Browsing by Author "Han, Zhi"

Now showing 1 - 10 of 19
  • Thumbnail Image
    Item
    Application of unsupervised deep learning algorithms for identification of specific clusters of chronic cough patients from EMR data
    (BMC, 2022-04-19) Shao, Wei; Luo, Xiao; Zhang, Zuoyi; Han, Zhi; Chandrasekaran, Vasu; Turzhitsky, Vladimir; Bali, Vishal; Roberts, Anna R.; Metzger, Megan; Baker, Jarod; La Rosa, Carmen; Weaver, Jessica; Dexter, Paul; Huang, Kun; Biostatistics and Health Data Science, School of Medicine
    Background: Chronic cough affects approximately 10% of adults. The lack of ICD codes for chronic cough makes it challenging to apply supervised learning methods to predict the characteristics of chronic cough patients, thereby requiring the identification of chronic cough patients by other mechanisms. We developed a deep clustering algorithm with auto-encoder embedding (DCAE) to identify clusters of chronic cough patients based on data from a large cohort of 264,146 patients from the Electronic Medical Records (EMR) system. We constructed features using the diagnosis within the EMR, then built a clustering-oriented loss function directly on embedded features of the deep autoencoder to jointly perform feature refinement and cluster assignment. Lastly, we performed statistical analysis on the identified clusters to characterize the chronic cough patients compared to the non-chronic cough patients. Results: The experimental results show that the DCAE model generated three chronic cough clusters and one non-chronic cough patient cluster. We found various diagnoses, medications, and lab tests highly associated with chronic cough patients by comparing the chronic cough cluster with the non-chronic cough cluster. Comparison of chronic cough clusters demonstrated that certain combinations of medications and diagnoses characterize some chronic cough clusters. Conclusions: To the best of our knowledge, this study is the first to test the potential of unsupervised deep learning methods for chronic cough investigation, which also shows a great advantage over existing algorithms for patient data clustering.
  • Thumbnail Image
    Item
    Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images
    (Springer Nature, 2023-01-27) Huang, Zhi; Shao, Wei; Han, Zhi; Alkashash, Ahmad Mahmoud; De la Sancha, Carlo; Parwani, Anil V.; Nitta, Hiroaki; Hou, Yanjun; Wang, Tongxin; Salama, Paul; Rizkalla, Maher; Zhang, Jie; Huang, Kun; Li, Zaibo; Electrical and Computer Engineering, School of Engineering and Technology
    Advances in computational algorithms and tools have made the prediction of cancer patient outcomes using computational pathology feasible. However, predicting clinical outcomes from pre-treatment histopathologic images remains a challenging task, limited by the poor understanding of tumor immune micro-environments. In this study, an automatic, accurate, comprehensive, interpretable, and reproducible whole slide image (WSI) feature extraction pipeline known as, IMage-based Pathological REgistration and Segmentation Statistics (IMPRESS), is described. We used both H&E and multiplex IHC (PD-L1, CD8+, and CD163+) images, investigated whether artificial intelligence (AI)-based algorithms using automatic feature extraction methods can predict neoadjuvant chemotherapy (NAC) outcomes in HER2-positive (HER2+) and triple-negative breast cancer (TNBC) patients. Features are derived from tumor immune micro-environment and clinical data and used to train machine learning models to accurately predict the response to NAC in breast cancer patients (HER2+ AUC = 0.8975; TNBC AUC = 0.7674). The results demonstrate that this method outperforms the results trained from features that were manually generated by pathologists. The developed image features and algorithms were further externally validated by independent cohorts, yielding encouraging results, especially for the HER2+ subtype.
  • Thumbnail Image
    Item
    Balanced Activity between Kv3 and Nav Channels Determines Fast-Spiking in Mammalian Central Neurons
    (Elsevier, 2018-11-30) Gu, Yuanzheng; Servello, Dustin; Han, Zhi; Lalchandani, Rupa R.; Ding, Jun B.; Huang, Kun; Gu, Chen; Medicine, School of Medicine
    Fast-spiking (FS) neurons can fire action potentials (APs) up to 1,000 Hz and play key roles in vital functions such as sound location, motor coordination, and cognition. Here we report that the concerted actions of Kv3 voltage-gated K+ (Kv) and Na+ (Nav) channels are sufficient and necessary for inducing and maintaining FS. Voltage-clamp analysis revealed a robust correlation between the Kv3/Nav current ratio and FS. Expressing Kv3 channels alone could convert ∼30%-60% slow-spiking (SS) neurons to FS in culture. In contrast, co-expression of either Nav1.2 or Nav1.6 together with Kv3.1 or Kv3.3, but not alone or with Kv1.2, converted SS to FS with 100% efficiency. Furthermore, RNA-sequencing-based genome-wide analysis revealed that the Kv3/Nav ratio and Kv3 expression levels strongly correlated with the maximal AP frequencies. Therefore, FS is established by the properly balanced activities of Kv3 and Nav channels and could be further fine-tuned by channel biophysical features and localization patterns.
  • Thumbnail Image
    Item
    BrcaSeg: A Deep Learning Approach for Tissue Quantification and Genomic Correlations of Histopathological Images
    (Elsevier, 2021) Lu, Zixiao; Zhan, Xiaohui; Wu, Yi; Cheng, Jun; Shao, Wei; Ni, Dong; Han, Zhi; Zhang, Jie; Feng, Qianjin; Huang, Kun; Medicine, School of Medicine
    Epithelial and stromal tissues are components of the tumor microenvironment and play a major role in tumor initiation and progression. Distinguishing stroma from epithelial tissues is critically important for spatial characterization of the tumor microenvironment. Here, we propose BrcaSeg, an image analysis pipeline based on a convolutional neural network (CNN) model to classify epithelial and stromal regions in whole-slide hematoxylin and eosin (H&E) stained histopathological images. The CNN model is trained using well-annotated breast cancer tissue microarrays and validated with images from The Cancer Genome Atlas (TCGA) Program. BrcaSeg achieves a classification accuracy of 91.02%, which outperforms other state-of-the-art methods. Using this model, we generate pixel-level epithelial/stromal tissue maps for 1000 TCGA breast cancer slide images that are paired with gene expression data. We subsequently estimate the epithelial and stromal ratios and perform correlation analysis to model the relationship between gene expression and tissue ratios. Gene Ontology (GO) enrichment analyses of genes that are highly correlated with tissue ratios suggest that the same tissue is associated with similar biological processes in different breast cancer subtypes, whereas each subtype also has its own idiosyncratic biological processes governing the development of these tissues. Taken all together, our approach can lead to new insights in exploring relationships between image-based phenotypes and their underlying genomic events and biological processes for all types of solid tumors. BrcaSeg can be accessed at https://github.com/Serian1992/ImgBio.
  • Thumbnail Image
    Item
    Computational analysis of pathological images enables a better diagnosis of TFE3 Xp11.2 translocation renal cell carcinoma
    (Nature Research, 2020) Cheng, Jun; Han, Zhi; Mehra, Rohit; Shao, Wei; Cheng, Michael; Feng, Qianjin; Ni, Dong; Huang, Kun; Cheng, Liang; Zhang, Jie; Medicine, School of Medicine
    TFE3 Xp11.2 translocation renal cell carcinoma (TFE3-RCC) generally progresses more aggressively compared with other RCC subtypes, but it is challenging to diagnose TFE3-RCC by traditional visual inspection of pathological images. In this study, we collect hematoxylin and eosin- stained histopathology whole-slide images of 74 TFE3-RCC cases (the largest cohort to date) and 74 clear cell RCC cases (ccRCC, the most common RCC subtype) with matched gender and tumor grade. An automatic computational pipeline is implemented to extract image features. Comparative study identifies 52 image features with significant differences between TFE3-RCC and ccRCC. Machine learning models are built to distinguish TFE3-RCC from ccRCC. Tests of the classification models on an external validation set reveal high accuracy with areas under ROC curve ranging from 0.842 to 0.894. Our results suggest that automatically derived image features can capture subtle morphological differences between TFE3-RCC and ccRCC and contribute to a potential guideline for TFE3-RCC diagnosis.
  • Thumbnail Image
    Item
    Computational Image Analysis Identifies Histopathological Image Features Associated With Somatic Mutations and Patient Survival in Gastric Adenocarcinoma
    (Frontiers Media, 2021-03-31) Cheng, Jun; Liu, Yuting; Huang, Wei; Hong, Wenhui; Wang, Lingling; Zhan, Xiaohui; Han, Zhi; Ni, Dong; Huang, Kun; Zhang, Jie; Medicine, School of Medicine
    Computational analysis of histopathological images can identify sub-visual objective image features that may not be visually distinguishable by human eyes, and hence provides better modeling of disease phenotypes. This study aims to investigate whether specific image features are associated with somatic mutations and patient survival in gastric adenocarcinoma (sample size = 310). An automated image analysis pipeline was developed to extract quantitative morphological features from H&E stained whole-slide images. We found that four frequently somatically mutated genes (TP53, ARID1A, OBSCN, and PIK3CA) were significantly associated with tumor morphological changes. A prognostic model built on the image features significantly stratified patients into low-risk and high-risk groups (log-rank test p-value = 2.6e-4). Multivariable Cox regression showed the model predicted risk index was an additional prognostic factor besides tumor grade and stage. Gene ontology enrichment analysis showed that the genes whose expressions mostly correlated with the contributing features in the prognostic model were enriched on biological processes such as cell cycle and muscle contraction. These results demonstrate that histopathological image features can reflect underlying somatic mutations and identify high-risk patients that may benefit from more precise treatment regimens. Both the image features and pipeline are highly interpretable to enable translational applications.
  • Thumbnail Image
    Item
    Condition-specific gene co-expression network mining identifies key pathways and regulators in the brain tissue of Alzheimer's disease patients
    (Biomed Central, 2018-12-31) Xiang, Shunian; Huang, Zhi; Wang, Tianfu; Han, Zhi; Yu, Christina Y.; Ni, Dong; Huang, Kun; Zhang, Jie; Medicine, School of Medicine
    BACKGROUND: Gene co-expression network (GCN) mining is a systematic approach to efficiently identify novel disease pathways, predict novel gene functions and search for potential disease biomarkers. However, few studies have systematically identified GCNs in multiple brain transcriptomic data of Alzheimer's disease (AD) patients and looked for their specific functions. METHODS: In this study, we first mined GCN modules from AD and normal brain samples in multiple datasets respectively; then identified gene modules that are specific to AD or normal samples; lastly, condition-specific modules with similar functional enrichments were merged and enriched differentially expressed upstream transcription factors were further examined for the AD/normal-specific modules. RESULTS: We obtained 30 AD-specific modules which showed gain of correlation in AD samples and 31 normal-specific modules with loss of correlation in AD samples compared to normal ones, using the network mining tool lmQCM. Functional and pathway enrichment analysis not only confirmed known gene functional categories related to AD, but also identified novel regulatory factors and pathways. Remarkably, pathway analysis suggested that a variety of viral, bacteria, and parasitic infection pathways are activated in AD samples. Furthermore, upstream transcription factor analysis identified differentially expressed upstream regulators such as ZFHX3 for several modules, which can be potential driver genes for AD etiology and pathology. CONCLUSIONS: Through our state-of-the-art network-based approach, AD/normal-specific GCN modules were identified using multiple transcriptomic datasets from multiple regions of the brain. Bacterial and viral infectious disease related pathways are the most frequently enriched in modules across datasets. Transcription factor ZFHX3 was identified as a potential driver regulator targeting the infectious diseases pathways in AD-specific modules. Our results provided new direction to the mechanism of AD as well as new candidates for drug targets.
  • Thumbnail Image
    Item
    Correlation Analysis of Histopathology and Proteogenomics Data for Breast Cancer
    (American Society for Biochemistry and Molecular Biology, 2019-08-09) Zhan, Xiaohui; Cheng, Jun; Huang, Zhi; Han, Zhi; Helm, Bryan; Liu, Xiaowen; Zhang, Jie; Wang, Tian-Fu; Ni, Dong; Huang, Kun; Medicine, School of Medicine
    Tumors are heterogeneous tissues with different types of cells such as cancer cells, fibroblasts, and lymphocytes. Although the morphological features of tumors are critical for cancer diagnosis and prognosis, the underlying molecular events and genes for tumor morphology are far from being clear. With the advancement in computational pathology and accumulation of large amount of cancer samples with matched molecular and histopathology data, researchers can carry out integrative analysis to investigate this issue. In this study, we systematically examine the relationships between morphological features and various molecular data in breast cancers. Specifically, we identified 73 breast cancer patients from the TCGA and CPTAC projects matched whole slide images, RNA-seq, and proteomic data. By calculating 100 different morphological features and correlating them with the transcriptomic and proteomic data, we inferred four major biological processes associated with various interpretable morphological features. These processes include metabolism, cell cycle, immune response, and extracellular matrix development, which are all hallmarks of cancers and the associated morphological features are related to area, density, and shapes of epithelial cells, fibroblasts, and lymphocytes. In addition, protein specific biological processes were inferred solely from proteomic data, suggesting the importance of proteomic data in obtaining a holistic understanding of the molecular basis for tumor tissue morphology. Furthermore, survival analysis yielded specific morphological features related to patient prognosis, which have a strong association with important molecular events based on our analysis. Overall, our study demonstrated the power for integrating multiple types of biological data for cancer samples in generating new hypothesis as well as identifying potential biomarkers predicting patient outcome. Future work includes causal analysis to identify key regulators for cancer tissue development and validating the findings using more independent data sets.
  • Thumbnail Image
    Item
    Deep learning-based cancer survival prognosis from RNA-seq data: approaches and evaluations
    (BMC, 2020) Huang, Zhi; Johnson, Travis S.; Han, Zhi; Helm, Bryan; Cao, Sha; Zhang, Chi; Salama, Paul; Rizkalla, Maher; Yu, Christina Y.; Cheng, Jun; Xiang, Shunian; Zhan, Xiaohui; Zhang, Jie; Huang, Kun; Medicine, School of Medicine
    Background: Recent advances in kernel-based Deep Learning models have introduced a new era in medical research. Originally designed for pattern recognition and image processing, Deep Learning models are now applied to survival prognosis of cancer patients. Specifically, Deep Learning versions of the Cox proportional hazards models are trained with transcriptomic data to predict survival outcomes in cancer patients. Methods: In this study, a broad analysis was performed on TCGA cancers using a variety of Deep Learning-based models, including Cox-nnet, DeepSurv, and a method proposed by our group named AECOX (AutoEncoder with Cox regression network). Concordance index and p-value of the log-rank test are used to evaluate the model performances. Results: All models show competitive results across 12 cancer types. The last hidden layers of the Deep Learning approaches are lower dimensional representations of the input data that can be used for feature reduction and visualization. Furthermore, the prognosis performances reveal a negative correlation between model accuracy, overall survival time statistics, and tumor mutation burden (TMB), suggesting an association among overall survival time, TMB, and prognosis prediction accuracy. Conclusions: Deep Learning based algorithms demonstrate superior performances than traditional machine learning based models. The cancer prognosis results measured in concordance index are indistinguishable across models while are highly variable across cancers. These findings shedding some light into the relationships between patient characteristics and survival learnability on a pan-cancer level.
  • Thumbnail Image
    Item
    Deep-Learning–Based Characterization of Tumor-Infiltrating Lymphocytes in Breast Cancers From Histopathology Images and Multiomics Data
    (American Society of Clinical Oncology, 2020-05) Lu, Zixiao; Xu, Siwen; Shao, Wei; Wu, Yi; Zhang, Jie; Han, Zhi; Feng, Qianjin; Huang, Kun; Medicine, School of Medicine
    Purpose: Tumor-infiltrating lymphocytes (TILs) and their spatial characterizations on whole-slide images (WSIs) of histopathology sections have become crucial in diagnosis, prognosis, and treatment response prediction for different cancers. However, fully automatic assessment of TILs on WSIs currently remains a great challenge because of the heterogeneity and large size of WSIs. We present an automatic pipeline based on a cascade-training U-net to generate high-resolution TIL maps on WSIs. Methods: We present global cell-level TIL maps and 43 quantitative TIL spatial image features for 1,000 WSIs of The Cancer Genome Atlas patients with breast cancer. For more specific analysis, all the patients were divided into three subtypes, namely, estrogen receptor (ER)-positive, ER-negative, and triple-negative groups. The associations between TIL scores and gene expression and somatic mutation were examined separately in three breast cancer subtypes. Both univariate and multivariate survival analyses were performed on 43 TIL image features to examine the prognostic value of TIL spatial patterns in different breast cancer subtypes. Results: The TIL score was in strong association with immune response pathway and genes (eg, programmed death-1 and CLTA4). Different breast cancer subtypes showed TIL score in association with mutations from different genes suggesting that different genetic alterations may lead to similar phenotypes. Spatial TIL features that represent density and distribution of TIL clusters were important indicators of the patient outcomes. Conclusion: Our pipeline can facilitate computational pathology-based discovery in cancer immunology and research on immunotherapy. Our analysis results are available for the research community to generate new hypotheses and insights on breast cancer immunology and development.