Cellular community detection for tissue phenotyping in colorectal cancer histology images

Classification of various types of tissue in cancer histology images based on the cellular compositions is an important step towards the development of computational pathology tools for systematic digital profiling of the spatial tumor microenvironment. Most existing methods for tissue phenotyping are limited to the classification of tumor and stroma and require large amount of annotated histology images which are often not available. In the current work, we pose the problem of identifying distinct tissue phenotypes as finding communities in cellular graphs or networks. First, we train a deep neural network for cell detection and classification into five distinct cellular components. Considering the detected nuclei as nodes, potential cell-cell connections are assigned using Delaunay triangulation resulting in a cell-level graph. Based on this cell graph, a feature vector capturing potential cell-cell connection of different types of cells is computed. These feature vectors are used to construct a patch-level graph based on chi-square distance. We map patch-level nodes to the geometric space by representing each node as a vector of geodesic distances from other nodes in the network and iteratively drifting the patch nodes in the direction of positive density gradients towards maximum density regions. The proposed algorithm is evaluated on a publicly available dataset and another new large-scale dataset consisting of 280K patches of seven tissue phenotypes. The estimated communities have significant biological meanings as verified by the expert pathologists. A comparison with current state-of-the-art methods reveals significant performance improvement in tissue phenotyping.     

Spatially Constrained Context-Aware Hierarchical Deep Correlation Filters for Nucleus Detection in Histology Images

Nucleus detection in histology images is a fundamental step for cellular-level analysis in computational pathology. In clinical practice, quantitative nuclear morphology can be used for diagnostic decision making, prognostic stratification, and treatment outcome prediction. Nucleus detection is a challenging task because of large variations in the shape of different types of nucleus such as nuclear clutter, heterogeneous chromatin distribution, and irregular and fuzzy boundaries. To address these challenges, we aim to accurately detect nuclei using spatially constrained context-aware correlation filters using hierarchical deep features extracted from multiple layers of a pre-trained network. During training, we extract contextual patches around each nucleus which are used as negative examples while the actual nucleus patch is used as a positive example. In order to spatially constrain the correlation filters, we propose to construct a spatial structural graph across different nucleus components encoding pairwise similarities. The correlation filters are constrained to act as eigenvectors of the Laplacian of the spatial graphs enforcing these to capture the nucleus structure. A novel objective function is proposed by embedding graph-based structural information as well as the contextual information within the discriminative correlation filter framework. The learned filters are constrained to be orthogonal to both the contextual patches and the spatial graph-Laplacian basis to improve the localization and discriminative performance. The proposed objective function trains a hierarchy of correlation filters on different deep feature layers to capture the heterogeneity in nuclear shape and texture. The proposed algorithm is evaluated on three publicly available datasets and compared with 15 current state-of-the-art methods demonstrating competitive performance in terms of accuracy, speed, and generalization.     

SRPN: similarity-based region proposal networks for nuclei and cells detection in histology images

The detection of nuclei and cells in histology images is of great value in both clinical practice and pathological studies. However, multiple reasons such as morphological variations of nuclei or cells make it a challenging task where conventional object detection methods cannot obtain satisfactory performance in many cases. A detection task consists of two sub-tasks, classification and localization. Under the condition of dense object detection, classification is a key to boost the detection performance. Considering this, we propose similarity based region proposal networks (SRPN) for nuclei and cells detection in histology images. In particular, a customised convolution layer termed as embedding layer is designed for network building. The embedding layer is added into the region proposal networks, enabling the networks to learn discriminative features based on similarity learning. Features obtained by similarity learning can significantly boost the classification performance compared to conventional methods. SRPN can be easily integrated into standard convolutional neural networks architectures such as the Faster R-CNN and RetinaNet. We test the proposed approach on tasks of multi-organ nuclei detection and signet ring cells detection in histological images. Experimental results show that networks applying similarity learning achieved superior performance on both tasks when compared to their counterparts. In particular, the proposed SRPN achieve state-of-the-art performance on the MoNuSeg benchmark for nuclei segmentation and detection while compared to previous methods, and on the signet ring cell detection benchmark when compared with baselines. The sourcecode is publicly available at: https://github.com/sigma10010/nuclei_cells_det.     

DCAN: Deep contour-aware networks for object instance segmentation from histology images

In histopathological image analysis, the morphology of histological structures, such as glands and nuclei, has been routinely adopted by pathologists to assess the malignancy degree of adenocarcinomas. Accurate detection and segmentation of these objects of interest from histology images is an essential prerequisite to obtain reliable morphological statistics for quantitative diagnosis. While manual annotation is error-prone, time-consuming and operator-dependant, automated detection and segmentation of objects of interest from histology images can be very challenging due to the large appearance variation, existence of strong mimics, and serious degeneration of histological structures. In order to meet these challenges, we propose a novel deep contour-aware network (DCAN) under a unified multi-task learning framework for more accurate detection and segmentation. In the proposed network, multi-level contextual features are explored based on an end-to-end fully convolutional network (FCN) to deal with the large appearance variation. We further propose to employ an auxiliary supervision mechanism to overcome the problem of vanishing gradients when training such a deep network. More importantly, our network can not only output accurate probability maps of histological objects, but also depict clear contours simultaneously for separating clustered object instances, which further boosts the segmentation performance. Our method ranked the first in two histological object segmentation challenges, including 2015 MICCAI Gland Segmentation Challenge and 2015 MICCAI Nuclei Segmentation Challenge. Extensive experiments on these two challenging datasets demonstrate the superior performance of our method, surpassing all the other methods by a significant margin.     

White blood cell classification via a discriminative region detection assisted feature aggregation network

White blood cell (WBC) classification plays an important role in human pathological diagnosis since WBCs will show different appearance when they fight with various disease pathogens. Although many previous white blood cell classification have been proposed and earned great success, their classification accuracy is still significantly affected by some practical issues such as uneven staining, boundary blur and nuclear intra-class variability. In this paper, we propose a deep neural network for WBC classification via discriminative region detection assisted feature aggregation (DRFA-Net), which can accurately locate the WBC area to boost final classification performance. Specifically, DRFA-Net uses an adaptive feature enhancement module to refine multi-level deep features in a bilateral manner for efficiently capturing both high-level semantic information and low-level details of WBC images. Considering the fact that background areas could inevitably produce interference, we design a network branch to detect the WBC area with the supervision of segmented ground truth. The bilaterally refined features obtained from two directions are finally aggregated for final classification, and the detected WBC area is utilized to highlight the features of discriminative regions by an attention mechanism. Extensive experiments on several public datasets are conducted to validate that our proposed DRFA-Net can obtain higher accuracies when compared with other state-of-the-art WBC classification methods.     

Breast cancer cell nuclei classification in histopathology images using deep neural networks

Purpose

Cell nuclei classification in breast cancer histopathology images plays an important role in effective diagnose since breast cancer can often be characterized by its expression in cell nuclei. However, due to the small and variant sizes of cell nuclei, and heavy noise in histopathology images, traditional machine learning methods cannot achieve desirable recognition accuracy. To address this challenge, this paper aims to present a novel deep neural network which performs representation learning and cell nuclei recognition in an end-to-end manner.

Methods

The proposed model hierarchically maps raw medical images into a latent space in which robustness is achieved by employing a stacked denoising autoencoder. A supervised classifier is further developed to improve the discrimination of the model by maximizing inter-subject separability in the latent space. The proposed method involves a cascade model which jointly learns a set of nonlinear mappings and a classifier from the given raw medical images. Such an on-the-shelf learning strategy makes obtaining discriminative features possible, thus leading to better recognition performance.

Results

Extensive experiments with benign and malignant breast cancer datasets are conducted to verify the effectiveness of the proposed method. Better performance was obtained when compared with other feature extraction methods, and higher recognition rate was achieved when compared with other seven classification methods.

Conclusions

We propose an end-to-end DNN model for cell nuclei and non-nuclei classification of histopathology images. It demonstrates that the proposed method can achieve promising performance in cell nuclei classification, and the proposed method is suitable for the cell nuclei classification task.

     

Accurate diagnosis of thyroid follicular lesions from nuclear morphology using supervised learning

Follicular lesions of the thyroid remain significant diagnostic challenges in surgical pathology and cytology. The diagnosis often requires considerable resources and ancillary tests including immunohistochemistry, molecular studies, and expert consultation. Visual analyses of nuclear morphological features, generally speaking, have not been helpful in distinguishing this group of lesions. Here we describe a method for distinguishing between follicular lesions of the thyroid based on nuclear morphology. The method utilizes an optimal transport-based linear embedding for segmented nuclei, together with an adaptation of existing classification methods. We show the method outputs assignments (classification results) which are near perfectly correlated with the clinical diagnosis of several lesion types’ lesions utilizing a database of 94 patients in total. Experimental comparisons also show the new method can significantly outperform standard numerical feature-type methods in terms of agreement with the clinical diagnosis gold standard. In addition, the new method could potentially be used to derive insights into biologically meaningful nuclear morphology differences in these lesions. Our methods could be incorporated into a tool for pathologists to aid in distinguishing between follicular lesions of the thyroid. In addition, these results could potentially provide nuclear morphological correlates of biological behavior and reduce health care costs by decreasing histotechnician and pathologist time and obviating the need for ancillary testing.     

One model is all you need: Multi-task learning enables simultaneous histology image segmentation and classification

The recent surge in performance for image analysis of digitised pathology slides can largely be attributed to the advances in deep learning. Deep models can be used to initially localise various structures in the tissue and hence facilitate the extraction of interpretable features for biomarker discovery. However, these models are typically trained for a single task and therefore scale poorly as we wish to adapt the model for an increasing number of different tasks. Also, supervised deep learning models are very data hungry and therefore rely on large amounts of training data to perform well. In this paper, we present a multi-task learning approach for segmentation and classification of nuclei, glands, lumina and different tissue regions that leverages data from multiple independent data sources. While ensuring that our tasks are aligned by the same tissue type and resolution, we enable meaningful simultaneous prediction with a single network. As a result of feature sharing, we also show that the learned representation can be used to improve the performance of additional tasks via transfer learning, including nuclear classification and signet ring cell detection. As part of this work, we train our developed Cerberus model on a huge amount of data, consisting of over 600 thousand objects for segmentation and 440 thousand patches for classification. We use our approach to process 599 colorectal whole-slide images from TCGA, where we localise 377 million, 900 thousand and 2.1 million nuclei, glands and lumina respectively. We make this resource available to remove a major barrier in the development of explainable models for computational pathology.     

Super-resolution land cover mapping by deep learning

Super-resolution mapping (SRM) is a technique to estimate a fine spatial resolution land cover map from coarse spatial resolution fractional proportion images. SRM is often based explicitly on the use of a spatial pattern model that represents the land cover mosaic at the fine spatial resolution. Recently developed deep learning methods have considerable potential as an alternative approach for SRM, based on learning the spatial pattern of land cover from existing fine resolution data such as land cover maps. This letter proposes a deep learning-based SRM algorithm (DeepSRM). A deep convolutional neural network was first trained to estimate a fine resolution indicator image for each class from the coarse resolution fractional image, and all indicator maps were then combined to create the final fine resolution land cover map based on the maximal value strategy. The results of an experiment undertaken with simulated images show that DeepSRM was superior to conventional hard classification and a suite of popular SRM algorithms, yielding the most accurate land cover representation. Consequently, methods such as DeepSRM may help exploit the potential of remote sensing as a source of accurate land cover information.     

High-resolution fiber optic microscopy with fluorescent contrast enhancement for the identification of axillary lymph node metastases in breast cancer: a pilot study

This prospective pilot study evaluates the potential of high-resolution fiber optic microscopy (HRFM) to identify lymph node metastases in breast cancer patients. 43 lymph nodes were collected from 14 consenting breast cancer patients. Proflavine dye was topically applied to lymph nodes ex vivo to allow visualization of nuclei. 242 images were collected at 105 sites with confirmed histopathologic diagnosis. Quantitative statistical features were calculated from images, assessed with one-way ANOVA, and were used to develop a classification algorithm with the goal of objectively discriminating between normal and metastatic tissue. A classification algorithm using mean image intensity and skewness achieved sensitivity of 79% (27/34) and specificity of 77% (55/71). This study demonstrates the technical feasibility and diagnostic potential of HRFM with fluorescent contrast in the ex vivo evaluation of lymph nodes from breast cancer patients.     

Feature-driven local cell graph (FLocK): New computational pathology-based descriptors for prognosis of lung cancer and HPV status of oropharyngeal cancers

Local spatial arrangement of nuclei in histopathology images of different cancer subtypes has been shown to have prognostic value. In order to capture localized nuclear architectural information, local cell cluster graph-based measurements have been proposed. However, conventional ways of cell graph construction only utilize nuclear spatial proximity, and do not differentiate between different cell types while constructing the graph. In this paper, we present feature-driven local cell cluster graph (FLocK), a new approach to constructing local cell graphs by simultaneously considering spatial proximity and attributes of the individual nuclei (e.g. shape, size, texture). In addition, we have designed a new set of quantitative graph-derived metrics to be extracted from FLocKs, in turn capturing the interplay between different proximally located clusters of nuclei. We have evaluated the efficacy of FLocK features extracted from H&E stained tissue images in two clinical applications: to classify short-term vs. long-term survival among patients of early stage non-small cell lung cancer (ES-NSCLC), and also to predict human papillomavirus (HPV) status of oropharyngeal squamous cell carcinoma (OP-SCCs).In the classification of long-term vs. short-term survival among patients of ES-NSCLC (training cohort, n = 434), the top 10 discriminative FLocK features related to the variation of FLocK size and intersected FLocK distance were identified, via Minimum Redundancy and Maximum Relevance (MRMR) selection, in 100 runs of 10-fold cross-validation, and in conjunction with a linear discriminant classifier yielded a mean AUC of 0.68 for predicting survival in the training cohort. This is better than other state-of-art histomorphometric and deep learning classifiers (cell cluster graphs (AUC = 0.62), global cell graph (AUC = 0.56), nuclear shape (AUC = 0.54), nuclear orientation (AUC = 0.61), AlexNet (AUC = 0.55), ResNet (AUC = 0.56)). The FLocK-based classifier yielded an AUC of 0.70 in an independent testing cohort (n = 150). The patients identified as “high-risk” had significantly poorer overall survival in the testing cohort, with a hazard ratio (95% confidence interval) of 2.24 (1.24-4.05), p = 0.01144).In the classification of HPV status of OP-SCC, the top three FLocK features pertaining to the portion of intersected FLocKs were used to construct a classifier, which yielded an AUC of 0.80 in the training cohort (n = 50), and an accuracy of 0.78 in an independent testing cohort (n = 35). The combination of FLocK measurements with cell cluster graphs, nuclear orientation, and nuclear shape improved the training AUC to 0.87, 0.91 and 0.85, respectively. Deep learning approaches yielded marginally better performance than the FLocK-based classifier in this application, with AUC = 0.78 for AlexNet, AUC = 0.81 for ResNet, and AUC = 0.76 for FLocK-based classifier in the testing cohort. However, the combination of two hand-crafted features: FLocK and nuclear orientation yielded a better performance (AUC = 0.84).FLocK provides a unique and quantitative way to analyze histology images of solid tumors and interrogate tumor morphology from a different aspect than existing histomorphometrics. The source code can be accessed at https://github.com/hacylu/FLocK.     

Using Siamese capsule networks for remote sensing scene classification

ABSTRACT

The convolutional neural network (CNN) is widely used for image classification because of its powerful feature extraction capability. The key challenge of CNN in remote sensing (RS) scene classification is that the size of data set is small and images in each category vary greatly in position and angle, while the spatial information will be lost in the pooling layers of CNN. Consequently, how to extract accurate and effective features is very important. To this end, we present a Siamese capsule network to address these issues. Firstly, we introduce capsules to extract the spatial information of the features so as to learn equivariant representations. Secondly, to improve the classification accuracy of the model on small data sets, the proposed model utilizes the structure of the Siamese network as embedded verification. Finally, the features learned through Capsule networks are regularized by a metric learning term to improve the robustness of our model. The effectiveness of the model on three benchmark RS data sets is verified by different experiments. Experimental results demonstrate that the comprehensive performance of the proposed method surpasses other existing methods.     

基于集成机器学习的卵巢癌多检验指标联合诊断模型

目的构建一种集成特征降维技术和人工神经网络分类器的机器学习诊断模型,开发临床常规血液指标对卵巢癌的辅助诊断价值。方法收集本院明确诊断的卵巢癌患者作为病例组(n=185),将其他恶性妇科肿瘤患者(n=138)、良性妇科疾病患者(n=339)与正常体检者(n=92)三类人群作为整体对照组。借助电子病历挖掘系统获取人口学资料以及肿瘤标志物、血细胞分析、性激素等6类共计28项实验室检测指标。通过主成分分析对检验数据进行特征提取,再将低维度特征集作为神经网络的输入层变量建立诊断模型,同时采用遗传算法优化神经网络的参数以提高模型的训练速度和分类精度。结果机器学习诊断模型的ROC曲线下面积达到0.948,敏感性为91.9%,特异性为86.9%,其诊断效能明显优于单项检测CA125的传统方式。该模型对不同病程分期的卵巢癌均能进行准确诊断,并且在三个对照亚组中均表现出对卵巢癌一定的鉴别能力。结论利用机器学习整合多项常规检验指标可有效提升卵巢癌的诊断效能,为卵巢癌的智能化辅助诊断提供了新思路。     

Joint hub identification for brain networks by multivariate graph inference

Recent developments in neuroimaging allow us to investigate the structural and functional connectivity between brain regions in vivo. Mounting evidence suggests that hub nodes play a central role in brain communication and neural integration. Such high centrality, however, makes hub nodes particularly susceptible to pathological network alterations and the identification of hub nodes from brain networks has attracted much attention in neuroimaging. Current popular hub identification methods often work in a univariate manner, i.e., selecting the hub nodes one after another based on either heuristic of the connectivity profile at each node or predefined settings of network modules. Since the topological information of the entire network (such as network modules) is not fully utilized, current methods have limited power to identify hubs that link multiple modules (connector hubs) and are biased toward identifying hubs having many connections within the same module (provincial hubs). To address this challenge, we propose a novel multivariate hub identification method. Our method identifies connector hubs as those that partition the network into disconnected components when they are removed from the network. Furthermore, we extend our hub identification method to find the population-based hub nodes from a group of network data. We have compared our hub identification method with existing methods on both simulated and human brain network data. Our proposed method achieves more accurate and replicable discovery of hub nodes and exhibits enhanced statistical power in identifying network alterations related to neurological disorders such as Alzheimer's disease and obsessive-compulsive disorder.     

Cross-attention multi-branch network for fundus diseases classification using SLO images

Fundus diseases classification is vital for the health of human beings. However, most of existing methods detect diseases by means of single angle fundus images, which lead to the lack of pathological information. To address this limitation, this paper proposes a novel deep learning method to complete different fundus diseases classification tasks using ultra-wide field scanning laser ophthalmoscopy (SLO) images, which have an ultra-wide field view of 180–200˚. The proposed deep model consists of multi-branch network, atrous spatial pyramid pooling module (ASPP), cross-attention and depth-wise attention module. Specifically, the multi-branch network employs the ResNet-34 model as the backbone to extract feature information, where the ResNet-34 model with two-branch is followed by the ASPP module to extract multi-scale spatial contextual features by setting different dilated rates. The depth-wise attention module can provide the global attention map from the multi-branch network, which enables the network to focus on the salient targets of interest. The cross-attention module adopts the cross-fusion mode to fuse the channel and spatial attention maps from the ResNet-34 model with two-branch, which can enhance the representation ability of the disease-specific features. The extensive experiments on our collected SLO images and two publicly available datasets demonstrate that the proposed method can outperform the state-of-the-art methods and achieve quite promising classification performance of the fundus diseases.     

Interpretability-Guided Inductive Bias For Deep Learning Based Medical Image

Deep learning methods provide state of the art performance for supervised learning based medical image analysis. However it is essential that trained models extract clinically relevant features for downstream tasks as, otherwise, shortcut learning and generalization issues can occur. Furthermore in the medical field, trustability and transparency of current deep learning systems is a much desired property. In this paper we propose an interpretability-guided inductive bias approach enforcing that learned features yield more distinctive and spatially consistent saliency maps for different class labels of trained models, leading to improved model performance. We achieve our objectives by incorporating a class-distinctiveness loss and a spatial-consistency regularization loss term. Experimental results for medical image classification and segmentation tasks show our proposed approach outperforms conventional methods, while yielding saliency maps in higher agreement with clinical experts. Additionally, we show how information from unlabeled images can be used to further boost performance. In summary, the proposed approach is modular, applicable to existing network architectures used for medical imaging applications, and yields improved learning rates, model robustness, and model interpretability.     

Triple U-net: Hematoxylin-aware nuclei segmentation with progressive dense feature aggregation

Nuclei segmentation is a vital step for pathological cancer research. It is still an open problem due to some difficulties, such as color inconsistency introduced by non-uniform manual operations, blurry tumor nucleus boundaries and overlapping tumor cells. In this paper, we aim to leverage the unique optical characteristic of H&E staining images that hematoxylin always stains cell nuclei blue, and eosin always stains the extracellular matrix and cytoplasm pink. Therefore, we extract the Hematoxylin component from RGB images by Beer-Lambert’s Law. According to the optical attribute, the extracted Hematoxylin component is robust to color inconsistency. With the Hematoxylin component, we propose a Hematoxylin-aware CNN model for nuclei segmentation without the necessity of color normalization. Our proposed network is formulated as a Triple U-net structure which includes an RGB branch, a Hematoxylin branch and a Segmentation branch. Then we propose a novel feature aggregation strategy to allow the network to fuse features progressively and to learn better feature representations from different branches. Extensive experiments are performed to qualitatively and quantitatively evaluate the effectiveness of our proposed method. In the meanwhile, it outperforms state-of-the-art methods on three different nuclei segmentation datasets.     

Self-calibrated brain network estimation and joint non-convex multi-task learning for identification of early Alzheimer's disease

Detection of early stages of Alzheimer's disease (AD) (i.e., mild cognitive impairment (MCI)) is important to maximize the chances to delay or prevent progression to AD. Brain connectivity networks inferred from medical imaging data have been commonly used to distinguish MCI patients from normal controls (NC). However, existing methods still suffer from limited performance, and classification remains mainly based on single modality data. This paper proposes a new model to automatically diagnosing MCI (early MCI (EMCI) and late MCI (LMCI)) and its earlier stages (i.e., significant memory concern (SMC)) by combining low-rank self-calibrated functional brain networks and structural brain networks for joint multi-task learning. Specifically, we first develop a new functional brain network estimation method. We introduce data quality indicators for self-calibration, which can improve data quality while completing brain network estimation, and perform correlation analysis combined with low-rank structure. Second, functional and structural connected neuroimaging patterns are integrated into our multi-task learning model to select discriminative and informative features for fine MCI analysis. Different modalities are best suited to undertake distinct classification tasks, and similarities and differences among multiple tasks are best determined through joint learning to determine most discriminative features. The learning process is completed by non-convex regularizer, which effectively reduces the penalty bias of trace norm and approximates the original rank minimization problem. Finally, the most relevant disease features classified using a support vector machine (SVM) for MCI identification. Experimental results show that our method achieves promising performance with high classification accuracy and can effectively discriminate between different sub-stages of MCI.     

Tumor Malignancy Detection Using Histopathology Imaging

Image segmentation and classification in the biomedical imaging field has high worth in cancer diagnosis and grading. The proposed method classifies the images based on a combination of handcrafted features and shape features using bag of visual words (BoW). The multistage segmentation technique to localize the nuclei in histopathology images includes the stain decomposition and histogram equalization to highlight the nucleus region, followed by the nuclei key point extraction using fast radial symmetry transform, normalized graph cut based on the nuclei region estimation, and nuclei boundary estimation using modified gradient. Subsequently, features from localized regions termed as handcrafted features and the shape features using BoW are extracted for classification. The experiments are performed using both the handcrafted features and BoW to take the advantages of both local nuclei features and globally spatial features. The simulation is performed on the Bisque and BreakHis data sets (with corresponding average accuracies of 93.87% and 96.96%, respectively) and confirms better diagnosis performance using the proposed method.