Image-Omics The Yuan Lab Publications Team Projects Contact

Narayanan P, et al. BioRxiv

Publications


TTG
TTG

Topological Tumor Graphs: a graph-based spatial model to infer stromal recruitment for immunosuppression in melanoma histology

Failmezger H^, Muralidhar S^, Rullan A, de Andrea CE, Sahai E, Yuan Y
Cancer Research (2019)

A graph-based algorithm is developed to study the immunosuppressive role of stromal cells via physical barrier and T cell exclusion within the vicinity of melanoma cells. Detailed tissue architectural information is integrated with copy number and transcriptomic data compressed using deep learning, to reveal potentially dysregulated molecular pathways.

Spatial niche
Spatial niche

Microenvironmental niche divergence shapes BRCA1-dysregulated ovarian cancer morphological plasticity

Heindl A, Khan AM, Rodrigues DN, Eason K, Sadanandam A, Orbegoso C, Punta M, Sottoriva A, Lise S, Banerjee S, Yuan Y
Nature Communications (2018) [Online Sweave]

We provide empirical evidence supporting the selective advantage of cancer cell subpopulation with morphological diversification in locally immunosuppressive microenvironment. Morphological diversification of cancer cells may be an important adaptation strategy with profound clinical implications.

Hybrid network
Hybrid network

Microtubule-mediated nuclear deformation drives the Epithelial-to-Mesenchymal Transition and breast cancer

Arias Garcia M, Rickman R, Sero J, Yuan Y, Chris Bakal
BioRxiv

Using an image-omic approach we identify Junctional Adhesion Molecule 3 (JAM3) as a regulator of cell nucleus shape in breast cancer. In vitro experiments validated that engagement of EMT following JAM3 depletion is due to changes in nuclear shape caused by microtubules. These results provide a mechanistic basis for the long-standing observations of how loss of cell-cell adhesion leads to EMT and cancer.

Ecoscore
Ecoscore

Analysis of tumor ecological balance reveals resource-dependent adaptive strategies of ovarian cancer

Nawaz S, Trahearn N, Heindl A, Banerjee S, Maley C, Sottoriva A, Yuan Y
EBioMedicine (2019)

We define EcoScore, a spatial measure of the ecological balance of stromal resource and immune hazard, to provide prognostic value stronger than, and independent of, known risk factors. Our study presents a biological basis for developing better assessments of tumor adaptive strategies in overcoming ecological constraints including immune surveillance and hypoxia.

SuperCRF
SuperCRF

Superpixel-Based Conditional Random Fields (SuperCRF): Incorporating Global and Local Context for Enhanced Deep Learning in Melanoma Histopathology

Zormpas-Petridis K, Failmezger H, Raza SEA, Roxanis I., Jamin Y, Yuan Y
Frontiers in Oncology (2019)

SuperCRF improves cell classification by introducing global and local context-based information much like pathologists do. Improvement in cell classification accuracy led to the identification of predictors of survival in melanoma patients from conventional H&E stained histopathology.

ConcordeNet
ConcordeNet

ConCORDe-Net: Cell Count Regularized Convolutional Neural Network for Cell Detection in Multiplex Immunohistochemistry Images

Hagos YB, Narayanan P, Akarca AU, Marafioti T, Yuan Y MICCAI (2019)

To detect single cells in multiplex immunohistochemistry Images, we developed Cell COunt RegularizeD Convolutional neural Network (ConCORDe-Net). ConCORDe-Net excels at differentiating closely located and weakly stained cells from background artefacts by incorporating a new cell count loss function to learn weak gradient boundaries.

DCIS ecology
DCIS ecology

Unmasking the tissue microecology of ductal carcinoma in situ with deep learning

Narayanan P, Raza SEA, Hall AH, Marks JM, King L, Hernandez, L, Dowsett M, Gusterson B, Carlo Maley, Hwang ES, Yuan Y ,
BioRxiv

Automated identification and segmentation of DCIS components have been challenging due to their high morphological diversity, and we developed a deep learning approach to accomplish these tasks. Our results show significantly more inflamed tissue ecology local to DCIS in invasive breast cancers compared with pure DCIS disease.

Immune Hotspots
Immune Hotspots

Relevance of spatial heterogeneity of immune infiltration for predicting risk of recurrence after endocrine therapy of ER+ breast cancer.

Heindl A, Sestak I, Naidoo R, Cuzick J, Dowsett M, Yuan Y
JNCI (2018) [Additional ppt]

We provide a missing link between inflammation and ER+ breast cancer outcome by examining tumour spatial architecture. The association between immune spatial scores and late recurrence suggests a lasting memory of protumour immunity that may impact disease progression and evolution of endocrine treatment resistance.

Ecological Diversity Index
Ecological diversity

Microenvironmental heterogeneity parallels breast cancer progression: A histology-genomics integration analysis

Natrajan R, Sailem H, Mardakheh FM, Arias MG, Dowsett M, Bakal C, Yuan Y
PLOS Medicine (2016) [Sweave; R package]

We propose a clinically relevant role of tumour microenvironmental diversity for advanced breast tumors and highlight that ecological statistics can be translated into medical advances for identifying new biomarkers and for understanding the synergistic interplay between the microenvironment and cancer genomics.

MapDe

Deconvolving convolutional neural network for cell detection

Raza SEA, AbdulJabbar K, Jamal-Hanjani M, Veeriah S, Le Quesne J, Swanton C, Yuan Y
ISBI (2019)

Conventional deep learning methods can be sensitive to broken chromatin architecture in tumour cells leading to over-detection of cells, and we overcome this challenge by designing a new deep learning algorithm with a mapping filter to generate better probability maps of cell centroids. A convolutional neural network (CNN) is modified to convolve it's output with the same mapping filter and is trained for the mapped labels.

DeepSDCS

DeepSDCS: Dissecting cancer proliferation heterogeneity in Ki67 digital whole slide images

Narayanan, P, Dodson A, Gusterson B, Dowsett M, Yuan Y
Medical Imaging with Deep Learning (2018)

Simultaneous Detection and Cell Segmentation (DeepSDCS) performs automated cell segmentation and detection in Ki67-stained immunohistochemistry images. The proposed network combines VGG16 with hypercolumn descriptors to form the vector of activation from specific layers to capture features at different granularity.

biopsy

Biopsy variability of lymphocytic infiltration in breast cancer subtypes and the ImmunoSkew score

Khan AM, Yuan Y*
Scientific Reports (2016)

Spatial heterogeneity in the immune microenvironment can skew immune scoring in biopsy samples. We systematically investigate biopsy variability for the lymphocytic infiltrate in 998 breast tumours using a novel virtual biopsy method. Biopsy variability of lymphocytic infiltrate differs considerably across breast cancer subtypes, with the HER2+ subtype having the highest variability.

Immune Scoring


Immune Hotspots
Hotspots

Beyond immune density: critical role of spatial heterogeneity in estrogen receptor-negative breast cancer

Nawaz S, Heindl A, Koelble K, Yuan Y
Modern Pathology (2015) [Sweave; data]

Using a statistical method widely applied in crime mapping, we quantify spatial clustering of cancer and immune cells in breast tumours. Unexpectedly high levels of immune-cancer co-clustering is indicative of favourable long-term prognosis in ER- breast cancer, an aggressive cancer type.

Colocalization
Colocalization

An ecological measure of immune-cancer colocalization as a prognostic factor for breast cancer

Maley CC, Koelble K, Natrajan R, Aktipis A, Yuan Y
Breast Cancer Research (2015) [Sweave; data]

Ecological methods applied for the study predator-prey relationship are here used to quantify spatial colocalization of cancer and immune cells in routine histology samples. Through this application, new reproducible, quantitative measures can be found for identifying high-risk breast cancer patients.

ITLR
ITLR

Modelling the spatial heterogeneity and molecular correlates of lymphocytic infiltration in triple-negative breast cancer

Yuan Y
Royal Society Interface (2015) [Sweave; data and functions]

This paper reports the first fully automated, computer-assisted method for scoring intratumour lymphocytes in breast cancer samples with the fusion of high-throughput image processing and robust statistical analysis.

Invited Reviews


Laboratory Investigation
Ecoscore

Mapping spatial heterogeneity in the tumor microenvironment: a new era for digital pathology

Heindl A, Nawaz S, Yuan Y
Laboratory Investigation (2015)

We review existing methods for analysing spatial heterogeneity in the tumour microenvironment and how they may be integrated with molecular profiling to help further our understanding of the complex relationship between cancer cells and the surrounding healthy tissue that can play a pivotal role in tumour progression.

Cancer Letters

Computational pathology: Exploring the spatial dimension of tumor ecology

Nawaz S, Yuan Y
Cancer Letters (2015)

Cancer and normal cells exhibit both co-operative and competitive relationships, analogous to living organisms. Considering the tumour as an ecological habitat of cancer cells, we discuss applications of ecological statistics to tumour histology data. This novel way of studying the microenvironment can expand our knowledge of cancer and reveal new clinical prognosticators.

Cold Spring Harbor Perspectives in Medicine

Spatial Heterogeneity in the Tumor Microenvironment

Yuan Y
Cold Spring Harb Perspect Med. (2016) [Limited reprints]

There is a desperate need to understand influence of the tumor microenvironment on cancer development and evolution. Applying principles and quantitative methods from ecology can suggest novel solutions to fulfil this need. We discuss spatial heterogeneity as a fundamental biological feature of the microenvironment.

Copyright © Yinyin Yuan's Lab, the Institute of Cancer Research, London. All Rights Reserved.