用于多组织乳腺癌图像分割的多染色多层级卷积网络
Multi-Stain Multi-Level Convolutional Network for Multi-Tissue Breast Cancer Image Segmentation
AI总结：
本文提出一种基于CNN的多染色多层级乳腺全切片多类组织分割模型，通过跨分辨率像素对齐非线性融合和多阶段上下文感知训练，实现染色与扫描仪不变性，并在新染色和新扫描仪数据上取得平均IOU 0.72。
摘要：
数字病理学和显微镜图像分析被广泛用于数字扫描的免疫组化（IHC）切片分割，主要目的是识别癌症并定位提示肿瘤存在的感兴趣区域（ROI）。然而，当前的ROI分割模型要么仅针对特定染色，要么由于多个实验室采用不同的染色方案或成像模态而受到染色和扫描仪差异的影响。此外，导管原位癌（DCIS）、腺泡等组织由于其结构相似性和颜色组成，常常被误分类为肿瘤。本文提出了一种新的基于卷积神经网络（CNN）的多类组织分割模型，用于组织病理学全切片乳腺切片，该模型将肿瘤分类，并将导管、腺泡、DCIS、鳞状上皮、血管、坏死等其他组织区域分割为独立类别。我们独特的跨空间分辨率像素对齐非线性融合使模型同时具备局部和全局视野，从而能够准确检测各类别。我们提出的模型还能够利用来自全切片图像（WSI）不同分辨率的多层级上下文，将褶皱、伪影、模糊区域、气泡等不良区域与组织区域分离开来。采用多阶段迭代训练，结合上下文感知增强和逐渐增加的噪声，利用来自513张切片的部分且有噪声的标注，高效训练了一个多染色通用模型。我们的训练流程使用了通过上下文感知增强生成的1200万个图像块，使模型在不同数据来源之间具有染色和扫描仪不变性。为了验证染色和扫描仪不变性的外推能力，我们在来自不同实验室的全新扫描仪（Motic）和全新染色（苏木精-伊红）的23000个图像块上对模型进行了评估。平均IOU为0.72，与模型在其他数据来源和扫描仪上的性能相当。
英文摘要：
Digital pathology and microscopy image analysis are widely employed in the segmentation of digitally scanned IHC slides, primarily to identify cancer and pinpoint regions of interest (ROI) indicative of tumor presence. However, current ROI segmentation models are either stain-specific or suffer from the issues of stain and scanner variance due to different staining protocols or modalities across multiple labs. Also, tissues like Ductal Carcinoma in Situ (DCIS), acini, etc. are often classified as Tumors due to their structural similarities and color compositions. In this paper, we proposed a novel convolutional neural network (CNN) based Multi-class Tissue Segmentation model for histopathology whole-slide Breast slides which classify tumors and segments other tissue regions such as Ducts, acini, DCIS, Squamous epithelium, Blood Vessels, Necrosis, etc. as a separate class. Our unique pixel-aligned non-linear merge across spatial resolutions empowers models with both local and global fields of view for accurate detection of various classes. Our proposed model is also able to separate bad regions such as folds, artifacts, blurry regions, bubbles, etc. from tissue regions using multi-level context from different resolutions of WSI. Multi-phase iterative training with context-aware augmentation and increasing noise was used to efficiently train a multi-stain generic model with partial and noisy annotations from 513 slides. Our training pipeline used 12 million patches generated using context-aware augmentations which made our model stain and scanner invariant across data sources. To extrapolate stain and scanner invariance, our model was evaluated on 23000 patches which were for a completely new stain (Hematoxylin and Eosin) from a completely new scanner (Motic) from a different lab. The mean IOU was 0.72 which is on par with model performance on other data sources and scanners.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
