[论文解读] Microscopic Nuclei Classification, Segmentation and Detection with improved Deep Convolutional Neural Network (DCNN) Approaches

Md Zahangir Alom, Chris Yakopcic+2 more|arXiv (Cornell University)|Nov 8, 2018

AI in cancer detection被引用 11

一句话总结

本论文提出了改进的深度卷积神经网络（DCNN）架构——DCRN用于核分类，R2U-Net用于分割，UD-Net用于检测，在病理全切片图像上实现了最先进性能。相较于近期方法，分类和检测任务的F1-score分别提升了3.4%和4.5%，R2U-Net在核分割任务中达到了92.15%的Dice系数。

ABSTRACT

Due to cellular heterogeneity, cell nuclei classification, segmentation, and detection from pathological images are challenging tasks. In the last few years, Deep Convolutional Neural Networks (DCNN) approaches have been shown state-of-the-art (SOTA) performance on histopathological imaging in different studies. In this work, we have proposed different advanced DCNN models and evaluated for nuclei classification, segmentation, and detection. First, the Densely Connected Recurrent Convolutional Network (DCRN) model is used for nuclei classification. Second, Recurrent Residual U-Net (R2U-Net) is applied for nuclei segmentation. Third, the R2U-Net regression model which is named UD-Net is used for nuclei detection from pathological images. The experiments are conducted with different datasets including Routine Colon Cancer(RCC) classification and detection dataset, and Nuclei Segmentation Challenge 2018 dataset. The experimental results show that the proposed DCNN models provide superior performance compared to the existing approaches for nuclei classification, segmentation, and detection tasks. The results are evaluated with different performance metrics including precision, recall, Dice Coefficient (DC), Means Squared Errors (MSE), F1-score, and overall accuracy. We have achieved around 3.4% and 4.5% better F-1 score for nuclei classification and detection tasks compared to recently published DCNN based method. In addition, R2U-Net shows around 92.15% testing accuracy in term of DC. These improved methods will help for pathological practices for better quantitative analysis of nuclei in Whole Slide Images(WSI) which ultimately will help for better understanding of different types of cancer in clinical workflow.

研究动机与目标

• 为解决由于细胞异质性导致的在组织病理学图像中对细胞核进行分类、分割和检测的挑战。
• 开发新型深度学习架构，使其在核分类、分割和检测任务中优于现有方法。
• 实现对全切片图像（WSI）中核的更精确、更定量的分析，以提升癌症诊断和临床工作流程。

提出的方法

• 提出密集连接循环卷积网络（DCRN）用于核分类，通过整合残差连接与密集连接以增强特征学习能力。
• 采用循环残差U-Net（R2U-Net）用于核分割，结合跳跃连接与循环残差块以提升特征表示能力。
• 开发R2U-Net的回归变体——UD-Net，通过从特征图预测边界框实现核检测。
• 在两个基准数据集上进行模型训练与评估：常规结肠癌（RCC）数据集和2018年核分割挑战赛数据集。
• 使用精确率、召回率、F1-score、Dice系数（DC）、均方误差（MSE）和总体准确率评估性能。
• 架构设计强调特征复用与分层表征学习，以增强在复杂组织病理学数据上的泛化能力。

实验结果

研究问题

• RQ1 与现有DCNN相比，密集连接循环卷积网络（DCRN）是否能在分类组织病理学图像中的显微镜下核方面实现更优性能？
• RQ2 通过结合残差学习与循环跳跃连接，R2U-Net架构是否能提升核分割的准确性？
• RQ3 所提出的UD-Net模型（R2U-Net的回归变体）是否在核检测任务中优于最先进方法？
• RQ4 所提出模型在基准组织病理学数据集上的性能指标（如F1-score和Dice系数）提升了多少？
• RQ5 这些模型能否实现对全切片图像（WSI）中核的更可靠、更定量的分析，以支持临床应用？

主要发现

• DCRN模型在核分类任务中相比近期发表的基于DCNN的方法，F1-score提高了3.4%。
• UD-Net模型在核检测任务中相比最新基于DCNN的方法，F1-score提高了4.5%。
• R2U-Net在核分割任务中测试的Dice系数（DC）达到92.15%，表明分割精度极高。
• 所提出模型在RCC和2018年核分割挑战赛数据集上，各项指标（包括精确率、召回率和F1-score）均表现出一致的性能提升。
• 改进的架构使对全切片图像（WSI）中细胞核的分析更加稳健和精确，支持癌症诊断中的更优临床决策。