An official website of the United States government
Histopathology plays a critical role in the diagnosis and surgical management of cancer. However, access to histopathology services, especially frozen section pathology during surgery, is limited in resource-constrained settings because preparing slides from resected tissue is time-consuming, labor-intensive, and requires expensive infrastructure. Here, we report a deep-learning-enabled microscope, named DeepDOF-SE, to rapidly scan intact tissue at cellular resolution without the need for physical sectioning. Three key features jointly make DeepDOF-SE practical. First, tissue specimens are stained directly with inexpensive vital fluorescent dyes and optically sectioned with ultra-violet excitation that localizes fluorescent emission to a thin surface layer. Second, a deep-learning algorithm extends the depth-of-field, allowing rapid acquisition of in-focus images from large areas of tissue even when the tissue surface is highly irregular. Finally, a semi-supervised generative adversarial network virtually stains DeepDOF-SE fluorescence images with hematoxylin-and-eosin appearance, facilitating image interpretation by pathologists without significant additional training. We developed the DeepDOF-SE platform using a data-driven approach and validated its performance by imaging surgical resections of suspected oral tumors. Our results show that DeepDOF-SE provides histological information of diagnostic importance, offering a rapid and affordable slide-free histology platform for intraoperative tumor margin assessment and in low-resource settings.
more »
« less
Cellphone enabled point-of-care assessment of breast tumor cytology and molecular HER2 expression from fine-needle aspirates
Abstract Management of breast cancer in limited-resource settings is hindered by a lack of low-cost, logistically sustainable approaches toward molecular and cellular diagnostic pathology services that are needed to guide therapy. To address these limitations, we have developed a multimodal cellphone-based platform—the EpiView-D4—that can evaluate both cellular morphology and molecular expression of clinically relevant biomarkers directly from fine-needle aspiration (FNA) of breast tissue specimens within 1 h. The EpiView-D4 is comprised of two components: (1) an immunodiagnostic chip built upon a “non-fouling” polymer brush-coating (the “D4”) which quantifies expression of protein biomarkers directly from crude cell lysates, and (2) a custom cellphone-based optical microscope (“EpiView”) designed for imaging cytology preparations and D4 assay readout. As a proof-of-concept, we used the EpiView-D4 for assessment of human epidermal growth factor receptor-2 (HER2) expression and validated the performance using cancer cell lines, animal models, and human tissue specimens. We found that FNA cytology specimens (prepared in less than 5 min with rapid staining kits) imaged by the EpiView-D4 were adequate for assessment of lesional cellularity and tumor content. We also found our device could reliably distinguish between HER2 expression levels across multiple different cell lines and animal xenografts. In a pilot study with human tissue (n = 19), we were able to accurately categorize HER2-negative and HER2-positve tumors from FNA specimens. Taken together, the EpiView-D4 offers a promising alternative to invasive—and often unavailable—pathology services and may enable the democratization of effective breast cancer management in limited-resource settings.
more »
« less
- Award ID(s):
- 1944167
- PAR ID:
- 10268124
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- npj Breast Cancer
- Volume:
- 7
- Issue:
- 1
- ISSN:
- 2374-4677
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The immunohistochemical (IHC) staining of the human epidermal growth factor receptor 2 (HER2) biomarker is widely practiced in breast tissue analysis, preclinical studies, and diagnostic decisions, guiding cancer treatment and investigation of pathogenesis. HER2 staining demands laborious tissue treatment and chemical processing performed by a histotechnologist, which typically takes one day to prepare in a laboratory, increasing analysis time and associated costs. Here, we describe a deep learning-based virtual HER2 IHC staining method using a conditional generative adversarial network that is trained to rapidly transform autofluorescence microscopic images of unlabeled/label-free breast tissue sections into bright-field equivalent microscopic images, matching the standard HER2 IHC staining that is chemically performed on the same tissue sections. The efficacy of this virtual HER2 staining framework was demonstrated by quantitative analysis, in which three board-certified breast pathologists blindly graded the HER2 scores of virtually stained and immunohistochemically stained HER2 whole slide images (WSIs) to reveal that the HER2 scores determined by inspecting virtual IHC images are as accurate as their immunohistochemically stained counterparts. A second quantitative blinded study performed by the same diagnosticians further revealed that the virtually stained HER2 images exhibit a comparable staining quality in the level of nuclear detail, membrane clearness, and absence of staining artifacts with respect to their immunohistochemically stained counterparts. This virtual HER2 staining framework bypasses the costly, laborious, and time-consuming IHC staining procedures in laboratory and can be extended to other types of biomarkers to accelerate the IHC tissue staining used in life sciences and biomedical workflow.more » « less
-
Breast cancer treatment can be improved with biomarkers for early detection and individualized therapy. A set of 86 microRNAs (miRNAs) were identified to separate breast cancer tumors from normal breast tissues (n = 52) with an overall accuracy of 90.4%. Six miRNAs had concordant expression in both tumors and breast cancer patient blood samples compared with the normal control samples. Twelve miRNAs showed concordant expression in tumors vs. normal breast tissues and patient survival (n = 1093), with seven as potential tumor suppressors and five as potential oncomiRs. From experimentally validated target genes of these 86 miRNAs, pan-sensitive and pan-resistant genes with concordant mRNA and protein expression associated with in-vitro drug response to 19 NCCN-recommended breast cancer drugs were selected. Combined with in-vitro proliferation assays using CRISPR-Cas9/RNAi and patient survival analysis, MEK inhibitors PD19830 and BRD-K12244279, pilocarpine, and tremorine were discovered as potential new drug options for treating breast cancer. Multi-omics biomarkers of response to the discovered drugs were identified using human breast cancer cell lines. This study presented an artificial intelligence pipeline of miRNA-based discovery of biomarkers, therapeutic targets, and repositioning drugs that can be applied to many cancer types.more » « less
-
During epithelial-to-mesenchymal transition (EMT), cancer cells lose their cell–cell adhesion junctions as they become more metastatic, altering cell motility and focal adhesion disassembly associated with increased detachment from the primary tumor and a migratory response into nearby tissue and vasculature. Current in vitro strategies characterizing a cell's metastatic potential heavily favor quantifying the presence of cell adhesion biomarkers through biochemical analysis; however, mechanical cues such as adhesion and motility directly relate to cell metastatic potential without needing to first identify a cell specific biomarker for a particular type of cancer. This paper presents a comprehensive comparison of two functional metrics of cancer aggression, wound closure migration velocity and cell detachment from a culture surface, for three pairs of epithelial cancer cell lines (breast, endometrium, tongue tissue origins). It was found that one functional metric alone was not sufficient to categorize the cancer cell lines; instead, both metrics were necessary to identify functional trends and accurately place cells on the spectrum of metastasis. On average, cell lines with low metastatic potential (MCF-7, Ishikawa, and Cal-27) were more aggressive through wound closure migration compared to loss of cell adhesion. On the other hand, cell lines with high metastatic potential (MDA-MB-231, KLE, and SCC-25) were on average more aggressive through loss of cell adhesion compared to wound closure migration. This trend was true independent of the tissue type where the cells originated, indicating that there is a relationship between metastatic potential and the predominate type of cancer aggression. Our work presents one of the first combined studies relating cell metastatic potential to functional migration and adhesion metrics across cancer cell lines from selected tissue origins, without needing to identify tissue-specific biomarkers to achieve success. Using functional metrics provides powerful clinical relevancy for future predictive tools of cancer metastasis.more » « less
-
Xu, Jinbo (Ed.)Abstract Motivation Motions of transmembrane receptors on cancer cell surfaces can reveal biophysical features of the cancer cells, thus providing a method for characterizing cancer cell phenotypes. While conventional analysis of receptor motions in the cell membrane mostly relies on the mean-squared displacement plots, much information is lost when producing these plots from the trajectories. Here we employ deep learning to classify breast cancer cell types based on the trajectories of epidermal growth factor receptor (EGFR). Our model is an artificial neural network trained on the EGFR motions acquired from six breast cancer cell lines of varying invasiveness and receptor status: MCF7 (hormone receptor positive), BT474 (HER2-positive), SKBR3 (HER2-positive), MDA-MB-468 (triple negative, TN), MDA-MB-231 (TN) and BT549 (TN). Results The model successfully classified the trajectories within individual cell lines with 83% accuracy and predicted receptor status with 85% accuracy. To further validate the method, epithelial–mesenchymal transition (EMT) was induced in benign MCF10A cells, noninvasive MCF7 cancer cells and highly invasive MDA-MB-231 cancer cells, and EGFR trajectories from these cells were tested. As expected, after EMT induction, both MCF10A and MCF7 cells showed higher rates of classification as TN cells, but not the MDA-MB-231 cells. Whereas deep learning-based cancer cell classifications are primarily based on the optical transmission images of cell morphology and the fluorescence images of cell organelles or cytoskeletal structures, here we demonstrated an alternative way to classify cancer cells using a dynamic, biophysical feature that is readily accessible. Availability and implementation A python implementation of deep learning-based classification can be found at https://github.com/soonwoohong/Deep-learning-for-EGFR-trajectory-classification. Supplementary information Supplementary data are available at Bioinformatics online.more » « less
