Iterrative Tangential Voting (ITV) is an advanced image processing algorithm, developed at Berkeley Data Science Center (BBDS) at Lawrence Berkeley National Laboratory for the inference of structural saliency. An example on vascular-structure enhancement through ITV is shown as follows,
Note
The characterization and classification of white blood cells (WBC) is critical for the diagnosis of anemia, leukemia and many other hematologic diseases. WBC Profiler is a software (matlab-based) package based on unsupervised feature learning for efficient and effective WBC characterization and recognition.
The Cancer Genome Atlas (TCGA) has been one of the clearing houses of genome-wide array data for the understanding of the molecular basis of cancer from large cohorts. These analyses are intrinsically from bulk measurements of mixed cell types, derived from frozen biopsy sections that include tissues with mixed histopathology and/or microanatomies (e.g., tumor, stroma). While bulk array profiling may provide insights into molecular aberrations, it provides only an average genome-wide measurement for a biopsy and fails to reveal inherent cellular composition and heterogeneity of a tumor. On the other hand, histology sections do not provide standardized measurements, but they are rich in content and continue to be the gold standard for the assessment of tissue neoplasm.
In this project, we aims to provide cellular morphometric context summarization for TCGA Kidney Renal Clear Cell Carcinoma (KIRC) Cohort, which can be further utilized for various end points, such as,
Examples can be found in our previous publication:
Visualization Tool: KIRC Whole Slide Images (WSI) and the corresponding segmentation results.
The Cancer Genome Atlas (TCGA) has been one of the clearing houses of genome-wide array data for the understanding of the molecular basis of cancer from large cohorts. These analyses are intrinsically from bulk measurements of mixed cell types, derived from frozen biopsy sections that include tissues with mixed histopathology and/or microanatomies (e.g., tumor, stroma). While bulk array profiling may provide insights into molecular aberrations, it provides only an average genome-wide measurement for a biopsy and fails to reveal inherent cellular composition and heterogeneity of a tumor. On the other hand, histology sections do not provide standardized measurements, but they are rich in content and continue to be the gold standard for the assessment of tissue neoplasm.
In this project, we aims to provide univariate cellular morphoetric summarization for TCGA Kidney Renal Clear Cell Carcinoma (KIRC) Cohort, which can be further utilized for various end points, such as,
Examples can be found in our previous publication:
Visualization Tool: KIRC Whole Slide Images (WSI) and the corresponding segmentation results.
Sparsity Constrained Convolutional Regression is a machine learning algorithm that was initially developed for the segmentation of nuclear regions in tissue histology.
The Cancer Genome Atlas (TCGA) has been one of the clearing houses of genome-wide array data for the understanding of the molecular basis of cancer from large cohorts. These analyses are intrinsically from bulk measurements of mixed cell types, derived from frozen biopsy sections that include tissues with mixed histopathology and/or microanatomies (e.g., tumor, stroma). While bulk array profiling may provide insights into molecular aberrations, it provides only an average genome-wide measurement for a biopsy and fails to reveal inherent cellular composition and heterogeneity of a tumor. On the other hand, histology sections do not provide standardized measurements, but they are rich in content and continue to be the gold standard for the assessment of tissue neoplasm.
In this project, we aims to provide joint cellular morphometric context summarization for TCGA Glioblastoma (GBM) and lower grade glioma (LGG) cohorts, which can be further utilized for various end points, such as,
Examples can be found in our previous publication:
Visualization Tool: GBM Whole Slide Images (WSI) and the corresponding segmentation results.
Visualization Tool: LGG Whole Slide Images (WSI) and the corresponding segmentation results.
The tyrosine kinase ErbB2 positive breast tumors have more aggressive tumor growth, poorer clinical outcome, and more resistance to radiotherapy, chemotherapy and hormone therapy. A humanized anti-ErbB2 monoclonal antibody Herceptin and a small molecules inhibitor Lapatinib were developed and approved by FDA to treat patients with ErbB2 amplification and overexpression. Unfortunately, most ErbB2+ breast cancers do not respond to Herceptin and Lapatinib, and the majority of responders become resistant within 12 months of initial therapy (defined as secondary drug resistance). Such differences in response to Lapatinib treatment is contributed by substantial heterogeneity within ErbB2+ breast cancers. To address this possibility, we carried out transcriptomic analysis of mammary tumors from genetically diverse MMTV-ErbB2 mice. This will help us to have a better understanding of the heterogeneous response to ErbB2 targeted therapy and permit us to design better and more individualized (personalized) treatment strategies for human ErbB2 positive breast cancer.
We used gene transcript profiling to gain a deeper understanding of the role of FBXW7 in tumor development and to determine the influence of mTOR inhibition by rapamycin on tumor transcriptome and biological functions. In comparison to tumors from p53 single heterozygous (p53+/-) mice, we find that tumors from Fbxw7/p53 double heterozygous (Fbxw7+/-p53+/-) mice show significant deregulation of cholesterol metabolic processes independent of rapamycin treatment, while cell cycle related genes were upregulated in tumors from placebo treated Fbxw7+/-p53+/- mice, but not in tumors from rapamycin treated Fbxw7+/-p53+/- mice. On the other hand, tumors from rapamycin treated Fbxw7+/-p53+/- mice were enriched for genes involved in the integrated stress response, an adaptive mechanism to survive in stressful environments.
BioQuant is a software, initially developed by the Imaing and Informatics Lab at Lawrence Berkeley National Laboratory, for large-scale high performance quantification of macromolecules involved in cell-cell adhesion, genomic instability, and DNA repair proteins, etc., which has been widely used by members at the Life Sciences Division of Lawrence Berkeley National Laboratory for scientific discoveries.
Iterrative Radial Voting is an advanced image processing algorithm, initially developed by the Imaing and Informatics Lab at Lawrence Berkeley National Laboratory for the inference of structural saliency and characterization of subcellular events. An example of kernel topology and radial object localization is illustrated as follows,
Stacked Predictive Sparse Decomposition is a machine learning algorithm that was initially developed for the classification of distinct regions of microanatomy and histopathology. This project contains the source code (matlab) for Stacked Predictive Sparse Decomposition that is described in the publication as follows,
Multispectral Convolutional Sparse Coding is a machine learning algorithm that was initially developed for the classification of distinct regions of microanatomy and histopathology. This project contains the source code (matlab) for Multispectral Convolutional Sparse Coding that is described in the publication as follows,
The Cancer Genome Atlas (TCGA) has been one of the clearing houses of genome-wide array data for the understanding of the molecular basis of cancer from large cohorts. These analyses are intrinsically from bulk measurements of mixed cell types, derived from frozen biopsy sections that include tissues with mixed histopathology and/or microanatomies (e.g., tumor, stroma). While bulk array profiling may provide insights into molecular aberrations, it provides only an average genome-wide measurement for a biopsy and fails to reveal inherent cellular composition and heterogeneity of a tumor. On the other hand, histology sections do not provide standardized measurements, but they are rich in content and continue to be the gold standard for the assessment of tissue neoplasm.
In this project, we aims to provide cellular morphometric context summarization for TCGA lower grade glioma (LGG) Cohort, which can be further utilized for various end points, such as,
Examples can be found in our previous publication:
Visualization Tool: LGG Whole Slide Images (WSI) and the corresponding segmentation results.
The Cancer Genome Atlas (TCGA) has been one of the clearing houses of genome-wide array data for the understanding of the molecular basis of cancer from large cohorts. These analyses are intrinsically from bulk measurements of mixed cell types, derived from frozen biopsy sections that include tissues with mixed histopathology and/or microanatomies (e.g., tumor, stroma). While bulk array profiling may provide insights into molecular aberrations, it provides only an average genome-wide measurement for a biopsy and fails to reveal inherent cellular composition and heterogeneity of a tumor. On the other hand, histology sections do not provide standardized measurements, but they are rich in content and continue to be the gold standard for the assessment of tissue neoplasm.
In this project, we aims to provide univariate cellular morphoetric summarization for TCGA lower grade glioma (LGG) Cohort, which can be further utilized for various end points, such as,
Examples can be found in our previous publication:
Visualization Tool: LGG Whole Slide Images (WSI) and the corresponding segmentation results.
The Cancer Genome Atlas (TCGA) has been one of the clearing houses of genome-wide array data for the understanding of the molecular basis of cancer from large cohorts. These analyses are intrinsically from bulk measurements of mixed cell types, derived from frozen biopsy sections that include tissues with mixed histopathology and/or microanatomies (e.g., tumor, stroma). While bulk array profiling may provide insights into molecular aberrations, it provides only an average genome-wide measurement for a biopsy and fails to reveal inherent cellular composition and heterogeneity of a tumor. On the other hand, histology sections do not provide standardized measurements, but they are rich in content and continue to be the gold standard for the assessment of tissue neoplasm.
In this project, we aims to provide cellular morphometric context summarization for TCGA Glioblastoma (GBM) Cohort, which can be further utilized for various end points, such as,
Examples can be found in our previous publication:
Visualization Tool: GBM Whole Slide Images (WSI) and the corresponding segmentation results.
The Cancer Genome Atlas (TCGA) has been one of the clearing houses of genome-wide array data for the understanding of the molecular basis of cancer from large cohorts. These analyses are intrinsically from bulk measurements of mixed cell types, derived from frozen biopsy sections that include tissues with mixed histopathology and/or microanatomies (e.g., tumor, stroma). While bulk array profiling may provide insights into molecular aberrations, it provides only an average genome-wide measurement for a biopsy and fails to reveal inherent cellular composition and heterogeneity of a tumor. On the other hand, histology sections do not provide standardized measurements, but they are rich in content and continue to be the gold standard for the assessment of tissue neoplasm.
In this project, we aims to provide univariate cellular morphoetric summarization for TCGA Glioblastoma (GBM) Cohort, which can be further utilized for various end points, such as,
Examples can be found in our previous publication:
Visualization Tool: GBM Whole Slide Images (WSI) and the corresponding segmentation results.
