更大规模最先进模型相当的分类性能？
• RQ2 训练集的划分方式如何影响不同架构模型的校准性能？
• RQ3 与现有模型相比，PlexusNet架构在多大程度上提升了模型校准性能和临床实用性？
• RQ4 PlexusNet的紧凑版本是否能有效减少癌症筛查中需要人工审阅的切片数量？
• RQ5 PlexusNet中每个架构组件对整体性能和效率的贡献是什么？

主要发现

• 经过良好拟合的PlexusNet模型在区分前列腺癌与正常组织时AUC达到0.963，性能与更大模型相当。
• 该模型参数量至少比对比模型小23倍，且校准性能和临床实用性更优。
• PlexusNet的更小变体在检测乳腺癌转移时AUC达0.978，同时将需检查的切片数量减少了43.8%而不损失准确性。
• 该紧凑模型的参数量仅为ResNet18的1/200，同时保持了高性能。
• PlexusNet在不同数据划分方案下均实现了良好校准，而基线模型对划分变化敏感。
• 消融研究证实，每个架构组件均对性能有显著贡献，尤其在特征聚合和参数效率方面。