Classification Of Nuclei Research Articles

A scale and region-enhanced decoding network for nuclei classification in histology image

Accurate classification of nuclei in histology images is essential for clinical diagnosis, prognosis, and therapeutic response prediction of cancer. However, this is still a challenging task due to (1) nuclei exhibiting a high level of heterogeneity within different types and (2) large intra-class variability including complex morphology and large variations of scale. To solve these problems, we propose a novel scale and region-enhanced decoding network based on the traditional U-shape structure for nuclei classification. We employ a nuclei detection head as region enhancement module in the decoding branch, which can enhance the nuclear regional information by locating the approximate bounding regions and provide more distinguish information for producing better feature maps of subsequent classification. Then, we propose a scale-aware feature fusion module, which fuses stage-wise feature maps generated from the decoder branch, to effectively learn multi-scale features. Finally, we utilize a scale attention module to calibrate the features and adapt to the most suitable scale in the hybrid multi-scale feature maps. In comparison with several state-of-the-art methods on two publicly available colonic cancer nuclei classification datasets, namely ConSep and Lizard, the proposed method obtains the highest accuracy of 0.860 and 0.927, respectively. It also achieves the highest accuracy of 0.838 on the PanNuke dataset collected from different tissues at different magnitudes. The independent validation on two subsets of the Lizard dataset indicates the proposed method obtains the highest accuracy. In conclusion, the proposed method can greatly improve classification performance, particularly for challenging nuclei with complex contexts and large-scale variations.

Merging nucleus datasets by correlation-based cross-training

Fine-grained nucleus classification is challenging because of the high inter-class similarity and intra-class variability. Therefore, a large number of labeled data is required for training effective nucleus classification models. However, it is challenging to label a large-scale nucleus classification dataset comparable to ImageNet in natural images, considering that high-quality nucleus labeling requires specific domain knowledge. In addition, the existing publicly available datasets are often inconsistently labeled with divergent labeling criteria. Due to this inconsistency, conventional models have to be trained on each dataset separately and work independently to infer their own classification results, limiting their classification performance. To fully utilize all annotated datasets, we formulate the nucleus classification task as a multi-label problem with missing labels to utilize all datasets in a unified framework. Specifically, we merge all datasets and combine their labels as multiple labels. Thus, each data has one ground-truth label and several missing labels. We devise a base classification module that is trained using all data but sparsely supervised by the ground-truth labels only. We then exploit the correlation among different label sets by a label correlation module. By doing so, we can have two trained basic modules and further cross-train them with both ground-truth labels and pseudo labels for the missing ones. Importantly, data without any ground-truth labels can also be involved in our framework, as we can regard them as data with all labels missing and generate the corresponding pseudo labels. We carefully re-organized multiple publicly available nucleus classification datasets, converted them into a uniform format, and tested the proposed framework on them. Experimental results show substantial improvement compared to the state-of-the-art methods. The code and data are available at https://w-h-zhang.github.io/projects/dataset_merging/dataset_merging.html.

Artificial Hummingbird Algorithm with Transfer-Learning-Based Mitotic Nuclei Classification on Histopathologic Breast Cancer Images.

Recently, artificial intelligence (AI) is an extremely revolutionized domain of medical image processing. Specifically, image segmentation is a task that generally aids in such an improvement. This boost performs great developments in the conversion of AI approaches in the research lab to real medical applications, particularly for computer-aided diagnosis (CAD) and image-guided operation. Mitotic nuclei estimates in breast cancer instances have a prognostic impact on diagnosis of cancer aggressiveness and grading methods. The automated analysis of mitotic nuclei is difficult due to its high similarity with nonmitotic nuclei and heteromorphic form. This study designs an artificial hummingbird algorithm with transfer-learning-based mitotic nuclei classification (AHBATL-MNC) on histopathologic breast cancer images. The goal of the AHBATL-MNC technique lies in the identification of mitotic and nonmitotic nuclei on histopathology images (HIs). For HI segmentation process, the PSPNet model is utilized to identify the candidate mitotic patches. Next, the residual network (ResNet) model is employed as feature extractor, and extreme gradient boosting (XGBoost) model is applied as a classifier. To enhance the classification performance, the parameter tuning of the XGBoost model takes place by making use of the AHBA approach. The simulation values of the AHBATL-MNC system are tested on medical imaging datasets and the outcomes are investigated in distinct measures. The simulation values demonstrate the enhanced outcomes of the AHBATL-MNC method compared to other current approaches.

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.

Nucleus segmentation and classification using residual SE-UNet and feature concatenation approach incervical cytopathology cell images.

Introduction: Pap smear is considered to be the primary examination for the diagnosis of cervical cancer. But the analysis of pap smear slides is a time-consuming task and tedious as it requires manual intervention. The diagnostic efficiency depends on the medical expertise of the pathologist, and human error often hinders the diagnosis. Automated segmentation and classification of cervical nuclei will help diagnose cervical cancer in earlier stages. Materials and Methods: The proposed methodology includes three models: a Residual-Squeeze-and-Excitation-module based segmentation model, a fusion-based feature extraction model, and a Multi-layer Perceptron classification model. In the fusion-based feature extraction model, three sets of deep features are extracted from these segmented nuclei using the pre-trained and fine-tuned VGG19, VGG-F, and CaffeNet models, and two hand-crafted descriptors, Bag-of-Features and Linear-Binary-Patterns, are extracted for each image. For this work, Herlev, SIPaKMeD, and ISBI2014 datasets are used for evaluation. The Herlev datasetis used for evaluating both segmentation and classification models. Whereas the SIPaKMeD and ISBI2014 are used for evaluating the classification model, and the segmentation model respectively. Results: The segmentation network enhanced the precision and ZSI by 2.04%, and 2.00% on the Herlev dataset, and the precision and recall by 0.68%, and 2.59% on the ISBI2014 dataset. The classification approach enhanced the accuracy, recall, and specificity by 0.59%, 0.47%, and 1.15% on the Herlev dataset, and by 0.02%, 0.15%, and 0.22% on the SIPaKMed dataset. Conclusion: The experiments demonstrate that the proposed work achieves promising performance on segmentation and classification in cervical cytopathology cell images..

Knowledge-Based Representation Learning for Nucleus Instance Classification From Histopathological Images.

The classification of nuclei in H&E-stained histopathological images is a fundamental step in the quantitative analysis of digital pathology. Most existing methods employ multi-class classification on the detected nucleus instances, while the annotation scale greatly limits their performance. Moreover, they often downplay the contextual information surrounding nucleus instances that is critical for classification. To explicitly provide contextual information to the classification model, we design a new structured input consisting of a content-rich image patch and a target instance mask. The image patch provides rich contextual information, while the target instance mask indicates the location of the instance to be classified and emphasizes its shape. Benefiting from our structured input format, we propose Structured Triplet for representation learning, a triplet learning framework on unlabelled nucleus instances with customized positive and negative sampling strategies. We pre-train a feature extraction model based on this framework with a large-scale unlabeled dataset, making it possible to train an effective classification model with limited annotated data. We also add two auxiliary branches, namely the attribute learning branch and the conventional self-supervised learning branch, to further improve its performance. As part of this work, we will release a new dataset of H&E-stained pathology images with nucleus instance masks, containing 20,187 patches of size 1024 ×1024 , where each patch comes from a different whole-slide image. The model pre-trained on this dataset with our framework significantly reduces the burden of extensive labeling. We show a substantial improvement in nucleus classification accuracy compared with the state-of-the-art methods.

A dual decoder U-Net-based model for nuclei instance segmentation in hematoxylin and eosin-stained histological images.

Even in the era of precision medicine, with various molecular tests based on omics technologies available to improve the diagnosis process, microscopic analysis of images derived from stained tissue sections remains crucial for diagnostic and treatment decisions. Among other cellular features, both nuclei number and shape provide essential diagnostic information. With the advent of digital pathology and emerging computerized methods to analyze the digitized images, nuclei detection, their instance segmentation and classification can be performed automatically. These computerized methods support human experts and allow for faster and more objective image analysis. While methods ranging from conventional image processing techniques to machine learning-based algorithms have been proposed, supervised convolutional neural network (CNN)-based techniques have delivered the best results. In this paper, we propose a CNN-based dual decoder U-Net-based model to perform nuclei instance segmentation in hematoxylin and eosin (H&E)-stained histological images. While the encoder path of the model is developed to perform standard feature extraction, the two decoder heads are designed to predict the foreground and distance maps of all nuclei. The outputs of the two decoder branches are then merged through a watershed algorithm, followed by post-processing refinements to generate the final instance segmentation results. Moreover, to additionally perform nuclei classification, we develop an independent U-Net-based model to classify the nuclei predicted by the dual decoder model. When applied to three publicly available datasets, our method achieves excellent segmentation performance, leading to average panoptic quality values of 50.8%, 51.3%, and 62.1% for the CryoNuSeg, NuInsSeg, and MoNuSAC datasets, respectively. Moreover, our model is the top-ranked method in the MoNuSAC post-challenge leaderboard.

Nuclei spotting for computational pathology in microscopic images

Identification and classification of nuclei from microscopy is vital to new pharmaceutical developments. Biologist lacks a robust and efficient way to detect nuclei to natural variation in their appearances as well as differences in image capturing methods. Identification and classification of nuclei from microscopy images is considered as a complex task. A successful implementation will aid researchers immensely in their fight to find pharmaceutical solutions to medical crises while saving both valuable research time and funding. In this study, we employed a modified U-Net a deep learning based approach for nuclei detection where we computed 0.78 value of IOU (intersection over union) on BBBC038v1 dataset.

DAN-NucNet: A dual attention based framework for nuclei segmentation in cancer histology images under wild clinical conditions

Nuclei segmentation plays an essential role in histology analysis. The nuclei segmentation in histology images is challenging in variable conditions (clinical wild), such as poor staining quality, stain variability, tissue variability, and conditions having higher morphological variability. Recently, some deep learning models have been proposed for nuclei segmentation. However, these models rarely solve the problems mentioned above simultaneously. Most of the information in Hematoxylin and Eosin (H&E) stained histology images is in its channel, and the remaining information is in the spatial domain. We observed that most problems could be solved by considering channel and spatial features simultaneously, e.g., the spatial and channel features provide the solution to the morphological variability and staining variability, respectively. Therefore, we propose a novel spatial-channel attention-based modified UNet architecture with ResNet blocks in encoder layers. The UNet baseline preserves coarse and fine features, thus proving the solution to the tissue variability. The proposed method significantly improves the segmentation performance compared to the state-of-the-art methods on three different benchmark datasets. We demonstrate that the proposed model is generalized for 20 cancer sites, more than any reported literature. The proposed model is less complex than most state-of-the-art models. The impact of the proposed model is that it will help improve further procedures such as nuclei instance segmentation, nuclei classification, and cancer grading.

Accurate classification of liver nuclei based on AI models for diagnostic support of hepatocellular carcinoma

Introduction: Hepatocellular carcinoma (HCC) is the most common primary liver cancer worldwide. Early diagnosis is crucial to improve management and provide survival benefits to patients with HCC. Liver biopsy coupled to histopathology remains the “gold standard”. Visual inspection of biopsy images is a crucial examination to identify tissue and cellular alterations related to HCC, but it is limited by long timelines and by the variability in interpretation. Therefore, recent advances in digital microscopy and automatic image analysis have been developed for HCC classification, thus facilitating the final diagnosis.

Attention augmented distance regression and classification network for nuclei instance segmentation and type classification in histology images

Nuclei instance segmentation and classification in histology plays a major role in routine pathology image examination, which enable morphological features analysis that further facilitates streamlined diagnosis and prognosis quantification. However, the nuclei in the tissue images obtained from different human organs are characterized with high variability in shape, size, morphology and spatial arrangements. Moreover, during digitization of tissue slide, the image quality is degraded because of added artifacts, poor contrast, blurred regions due to failed auto-focus and inconsistent staining procedure. Owing to these challenges, it is difficult to build a generalized feature representation that can achieve precise segmentation and classification of nuclei instances in complex tumor micro-environment of tissue specimens obtained from various organs. To address these problems, we propose a novel deep learning model, that harnesses horizontal and vertical distance information hidden among the nuclei instances to successfully delineate the challenging nuclei. Our proposed methodology uses soft attention mechanism to generate relevant feature activation and prune irrelevant and noisy information. These attention units produce more precise and refined feature maps resulting in finer instances segmentation and accurate classification in the overlapping nuclei, the nuclei with touching boundaries and reduction in false positives. We train our model on publicly available data-sets (Kumar, CoNSep, CPM-17 and a new data-set PanNuke). Our methodology shows superior performance in nuclei classification and segmentation in comparison with recently published methods. The code and the obtained results have been made public at the following link: http://t.ly/eGkV.

Intermediate-mass black holes and the Fundamental Plane of black hole accretion

ABSTRACT We present new 5 GHz Very Large Array observations of a sample of eight active intermediate-mass black holes with masses 104.9 M⊙ < M < 106.1 M⊙ found in galaxies with stellar masses M* < 3 × 109 M⊙. We detected five of the eight sources at high significance. Of the detections, four were consistent with a point source, and one (SDSS J095418.15+471725.1, with black hole mass M < 105 M⊙) clearly shows extended emission that has a jet morphology. Combining our new radio data with the black hole masses and literature X-ray measurements, we put the sources on the Fundamental Plane of black hole accretion. We find that the extent to which the sources agree with the Fundamental Plane depends on their star-forming/composite/active galactic nucleus (AGN) classification based on optical narrow emission-line ratios. The single star-forming source is inconsistent with the Fundamental Plane. The three composite sources are consistent, and three of the four AGN sources are inconsistent with the Fundamental Plane. We argue that this inconsistency is genuine and not a result of misattributing star formation to black hole activity. Instead, we identify the sources in our sample that have AGN-like optical emission-line ratios as not following the Fundamental Plane and thus caution the use of the Fundamental Plane to estimate masses without additional constraints, such as radio spectral index, radiative efficiency, or the Eddington fraction.

Detecting and Classifying Nuclei Using Multi-Scale Fully Convolutional Network.

The detection and classification of nuclei play an important role in the histopathological analysis. It aims to find out the distribution of nuclei in the histopathology images for the next step of analysis and research. However, it is very challenging to detect and localize nuclei in histopathology images because the size of nuclei accounts for only a few pixels in images, making it difficult to be detected. Most automatic detection machine learning algorithms use patches, which are small pieces of images including a single cell, as training data, and then apply a sliding window strategy to detect nuclei on histopathology images. These methods require preprocessing of data set, which is a very tedious work, and it is also difficult to localize the detected results on original images. Fully convolutional network-based deep learning methods are able to take images as raw inputs, and output results of corresponding size, which makes it well suited for nuclei detection and classification task. In this study, we propose a novel multi-scale fully convolution network, named Cell Fully Convolutional Network (CFCN), with dilated convolution for fine-grained nuclei classification and localization in histology images. We trained CFCN in a typical histology image data set, and the experimental results show that CFCN outperforms the other state-of-the-art nuclei classification models, and the F1 score reaches 0.750.

Nucleus classification in histology images using message passing network.

Identification of nuclear components in the histology landscape is an important step towards developing computational pathology tools for the profiling of tumor micro-environment. Most existing methods for the identification of such components are limited in scope due to heterogeneous nature of the nuclei. Graph-based methods offer a natural way to formulate the nucleus classification problem to incorporate both appearance and geometric locations of the nuclei. The main challenge is to define models that can handle such an unstructured domain. Current approaches focus on learning better features and then employ well-known classifiers for identifying distinct nuclear phenotypes. In contrast, we propose a message passing network that is a fully learnable framework build on classical network flow formulation. Based on physical interaction of the nuclei, a nearest neighbor graph is constructed such that the nodes represent the nuclei centroids. For each edge and node, appearance and geometric features are computed which are then used for the construction of messages utilized for diffusing contextual information to the neighboring nodes. Such an algorithm can infer global information over an entire network and predict biologically meaningful nuclear communities. We show that learning such communities improves the performance of nucleus classification task in histology images. The proposed algorithm can be used as a component in existing state-of-the-art methods resulting in improved nucleus classification performance across four different publicly available datasets.

SONNET: A Self-Guided Ordinal Regression Neural Network for Segmentation and Classification of Nuclei in Large-Scale Multi-Tissue Histology Images.

Automated nuclei segmentation and classification are the keys to analyze and understand the cellular characteristics and functionality, supporting computer-aided digital pathology in disease diagnosis. However, the task still remains challenging due to the intrinsic variations in size, intensity, and morphology of different types of nuclei. Herein, we propose a self-guided ordinal regression neural network for simultaneous nuclear segmentation and classification that can exploit the intrinsic characteristics of nuclei and focus on highly uncertain areas during training. The proposed network formulates nuclei segmentation as an ordinal regression learning by introducing a distance decreasing discretization strategy, which stratifies nuclei in a way that inner regions forming a regular shape of nuclei are separated from outer regions forming an irregular shape. It also adopts a self-guided training strategy to adaptively adjust the weights associated with nuclear pixels, depending on the difficulty of the pixels that is assessed by the network itself. To evaluate the performance of the proposed network, we employ large-scale multi-tissue datasets with 276349 exhaustively annotated nuclei. We show that the proposed network achieves the state-of-the-art performance in both nuclei segmentation and classification in comparison to several methods that are recently developed for segmentation and/or classification.

A Pragmatic Machine Learning Approach to Quantify Tumor-Infiltrating Lymphocytes in Whole Slide Images.

Simple SummaryTumor tissues sampled from patients contain prognostic and predictive information beyond what is currently being used in clinical practice. Large-scale digitization enables new ways of exploiting this information. The most promising analysis pipelines include deep learning/artificial intelligence (AI). However, to ensure success, AI often requires a time-consuming curation of data. In our approach, we repurposed AI pipelines and training data for cell segmentation and classification to identify tissue-infiltrating lymphocytes (TILs) in lung cancer tissue. We showed that our approach is able to identify TILs and provide prognostic information in an unseen dataset from lung cancer patients. Our methods can be adapted in myriad ways and may help pave the way for the large-scale deployment of digital pathology.Increased levels of tumor-infiltrating lymphocytes (TILs) indicate favorable outcomes in many types of cancer. The manual quantification of immune cells is inaccurate and time-consuming for pathologists. Our aim is to leverage a computational solution to automatically quantify TILs in standard diagnostic hematoxylin and eosin-stained sections (H&E slides) from lung cancer patients. Our approach is to transfer an open-source machine learning method for the segmentation and classification of nuclei in H&E slides trained on public data to TIL quantification without manual labeling of the data. Our results show that the resulting TIL quantification correlates to the patient prognosis and compares favorably to the current state-of-the-art method for immune cell detection in non-small cell lung cancer (current standard CD8 cells in DAB-stained TMAs HR 0.34, 95% CI 0.17–0.68 vs. TILs in HE WSIs: HoVer-Net PanNuke Aug Model HR 0.30, 95% CI 0.15–0.60 and HoVer-Net MoNuSAC Aug model HR 0.27, 95% CI 0.14–0.53). Our approach bridges the gap between machine learning research, translational clinical research and clinical implementation. However, further validation is warranted before implementation in a clinical setting.

Abstract 464: AI-powered segmentation and analysis of nuclei morphology predicts genomic and clinical markers in multiple cancer types

Abstract Morphological features of cancer cell nuclei are linked to gene expression signatures and genomic alterations. In addition, pathologists have leveraged nuclear morphology as diagnostic and prognostic markers. To enable the use of nuclear morphology in digital pathology, we developed a pan-tissue, deep-learning-based digital pathology pipeline for exhaustive nucleus detection, instance segmentation, and classification. We collected > 29,000 manual nucleus annotations from hematoxylin and eosin (H&E)-stained pathology images from 21 tumor types at 40x and 20x magnification from The Cancer Genome Atlas (TCGA) project, as well as a proprietary set of H&E-stained tissue biopsies of skin, liver non-alcoholic steatohepatitis (NASH), colon inflammatory bowel disease (IBD), and kidney lupus. Annotations were used to train an object detection and segmentation model for identifying nuclei. Application of the model to held-out test data, including held-out tissue types, demonstrated performance comparable to state-of-the-art models described in the literature (mean Dice score = 0.80, aggregated Jaccard index = 0.60). We deployed our model to segment nuclei in H&E slides from the breast cancer (BRCA, N = 941) and prostate adenocarcinoma (PRAD, N = 457) TCGA cohorts. We extracted interpretable features describing the shape (circularity, eccentricity), size, staining intensity (mean and standard deviation), and texture of each nucleus. Nuclei were assigned as cancer or other cell types using separately trained convolutional neural networks for BRCA and PRAD. We used the mean and standard deviation of each feature sampled from a random subset of cancer nuclei to summarize the nuclear morphology on each slide (mean (range) = 10,068 (5,981-10,452) cancer cells from each BRCA slide; mean (range) = 10,053 (5,029-10,495) cancer cells from each PRAD slide). We used nuclear features to construct random forest classification models for predicting markers of genomic instability and prognosis: whole-genome doubling (WGD) and homologous recombination deficiency (HRD) status separately in BRCA and PRAD, HER2 subtype in BRCA, and Gleason grade in PRAD. Nuclear features were predictive of WGD (area under the receiver operating characteristic curve (AUROC) = 0.78 BRCA, = 0.69 PRAD) and binarized HRD status (AUROC = 0.65 BRCA, = 0.68 PRAD) on held-out test sets. Nuclear features were predictive of HER2-enriched breast cancer vs. other molecular subtypes (AUROC = 0.72), and distinguished between low risk (6) and moderate/high risk (7-10) Gleason grade in PRAD (AUROC = 0.72). In summary, we present a powerful pan-tissue approach for nucleus segmentation and featurization, which enables the construction of predictive models and the identification of features linking nuclear morphology with clinically-relevant prognostic biomarkers across multiple cancer types. Citation Format: John Abel, Suyog Jain, Deepta Rajan, Ken Leidal, Harshith Padigela, Aaditya Prakash, Jake Conway, Michael Nercessian, Christian Kirkup, Robert Egger, Ben Trotter, Andrew Beck, Ilan Wapinski, Michael G. Drage, Limin Yu, Amaro Taylor-Weiner. AI-powered segmentation and analysis of nuclei morphology predicts genomic and clinical markers in multiple cancer types [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 464.

NuCLS: A scalable crowdsourcing approach and dataset for nucleus classification and segmentation in breast cancer.

BackgroundDeep learning enables accurate high-resolution mapping of cells and tissue structures that can serve as the foundation of interpretable machine-learning models for computational pathology. However, generating adequate labels for these structures is a critical barrier, given the time and effort required from pathologists.ResultsThis article describes a novel collaborative framework for engaging crowds of medical students and pathologists to produce quality labels for cell nuclei. We used this approach to produce the NuCLS dataset, containing >220,000 annotations of cell nuclei in breast cancers. This builds on prior work labeling tissue regions to produce an integrated tissue region- and cell-level annotation dataset for training that is the largest such resource for multi-scale analysis of breast cancer histology. This article presents data and analysis results for single and multi-rater annotations from both non-experts and pathologists. We present a novel workflow that uses algorithmic suggestions to collect accurate segmentation data without the need for laborious manual tracing of nuclei. Our results indicate that even noisy algorithmic suggestions do not adversely affect pathologist accuracy and can help non-experts improve annotation quality. We also present a new approach for inferring truth from multiple raters and show that non-experts can produce accurate annotations for visually distinctive classes.ConclusionsThis study is the most extensive systematic exploration of the large-scale use of wisdom-of-the-crowd approaches to generate data for computational pathology applications.

RESOLVE and ECO: Finding Low-metallicity z ∼ 0 Dwarf AGN Candidates Using Optimized Emission-line Diagnostics

Existing star-forming vs. active galactic nucleus (AGN) classification schemes using optical emission-line diagnostics mostly fail for low-metallicity and/or highly star-forming galaxies, missing AGN in typical z ∼ 0 dwarfs. To recover AGN in dwarfs with strong emission lines (SELs), we present a classification scheme optimizing the use of existing optical diagnostics. We use Sloan Digital Sky Survey emission-line catalogs overlapping the volume- and mass-limited REsolved Spectroscopy Of a Local VolumE (RESOLVE) and Environmental COntex (ECO) surveys to determine the AGN percentage in SEL dwarfs. Our photoionization grids show that the [O iii]/Hβ versus [S ii]/Hα diagram (S ii plot) and [O iii]/Hβ versus [O i]/Hα diagram (O i plot) are less metallicity sensitive and more successful in identifying dwarf AGN than the popular [O iii]/Hβ versus [N ii]/Hα diagnostic (N ii plot or “BPT diagram”). We identify a new category of “star-forming AGN” (SF-AGN) classified as star-forming by the N ii plot but as AGN by the S ii and/or O i plots. Including SF-AGN, we find the z ∼ 0 AGN percentage in dwarfs with SELs to be ∼3%–16%, far exceeding most previous optical estimates (∼1%). The large range in our dwarf AGN percentage reflects differences in spectral fitting methodologies between catalogs. The highly complete nature of RESOLVE and ECO allows us to normalize strong emission-line galaxy statistics to the full galaxy population, reducing the dwarf AGN percentage to ∼0.6%–3.0%. The newly identified SF-AGN are mostly gas-rich dwarfs with halo mass <1011.5 M ⊙, where highly efficient cosmic gas accretion is expected. Almost all SF-AGN also have low metallicities (Z ≲ 0.4 Z ⊙), demonstrating the advantage of our method.

Automatic detection of head and neck squamous cell carcinoma on histologic slides using hyperspectral microscopic imaging.

.SignificanceAutomatic, fast, and accurate identification of cancer on histologic slides has many applications in oncologic pathology.AimThe purpose of this study is to investigate hyperspectral imaging (HSI) for automatic detection of head and neck cancer nuclei in histologic slides, as well as cancer region identification based on nuclei detection.ApproachA customized hyperspectral microscopic imaging system was developed and used to scan histologic slides from 20 patients with squamous cell carcinoma (SCC). Hyperspectral images and red, green, and blue (RGB) images of the histologic slides with the same field of view were obtained and registered. A principal component analysis-based nuclei segmentation method was developed to extract nuclei patches from the hyperspectral images and the coregistered RGB images. Spectra-based support vector machine and patch-based convolutional neural networks (CNNs) were implemented for nuclei classification. The CNNs were trained with RGB patches (RGB-CNN) and hyperspectral patches (HSI-CNN) of the segmented nuclei and the utility of the extra spectral information provided by HSI was evaluated. Furthermore, cancer region identification was implemented by image-wise classification based on the percentage of cancerous nuclei detected in each image.ResultsRGB-CNN, which mainly used the spatial information of nuclei, resulted in a 0.81 validation accuracy and 0.74 testing accuracy. HSI-CNN, which utilized the spatial and spectral features of the nuclei, showed significant improvement in classification performance and achieved 0.89 validation accuracy as well as 0.82 testing accuracy. Furthermore, the image-wise cancer region identification based on nuclei detection could generally improve the cancer detection rate.ConclusionsWe demonstrated that the morphological and spectral information contribute to SCC nuclei differentiation and that the spectral information within hyperspectral images could improve classification performance.