Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 65
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
Cancer Res ; 2020 Dec 21.
Artigo em Inglês | MEDLINE | ID: mdl-33355190

RESUMO

Whole-slide histology images contain information that is valuable for clinical and basic science investigations of cancer, but extracting quantitative measurements from these images is challenging for researchers who are not image analysis specialists. In this paper, we describe HistomicsML2, a software tool for learn-by-example training of machine learning classifiers for histologic patterns in whole-slide images. This tool improves training efficiency and classifier performance by guiding users to the most informative training examples for labeling and can be used to develop classifiers for prospective application or as a rapid annotation tool that is adaptable to different cancer types. HistomicsML2 runs as a containerized server application that provides web-based user interfaces for classifier training, validation, exporting inference results, and collaborative review and can be deployed on GPU servers or cloud platforms. We demonstrate the utility of this tool by using it to classify tumor-infiltrating lymphocytes in breast carcinoma and cutaneous melanoma.

2.
A A Pract ; 14(6): e01205, 2020 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-32784327

RESUMO

Emergence delirium is a well-known phenomenon that may be encountered after general anesthesia. A common approach to this issue is to risk stratify patients preoperatively and treat them postoperatively if emergence delirium occurs. We present the case of a patient with Barrett esophagus and a history of severe and refractory emergence delirium, who was successfully treated prophylactically with physostigmine, resulting in decreased risk of harm to the patient, trauma to the perioperative staff, and a safer and more positive recovery.

3.
Acta Neuropathol Commun ; 8(1): 59, 2020 04 28.
Artigo em Inglês | MEDLINE | ID: mdl-32345363

RESUMO

Semi-quantitative scoring schemes like the Consortium to Establish a Registry for Alzheimer's Disease (CERAD) are the most commonly used method in Alzheimer's disease (AD) neuropathology practice. Computational approaches based on machine learning have recently generated quantitative scores for whole slide images (WSIs) that are highly correlated with human derived semi-quantitative scores, such as those of CERAD, for Alzheimer's disease pathology. However, the robustness of such models have yet to be tested in different cohorts. To validate previously published machine learning algorithms using convolutional neural networks (CNNs) and determine if pathological heterogeneity may alter algorithm derived measures, 40 cases from the Goizueta Emory Alzheimer's Disease Center brain bank displaying an array of pathological diagnoses (including AD with and without Lewy body disease (LBD), and / or TDP-43-positive inclusions) and levels of Aß pathologies were evaluated. Furthermore, to provide deeper phenotyping, amyloid burden in gray matter vs whole tissue were compared, and quantitative CNN scores for both correlated significantly to CERAD-like scores. Quantitative scores also show clear stratification based on AD pathologies with or without additional diagnoses (including LBD and TDP-43 inclusions) vs cases with no significant neurodegeneration (control cases) as well as NIA Reagan scoring criteria. Specifically, the concomitant diagnosis group of AD + TDP-43 showed significantly greater CNN-score for cored plaques than the AD group. Finally, we report that whole tissue computational scores correlate better with CERAD-like categories than focusing on computational scores from a field of view with densest pathology, which is the standard of practice in neuropathological assessment per CERAD guidelines. Together these findings validate and expand CNN models to be robust to cohort variations and provide additional proof-of-concept for future studies to incorporate machine learning algorithms into neuropathological practice.

4.
Lab Invest ; 100(1): 98-109, 2020 01.
Artigo em Inglês | MEDLINE | ID: mdl-31570774

RESUMO

Bone marrow aspirate (BMA) differential cell counts (DCCs) are critical for the classification of hematologic disorders. While manual counts are considered the gold standard, they are labor intensive, time consuming, and subject to bias. A reliable automated counter has yet to be developed, largely due to the inherent complexity of bone marrow specimens. Digital pathology imaging coupled with machine learning algorithms represents a highly promising emerging technology for this purpose. Yet, training datasets for BMA cellular constituents, critical for building and validating machine learning algorithms, are lacking. Herein, we report our experience creating and employing such datasets to develop a machine learning algorithm to detect and classify BMA cells. Utilizing a web-based system that we developed for annotating and managing digital pathology images, over 10,000 cells from scanned whole slide images of BMA smears were manually annotated, including all classes that comprise the standard clinical DCC. We implemented a two-stage, detection and classification approach that allows design flexibility and improved classification accuracy. In a sixfold cross-validation, our algorithms achieved high overall accuracy in detection (0.959 ± 0.008 precision-recall AUC) and classification (0.982 ± 0.03 ROC AUC) using nonneoplastic samples. Testing on a small set of acute myeloid leukemia and multiple myeloma samples demonstrated similar detection and classification performance. In summary, our algorithms showed promising early results and represent an important initial step in the effort to devise a reliable, objective method to automate DCCs. With further development to include formal clinical validation, such a system has the potential to assist in disease diagnosis and prognosis, and significantly impact clinical practice.


Assuntos
Células da Medula Óssea , Aprendizado de Máquina , Patologia/métodos , Contagem de Células , Conjuntos de Dados como Assunto , Humanos
5.
J Am Acad Dermatol ; 82(3): 622-627, 2020 Mar.
Artigo em Inglês | MEDLINE | ID: mdl-31306724

RESUMO

BACKGROUND: Computer vision has promise in image-based cutaneous melanoma diagnosis but clinical utility is uncertain. OBJECTIVE: To determine if computer algorithms from an international melanoma detection challenge can improve dermatologists' accuracy in diagnosing melanoma. METHODS: In this cross-sectional study, we used 150 dermoscopy images (50 melanomas, 50 nevi, 50 seborrheic keratoses) from the test dataset of a melanoma detection challenge, along with algorithm results from 23 teams. Eight dermatologists and 9 dermatology residents classified dermoscopic lesion images in an online reader study and provided their confidence level. RESULTS: The top-ranked computer algorithm had an area under the receiver operating characteristic curve of 0.87, which was higher than that of the dermatologists (0.74) and residents (0.66) (P < .001 for all comparisons). At the dermatologists' overall sensitivity in classification of 76.0%, the algorithm had a superior specificity (85.0% vs. 72.6%, P = .001). Imputation of computer algorithm classifications into dermatologist evaluations with low confidence ratings (26.6% of evaluations) increased dermatologist sensitivity from 76.0% to 80.8% and specificity from 72.6% to 72.8%. LIMITATIONS: Artificial study setting lacking the full spectrum of skin lesions as well as clinical metadata. CONCLUSION: Accumulating evidence suggests that deep neural networks can classify skin images of melanoma and its benign mimickers with high accuracy and potentially improve human performance.


Assuntos
Aprendizado Profundo , Dermoscopia/métodos , Interpretação de Imagem Assistida por Computador/métodos , Melanoma/diagnóstico , Neoplasias Cutâneas/diagnóstico , Colômbia , Estudos Transversais , Dermatologistas/estatística & dados numéricos , Dermoscopia/estatística & dados numéricos , Diagnóstico Diferencial , Humanos , Cooperação Internacional , Internato e Residência/estatística & dados numéricos , Israel , Ceratose Seborreica/diagnóstico , Melanoma/patologia , Nevo/diagnóstico , Curva ROC , Pele/diagnóstico por imagem , Pele/patologia , Neoplasias Cutâneas/patologia , Espanha , Estados Unidos
6.
Brain Commun ; 1(1): fcz014, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31633109

RESUMO

The G4C2 hexanucleotide repeat expansion mutation in the C9orf72 gene is the most common genetic cause underlying both amyotrophic lateral sclerosis and frontotemporal dementia. Pathologically, these two neurodegenerative disorders are linked by the common presence of abnormal phosphorylated TDP-43 neuronal cytoplasmic inclusions. We compared the number and size of phosphorylated TDP-43 inclusions and their morphology in hippocampi from patients dying with sporadic versus C9orf72-related amyotrophic lateral sclerosis with pathologically defined frontotemporal lobar degeneration with phosphorylated TDP-43 inclusions, the pathological substrate of clinical frontotemporal dementia in patients with amyotrophic lateral sclerosis. In sporadic cases, there were numerous consolidated phosphorylated TDP-43 inclusions that were variable in size, whereas inclusions in C9orf72 amyotrophic lateral sclerosis/frontotemporal lobar degeneration were quantitatively smaller than those in sporadic cases. Also, C9orf72 amyotrophic lateral sclerosis/frontotemporal lobar degeneration homogenized brain contained soluble cytoplasmic TDP-43 that was largely absent in sporadic cases. To better understand these pathological differences, we modelled TDP-43 inclusion formation in fibroblasts derived from sporadic or C9orf72-related amyotrophic lateral sclerosis/frontotemporal dementia patients. We found that both sporadic and C9orf72 amyotrophic lateral sclerosis/frontotemporal dementia patient fibroblasts showed impairment in TDP-43 degradation by the proteasome, which may explain increased TDP-43 protein levels found in both sporadic and C9orf72 amyotrophic lateral sclerosis/frontotemporal lobar degeneration frontal cortex and hippocampus. Fibroblasts derived from sporadic patients, but not C9orf72 patients, demonstrated the ability to sequester cytoplasmic TDP-43 into aggresomes via microtubule-dependent mechanisms. TDP-43 aggresomes in vitro and TDP-43 neuronal inclusions in vivo were both tightly localized with autophagy markers and, therefore, were likely to function similarly as sites for autophagic degradation. The inability for C9orf72 fibroblasts to form TDP-43 aggresomes, together with the observations that TDP-43 protein was soluble in the cytoplasm and formed smaller inclusions in the C9orf72 brain compared with sporadic disease, suggests a loss of protein quality control response to sequester and degrade TDP-43 in C9orf72-related diseases.

7.
A A Pract ; 13(11): 413-414, 2019 Dec 01.
Artigo em Inglês | MEDLINE | ID: mdl-31567272

RESUMO

In 2016, the American Medical Association officially dismissed pain as a vital sign quoting the opioid epidemic as a major reason. Clinically, pain remains very relevant and we present the case of a patient with achalasia treated via peroral endoscopic myotomy procedure (POEM). Given that similar patients previously failed traditional pain management modalities, regional anesthesia was used in this patient's pain management. The positive outcomes yielded from this technique convinced our gastroenterological colleagues to request regional anesthesia for future patients, altering their approach to pain management.


Assuntos
Acalasia Esofágica/cirurgia , Miotomia/efeitos adversos , Bloqueio Nervoso/métodos , Dor Pós-Operatória/prevenção & controle , Humanos , Masculino , Pessoa de Meia-Idade , Cirurgia Endoscópica por Orifício Natural , Resultado do Tratamento
8.
Mol Cancer Res ; 17(12): 2395-2409, 2019 12.
Artigo em Inglês | MEDLINE | ID: mdl-31548239

RESUMO

Molecular events activating the PI3K pathway are frequently detected in human tumors and the activation of PI3K signaling alters numerous cellular processes including tumor cell proliferation, survival, and motility. More recent studies have highlighted the impact of PI3K signaling on the cellular response to interferons and other immunologic processes relevant to antitumor immunity. Given the ability of IFNγ to regulate antigen processing and presentation and the pivotal role of MHC class I (MHCI) and II (MHCII) expression in T-cell-mediated antitumor immunity, we sought to determine the impact of PI3K signaling on MHCI and MHCII induction by IFNγ. We found that the induction of cell surface MHCI and MHCII molecules by IFNγ is enhanced by the clinical grade PI3K inhibitors dactolisib and pictilisib. We also found that PI3K inhibition increases STAT1 protein levels following IFNγ treatment and increases accessibility at genomic STAT1-binding motifs. Conversely, we found that pharmacologic activation of PI3K signaling can repress the induction of MHCI and MHCII molecules by IFNγ, and likewise, the loss of PTEN attenuates the induction of MHCI, MHCII, and STAT1 by IFNγ. Consistent with these in vitro studies, we found that within human head and neck squamous cell carcinomas, intratumoral regions with high phospho-AKT IHC staining had reduced MHCI IHC staining. IMPLICATIONS: Collectively, these findings demonstrate that MHC expression can be modulated by PI3K signaling and suggest that activation of PI3K signaling may promote immune escape via effects on antigen presentation.


Assuntos
Interferon gama/farmacologia , Fosfatidilinositol 3-Quinase/genética , Fator de Transcrição STAT1/genética , Carcinoma de Células Escamosas de Cabeça e Pescoço/tratamento farmacológico , Apresentação do Antígeno/genética , Apresentação do Antígeno/imunologia , Sítios de Ligação/genética , Proliferação de Células/efeitos dos fármacos , Proliferação de Células/genética , Proteínas de Ligação a DNA/genética , Regulação Neoplásica da Expressão Gênica/genética , Regulação Neoplásica da Expressão Gênica/imunologia , Genes MHC Classe I/genética , Genes MHC Classe I/imunologia , Genes MHC da Classe II/genética , Genes MHC da Classe II/imunologia , Genômica , Humanos , Interferon gama/genética , PTEN Fosfo-Hidrolase/genética , Fosfatidilinositol 3-Quinase/imunologia , Ligação Proteica/genética , Inibidores de Proteínas Quinases/farmacologia , Proteínas Proto-Oncogênicas c-akt/genética , Transdução de Sinais/efeitos dos fármacos , Transdução de Sinais/imunologia , Carcinoma de Células Escamosas de Cabeça e Pescoço/genética , Carcinoma de Células Escamosas de Cabeça e Pescoço/imunologia , Carcinoma de Células Escamosas de Cabeça e Pescoço/patologia
9.
J Neurosci ; 39(39): 7748-7758, 2019 09 25.
Artigo em Inglês | MEDLINE | ID: mdl-31477568

RESUMO

Humans have bred different lineages of domestic dogs for different tasks such as hunting, herding, guarding, or companionship. These behavioral differences must be the result of underlying neural differences, but surprisingly, this topic has gone largely unexplored. The current study examined whether and how selective breeding by humans has altered the gross organization of the brain in dogs. We assessed regional volumetric variation in MRI studies of 62 male and female dogs of 33 breeds. Neuroanatomical variation is plainly visible across breeds. This variation is distributed nonrandomly across the brain. A whole-brain, data-driven independent components analysis established that specific regional subnetworks covary significantly with each other. Variation in these networks is not simply the result of variation in total brain size, total body size, or skull shape. Furthermore, the anatomy of these networks correlates significantly with different behavioral specialization(s) such as sight hunting, scent hunting, guarding, and companionship. Importantly, a phylogenetic analysis revealed that most change has occurred in the terminal branches of the dog phylogenetic tree, indicating strong, recent selection in individual breeds. Together, these results establish that brain anatomy varies significantly in dogs, likely due to human-applied selection for behavior.SIGNIFICANCE STATEMENT Dog breeds are known to vary in cognition, temperament, and behavior, but the neural origins of this variation are unknown. In an MRI-based analysis, we found that brain anatomy covaries significantly with behavioral specializations such as sight hunting, scent hunting, guarding, and companionship. Neuroanatomical variation is not simply driven by brain size, body size, or skull shape, and is focused in specific networks of regions. Nearly all of the identified variation occurs in the terminal branches of the dog phylogenetic tree, indicating strong, recent selection in individual breeds. These results indicate that through selective breeding, humans have significantly altered the brains of different lineages of domestic dogs in different ways.


Assuntos
Encéfalo/anatomia & histologia , Cães/fisiologia , Sistema Nervoso/anatomia & histologia , Animais , Comportamento Animal , Tamanho Corporal , Encéfalo/diagnóstico por imagem , Cruzamento , Feminino , Variação Genética , Processamento de Imagem Assistida por Computador , Imagem por Ressonância Magnética , Masculino , Rede Nervosa/anatomia & histologia , Rede Nervosa/diagnóstico por imagem , Sistema Nervoso/diagnóstico por imagem , Tamanho do Órgão , Filogenia , Comportamento Predatório , Crânio/anatomia & histologia , Crânio/diagnóstico por imagem , Olfato/fisiologia , Especificidade da Espécie
10.
Semin Cutan Med Surg ; 38(1): E43-E48, 2019 Mar 01.
Artigo em Inglês | MEDLINE | ID: mdl-31051023

RESUMO

In this chapter, we present the use of whole slide imaging (WSI) and dermoscopy in the field of dermatology. Image digitization has allowed for increasing computer-assisted clinical decision-making. An introduction to common digital imaging data sources such as WSI and dermoscopy is provided. We also review some commonly used image quantification methods and their potential applications in dermatology. Finally, we review how machine learning approaches utilize novel large dermatology image datasets.


Assuntos
Sistemas de Apoio a Decisões Clínicas , Dermoscopia , Neoplasias Cutâneas/diagnóstico , Humanos , Interpretação de Imagem Assistida por Computador , Processamento de Imagem Assistida por Computador , Aprendizado de Máquina , Neoplasias Cutâneas/diagnóstico por imagem
11.
Bioinformatics ; 35(18): 3461-3467, 2019 09 15.
Artigo em Inglês | MEDLINE | ID: mdl-30726865

RESUMO

MOTIVATION: While deep-learning algorithms have demonstrated outstanding performance in semantic image segmentation tasks, large annotation datasets are needed to create accurate models. Annotation of histology images is challenging due to the effort and experience required to carefully delineate tissue structures, and difficulties related to sharing and markup of whole-slide images. RESULTS: We recruited 25 participants, ranging in experience from senior pathologists to medical students, to delineate tissue regions in 151 breast cancer slides using the Digital Slide Archive. Inter-participant discordance was systematically evaluated, revealing low discordance for tumor and stroma, and higher discordance for more subjectively defined or rare tissue classes. Feedback provided by senior participants enabled the generation and curation of 20 000+ annotated tissue regions. Fully convolutional networks trained using these annotations were highly accurate (mean AUC=0.945), and the scale of annotation data provided notable improvements in image classification accuracy. AVAILABILITY AND IMPLEMENTATION: Dataset is freely available at: https://goo.gl/cNM4EL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.


Assuntos
Neoplasias da Mama , Crowdsourcing , Algoritmos , Técnicas Histológicas , Humanos
12.
Anesthesiology ; 130(3): 503-504, 2019 Mar.
Artigo em Inglês | MEDLINE | ID: mdl-30676418
13.
Proc Natl Acad Sci U S A ; 115(13): E2970-E2979, 2018 03 27.
Artigo em Inglês | MEDLINE | ID: mdl-29531073

RESUMO

Cancer histology reflects underlying molecular processes and disease progression and contains rich phenotypic information that is predictive of patient outcomes. In this study, we show a computational approach for learning patient outcomes from digital pathology images using deep learning to combine the power of adaptive machine learning algorithms with traditional survival models. We illustrate how these survival convolutional neural networks (SCNNs) can integrate information from both histology images and genomic biomarkers into a single unified framework to predict time-to-event outcomes and show prediction accuracy that surpasses the current clinical paradigm for predicting the overall survival of patients diagnosed with glioma. We use statistical sampling techniques to address challenges in learning survival from histology images, including tumor heterogeneity and the need for large training cohorts. We also provide insights into the prediction mechanisms of SCNNs, using heat map visualization to show that SCNNs recognize important structures, like microvascular proliferation, that are related to prognosis and that are used by pathologists in grading. These results highlight the emerging role of deep learning in precision medicine and suggest an expanding utility for computational analysis of histology in the future practice of pathology.


Assuntos
Neoplasias Encefálicas/genética , Neoplasias Encefálicas/patologia , Genômica/métodos , Glioma/genética , Glioma/patologia , Técnicas Histológicas/métodos , Redes Neurais de Computação , Algoritmos , Neoplasias Encefálicas/terapia , Glioma/terapia , Humanos , Processamento de Imagem Assistida por Computador , Medicina de Precisão , Prognóstico
14.
J Am Acad Dermatol ; 78(2): 270-277.e1, 2018 02.
Artigo em Inglês | MEDLINE | ID: mdl-28969863

RESUMO

BACKGROUND: Computer vision may aid in melanoma detection. OBJECTIVE: We sought to compare melanoma diagnostic accuracy of computer algorithms to dermatologists using dermoscopic images. METHODS: We conducted a cross-sectional study using 100 randomly selected dermoscopic images (50 melanomas, 44 nevi, and 6 lentigines) from an international computer vision melanoma challenge dataset (n = 379), along with individual algorithm results from 25 teams. We used 5 methods (nonlearned and machine learning) to combine individual automated predictions into "fusion" algorithms. In a companion study, 8 dermatologists classified the lesions in the 100 images as either benign or malignant. RESULTS: The average sensitivity and specificity of dermatologists in classification was 82% and 59%. At 82% sensitivity, dermatologist specificity was similar to the top challenge algorithm (59% vs. 62%, P = .68) but lower than the best-performing fusion algorithm (59% vs. 76%, P = .02). Receiver operating characteristic area of the top fusion algorithm was greater than the mean receiver operating characteristic area of dermatologists (0.86 vs. 0.71, P = .001). LIMITATIONS: The dataset lacked the full spectrum of skin lesions encountered in clinical practice, particularly banal lesions. Readers and algorithms were not provided clinical data (eg, age or lesion history/symptoms). Results obtained using our study design cannot be extrapolated to clinical practice. CONCLUSION: Deep learning computer vision systems classified melanoma dermoscopy images with accuracy that exceeded some but not all dermatologists.


Assuntos
Algoritmos , Dermatologistas , Dermoscopia , Lentigo/diagnóstico por imagem , Melanoma/diagnóstico , Nevo/diagnóstico por imagem , Neoplasias Cutâneas/diagnóstico por imagem , Congressos como Assunto , Estudos Transversais , Diagnóstico por Computador , Humanos , Aprendizado de Máquina , Melanoma/patologia , Curva ROC , Neoplasias Cutâneas/patologia
15.
Cancer Res ; 77(21): e75-e78, 2017 11 01.
Artigo em Inglês | MEDLINE | ID: mdl-29092945

RESUMO

Tissue-based cancer studies can generate large amounts of histology data in the form of glass slides. These slides contain important diagnostic, prognostic, and biological information and can be digitized into expansive and high-resolution whole-slide images using slide-scanning devices. Effectively utilizing digital pathology data in cancer research requires the ability to manage, visualize, share, and perform quantitative analysis on these large amounts of image data, tasks that are often complex and difficult for investigators with the current state of commercial digital pathology software. In this article, we describe the Digital Slide Archive (DSA), an open-source web-based platform for digital pathology. DSA allows investigators to manage large collections of histologic images and integrate them with clinical and genomic metadata. The open-source model enables DSA to be extended to provide additional capabilities. Cancer Res; 77(21); e75-78. ©2017 AACR.


Assuntos
Processamento de Imagem Assistida por Computador , Bibliotecas Digitais , Neoplasias/patologia , Software , Humanos , Internet
16.
Sci Rep ; 7(1): 14588, 2017 11 06.
Artigo em Inglês | MEDLINE | ID: mdl-29109450

RESUMO

Whole-slide imaging of histologic sections captures tissue microenvironments and cytologic details in expansive high-resolution images. These images can be mined to extract quantitative features that describe tissues, yielding measurements for hundreds of millions of histologic objects. A central challenge in utilizing this data is enabling investigators to train and evaluate classification rules for identifying objects related to processes like angiogenesis or immune response. In this paper we describe HistomicsML, an interactive machine-learning system for digital pathology imaging datasets. This framework uses active learning to direct user feedback, making classifier training efficient and scalable in datasets containing 108+ histologic objects. We demonstrate how this system can be used to phenotype microvascular structures in gliomas to predict survival, and to explore the molecular pathways associated with these phenotypes. Our approach enables researchers to unlock phenotypic information from digital pathology datasets to investigate prognostic image biomarkers and genotype-phenotype associations.


Assuntos
Técnicas Histológicas , Interpretação de Imagem Assistida por Computador , Aprendizado de Máquina , Biomarcadores Tumorais/metabolismo , Neoplasias Encefálicas/diagnóstico por imagem , Neoplasias Encefálicas/genética , Neoplasias Encefálicas/metabolismo , Neoplasias Encefálicas/patologia , Estudos de Coortes , Células Endoteliais/metabolismo , Células Endoteliais/patologia , Estudos de Associação Genética , Glioma/diagnóstico , Glioma/genética , Glioma/metabolismo , Glioma/patologia , Humanos , Interpretação de Imagem Assistida por Computador/métodos , Microvasos/metabolismo , Microvasos/patologia , Molécula-1 de Adesão Celular Endotelial a Plaquetas/metabolismo , Prognóstico , RNA Mensageiro/metabolismo , Software
17.
Sci Rep ; 7(1): 11707, 2017 09 15.
Artigo em Inglês | MEDLINE | ID: mdl-28916782

RESUMO

Translating the vast data generated by genomic platforms into accurate predictions of clinical outcomes is a fundamental challenge in genomic medicine. Many prediction methods face limitations in learning from the high-dimensional profiles generated by these platforms, and rely on experts to hand-select a small number of features for training prediction models. In this paper, we demonstrate how deep learning and Bayesian optimization methods that have been remarkably successful in general high-dimensional prediction tasks can be adapted to the problem of predicting cancer outcomes. We perform an extensive comparison of Bayesian optimized deep survival models and other state of the art machine learning methods for survival analysis, and describe a framework for interpreting deep survival models using a risk backpropagation technique. Finally, we illustrate that deep survival models can successfully transfer information across diseases to improve prognostic accuracy. We provide an open-source software implementation of this framework called SurvivalNet that enables automatic training, evaluation and interpretation of deep survival models.


Assuntos
Aprendizado Profundo , Genômica/métodos , Prognóstico , Software , Sobrevida , Teorema de Bayes , Conjuntos de Dados como Assunto , Humanos , Neoplasias/genética , Neoplasias/mortalidade , Redes Neurais de Computação , Resultado do Tratamento
18.
J Pathol ; 241(3): 375-391, 2017 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-27861902

RESUMO

The histopathological evaluation of morphological features in breast tumours provides prognostic information to guide therapy. Adjunct molecular analyses provide further diagnostic, prognostic and predictive information. However, there is limited knowledge of the molecular basis of morphological phenotypes in invasive breast cancer. This study integrated genomic, transcriptomic and protein data to provide a comprehensive molecular profiling of morphological features in breast cancer. Fifteen pathologists assessed 850 invasive breast cancer cases from The Cancer Genome Atlas (TCGA). Morphological features were significantly associated with genomic alteration, DNA methylation subtype, PAM50 and microRNA subtypes, proliferation scores, gene expression and/or reverse-phase protein assay subtype. Marked nuclear pleomorphism, necrosis, inflammation and a high mitotic count were associated with the basal-like subtype, and had a similar molecular basis. Omics-based signatures were constructed to predict morphological features. The association of morphology transcriptome signatures with overall survival in oestrogen receptor (ER)-positive and ER-negative breast cancer was first assessed by use of the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset; signatures that remained prognostic in the METABRIC multivariate analysis were further evaluated in five additional datasets. The transcriptomic signature of poorly differentiated epithelial tubules was prognostic in ER-positive breast cancer. No signature was prognostic in ER-negative breast cancer. This study provided new insights into the molecular basis of breast cancer morphological phenotypes. The integration of morphological with molecular data has the potential to refine breast cancer classification, predict response to therapy, enhance our understanding of breast cancer biology, and improve clinical management. This work is publicly accessible at www.dx.ai/tcga_breast. Copyright © 2016 Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.


Assuntos
Biomarcadores Tumorais/genética , Neoplasias da Mama/patologia , Neoplasias da Mama/metabolismo , Bases de Dados Genéticas , Feminino , Perfilação da Expressão Gênica , Genômica , Humanos , Invasividade Neoplásica , Fenótipo , Receptores Estrogênicos/metabolismo
19.
Front Neuroinform ; 10: 46, 2016.
Artigo em Inglês | MEDLINE | ID: mdl-27867354

RESUMO

Recent progress in diffusion MRI and tractography algorithms as well as the launch of the Human Connectome Project (HCP) have provided brain research with an abundance of structural connectivity data. In this work, we describe and evaluate a method that can infer the structural brain network that interconnects a given set of Regions of Interest (ROIs) from probabilistic tractography data. The proposed method, referred to as Minimum Asymmetry Network Inference Algorithm (MANIA), does not determine the connectivity between two ROIs based on an arbitrary connectivity threshold. Instead, we exploit a basic limitation of the tractography process: the observed streamlines from a source to a target do not provide any information about the polarity of the underlying white matter, and so if there are some fibers connecting two voxels (or two ROIs) X and Y, tractography should be able in principle to follow this connection in both directions, from X to Y and from Y to X. We leverage this limitation to formulate the network inference process as an optimization problem that minimizes the (appropriately normalized) asymmetry of the observed network. We evaluate the proposed method using both the FiberCup dataset and based on a noise model that randomly corrupts the observed connectivity of synthetic networks. As a case-study, we apply MANIA on diffusion MRI data from 28 healthy subjects to infer the structural network between 18 corticolimbic ROIs that are associated with various neuropsychiatric conditions including depression, anxiety and addiction.

20.
BMC Cancer ; 16: 611, 2016 08 08.
Artigo em Inglês | MEDLINE | ID: mdl-27502180

RESUMO

BACKGROUND: Glioblastoma (GBM) tumors exhibit strong phenotypic differences that can be quantified using magnetic resonance imaging (MRI), but the underlying biological drivers of these imaging phenotypes remain largely unknown. An Imaging-Genomics analysis was performed to reveal the mechanistic associations between MRI derived quantitative volumetric tumor phenotype features and molecular pathways. METHODS: One hundred fourty one patients with presurgery MRI and survival data were included in our analysis. Volumetric features were defined, including the necrotic core (NE), contrast-enhancement (CE), abnormal tumor volume assessed by post-contrast T1w (tumor bulk or TB), tumor-associated edema based on T2-FLAIR (ED), and total tumor volume (TV), as well as ratios of these tumor components. Based on gene expression where available (n = 91), pathway associations were assessed using a preranked gene set enrichment analysis. These results were put into context of molecular subtypes in GBM and prognostication. RESULTS: Volumetric features were significantly associated with diverse sets of biological processes (FDR < 0.05). While NE and TB were enriched for immune response pathways and apoptosis, CE was associated with signal transduction and protein folding processes. ED was mainly enriched for homeostasis and cell cycling pathways. ED was also the strongest predictor of molecular GBM subtypes (AUC = 0.61). CE was the strongest predictor of overall survival (C-index = 0.6; Noether test, p = 4x10(-4)). CONCLUSION: GBM volumetric features extracted from MRI are significantly enriched for information about the biological state of a tumor that impacts patient outcomes. Clinical decision-support systems could exploit this information to develop personalized treatment strategies on the basis of noninvasive imaging.


Assuntos
Neoplasias Encefálicas/diagnóstico por imagem , Redes Reguladoras de Genes , Genômica/métodos , Glioblastoma/diagnóstico por imagem , Imagem por Ressonância Magnética/métodos , Apoptose , Neoplasias Encefálicas/genética , Ciclo Celular , Sistemas de Apoio a Decisões Clínicas , Regulação Neoplásica da Expressão Gênica , Glioblastoma/genética , Humanos , Fenótipo , Transdução de Sinais , Análise de Sobrevida
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...