1
|
Hörst F, Rempe M, Heine L, Seibold C, Keyl J, Baldini G, Ugurel S, Siveke J, Grünwald B, Egger J, Kleesiek J. CellViT: Vision Transformers for precise cell segmentation and classification. Med Image Anal 2024; 94:103143. [PMID: 38507894 DOI: 10.1016/j.media.2024.103143] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Revised: 02/14/2024] [Accepted: 03/12/2024] [Indexed: 03/22/2024]
Abstract
Nuclei detection and segmentation in hematoxylin and eosin-stained (H&E) tissue images are important clinical tasks and crucial for a wide range of applications. However, it is a challenging task due to nuclei variances in staining and size, overlapping boundaries, and nuclei clustering. While convolutional neural networks have been extensively used for this task, we explore the potential of Transformer-based networks in combination with large scale pre-training in this domain. Therefore, we introduce a new method for automated instance segmentation of cell nuclei in digitized tissue samples using a deep learning architecture based on Vision Transformer called CellViT. CellViT is trained and evaluated on the PanNuke dataset, which is one of the most challenging nuclei instance segmentation datasets, consisting of nearly 200,000 annotated nuclei into 5 clinically important classes in 19 tissue types. We demonstrate the superiority of large-scale in-domain and out-of-domain pre-trained Vision Transformers by leveraging the recently published Segment Anything Model and a ViT-encoder pre-trained on 104 million histological image patches - achieving state-of-the-art nuclei detection and instance segmentation performance on the PanNuke dataset with a mean panoptic quality of 0.50 and an F1-detection score of 0.83. The code is publicly available at https://github.com/TIO-IKIM/CellViT.
Collapse
Affiliation(s)
- Fabian Hörst
- Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), 45131 Essen, Germany; Cancer Research Center Cologne Essen (CCCE), West German Cancer Center Essen, University Hospital Essen (AöR), 45147 Essen, Germany.
| | - Moritz Rempe
- Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), 45131 Essen, Germany; Cancer Research Center Cologne Essen (CCCE), West German Cancer Center Essen, University Hospital Essen (AöR), 45147 Essen, Germany
| | - Lukas Heine
- Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), 45131 Essen, Germany; Cancer Research Center Cologne Essen (CCCE), West German Cancer Center Essen, University Hospital Essen (AöR), 45147 Essen, Germany
| | - Constantin Seibold
- Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), 45131 Essen, Germany; Clinic for Nuclear Medicine, University Hospital Essen (AöR), 45147 Essen, Germany
| | - Julius Keyl
- Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), 45131 Essen, Germany; Institute of Pathology, University Hospital Essen (AöR), 45147 Essen, Germany
| | - Giulia Baldini
- Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), 45131 Essen, Germany; Institute of Interventional and Diagnostic Radiology and Neuroradiology, University Hospital Essen (AöR), 45147 Essen, Germany
| | - Selma Ugurel
- Department of Dermatology, University Hospital Essen (AöR), 45147 Essen, Germany; German Cancer Consortium (DKTK, Partner site Essen), 69120 Heidelberg, Germany
| | - Jens Siveke
- West German Cancer Center, partner site Essen, a partnership between German Cancer Research Center (DKFZ) and University Hospital Essen, University Hospital Essen (AöR), 45147 Essen, Germany; Bridge Institute of Experimental Tumor Therapy (BIT) and Division of Solid Tumor Translational Oncology (DKTK), West German Cancer Center Essen, University Hospital Essen (AöR), University of Duisburg-Essen, 45147 Essen, Germany
| | - Barbara Grünwald
- Department of Urology, West German Cancer Center, 45147 University Hospital Essen (AöR), Germany; Princess Margaret Cancer Centre, M5G 2M9 Toronto, Ontario, Canada
| | - Jan Egger
- Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), 45131 Essen, Germany; Cancer Research Center Cologne Essen (CCCE), West German Cancer Center Essen, University Hospital Essen (AöR), 45147 Essen, Germany
| | - Jens Kleesiek
- Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), 45131 Essen, Germany; Cancer Research Center Cologne Essen (CCCE), West German Cancer Center Essen, University Hospital Essen (AöR), 45147 Essen, Germany; German Cancer Consortium (DKTK, Partner site Essen), 69120 Heidelberg, Germany; Department of Physics, TU Dortmund University, 44227 Dortmund, Germany
| |
Collapse
|
2
|
Alsup AM, Fowlds K, Cho M, Luber JM. BetaBuddy: An automated end-to-end computer vision pipeline for analysis of calcium fluorescence dynamics in β-cells. PLoS One 2024; 19:e0299549. [PMID: 38489336 PMCID: PMC10942061 DOI: 10.1371/journal.pone.0299549] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2023] [Accepted: 02/12/2024] [Indexed: 03/17/2024] Open
Abstract
Insulin secretion from pancreatic β-cells is integral in maintaining the delicate equilibrium of blood glucose levels. Calcium is known to be a key regulator and triggers the release of insulin. This sub-cellular process can be monitored and tracked through live-cell imaging and subsequent cell segmentation, registration, tracking, and analysis of the calcium level in each cell. Current methods of analysis typically require the manual outlining of β-cells, involve multiple software packages, and necessitate multiple researchers-all of which tend to introduce biases. Utilizing deep learning algorithms, we have therefore created a pipeline to automatically segment and track thousands of cells, which greatly reduces the time required to gather and analyze a large number of sub-cellular images and improve accuracy. Tracking cells over a time-series image stack also allows researchers to isolate specific calcium spiking patterns and spatially identify those of interest, creating an efficient and user-friendly analysis tool. Using our automated pipeline, a previous dataset used to evaluate changes in calcium spiking activity in β-cells post-electric field stimulation was reanalyzed. Changes in spiking activity were found to be underestimated previously with manual segmentation. Moreover, the machine learning pipeline provides a powerful and rapid computational approach to examine, for example, how calcium signaling is regulated by intracellular interactions.
Collapse
Affiliation(s)
- Anne M. Alsup
- Department of Bioengineering, University of Texas at Arlington, Arlington, TX, United States of America
| | - Kelli Fowlds
- Department of Bioengineering, University of Texas at Arlington, Arlington, TX, United States of America
| | - Michael Cho
- Department of Bioengineering, University of Texas at Arlington, Arlington, TX, United States of America
| | - Jacob M. Luber
- Department of Bioengineering, University of Texas at Arlington, Arlington, TX, United States of America
- Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, United States of America
- Multi-Interprofessional Center for Health Informatics, University of Texas at Arlington, Arlington, TX, United States of America
| |
Collapse
|
3
|
Alexeree SMI, Abou-Seri HM, El-Din HES, Youssef D, Ramadan MA. Green synthesis of silver and iron oxide nanoparticles mediated photothermal effects on Blastocystis hominis. Lasers Med Sci 2024; 39:43. [PMID: 38246979 PMCID: PMC10800310 DOI: 10.1007/s10103-024-03984-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Accepted: 01/05/2024] [Indexed: 01/23/2024]
Abstract
The evolution of parasite resistance to antiparasitic agents has become a serious health issue indicating a critical and pressing need to develop new therapeutics that can conquer drug resistance. Nanoparticles are novel, promising emerging drug carriers that have demonstrated efficiency in treating many parasitic diseases. Lately, attention has been drawn to a broad-spectrum nanoparticle capable of converting absorbed light into heat via the photothermal effect phenomenon. The present study is the first to assess the effect of silver nanoparticles (Ag NPs) and iron oxide nanoparticles (Fe3O4 NPs) as sole agents and with the combined action of the light-emitting diode (LED) on Blastocystis hominins (B. hominis) in vitro. Initially, the aqueous synthesized nanoparticles were characterized by UV-Vis spectroscopy, zeta potential, and transmission electron microscopy (TEM). The anti-blastocyst efficiency of these NPs was tested separately in dark conditions. As these NPs have a wide absorption spectrum in the visible regions, they were also excited by a continuous wave LED of wavelength band (400-700 nm) to test the photothermal effect. The sensitivity of B. hominis cysts was evaluated using scanning laser confocal microscopy whereas the live and dead cells were accurately segmented based on superpixels and the k-mean clustering algorithm. Our findings showed that this excitation led to hyperthermia that induced a significant reduction in the number of cysts treated with photothermally active NPs. The results of this study elucidate the potential role of photothermally active NPs as an effective anti-blastocystis agent. By using this approach, new therapeutic antiparasitic agents can be developed.
Collapse
Affiliation(s)
- Shaimaa M I Alexeree
- Department of Laser Application in Metrology, Photochemistry, and Agricultural, National Institute of Laser Enhanced Science, Cairo University, Giza, Egypt.
| | - Hanan M Abou-Seri
- Department of Parasitology, Faculty of Medicine, Ain Shams University, Cairo, Egypt
| | - Hala E Shams El-Din
- Department of Parasitology, Faculty of Medicine, Ain Shams University, Cairo, Egypt
| | - Doaa Youssef
- Department of Engineering Applications of Lasers, National Institute of Laser Enhanced Science, Cairo University, Giza, Egypt
| | - Marwa A Ramadan
- Department of Laser Application in Metrology, Photochemistry, and Agricultural, National Institute of Laser Enhanced Science, Cairo University, Giza, Egypt
| |
Collapse
|
4
|
Stine JS, Aziere N, Harper BJ, Harper SL. A Novel Approach for Identifying Nanoplastics by Assessing Deformation Behavior with Scanning Electron Microscopy. MICROMACHINES 2023; 14:1903. [PMID: 37893340 PMCID: PMC10609349 DOI: 10.3390/mi14101903] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/02/2023] [Revised: 09/27/2023] [Accepted: 10/04/2023] [Indexed: 10/29/2023]
Abstract
As plastic production continues to increase globally, plastic waste accumulates and degrades into smaller plastic particles. Through chemical and biological processes, nanoscale plastic particles (nanoplastics) are formed and are expected to exist in quantities of several orders of magnitude greater than those found for microplastics. Due to their small size and low mass, nanoplastics remain challenging to detect in the environment using most standard analytical methods. The goal of this research is to adapt existing tools to address the analytical challenges posed by the identification of nanoplastics. Given the unique and well-documented properties of anthropogenic plastics, we hypothesized that nanoplastics could be differentiated by polymer type using spatiotemporal deformation data collected through irradiation with scanning electron microscopy (SEM). We selected polyvinyl chloride (PVC), polyethylene terephthalate (PET), and high-density polyethylene (HDPE) to capture a range of thermodynamic properties and molecular structures encompassed by commercially available plastics. Pristine samples of each polymer type were chosen and individually milled to generate micro and nanoscale particles for SEM analysis. To test the hypothesis that polymers could be differentiated from other constituents in complex samples, the polymers were compared against proxy materials common in environmental media, i.e., algae, kaolinite clay, and nanocellulose. Samples for SEM analysis were prepared uncoated to enable observation of polymer deformation under set electron beam parameters. For each sample type, particles approximately 1 µm in diameter were chosen, and videos of particle deformation were recorded and studied. Blinded samples were also prepared with mixtures of the aforementioned materials to test the viability of this method for identifying near-nanoscale plastic particles in environmental media. Based on the evidence collected, deformation patterns between plastic particles and particles present in common environmental media show significant differences. A computer vision algorithm was also developed and tested against manual measurements to improve the usefulness and efficiency of this method further.
Collapse
Affiliation(s)
- Jared S. Stine
- School of Chemical, Biological and Environmental Engineering, Oregon State University, Corvallis, OR 97331, USA;
- Department of Environmental and Molecular Toxicology, Oregon State University, Corvallis, OR 97331, USA;
| | - Nicolas Aziere
- School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, OR 97331, USA;
| | - Bryan J. Harper
- Department of Environmental and Molecular Toxicology, Oregon State University, Corvallis, OR 97331, USA;
| | - Stacey L. Harper
- School of Chemical, Biological and Environmental Engineering, Oregon State University, Corvallis, OR 97331, USA;
- Department of Environmental and Molecular Toxicology, Oregon State University, Corvallis, OR 97331, USA;
| |
Collapse
|
5
|
Fanucci KA, Bai Y, Pelekanou V, Nahleh ZA, Shafi S, Burela S, Barlow WE, Sharma P, Thompson AM, Godwin AK, Rimm DL, Hortobagyi GN, Liu Y, Wang L, Wei W, Pusztai L, Blenman KRM. Image analysis-based tumor infiltrating lymphocytes measurement predicts breast cancer pathologic complete response in SWOG S0800 neoadjuvant chemotherapy trial. NPJ Breast Cancer 2023; 9:38. [PMID: 37179362 PMCID: PMC10182981 DOI: 10.1038/s41523-023-00535-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2022] [Accepted: 04/11/2023] [Indexed: 05/15/2023] Open
Abstract
We assessed the predictive value of an image analysis-based tumor-infiltrating lymphocytes (TILs) score for pathologic complete response (pCR) and event-free survival in breast cancer (BC). About 113 pretreatment samples were analyzed from patients with stage IIB-IIIC HER-2-negative BC randomized to neoadjuvant chemotherapy ± bevacizumab. TILs quantification was performed on full sections using QuPath open-source software with a convolutional neural network cell classifier (CNN11). We used easTILs% as a digital metric of TILs score defined as [sum of lymphocytes area (mm2)/stromal area(mm2)] × 100. Pathologist-read stromal TILs score (sTILs%) was determined following published guidelines. Mean pretreatment easTILs% was significantly higher in cases with pCR compared to residual disease (median 36.1 vs.14.8%, p < 0.001). We observed a strong positive correlation (r = 0.606, p < 0.0001) between easTILs% and sTILs%. The area under the prediction curve (AUC) was higher for easTILs% than sTILs%, 0.709 and 0.627, respectively. Image analysis-based TILs quantification is predictive of pCR in BC and had better response discrimination than pathologist-read sTILs%.
Collapse
Affiliation(s)
- Kristina A Fanucci
- Department of Internal Medicine Section of Medical Oncology and Yale Cancer Center, Yale School of Medicine, 333 Cedar St, New Haven, CT, 06520, USA
| | - Yalai Bai
- Department of Pathology, Yale School of Medicine, 310 Cedar St, New Haven, CT, 06520, USA
| | - Vasiliki Pelekanou
- Department of Pathology, Yale School of Medicine, 310 Cedar St, New Haven, CT, 06520, USA
- Bayer Pharmaceuticals, 245 First St Cambridge Science Center 100 and 200 Floors 1 and 2, Cambridge, MA, 02142, USA
| | - Zeina A Nahleh
- Department of Hematology/Oncology, Cleveland Clinic Florida, Maroone Cancer Center, 2950 Cleveland Clinic Blvd, Weston, FL, 33331, USA
| | - Saba Shafi
- Department of Pathology, Yale School of Medicine, 310 Cedar St, New Haven, CT, 06520, USA
- Department of Pathology, Ohio State University, 6100 Optometry Clinic & Health Sciences Faculty Office Building, 1664 Neil Avenue, Columbus, OH, 43210, USA
| | - Sneha Burela
- Department of Pathology, Yale School of Medicine, 310 Cedar St, New Haven, CT, 06520, USA
| | - William E Barlow
- SWOG Statistics and Data Management Center, 1730 Minor Avenue Suite 1900, Seattle, WA, 98101, USA
| | - Priyanka Sharma
- Department of Medical Oncology, University of Kansas Medical Center, 3901 Rainbow Boulevard, Kansas City, KS, 66160, USA
| | - Alastair M Thompson
- Section of Breast Surgery, 1 Baylor Plaza, Baylor College of Medicine, Houston, TX, 77030, USA
| | - Andrew K Godwin
- Department of Medical Oncology, University of Kansas Medical Center, 3901 Rainbow Boulevard, Kansas City, KS, 66160, USA
| | - David L Rimm
- Department of Pathology, Yale School of Medicine, 310 Cedar St, New Haven, CT, 06520, USA
| | - Gabriel N Hortobagyi
- Department of Breast Medical Oncology, MD Anderson Cancer Center, 1515 Holcombe Blvd, Houston, TX, 77030, USA
| | - Yihan Liu
- Department of Biostatistics, Yale School of Public Health, 60 College Street, New Haven, CT, 06520, USA
| | - Leona Wang
- Department of Biostatistics, Yale School of Public Health, 60 College Street, New Haven, CT, 06520, USA
| | - Wei Wei
- Department of Biostatistics, Yale School of Public Health, 60 College Street, New Haven, CT, 06520, USA
| | - Lajos Pusztai
- Department of Internal Medicine Section of Medical Oncology and Yale Cancer Center, Yale School of Medicine, 333 Cedar St, New Haven, CT, 06520, USA
| | - Kim R M Blenman
- Department of Internal Medicine Section of Medical Oncology and Yale Cancer Center, Yale School of Medicine, 333 Cedar St, New Haven, CT, 06520, USA.
- Department of Computer Science, Yale School of Engineering and Applied Science, 17 Hillhouse Avenue, New Haven, CT, 06520, USA.
| |
Collapse
|
6
|
Alsup AM, Fowlds K, Cho M, Luber JM. BetaBuddy: An end-to-end computer vision pipeline for the automated analysis of insulin secreting β-cells. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.04.06.535890. [PMID: 37066375 PMCID: PMC10104060 DOI: 10.1101/2023.04.06.535890] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/18/2023]
Abstract
Insulin secretion from pancreatic β-cells is integral in maintaining the delicate equilibrium of blood glucose levels. Calcium is known to be a key regulator and triggers the release of insulin. This sub-cellular process can be monitored and tracked through live-cell imaging and subsequent cell segmentation, registration, tracking, and analysis of the calcium level in each cell. Current methods of analysis typically require the manual outlining of β-cells, involve multiple software packages, and necessitate multiple researchers - all of which tend to introduce biases. Utilizing deep learning algorithms, we have therefore created a pipeline to automatically segment and track thousands of cells, which greatly reduces the time required to gather and analyze a large number of sub-cellular images and improve accuracy. Tracking cells over a time-series image stack also allows researchers to isolate specific calcium spiking patterns and spatially identify those of interest, creating an efficient and user-friendly analysis tool. Using our automated pipeline, a previous dataset used to evaluate changes in calcium spiking activity in β-cells post-electric field stimulation was reanalyzed. Changes in spiking activity were found to be underestimated previously with manual segmentation. Moreover, the machine learning pipeline provides a powerful and rapid computational approach to examine, for example, how calcium signaling is regulated by intracellular interactions in a cluster of β-cells.
Collapse
Affiliation(s)
- Anne M. Alsup
- Department of Bioengineering, University of Texas at Arlington, Arlington, TX, United States of America
| | - Kelli Fowlds
- Department of Bioengineering, University of Texas at Arlington, Arlington, TX, United States of America
| | - Michael Cho
- Department of Bioengineering, University of Texas at Arlington, Arlington, TX, United States of America
| | - Jacob M. Luber
- Department of Bioengineering, University of Texas at Arlington, Arlington, TX, United States of America
- Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, United States of America
- Multi-Interprofessional Center for Health Informatics, University of Texas at Arlington, Arlington, TX, United States of America
| |
Collapse
|
7
|
Verdicchio M, Brancato V, Cavaliere C, Isgrò F, Salvatore M, Aiello M. A pathomic approach for tumor-infiltrating lymphocytes classification on breast cancer digital pathology images. Heliyon 2023; 9:e14371. [PMID: 36950640 PMCID: PMC10025040 DOI: 10.1016/j.heliyon.2023.e14371] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2023] [Revised: 03/03/2023] [Accepted: 03/03/2023] [Indexed: 03/11/2023] Open
Abstract
Background and objectives The detection of tumor-infiltrating lymphocytes (TILs) could aid in the development of objective measures of the infiltration grade and can support decision-making in breast cancer (BC). However, manual quantification of TILs in BC histopathological whole slide images (WSI) is currently based on a visual assessment, thus resulting not standardized, not reproducible, and time-consuming for pathologists. In this work, a novel pathomic approach, aimed to apply high-throughput image feature extraction techniques to analyze the microscopic patterns in WSI, is proposed. In fact, pathomic features provide additional information concerning the underlying biological processes compared to the WSI visual interpretation, thus providing more easily interpretable and explainable results than the most frequently investigated Deep Learning based methods in the literature. Methods A dataset containing 1037 regions of interest with tissue compartments and TILs annotated on 195 TNBC and HER2+ BC hematoxylin and eosin (H&E)-stained WSI was used. After segmenting nuclei within tumor-associated stroma using a watershed-based approach, 71 pathomic features were extracted from each nucleus and reduced using a Spearman's correlation filter followed by a nonparametric Wilcoxon rank-sum test and least absolute shrinkage and selection operator. The relevant features were used to classify each candidate nucleus as either TILs or non-TILs using 5 multivariable machine learning classification models trained using 5-fold cross-validation (1) without resampling, (2) with the synthetic minority over-sampling technique and (3) with downsampling. The prediction performance of the models was assessed using ROC curves. Results 21 features were selected, with most of them related to the well-known TILs properties of having regular shape, clearer margins, high peak intensity, more homogeneous enhancement and different textural pattern than other cells. The best performance was obtained by Random-Forest with ROC AUC of 0.86, regardless of resampling technique. Conclusions The presented approach holds promise for the classification of TILs in BC H&E-stained WSI and could provide support to pathologists for a reliable, rapid and interpretable clinical assessment of TILs in BC.
Collapse
Affiliation(s)
| | - Valentina Brancato
- IRCCS SYNLAB SDN, Via E. Gianturco 113, Naples, 80143, Italy
- Corresponding author.
| | - Carlo Cavaliere
- IRCCS SYNLAB SDN, Via E. Gianturco 113, Naples, 80143, Italy
| | - Francesco Isgrò
- Department of Electrical Engineering and Information Technologies, University of Naples Federico II, Claudio 21, Naples, 80125, Italy
| | - Marco Salvatore
- IRCCS SYNLAB SDN, Via E. Gianturco 113, Naples, 80143, Italy
| | - Marco Aiello
- IRCCS SYNLAB SDN, Via E. Gianturco 113, Naples, 80143, Italy
| |
Collapse
|
8
|
Kalinathan L, Kathavarayan RS. Segmentation of Multiple Nuclei from Non-overlapping Immuno-histochemically Stained Histological Hepatic Images. J Digit Imaging 2023; 36:231-239. [PMID: 35918474 PMCID: PMC9984616 DOI: 10.1007/s10278-022-00688-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2021] [Revised: 07/23/2021] [Accepted: 07/19/2022] [Indexed: 10/16/2022] Open
Abstract
In this paper, we describe an algorithm for accurately segmenting multiple nudfclei from clumps of non-overlapping immuno-histochemically stained histological hepatic (liver) images. This problem is notoriously difficult because of the degree of presence of stains among the multi-nucleated cells, the poor contrast of cell cytoplasm, and the presence of mucus, blood, and inflammatory cells in the images. Hepatocellular carcinoma, characterized by cellular and nuclear enlargement, nuclear pleomorphism, and multi-nucleation, poses a prominent threat. Our proposed method addresses the aforementioned issues for an automated diagnosis system by judging the presence of multiple nuclei in a two-step process: the Quickhull algorithm defines the convex hull of each cell in the image and candidate nuclei regions are located with morphological operations. A combination of features containing local minima and shape-dependent features is extracted for the detection of single or multiple nuclei in each cell with a significant reduction in the number of false positives and false negatives providing an accuracy of 89.76%.
Collapse
Affiliation(s)
- Lekshmi Kalinathan
- Sri Sivasubramaniya Nadar College of Engineering, Anna University, Chennai, India
| | | |
Collapse
|
9
|
Chen S, Ding C, Liu M, Cheng J, Tao D. CPP-Net: Context-aware Polygon Proposal Network for Nucleus Segmentation. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2023; PP:980-994. [PMID: 37022023 DOI: 10.1109/tip.2023.3237013] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
Nucleus segmentation is a challenging task due to the crowded distribution and blurry boundaries of nuclei. To differentiate between touching and overlapping nuclei, recent approaches have represented nuclei in the form of polygons, and have accordingly achieved promising performance. Each polygon is represented by a set of centroid-to-boundary distances, which are in turn predicted by features of the centroid pixel for a single nucleus. However, the use of the centroid pixel alone does not provide sufficient contextual information for robust prediction and therefore affects the segmentation accuracy. To address this problem, we propose a Context-aware Polygon Proposal Network (CPP-Net) for nucleus segmentation. First, we sample a point set rather than a single pixel within each cell for distance prediction; this strategy substantially enhances the contextual information and thereby improves the prediction robustness. Second, we propose a Confidence-basedWeighting Module, which adaptively fuses the predictions from the sampled point set. Third, we introduce a novel Shape-Aware Perceptual (SAP) loss that constrains the shape of the predicted polygons. This SAP loss is based on an additional network that is pre-trained by means of mapping the centroid probability map and the pixel-to-boundary distance maps to a different nucleus representation. Extensive experiments demonstrate the effectiveness of each component in the proposed CPP-Net. Finally, CPP-Net is found to achieve state-of-the-art performance on three publicly available databases, namely DSB2018, BBBC06, and PanNuke. The code of this paper will be released.
Collapse
|
10
|
Grijalva Garces D, Radtke CP, Hubbuch J. A Novel Approach for the Manufacturing of Gelatin-Methacryloyl. Polymers (Basel) 2022; 14:polym14245424. [PMID: 36559791 PMCID: PMC9786334 DOI: 10.3390/polym14245424] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Revised: 11/26/2022] [Accepted: 12/09/2022] [Indexed: 12/14/2022] Open
Abstract
Gelatin and its derivatives contain cell adhesion moieties as well as sites that enable proteolytic degradation, thus allowing cellular proliferation and migration. The processing of gelatin to its derivatives and/or gelatin-containing products is challenged by its gelation below 30 ∘C. In this study, a novel strategy was developed for the dissolution and subsequent modification of gelatin to its derivative gelatin-methacryloyl (GelMA). This approach was based on the presence of urea in the buffer media, which enabled the processing at room temperature, i.e., lower than the sol-gel transition point of the gelatin solutions. The degree of functionalization was controlled by the ratio of reactant volume to the gelatin concentration. Hydrogels with tailored mechanical properties were produced by variations of the GelMA concentration and its degree of functionalization. Moreover, the biocompatibility of hydrogels was assessed and compared to hydrogels formulated with GelMA produced by the conventional method. NIH 3T3 fibroblasts were seeded onto hydrogels and the viability showed no difference from the control after a three-day incubation period.
Collapse
Affiliation(s)
- David Grijalva Garces
- Institute of Functional Interfaces, Karlsruhe Institute of Technology, 76344 Eggenstein-Leopoldshafen, Germany
- Institute of Process Engineering in Life Sciences Section IV: Biomolecular Separation Engineering, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
| | - Carsten Philipp Radtke
- Institute of Process Engineering in Life Sciences Section IV: Biomolecular Separation Engineering, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
| | - Jürgen Hubbuch
- Institute of Functional Interfaces, Karlsruhe Institute of Technology, 76344 Eggenstein-Leopoldshafen, Germany
- Institute of Process Engineering in Life Sciences Section IV: Biomolecular Separation Engineering, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
- Correspondence:
| |
Collapse
|
11
|
Utility of Fluorescence In Situ Hybridization in Clinical and Research Applications. Clin Lab Med 2022; 42:573-586. [PMID: 36368783 DOI: 10.1016/j.cll.2022.09.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|
12
|
Qureshi MH, Ozlu N, Bayraktar H. Adaptive tracking algorithm for trajectory analysis of cells and layer-by-layer assessment of motility dynamics. Comput Biol Med 2022; 150:106193. [PMID: 37859286 DOI: 10.1016/j.compbiomed.2022.106193] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2022] [Revised: 09/26/2022] [Accepted: 10/08/2022] [Indexed: 11/03/2022]
Abstract
Tracking biological objects such as cells or subcellular components imaged with time-lapse microscopy enables us to understand the molecular principles about the dynamics of cell behaviors. However, automatic object detection, segmentation and extracting trajectories remain as a rate-limiting step due to intrinsic challenges of video processing. This paper presents an adaptive tracking algorithm (Adtari) that automatically finds the optimum search radius and cell linkages to determine trajectories in consecutive frames. A critical assumption in most tracking studies is that displacement remains unchanged throughout the movie and cells in a few frames are usually analyzed to determine its magnitude. Tracking errors and inaccurate association of cells may occur if the user does not correctly evaluate the value or prior knowledge is not present on cell movement. The key novelty of our method is that minimum intercellular distance and maximum displacement of cells between frames are dynamically computed and used to determine the threshold distance. Since the space between cells is highly variable in a given frame, our software recursively alters the magnitude to determine all plausible matches in the trajectory analysis. Our method therefore eliminates a major preprocessing step where a constant distance was used to determine the neighbor cells in tracking methods. Cells having multiple overlaps and splitting events were further evaluated by using the shape attributes including perimeter, area, ellipticity and distance. The features were applied to determine the closest matches by minimizing the difference in their magnitudes. Finally, reporting section of our software were used to generate instant maps by overlaying cell features and trajectories. Adtari was validated by using videos with variable signal-to-noise, contrast ratio and cell density. We compared the adaptive tracking with constant distance and other methods to evaluate performance and its efficiency. Our algorithm yields reduced mismatch ratio, increased ratio of whole cell track, higher frame tracking efficiency and allows layer-by-layer assessment of motility to characterize single-cells. Adaptive tracking provides a reliable, accurate, time efficient and user-friendly open source software that is well suited for analysis of 2D fluorescence microscopy video datasets.
Collapse
Affiliation(s)
- Mohammad Haroon Qureshi
- Department of Molecular Biology and Genetics, Koç University, Rumelifeneri Yolu, Sariyer, 34450, Istanbul, Turkey; Center for Translational Research, Koç University, Rumelifeneri Yolu, Sariyer, 34450, Istanbul, Turkey
| | - Nurhan Ozlu
- Department of Molecular Biology and Genetics, Koç University, Rumelifeneri Yolu, Sariyer, 34450, Istanbul, Turkey
| | - Halil Bayraktar
- Department of Molecular Biology and Genetics, Istanbul Technical University, Maslak, Sariyer, 34467, Istanbul, Turkey.
| |
Collapse
|
13
|
Brancato V, Cavaliere C, Garbino N, Isgrò F, Salvatore M, Aiello M. The relationship between radiomics and pathomics in Glioblastoma patients: Preliminary results from a cross-scale association study. Front Oncol 2022; 12:1005805. [PMID: 36276163 PMCID: PMC9582951 DOI: 10.3389/fonc.2022.1005805] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2022] [Accepted: 09/21/2022] [Indexed: 12/01/2022] Open
Abstract
Glioblastoma multiforme (GBM) typically exhibits substantial intratumoral heterogeneity at both microscopic and radiological resolution scales. Diffusion Weighted Imaging (DWI) and dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) are two functional MRI techniques that are commonly employed in clinic for the assessment of GBM tumor characteristics. This work presents initial results aiming at determining if radiomics features extracted from preoperative ADC maps and post-contrast T1 (T1C) images are associated with pathomic features arising from H&E digitized pathology images. 48 patients from the public available CPTAC-GBM database, for which both radiology and pathology images were available, were involved in the study. 91 radiomics features were extracted from ADC maps and post-contrast T1 images using PyRadiomics. 65 pathomic features were extracted from cell detection measurements from H&E images. Moreover, 91 features were extracted from cell density maps of H&E images at four different resolutions. Radiopathomic associations were evaluated by means of Spearman's correlation (ρ) and factor analysis. p values were adjusted for multiple correlations by using a false discovery rate adjustment. Significant cross-scale associations were identified between pathomics and ADC, both considering features (n = 186, 0.45 < ρ < 0.74 in absolute value) and factors (n = 5, 0.48 < ρ < 0.54 in absolute value). Significant but fewer ρ values were found concerning the association between pathomics and radiomics features (n = 53, 0.5 < ρ < 0.65 in absolute value) and factors (n = 2, ρ = 0.63 and ρ = 0.53 in absolute value). The results of this study suggest that cross-scale associations may exist between digital pathology and ADC and T1C imaging. This can be useful not only to improve the knowledge concerning GBM intratumoral heterogeneity, but also to strengthen the role of radiomics approach and its validation in clinical practice as "virtual biopsy", introducing new insights for omics integration toward a personalized medicine approach.
Collapse
Affiliation(s)
| | | | | | - Francesco Isgrò
- Department of Electrical Engineering and Information Technologies, University of Napoli Federico II, Napoli, Italy
| | | | | |
Collapse
|
14
|
Acs B, Leung SCY, Kidwell KM, Arun I, Augulis R, Badve SS, Bai Y, Bane AL, Bartlett JMS, Bayani J, Bigras G, Blank A, Buikema H, Chang MC, Dietz RL, Dodson A, Fineberg S, Focke CM, Gao D, Gown AM, Gutierrez C, Hartman J, Kos Z, Lænkholm AV, Laurinavicius A, Levenson RM, Mahboubi-Ardakani R, Mastropasqua MG, Nofech-Mozes S, Osborne CK, Penault-Llorca FM, Piper T, Quintayo MA, Rau TT, Reinhard S, Robertson S, Salgado R, Sugie T, van der Vegt B, Viale G, Zabaglo LA, Hayes DF, Dowsett M, Nielsen TO, Rimm DL. Systematically higher Ki67 scores on core biopsy samples compared to corresponding resection specimen in breast cancer: a multi-operator and multi-institutional study. Mod Pathol 2022; 35:1362-1369. [PMID: 35729220 PMCID: PMC9514990 DOI: 10.1038/s41379-022-01104-9] [Citation(s) in RCA: 17] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Revised: 04/11/2022] [Accepted: 05/05/2022] [Indexed: 02/06/2023]
Abstract
Ki67 has potential clinical importance in breast cancer but has yet to see broad acceptance due to inter-laboratory variability. Here we tested an open source and calibrated automated digital image analysis (DIA) platform to: (i) investigate the comparability of Ki67 measurement across corresponding core biopsy and resection specimen cases, and (ii) assess section to section differences in Ki67 scoring. Two sets of 60 previously stained slides containing 30 core-cut biopsy and 30 corresponding resection specimens from 30 estrogen receptor-positive breast cancer patients were sent to 17 participating labs for automated assessment of average Ki67 expression. The blocks were centrally cut and immunohistochemically (IHC) stained for Ki67 (MIB-1 antibody). The QuPath platform was used to evaluate tumoral Ki67 expression. Calibration of the DIA method was performed as in published studies. A guideline for building an automated Ki67 scoring algorithm was sent to participating labs. Very high correlation and no systematic error (p = 0.08) was found between consecutive Ki67 IHC sections. Ki67 scores were higher for core biopsy slides compared to paired whole sections from resections (p ≤ 0.001; median difference: 5.31%). The systematic discrepancy between core biopsy and corresponding whole sections was likely due to pre-analytical factors (tissue handling, fixation). Therefore, Ki67 IHC should be tested on core biopsy samples to best reflect the biological status of the tumor.
Collapse
Affiliation(s)
- Balazs Acs
- Department of Pathology, Yale University School of Medicine, New Haven, CT, USA.
- Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden.
- Department of Clinical Pathology and Cancer Diagnostics, Karolinska University Hospital, Stockholm, Sweden.
| | | | - Kelley M Kidwell
- Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, MI, USA
| | - Indu Arun
- Tata Medical Center, Kolkata, West Bengal, India
| | - Renaldas Augulis
- Vilnius University Faculty of Medicine and National Center of Pathology, Vilnius University Hospital Santaros Clinics, Vilnius, Lithuania
| | - Sunil S Badve
- Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, GA, USA
| | - Yalai Bai
- Department of Pathology, Yale University School of Medicine, New Haven, CT, USA
| | - Anita L Bane
- Juravinski Hospital and Cancer Centre, McMaster University, Hamilton, ON, Canada
| | - John M S Bartlett
- Ontario Institute for Cancer Research, Toronto, ON, Canada
- Edinburgh Cancer Research Centre, Western General Hospital, Edinburgh, United Kingdom
| | - Jane Bayani
- Ontario Institute for Cancer Research, Toronto, ON, Canada
| | - Gilbert Bigras
- Department of Laboratory Medicine and Pathology, University of Alberta, Edmonton, AB, Canada
| | - Annika Blank
- Institute of Pathology, University of Bern, Bern, Switzerland
- Institute of Pathology, Triemli Hospital Zurich, Zurich, Switzerland
| | - Henk Buikema
- University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Martin C Chang
- Department of Pathology & Laboratory Medicine, University of Vermont Medical Center, Burlington, VT, USA
| | - Robin L Dietz
- Department of Pathology, Olive View-UCLA Medical Center, Los Angeles, CA, USA
| | - Andrew Dodson
- UK NEQAS for Immunocytochemistry and In-Situ Hybridisation, London, United Kingdom
| | - Susan Fineberg
- Montefiore Medical Center and the Albert Einstein College of Medicine, Bronx, NY, USA
| | - Cornelia M Focke
- Dietrich-Bonhoeffer Medical Center, Neubrandenburg, Mecklenburg-Vorpommern, Germany
| | - Dongxia Gao
- University of British Columbia, Vancouver, BC, Canada
| | | | - Carolina Gutierrez
- Lester and Sue Smith Breast Center and Dan L. Duncan Comprehensive Cancer Center, Baylor College of Medicine, Houston, TX, USA
| | - Johan Hartman
- Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden
- Department of Clinical Pathology and Cancer Diagnostics, Karolinska University Hospital, Stockholm, Sweden
| | - Zuzana Kos
- Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, BC, Canada
| | - Anne-Vibeke Lænkholm
- Department of Surgical Pathology, Zealand University Hospital, Roskilde, Denmark
| | - Arvydas Laurinavicius
- Vilnius University Faculty of Medicine and National Center of Pathology, Vilnius University Hospital Santaros Clinics, Vilnius, Lithuania
| | - Richard M Levenson
- Department of Medical Pathology and Laboratory Medicine, University of California Davis Medical Center, Sacramento, CA, USA
| | - Rustin Mahboubi-Ardakani
- Department of Medical Pathology and Laboratory Medicine, University of California Davis Medical Center, Sacramento, CA, USA
| | | | - Sharon Nofech-Mozes
- University of Toronto Sunnybrook Health Sciences Centre, Toronto, ON, Canada
| | - C Kent Osborne
- Lester and Sue Smith Breast Center and Dan L. Duncan Comprehensive Cancer Center, Baylor College of Medicine, Houston, TX, USA
| | - Frédérique M Penault-Llorca
- Imagerie Moléculaire et Stratégies Théranostiques, UMR1240, Université Clermont Auvergne, INSERM, Clermont-Ferrand, France
- Service de Pathologie, Centre Jean PERRIN, Clermont-Ferrand, France
| | - Tammy Piper
- Edinburgh Cancer Research Centre, Western General Hospital, Edinburgh, United Kingdom
| | | | - Tilman T Rau
- Institute of Pathology, University of Bern, Bern, Switzerland
- Institute of Pathology, Heinrich Heine University and University Hospital of Duesseldorf, Duesseldorf, Germany
| | - Stefan Reinhard
- Institute of Pathology, University of Bern, Bern, Switzerland
| | - Stephanie Robertson
- Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden
- Department of Clinical Pathology and Cancer Diagnostics, Karolinska University Hospital, Stockholm, Sweden
| | - Roberto Salgado
- Department of Pathology, GZA-ZNA, Antwerp, Belgium
- Peter MacCallum Cancer Centre, University of Melbourne, Melbourne, VIC, Australia
| | | | - Bert van der Vegt
- University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Giuseppe Viale
- European Institute of Oncology, Milan, Italy
- European Institute of Oncology IRCCS, and University of Milan, Milan, Italy
| | - Lila A Zabaglo
- The Institute of Cancer Research, London, United Kingdom
| | - Daniel F Hayes
- University of Michigan Rogel Cancer Center, Ann Arbor, MI, USA
| | - Mitch Dowsett
- The Institute of Cancer Research, London, United Kingdom
| | | | - David L Rimm
- Department of Pathology, Yale University School of Medicine, New Haven, CT, USA.
| | | |
Collapse
|
15
|
Friebel A, Johann T, Drasdo D, Hoehme S. Guided interactive image segmentation using machine learning and color-based image set clustering. Bioinformatics 2022; 38:4622-4628. [PMID: 35976110 PMCID: PMC9525009 DOI: 10.1093/bioinformatics/btac547] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2021] [Revised: 03/04/2022] [Indexed: 12/24/2022] Open
Abstract
MOTIVATION Over the last decades, image processing and analysis have become one of the key technologies in systems biology and medicine. The quantification of anatomical structures and dynamic processes in living systems is essential for understanding the complex underlying mechanisms and allows, i.e. the construction of spatio-temporal models that illuminate the interplay between architecture and function. Recently, deep learning significantly improved the performance of traditional image analysis in cases where imaging techniques provide large amounts of data. However, if only a few images are available or qualified annotations are expensive to produce, the applicability of deep learning is still limited. RESULTS We present a novel approach that combines machine learning-based interactive image segmentation using supervoxels with a clustering method for the automated identification of similarly colored images in large image sets which enables a guided reuse of interactively trained classifiers. Our approach solves the problem of deteriorated segmentation and quantification accuracy when reusing trained classifiers which is due to significant color variability prevalent and often unavoidable in biological and medical images. This increase in efficiency improves the suitability of interactive segmentation for larger image sets, enabling efficient quantification or the rapid generation of training data for deep learning with minimal effort. The presented methods are applicable for almost any image type and represent a useful tool for image analysis tasks in general. AVAILABILITY AND IMPLEMENTATION The presented methods are implemented in our image processing software TiQuant which is freely available at tiquant.hoehme.com. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Adrian Friebel
- Institute of Computer Science, Leipzig University, Leipzig 04107, Germany
| | - Tim Johann
- IfADo—Leibniz Research Centre for Working Environment and Human Factors, Dortmund 44139, Germany
| | - Dirk Drasdo
- IfADo—Leibniz Research Centre for Working Environment and Human Factors, Dortmund 44139, Germany,INRIA Saclay-Île de France, Group SIMBIOTX, Palaiseau 91120, France
| | | |
Collapse
|
16
|
Jiang Q, Sudalagunta P, Silva MC, Canevarolo RR, Zhao X, Ahmed KT, Alugubelli RR, DeAvila G, Tungesvik A, Perez L, Gatenby RA, Gillies RJ, Baz R, Meads MB, Shain KH, Silva AS, Zhang W. CancerCellTracker: a brightfield time-lapse microscopy framework for cancer drug sensitivity estimation. Bioinformatics 2022; 38:4002-4010. [PMID: 35751591 PMCID: PMC9991899 DOI: 10.1093/bioinformatics/btac417] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2022] [Revised: 05/18/2022] [Accepted: 06/22/2022] [Indexed: 12/24/2022] Open
Abstract
MOTIVATION Time-lapse microscopy is a powerful technique that relies on images of live cells cultured ex vivo that are captured at regular intervals of time to describe and quantify their behavior under certain experimental conditions. This imaging method has great potential in advancing the field of precision oncology by quantifying the response of cancer cells to various therapies and identifying the most efficacious treatment for a given patient. Digital image processing algorithms developed so far require high-resolution images involving very few cells originating from homogeneous cell line populations. We propose a novel framework that tracks cancer cells to capture their behavior and quantify cell viability to inform clinical decisions in a high-throughput manner. RESULTS The brightfield microscopy images a large number of patient-derived cells in an ex vivo reconstruction of the tumor microenvironment treated with 31 drugs for up to 6 days. We developed a robust and user-friendly pipeline CancerCellTracker that detects cells in co-culture, tracks these cells across time and identifies cell death events using changes in cell attributes. We validated our computational pipeline by comparing the timing of cell death estimates by CancerCellTracker from brightfield images and a fluorescent channel featuring ethidium homodimer. We benchmarked our results using a state-of-the-art algorithm implemented in ImageJ and previously published in the literature. We highlighted CancerCellTracker's efficiency in estimating the percentage of live cells in the presence of bone marrow stromal cells. AVAILABILITY AND IMPLEMENTATION https://github.com/compbiolabucf/CancerCellTracker. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Qibing Jiang
- Department of Computer Science, University of Central Florida, Orlando, FL 32816, USA
| | - Praneeth Sudalagunta
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Maria C Silva
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Rafael R Canevarolo
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Xiaohong Zhao
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | | | - Raghunandan Reddy Alugubelli
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Gabriel DeAvila
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Alexandre Tungesvik
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Lia Perez
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Robert A Gatenby
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Robert J Gillies
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Rachid Baz
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Mark B Meads
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Kenneth H Shain
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Ariosto S Silva
- Departments of Malignant Hematology and Chemical Biology and Molecular Medicine, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA
| | - Wei Zhang
- Department of Computer Science, University of Central Florida, Orlando, FL 32816, USA
| |
Collapse
|
17
|
Chand S. Semantic segmentation of human cell nucleus using deep U-Net and other versions of U-Net models. NETWORK (BRISTOL, ENGLAND) 2022; 33:167-186. [PMID: 35822269 DOI: 10.1080/0954898x.2022.2096938] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/06/2021] [Revised: 04/04/2022] [Accepted: 06/27/2022] [Indexed: 06/15/2023]
Abstract
The deep learning models play an essential role in many areas, including medical image analysis. These models extract important features without human intervention. In this paper, we propose a deep convolution neural network, named as deep U-Net model, for the segmentation of the cell nucleus, a critical functional unit that determines the function and structure of the body. The nucleus contains all kinds of DNA, RNA, chromosomes, and genes governing all life activities, and its disorder may lead to different types of diseases such as cancer, heart disease, diabetes, Alzheimer's, etc. If the nucleus structure is known correctly, diseases due to nucleus disorder may be detected early. It may also reduce the drug discovery time if the shape and size of the nucleus are known. We evaluate the performance of the proposed models on the nucleus segmentation data set used by the Data Science Bowl 2018 competition hosted by Kaggle. We compare its performance with that of the U-Net, Attention U-Net, R2U-Net, Attention R2U-Net, and both versions of the U-Net++ with and without supervision, in terms of loss, dice coefficient, dice loss, intersection over union, and accuracy. Our model performs better than the existing models.
Collapse
Affiliation(s)
- Satish Chand
- School of Computer and Systems Sciences, Jawaharlal Nehru Univesity, New Delhi, India
| |
Collapse
|
18
|
Semantic Image Segmentation Using Scant Pixel Annotations. MACHINE LEARNING AND KNOWLEDGE EXTRACTION 2022. [DOI: 10.3390/make4030029] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
The success of deep networks for the semantic segmentation of images is limited by the availability of annotated training data. The manual annotation of images for segmentation is a tedious and time-consuming task that often requires sophisticated users with significant domain expertise to create high-quality annotations over hundreds of images. In this paper, we propose the segmentation with scant pixel annotations (SSPA) approach to generate high-performing segmentation models using a scant set of expert annotated images. The models are generated by training them on images with automatically generated pseudo-labels along with a scant set of expert annotated images selected using an entropy-based algorithm. For each chosen image, experts are directed to assign labels to a particular group of pixels, while a set of replacement rules that leverage the patterns learned by the model is used to automatically assign labels to the remaining pixels. The SSPA approach integrates active learning and semi-supervised learning with pseudo-labels, where expert annotations are not essential but generated on demand. Extensive experiments on bio-medical and biofilm datasets show that the SSPA approach achieves state-of-the-art performance with less than 5% cumulative annotation of the pixels of the training data by the experts.
Collapse
|
19
|
Zheng X, Weng Y, Wang Y, Xin Y, Wu J, Ziad Masoud Abu Said A, Nguelemo Mayopa K, Akiti S, Li X, Wang C, Wang J, Eliasy A, Bao F, Chen S, Elsheikh A. Long-term Effects of Riboflavin Ultraviolet-A-Induced CXL With Different Irradiances on the Biomechanics of In Vivo Rabbit Corneas. J Refract Surg 2022; 38:389-397. [PMID: 35686711 DOI: 10.3928/1081597x-20220425-01] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
Abstract
PURPOSE To evaluate the long-term effects of ultraviolet-A corneal cross-linking (CXL) with different irrandiances on the biomechanical properties of rabbit corneas and the corresponding changes in stromal microstructure. METHODS The study involved the left eyes of 85 healthy white Japanese rabbits, randomly divided into five groups (n = 16 to 18 each). After removing the epithelium, the first four groups were exposed to riboflavin (0.22% concentration by volume) and ultraviolet-A (370 nm) at different CXL irradiations but with the same total dose (5.4 J/cm2). The four groups were defined as standard CXL (SCXL; 3 mW/cm2 for 30 minutes, n = 17), accelerated CXL1 (ACXL1; 9 mW/cm2 for 10 minutes, n = 16), accelerated CXL2 (ACXL2; 18 mW/cm2 for 5 minutes, n = 17), and accelerated CXL3 (ACXL3; 30 mW/cm2 for 3 minutes, n = 17). The control group (n = 18) was treated with riboflavin without ultraviolet-A exposure. Nine months after CXL, 10 corneas from each group were tested ex vivo under inflation, and the tangent modulus (Et) was estimated using an inverse analysis process. The remaining six to eight specimens in each group were examined by electron microscopy to determine the mean fibril diameter and interfibrillar spacing. RESULTS The SCXL and ACXL1 groups showed statistically significant differences in Et at all stresses (0.005, 0.010, and 0.015 MPa) analyzed compared to the control group (all P < .01), but the differences were non-significant in the ACXL3 group (P = 1.000, .785, and .679, respectively). For the ACXL2 group, there was no statistical difference in Et under the low stress of 0.005 MPa (P = .155), but the differences became significant at 0.010 and 0.015 MPa when compared with the control group (all P < .05). CONCLUSIONS CXL had a significant effect on corneal biomechanics in both standard and accelerated procedures. However, standard CXL was the most effective, and this effectiveness decreased gradually with increasing ultraviolet-A power intensity. [J Refract Surg. 2022;38(6):389-397.].
Collapse
|
20
|
Ma L, Little JV, Chen AY, Myers L, Sumer BD, Fei B. Automatic detection of head and neck squamous cell carcinoma on histologic slides using hyperspectral microscopic imaging. JOURNAL OF BIOMEDICAL OPTICS 2022; 27:046501. [PMID: 35484692 PMCID: PMC9050479 DOI: 10.1117/1.jbo.27.4.046501] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/22/2021] [Accepted: 04/05/2022] [Indexed: 06/14/2023]
Abstract
SIGNIFICANCE Automatic, fast, and accurate identification of cancer on histologic slides has many applications in oncologic pathology. AIM The purpose of this study is to investigate hyperspectral imaging (HSI) for automatic detection of head and neck cancer nuclei in histologic slides, as well as cancer region identification based on nuclei detection. APPROACH A customized hyperspectral microscopic imaging system was developed and used to scan histologic slides from 20 patients with squamous cell carcinoma (SCC). Hyperspectral images and red, green, and blue (RGB) images of the histologic slides with the same field of view were obtained and registered. A principal component analysis-based nuclei segmentation method was developed to extract nuclei patches from the hyperspectral images and the coregistered RGB images. Spectra-based support vector machine and patch-based convolutional neural networks (CNNs) were implemented for nuclei classification. The CNNs were trained with RGB patches (RGB-CNN) and hyperspectral patches (HSI-CNN) of the segmented nuclei and the utility of the extra spectral information provided by HSI was evaluated. Furthermore, cancer region identification was implemented by image-wise classification based on the percentage of cancerous nuclei detected in each image. RESULTS RGB-CNN, which mainly used the spatial information of nuclei, resulted in a 0.81 validation accuracy and 0.74 testing accuracy. HSI-CNN, which utilized the spatial and spectral features of the nuclei, showed significant improvement in classification performance and achieved 0.89 validation accuracy as well as 0.82 testing accuracy. Furthermore, the image-wise cancer region identification based on nuclei detection could generally improve the cancer detection rate. CONCLUSIONS We demonstrated that the morphological and spectral information contribute to SCC nuclei differentiation and that the spectral information within hyperspectral images could improve classification performance.
Collapse
Affiliation(s)
- Ling Ma
- University of Texas at Dallas, Department of Bioengineering, Richardson, Texas, United States
- Tianjin University, State Key Laboratory of Precision Measurement Technology and Instruments, Tianjin, China
| | - James V. Little
- Emory University School of Medicine, Department of Pathology and Laboratory Medicine, Atlanta, Georgia, United States
| | - Amy Y. Chen
- Emory University School of Medicine, Department of Otolaryngology, Atlanta, Georgia, United States
| | - Larry Myers
- The University of Texas Southwestern Medical Center, Department of Otolaryngology, Dallas, Texas, United States
| | - Baran D. Sumer
- The University of Texas Southwestern Medical Center, Department of Otolaryngology, Dallas, Texas, United States
| | - Baowei Fei
- University of Texas at Dallas, Department of Bioengineering, Richardson, Texas, United States
- The University of Texas Southwestern Medical Center, Advanced Imaging Research Center, Dallas, Texas, United States
- The University of Texas Southwestern Medical Center, Department of Radiology, Dallas, Texas, United States
| |
Collapse
|
21
|
Pan W, Liu Z, Song W, Zhen X, Yuan K, Xu F, Lin GN. An Integrative Segmentation Framework for Cell Nucleus of Fluorescence Microscopy. Genes (Basel) 2022; 13:genes13030431. [PMID: 35327985 PMCID: PMC8950038 DOI: 10.3390/genes13030431] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2022] [Revised: 02/22/2022] [Accepted: 02/23/2022] [Indexed: 01/27/2023] Open
Abstract
Nucleus segmentation of fluorescence microscopy is a critical step in quantifying measurements in cell biology. Automatic and accurate nucleus segmentation has powerful applications in analyzing intrinsic characterization in nucleus morphology. However, existing methods have limited capacity to perform accurate segmentation in challenging samples, such as noisy images and clumped nuclei. In this paper, inspired by the idea of cascaded U-Net (or W-Net) and its remarkable performance improvement in medical image segmentation, we proposed a novel framework called Attention-enhanced Simplified W-Net (ASW-Net), in which a cascade-like structure with between-net connections was used. Results showed that this lightweight model could reach remarkable segmentation performance in the BBBC039 testing set (aggregated Jaccard index, 0.90). In addition, our proposed framework performed better than the state-of-the-art methods in terms of segmentation performance. Moreover, we further explored the effectiveness of our designed network by visualizing the deep features from the network. Notably, our proposed framework is open source.
Collapse
Affiliation(s)
- Weihao Pan
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China; (W.P.); (Z.L.); (W.S.); (X.Z.); (K.Y.)
| | - Zhe Liu
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China; (W.P.); (Z.L.); (W.S.); (X.Z.); (K.Y.)
| | - Weichen Song
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China; (W.P.); (Z.L.); (W.S.); (X.Z.); (K.Y.)
| | - Xuyang Zhen
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China; (W.P.); (Z.L.); (W.S.); (X.Z.); (K.Y.)
| | - Kai Yuan
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China; (W.P.); (Z.L.); (W.S.); (X.Z.); (K.Y.)
| | - Fei Xu
- State Key Laboratory of Functional Materials for Informatics, Shanghai Institute of Microsystem and Information Technology (SIMIT), Chinese Academy of Sciences, Shanghai 200050, China
- College of Science, Donghua University, Shanghai 201620, China
- Correspondence: (F.X.); (G.N.L.)
| | - Guan Ning Lin
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China; (W.P.); (Z.L.); (W.S.); (X.Z.); (K.Y.)
- Correspondence: (F.X.); (G.N.L.)
| |
Collapse
|
22
|
Gomariz A, Portenier T, Nombela-Arrieta C, Goksel O. Probabilistic spatial analysis in quantitative microscopy with uncertainty-aware cell detection using deep Bayesian regression. SCIENCE ADVANCES 2022; 8:eabi8295. [PMID: 35119934 PMCID: PMC8816343 DOI: 10.1126/sciadv.abi8295] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/05/2021] [Accepted: 12/14/2021] [Indexed: 06/14/2023]
Abstract
The investigation of biological systems with three-dimensional microscopy demands automatic cell identification methods that not only are accurate but also can imply the uncertainty in their predictions. The use of deep learning to regress density maps is a popular successful approach for extracting cell coordinates from local peaks in a postprocessing step, which then, however, hinders any meaningful probabilistic output. We propose a framework that can operate on large microscopy images and output probabilistic predictions (i) by integrating deep Bayesian learning for the regression of uncertainty-aware density maps, where peak detection algorithms generate cell proposals, and (ii) by learning a mapping from prediction proposals to a probabilistic space that accurately represents the chances of a successful prediction. Using these calibrated predictions, we propose a probabilistic spatial analysis with Monte Carlo sampling. We demonstrate this in a bone marrow dataset, where our proposed methods reveal spatial patterns that are otherwise undetectable.
Collapse
Affiliation(s)
- Alvaro Gomariz
- Computer-assisted Applications in Medicine, ETH Zurich, Zurich, Switzerland
- Department of Medical Oncology and Hematology, University Hospital and University of Zurich, Zurich, Switzerland
| | - Tiziano Portenier
- Computer-assisted Applications in Medicine, ETH Zurich, Zurich, Switzerland
| | - César Nombela-Arrieta
- Department of Medical Oncology and Hematology, University Hospital and University of Zurich, Zurich, Switzerland
| | - Orcun Goksel
- Computer-assisted Applications in Medicine, ETH Zurich, Zurich, Switzerland
- Centre for Image Analysis, Department of Information Technology, Uppsala University, Uppsala, Sweden
| |
Collapse
|
23
|
|
24
|
Zafar MM, Rauf Z, Sohail A, Khan AR, Obaidullah M, Khan SH, Lee YS, Khan A. Detection of tumour infiltrating lymphocytes in CD3 and CD8 stained histopathological images using a two-phase deep CNN. Photodiagnosis Photodyn Ther 2021; 37:102676. [PMID: 34890783 DOI: 10.1016/j.pdpdt.2021.102676] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2021] [Revised: 11/10/2021] [Accepted: 12/06/2021] [Indexed: 12/26/2022]
Abstract
BACKGROUND Immuno-score, a prognostic measure for cancer, employed in determining tumor grade and type, is generated by counting the number of Tumour-Infiltrating Lymphocytes (TILs) in CD3 and CD8 stained histopathological tissue samples. Significant stain variations and heterogeneity in lymphocytes' spatial distribution and density make automated counting of TILs' a challenging task. METHODS This work addresses the aforementioned challenges by developing a pipeline "Two-Phase Deep Convolutional Neural Network based Lymphocyte Counter (TDC-LC)" to detect lymphocytes in CD3 and CD8 stained histology images. The proposed pipeline sequentially works by removing hard negative examples (artifacts) in the first phase using a custom CNN "LSATM-Net" that exploits the idea of a split, asymmetric transform, and merge. Whereas, in the second phase, instance segmentation is performed to detect and generate a lymphocyte count against the remaining samples. Furthermore, the effectiveness of the proposed pipeline is measured by comparing it with the state-of-the-art single- and two-stage detectors. The inference code is available at GitHub Repository https://github.com/m-mohsin-zafar/tdc-lc. RESULTS The empirical evaluation on samples from LYSTO dataset shows that the proposed LSTAM-Net can learn variations in the images and precisely remove the hard negative stain artifacts with an F-score of 0.74. The detection analysis shows that the proposed TDC-LC outperforms the existing models in identifying and counting lymphocytes with high Recall (0.87) and F-score (0.89). Moreover, the commendable performance of the proposed TDC-LC in different organs suggests a good generalization. CONCLUSION The promising performance of the proposed pipeline suggests that it can serve as an automated system for detecting and counting lymphocytes from patches of tissue samples thereby reducing the burden on pathologists.
Collapse
Affiliation(s)
- Muhammad Mohsin Zafar
- Pattern Recognition Lab, Department of Computer & Information Sciences, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan; Faculty of Computer Science and Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi 23640, District Swabi, Khyber Pakhtunkhwa, Pakistan
| | - Zunaira Rauf
- Pattern Recognition Lab, Department of Computer & Information Sciences, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan; PIEAS Artificial Intelligence Center (PAIC), Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan
| | - Anabia Sohail
- Pattern Recognition Lab, Department of Computer & Information Sciences, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan; PIEAS Artificial Intelligence Center (PAIC), Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan
| | - Abdul Rehman Khan
- Pattern Recognition Lab, Department of Computer & Information Sciences, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan; Center for Mathematical Sciences, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan
| | - Muhammad Obaidullah
- Pattern Recognition Lab, Department of Computer & Information Sciences, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan; Center for Mathematical Sciences, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan
| | - Saddam Hussain Khan
- Pattern Recognition Lab, Department of Computer & Information Sciences, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan; PIEAS Artificial Intelligence Center (PAIC), Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan
| | - Yeon Soo Lee
- Deparment of Biomedical Engineering, College of Medical Sciences, Catholic University of Daegu, South Korea.
| | - Asifullah Khan
- Pattern Recognition Lab, Department of Computer & Information Sciences, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan; PIEAS Artificial Intelligence Center (PAIC), Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan; Deparment of Biomedical Engineering, College of Medical Sciences, Catholic University of Daegu, South Korea; Center for Mathematical Sciences, Pakistan Institute of Engineering & Applied Sciences, Nilore, Islamabad 45650, Pakistan.
| |
Collapse
|
25
|
Duanmu H, Wang F, Teodoro G, Kong J. Foveal blur-boosted segmentation of nuclei in histopathology images with shape prior knowledge and probability map constraints. Bioinformatics 2021; 37:3905-3913. [PMID: 34081103 PMCID: PMC11025700 DOI: 10.1093/bioinformatics/btab418] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2020] [Revised: 04/07/2021] [Accepted: 06/02/2021] [Indexed: 11/13/2022] Open
Abstract
MOTIVATION In most tissue-based biomedical research, the lack of sufficient pathology training images with well-annotated ground truth inevitably limits the performance of deep learning systems. In this study, we propose a convolutional neural network with foveal blur enriching datasets with multiple local nuclei regions of interest derived from original pathology images. We further propose a human-knowledge boosted deep learning system by inclusion to the convolutional neural network new loss function terms capturing shape prior knowledge and imposing smoothness constraints on the predicted probability maps. RESULTS Our proposed system outperforms all state-of-the-art deep learning and non-deep learning methods by Jaccard coefficient, Dice coefficient, Accuracy and Panoptic Quality in three independent datasets. The high segmentation accuracy and execution speed suggest its promising potential for automating histopathology nuclei segmentation in biomedical research and clinical settings. AVAILABILITY AND IMPLEMENTATION The codes, the documentation and example data are available on an open source at: https://github.com/HongyiDuanmu26/FovealBoosted. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Hongyi Duanmu
- Department of Computer Science, Stony Brook University, Stony Brook, NY 11794, USA
| | - Fusheng Wang
- Department of Computer Science, Stony Brook University, Stony Brook, NY 11794, USA
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY 11794, USA
| | - George Teodoro
- Department of Computer Science, Federal University of Minas Gerais, Belo Horizonte 31270-901, Brazil
| | - Jun Kong
- Department of Mathematics and Statistics and Computer Science, Georgia State University, Atlanta, GA 30303, USA
- Department of Computer Science and Winship Cancer Institute, Emory University, Atlanta, GA 30322, USA
| |
Collapse
|
26
|
Belini VL, Junior OM, Ceccato-Antonini SR, Suhr H, Wiedemann P. Morphometric quantification of a pseudohyphae forming Saccharomyces cerevisiae strain using in situ microscopy and image analysis. J Microbiol Methods 2021; 190:106338. [PMID: 34597736 DOI: 10.1016/j.mimet.2021.106338] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2021] [Revised: 09/21/2021] [Accepted: 09/21/2021] [Indexed: 11/30/2022]
Abstract
Yeast morphology and counting are highly important in fermentation as they are often associated with productivity and can be influenced by process conditions. At present, time-consuming and offline methods are utilized for routine analysis of yeast morphology and cell counting using a haemocytometer. In this study, we demonstrate the application of an in situ microscope to obtain a fast stream of pseudohyphae images from agitated sample suspensions of a Saccharomyces cerevisiae strain, whose morphology in cell clusters is frequently found in the bioethanol fermentation industry. The large statistics of microscopic images allow for online determination of the principal morphological characteristics of the pseudohyphae, including the number of constituent cells, cell-size, number of branches, and length of branches. The distributions of these feature values are calculated online, constituting morphometric monitoring of the pseudohyphae population. By providing representative data, the proposed system can improve the effectiveness of morphological characterization, which in turn can help to improve the understanding and control of bioprocesses in which pseudohyphal-like morphologies are found.
Collapse
Affiliation(s)
- Valdinei L Belini
- Department of Electrical Engineering, Universidade Federal de São Carlos, Rodovia Washington Luís, km 235, São Carlos, SP CEP 13565-905, Brazil.
| | - Orides M Junior
- Computing Department, Universidade Federal de São Carlos, Rodovia Washington Luís, km 235, São Carlos, SP CEP 13565-905, Brazil
| | - Sandra R Ceccato-Antonini
- Department of Agroindustrial Technology and Rural Socio-Economics, Universidade Federal de São Carlos, Via Anhanguera, km 174, Araras, SP CEP 13600-970, Brazil
| | - Hajo Suhr
- Department of Information Technology, Mannheim University of Applied Sciences, Paul-Wittsack-Straße 10, 68163 Mannheim, Germany
| | - Philipp Wiedemann
- Department of Biotechnology, Mannheim University of Applied Sciences, Paul-Wittsack-Straße 10, 68163 Mannheim, Germany
| |
Collapse
|
27
|
Bao R, Al-Shakarji NM, Bunyak F, Palaniappan K. DMNet: Dual-Stream Marker Guided Deep Network for Dense Cell Segmentation and Lineage Tracking. ... IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS. IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION 2021; 2021:3354-3363. [PMID: 35386855 DOI: 10.1109/iccvw54120.2021.00375] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
Accurate segmentation and tracking of cells in microscopy image sequences is extremely beneficial in clinical diagnostic applications and biomedical research. A continuing challenge is the segmentation of dense touching cells and deforming cells with indistinct boundaries, in low signal-to-noise-ratio images. In this paper, we present a dual-stream marker-guided network (DMNet) for segmentation of touching cells in microscopy videos of many cell types. DMNet uses an explicit cell marker-detection stream, with a separate mask-prediction stream using a distance map penalty function, which enables supervised training to focus attention on touching and nearby cells. For multi-object cell tracking we use M2Track tracking-by-detection approach with multi-step data association. Our M2Track with mask overlap includes short term track-to-cell association followed by track-to-track association to re-link tracklets with missing segmentation masks over a short sequence of frames. Our combined detection, segmentation and tracking algorithm has proven its potential on the IEEE ISBI 2021 6th Cell Tracking Challenge (CTC-6) where we achieved multiple top three rankings for diverse cell types. Our team name is MU-Ba-US, and the implementation of DMNet is available at, http://celltrackingchallenge.net/participants/MU-Ba-US/.
Collapse
Affiliation(s)
- Rina Bao
- University of Missouri-Columbia, MO 65211, USA
| | | | | | | |
Collapse
|
28
|
Hermsen M, Volk V, Bräsen JH, Geijs DJ, Gwinner W, Kers J, Linmans J, Schaadt NS, Schmitz J, Steenbergen EJ, Swiderska-Chadaj Z, Smeets B, Hilbrands LB, Feuerhake F, van der Laak JAWM. Quantitative assessment of inflammatory infiltrates in kidney transplant biopsies using multiplex tyramide signal amplification and deep learning. J Transl Med 2021; 101:970-982. [PMID: 34006891 PMCID: PMC8292146 DOI: 10.1038/s41374-021-00601-w] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2021] [Revised: 03/09/2021] [Accepted: 03/11/2021] [Indexed: 12/20/2022] Open
Abstract
Delayed graft function (DGF) is a strong risk factor for development of interstitial fibrosis and tubular atrophy (IFTA) in kidney transplants. Quantitative assessment of inflammatory infiltrates in kidney biopsies of DGF patients can reveal predictive markers for IFTA development. In this study, we combined multiplex tyramide signal amplification (mTSA) and convolutional neural networks (CNNs) to assess the inflammatory microenvironment in kidney biopsies of DGF patients (n = 22) taken at 6 weeks post-transplantation. Patients were stratified for IFTA development (<10% versus ≥10%) from 6 weeks to 6 months post-transplantation, based on histopathological assessment by three kidney pathologists. One mTSA panel was developed for visualization of capillaries, T- and B-lymphocytes and macrophages and a second mTSA panel for T-helper cell and macrophage subsets. The slides were multi spectrally imaged and custom-made python scripts enabled conversion to artificial brightfield whole-slide images (WSI). We used an existing CNN for the detection of lymphocytes with cytoplasmatic staining patterns in immunohistochemistry and developed two new CNNs for the detection of macrophages and nuclear-stained lymphocytes. F1-scores were 0.77 (nuclear-stained lymphocytes), 0.81 (cytoplasmatic-stained lymphocytes), and 0.82 (macrophages) on a test set of artificial brightfield WSI. The CNNs were used to detect inflammatory cells, after which we assessed the peritubular capillary extent, cell density, cell ratios, and cell distance in the two patient groups. In this cohort, distance of macrophages to other immune cells and peritubular capillary extent did not vary significantly at 6 weeks post-transplantation between patient groups. CD163+ cell density was higher in patients with ≥10% IFTA development 6 months post-transplantation (p < 0.05). CD3+CD8-/CD3+CD8+ ratios were higher in patients with <10% IFTA development (p < 0.05). We observed a high correlation between CD163+ and CD4+GATA3+ cell density (R = 0.74, p < 0.001). Our study demonstrates that CNNs can be used to leverage reliable, quantitative results from mTSA-stained, multi spectrally imaged slides of kidney transplant biopsies.
Collapse
Affiliation(s)
- Meyke Hermsen
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Valery Volk
- Institute for Pathology, Hannover Medical School, Hannover, Germany
| | | | - Daan J Geijs
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Wilfried Gwinner
- Department of Nephrology, Hannover Medical School, Hannover, Germany
| | - Jesper Kers
- Department of Pathology, Amsterdam University Medical Centers, Amsterdam, The Netherlands
- Department of Pathology, Leiden University Medical Center, Leiden, The Netherlands
- Center for Analytical Sciences Amsterdam (CASA), Van 't Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam, Amsterdam, The Netherlands
| | - Jasper Linmans
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Nadine S Schaadt
- Institute of Diagnostic and Interventional Neuroradiology, Hannover Medical School, Hannover, Germany
| | - Jessica Schmitz
- Institute for Pathology, Hannover Medical School, Hannover, Germany
| | - Eric J Steenbergen
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Zaneta Swiderska-Chadaj
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
- Faculty of Electrical Engineering, Warsaw University of Technology, Warsaw, Poland
| | - Bart Smeets
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Luuk B Hilbrands
- Department of Nephrology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Friedrich Feuerhake
- Institute for Pathology, Hannover Medical School, Hannover, Germany
- Institute for Neuropathology, University Clinic Freiburg, Freiburg, Germany
| | - Jeroen A W M van der Laak
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands.
- Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden.
| |
Collapse
|
29
|
Bai Y, Cole K, Martinez-Morilla S, Ahmed FS, Zugazagoitia J, Staaf J, Bosch A, Ehinger A, Niméus E, Hartman J, Acs B, Rimm DL. An Open Source, Automated Tumor Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer. Clin Cancer Res 2021; 27:5557-5565. [PMID: 34088723 DOI: 10.1158/1078-0432.ccr-21-0325] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2021] [Revised: 03/29/2021] [Accepted: 06/02/2021] [Indexed: 11/16/2022]
Abstract
PURPOSE Although tumor infiltrating lymphocytes (TIL) assessment has been acknowledged to have both prognostic and predictive importance in triple negative breast cancer (TNBC), it is subject to inter and intra-observer variability that has prevented widespread adoption. Here we constructed a machine-learning based breast cancer TIL scoring approach and validated its prognostic potential in multiple TNBC cohorts. EXPERIMENTAL DESIGN Using the QuPath open source software, we built a neural-network classifier for tumor cells, lymphocytes, fibroblasts and "other" cells on hematoxylin-eosin (H&E) stained sections. We analyzed the classifier-derived TIL measurements with five unique constructed TIL variables. A retrospective collection of 171 TNBC cases was used as the discovery set to identify the optimal association of machine-read TIL variables with patient outcome. For validation we evaluated a retrospective collection of 749 TNBC patients comprised of four independent validation subsets. RESULTS We found that all five machine TIL variables had significant prognostic association with outcomes (p{less than or equal to}0.01 for all comparisons) but showed cell specific variation in validation sets. Cox regression analysis demonstrated that all five TIL variables were independently associated with improved overall survival after adjusting for clinicopathological factors including stage, age and histological grade (p{less than or equal to}0.003 for all analyses). CONCLUSIONS Neural net driven cell classifier defined TIL variables were robust and independent prognostic factors in several independent validation cohorts of TNBC patients. These objective, open source TIL variables are freely available to download and can now be considered for testing in a prospective setting to assess clinical utility.
Collapse
Affiliation(s)
| | | | | | | | | | | | - Ana Bosch
- Department of Clinical Sciences. Division of Oncology, Lund University
| | - Anna Ehinger
- Clinical Genetics and Pathology, Lund University
| | - Emma Niméus
- Oncology and Pathology, Clinical Sciences, Lund University
| | - Johan Hartman
- Dept of Oncology and Pathology, Karolinska Institute
| | - Balazs Acs
- Department of Oncology-Pathology, Karolinska Institute
| | - David L Rimm
- Department of Pathology, Yale School of Medicine
| |
Collapse
|
30
|
Matikas A, Wang K, Lagoudaki E, Acs B, Zerdes I, Hartman J, Azavedo E, Bjöhle J, Carlsson L, Einbeigi Z, Hedenfalk I, Hellström M, Lekberg T, Loman N, Saracco A, von Wachenfeldt A, Rotstein S, Bergqvist M, Bergh J, Hatschek T, Foukakis T. Prognostic role of serum thymidine kinase 1 kinetics during neoadjuvant chemotherapy for early breast cancer. ESMO Open 2021; 6:100076. [PMID: 33714010 PMCID: PMC7957142 DOI: 10.1016/j.esmoop.2021.100076] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2021] [Revised: 01/24/2021] [Accepted: 02/08/2021] [Indexed: 11/30/2022] Open
Abstract
Background Emerging data support the use of thymidine kinase 1 (TK1) activity as a prognostic marker and for monitoring of response in breast cancer (BC). The long-term prognostic value of TK1 kinetics during neoadjuvant chemotherapy is unclear, which this study aimed to elucidate. Methods Material from patients enrolled to the single-arm prospective PROMIX trial of neoadjuvant epirubicin, docetaxel and bevacizumab for early BC was used. Ki67 in baseline biopsies was assessed both centrally and by automated digital imaging analysis. TK1 activity was measured from blood samples obtained at baseline and following two cycles of chemotherapy. The associations of TK1 and its kinetics as well as Ki67 with event-free survival and overall survival (OS) were evaluated using multivariable Cox regression models. Results Central Ki67 counting had excellent correlation with the results of digital image analysis (r = 0.814), but not with the diagnostic samples (r = 0.234), while it was independently prognostic for worse OS [adjusted hazard ratio (HRadj) = 2.72, 95% confidence interval (CI) 1.19-6.21, P = 0.02]. Greater increase in TK1 activity after two cycles of chemotherapy resulted in improved event-free survival (HRadj = 0.50, 95% CI 0.26-0.97, P = 0.04) and OS (HRadj = 0.46, 95% CI 0.95, P = 0.04). There was significant interaction between the prognostic value of TK1 kinetics and Ki67 (pinteraction 0.04). Conclusion Serial measurement of serum TK1 activity during neoadjuvant chemotherapy provides long-term prognostic information in BC patients. The ease of obtaining serial samples for TK1 assessment motivates further evaluation in larger studies. This is a correlative analysis of a prospective phase II study on neoadjuvant chemotherapy for breast cancer. Serial measurement of serum TK1 activity during treatment provides independent long-term prognostic information. We demonstrate the validity and clinical utility of both central and automated image analysis-based Ki67 assessment. Finally, we explore the biologic correlations between TK1 and Ki67.
Collapse
Affiliation(s)
- A Matikas
- Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden; Breast Center, Theme Cancer, Karolinska University Hospital, Stockholm, Sweden.
| | - K Wang
- Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden
| | - E Lagoudaki
- Pathology Department, University Hospital of Heraklion, Heraklion, Greece
| | - B Acs
- Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden; Department of Clinical Pathology and Cytology, Karolinska University Laboratory, Stockholm, Sweden
| | - I Zerdes
- Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden
| | - J Hartman
- Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden; Department of Clinical Pathology and Cytology, Karolinska University Laboratory, Stockholm, Sweden
| | - E Azavedo
- Department of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden
| | - J Bjöhle
- Breast Center, Theme Cancer, Karolinska University Hospital, Stockholm, Sweden
| | - L Carlsson
- Department of Oncology, Sundsvall General Hospital, Sundsvall, Sweden
| | - Z Einbeigi
- Department of Medicine and Department of Oncology, Southern Älvsborg Hospital, Borås, Sweden; Institute of Clinical Sciences, Sahlgrenska Academy, Sahlgrenska University Hospital, Gothenburg, Sweden
| | - I Hedenfalk
- Division of Oncology, Department of Clinical Sciences Lund, Lund University, Lund, Sweden
| | - M Hellström
- Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden
| | - T Lekberg
- Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden; Breast Center, Theme Cancer, Karolinska University Hospital, Stockholm, Sweden
| | - N Loman
- Division of Oncology, Department of Clinical Sciences Lund, Lund University, Lund, Sweden; Department of Hematology, Oncology and Radiation Physics Skåne University Hospital, Lund, Sweden
| | - A Saracco
- Breast Center, Södersjukhuset, Stockholm, Sweden
| | - A von Wachenfeldt
- Department of Clinical Science and Education, Karolinska Institutet, Stockholm, Sweden
| | - S Rotstein
- Breast Center, Theme Cancer, Karolinska University Hospital, Stockholm, Sweden
| | - M Bergqvist
- Biovica International, Uppsala Science Park, Uppsala, Sweden
| | - J Bergh
- Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden; Breast Center, Theme Cancer, Karolinska University Hospital, Stockholm, Sweden
| | - T Hatschek
- Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden; Breast Center, Theme Cancer, Karolinska University Hospital, Stockholm, Sweden
| | - T Foukakis
- Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden; Breast Center, Theme Cancer, Karolinska University Hospital, Stockholm, Sweden
| |
Collapse
|
31
|
Mota SM, Rogers RE, Haskell AW, McNeill EP, Kaunas R, Gregory CA, Giger ML, Maitland KC. Automated mesenchymal stem cell segmentation and machine learning-based phenotype classification using morphometric and textural analysis. J Med Imaging (Bellingham) 2021; 8:014503. [PMID: 33542945 PMCID: PMC7849042 DOI: 10.1117/1.jmi.8.1.014503] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2020] [Accepted: 01/11/2021] [Indexed: 01/22/2023] Open
Abstract
Purpose: Mesenchymal stem cells (MSCs) have demonstrated clinically relevant therapeutic effects for treatment of trauma and chronic diseases. The proliferative potential, immunomodulatory characteristics, and multipotentiality of MSCs in monolayer culture is reflected by their morphological phenotype. Standard techniques to evaluate culture viability are subjective, destructive, or time-consuming. We present an image analysis approach to objectively determine morphological phenotype of MSCs for prediction of culture efficacy. Approach: The algorithm was trained using phase-contrast micrographs acquired during the early and mid-logarithmic stages of MSC expansion. Cell regions are localized using edge detection, thresholding, and morphological operations, followed by cell marker identification using H-minima transform within each region to differentiate individual cells from cell clusters. Clusters are segmented using marker-controlled watershed to obtain single cells. Morphometric and textural features are extracted to classify cells based on phenotype using machine learning. Results: Algorithm performance was validated using an independent test dataset of 186 MSCs in 36 culture images. Results show 88% sensitivity and 86% precision for overall cell detection and a mean Sorensen-Dice coefficient of 0.849 ± 0.106 for segmentation per image. The algorithm exhibited an area under the curve of 0.816 (CI 95 = 0.769 to 0.886) and 0.787 (CI 95 = 0.716 to 0.851) for classifying MSCs according to their phenotype at early and mid-logarithmic expansion, respectively. Conclusions: The proposed method shows potential to segment and classify low and moderately dense MSCs based on phenotype with high accuracy and robustness. It enables quantifiable and consistent morphology-based quality assessment for various culture protocols to facilitate cytotherapy development.
Collapse
Affiliation(s)
- Sakina M. Mota
- Texas A&M University, Department of Biomedical Engineering, College Station, Texas, United States
| | - Robert E. Rogers
- Texas A&M Health Science Center, College of Medicine, Bryan, Texas, United States
| | - Andrew W. Haskell
- Texas A&M Health Science Center, College of Medicine, Bryan, Texas, United States
| | - Eoin P. McNeill
- Texas A&M Health Science Center, College of Medicine, Bryan, Texas, United States
| | - Roland Kaunas
- Texas A&M University, Department of Biomedical Engineering, College Station, Texas, United States
- Texas A&M Health Science Center, College of Medicine, Bryan, Texas, United States
| | - Carl A. Gregory
- Texas A&M Health Science Center, College of Medicine, Bryan, Texas, United States
| | - Maryellen L. Giger
- University of Chicago, Department of Radiology, Committee on Medical Physics, Chicago, Illinois, United States
| | - Kristen C. Maitland
- Texas A&M University, Department of Biomedical Engineering, College Station, Texas, United States
| |
Collapse
|
32
|
Kim H, Baik JW, Jeon S, Kim JY, Kim C. PAExM: label-free hyper-resolution photoacoustic expansion microscopy. OPTICS LETTERS 2020; 45:6755-6758. [PMID: 33325889 DOI: 10.1364/ol.404041] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/11/2023]
Abstract
Reflection-mode ultraviolet photoacoustic microscopy (UV-PAM) is capable of imaging cell nuclei in thick tissue without complex preparation procedures, but it is challenging to distinguish adjacent nuclei due to the limited spatial resolution. Tissue expansion technology has recently been developed to exceed the diffraction-limited fluorescence microscopies, but it is accompanied by limitations including additional staining. Herein, photoacoustic expansion microscopy (PAExM) is presented, which is an advanced histologic imaging strategy combining advantages of fast label-free reflection-mode UV-PAM and the tissue expansion technology. Clustered cell nuclei in an enlarged volume of a mouse brain section can be visually resolved without staining, demonstrating a great potential of the system to be widely used for histologic applications throughout biomedical fields.
Collapse
|
33
|
Braiki M, Benzinou A, Nasreddine K, Hymery N. Automatic Human Dendritic Cells Segmentation Using K-Means Clustering and Chan-Vese Active Contour Model. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020; 195:105520. [PMID: 32497772 DOI: 10.1016/j.cmpb.2020.105520] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/17/2019] [Revised: 03/09/2020] [Accepted: 04/23/2020] [Indexed: 06/11/2023]
Abstract
BACKGROUND AND OBJECTIVE Nowadays, the number of pathologies related to food are multiplied. Mycotoxins are one of the most severe food contaminants that cause serious effects on the human health. Therefore, it is necessary to develop an assessment tool for evaluating their impact on the immune response. Recently, a new investigational method using human dendritic cells was endorsed by biologists. Nevertheless, analysis of the morphological features and the behavior of these cells remains merely visual. In addition, this manual analysis is difficult and time-consuming. Here, we focus mainly on automating the evaluation process by using advanced image processing technology. METHODS An automatic segmentation approach of microscopic dendritic cell images is developed to provide a fast and objective evaluation. First, a combination of K-means clustering and mathematical morphology is used to detect dendritic cells. Second, a region-based Chan-Vese active contour model is used to segment the detected cells more precisely. Finally, dendritic cells are extracted by a filtering based on eccentricity measure. RESULTS The proposed scheme is tested on an actual dataset containing 421 microscopic dendritic cell images. The experimental results show high conformity between the results of the proposed scheme and ground-truth elaborated by biological expert. Moreover, a comparative study with other state-of-art segmentation schemes demonstrates the efficiency of the proposed method. It gives the highest average accuracy rate (99.42 %) compared to recent studied approaches. CONCLUSIONS The proposed image segmentation method for morphological analysis of dendrite inhibition can consistently be used as an assessment tool for biologists to facilitate the evaluation of serious health impacts of mycotoxins.
Collapse
Affiliation(s)
- Marwa Braiki
- ENIB, UMR CNRS 6285 LabSTICC, 29238, Brest, France; UTM, ISTMT, LR13ES07 (LRBTM), 1006, Tunis, Tunisie
| | | | | | | |
Collapse
|
34
|
Yang L, Ghosh RP, Franklin JM, Chen S, You C, Narayan RR, Melcher ML, Liphardt JT. NuSeT: A deep learning tool for reliably separating and analyzing crowded cells. PLoS Comput Biol 2020; 16:e1008193. [PMID: 32925919 PMCID: PMC7515182 DOI: 10.1371/journal.pcbi.1008193] [Citation(s) in RCA: 44] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2020] [Revised: 09/24/2020] [Accepted: 07/25/2020] [Indexed: 01/30/2023] Open
Abstract
Segmenting cell nuclei within microscopy images is a ubiquitous task in biological research and clinical applications. Unfortunately, segmenting low-contrast overlapping objects that may be tightly packed is a major bottleneck in standard deep learning-based models. We report a Nuclear Segmentation Tool (NuSeT) based on deep learning that accurately segments nuclei across multiple types of fluorescence imaging data. Using a hybrid network consisting of U-Net and Region Proposal Networks (RPN), followed by a watershed step, we have achieved superior performance in detecting and delineating nuclear boundaries in 2D and 3D images of varying complexities. By using foreground normalization and additional training on synthetic images containing non-cellular artifacts, NuSeT improves nuclear detection and reduces false positives. NuSeT addresses common challenges in nuclear segmentation such as variability in nuclear signal and shape, limited training sample size, and sample preparation artifacts. Compared to other segmentation models, NuSeT consistently fares better in generating accurate segmentation masks and assigning boundaries for touching nuclei.
Collapse
Affiliation(s)
- Linfeng Yang
- Bioengineering, Stanford University, Stanford, CA, United States of America
- BioX Institute, Stanford University, Stanford, CA, United States of America
- ChEM-H, Stanford University, Stanford, CA, United States of America
- Cell Biology Division, Stanford Cancer Institute, Stanford, CA, United States of America
| | - Rajarshi P. Ghosh
- Bioengineering, Stanford University, Stanford, CA, United States of America
- BioX Institute, Stanford University, Stanford, CA, United States of America
- ChEM-H, Stanford University, Stanford, CA, United States of America
- Cell Biology Division, Stanford Cancer Institute, Stanford, CA, United States of America
| | - J. Matthew Franklin
- Bioengineering, Stanford University, Stanford, CA, United States of America
- BioX Institute, Stanford University, Stanford, CA, United States of America
- ChEM-H, Stanford University, Stanford, CA, United States of America
- Cell Biology Division, Stanford Cancer Institute, Stanford, CA, United States of America
- Chemical Engineering, Stanford University, Stanford, CA, United States of America
| | - Simon Chen
- Department of Pathology, Stanford University School of Medicine, Stanford, CA, United States of America
| | - Chenyu You
- Electrical Engineering, Stanford University, Stanford, CA, United States of America
| | - Raja R. Narayan
- Department of Surgery, Stanford University School of Medicine, Stanford, CA, United States of America
| | - Marc L. Melcher
- Department of Surgery, Stanford University School of Medicine, Stanford, CA, United States of America
| | - Jan T. Liphardt
- Bioengineering, Stanford University, Stanford, CA, United States of America
- BioX Institute, Stanford University, Stanford, CA, United States of America
- ChEM-H, Stanford University, Stanford, CA, United States of America
- Cell Biology Division, Stanford Cancer Institute, Stanford, CA, United States of America
| |
Collapse
|
35
|
Panayides AS, Amini A, Filipovic ND, Sharma A, Tsaftaris SA, Young A, Foran D, Do N, Golemati S, Kurc T, Huang K, Nikita KS, Veasey BP, Zervakis M, Saltz JH, Pattichis CS. AI in Medical Imaging Informatics: Current Challenges and Future Directions. IEEE J Biomed Health Inform 2020; 24:1837-1857. [PMID: 32609615 PMCID: PMC8580417 DOI: 10.1109/jbhi.2020.2991043] [Citation(s) in RCA: 105] [Impact Index Per Article: 26.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
This paper reviews state-of-the-art research solutions across the spectrum of medical imaging informatics, discusses clinical translation, and provides future directions for advancing clinical practice. More specifically, it summarizes advances in medical imaging acquisition technologies for different modalities, highlighting the necessity for efficient medical data management strategies in the context of AI in big healthcare data analytics. It then provides a synopsis of contemporary and emerging algorithmic methods for disease classification and organ/ tissue segmentation, focusing on AI and deep learning architectures that have already become the de facto approach. The clinical benefits of in-silico modelling advances linked with evolving 3D reconstruction and visualization applications are further documented. Concluding, integrative analytics approaches driven by associate research branches highlighted in this study promise to revolutionize imaging informatics as known today across the healthcare continuum for both radiology and digital pathology applications. The latter, is projected to enable informed, more accurate diagnosis, timely prognosis, and effective treatment planning, underpinning precision medicine.
Collapse
|
36
|
Robertson S, Acs B, Lippert M, Hartman J. Prognostic potential of automated Ki67 evaluation in breast cancer: different hot spot definitions versus true global score. Breast Cancer Res Treat 2020; 183:161-175. [PMID: 32572716 PMCID: PMC7376512 DOI: 10.1007/s10549-020-05752-w] [Citation(s) in RCA: 26] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2020] [Accepted: 06/13/2020] [Indexed: 12/19/2022]
Abstract
PURPOSE The proliferation-associated biomarker Ki67 has potential utility in breast cancer, including aiding decisions based on prognosis, but has unacceptable inter- and intralaboratory variability. The aim of this study was to compare the prognostic potential for Ki67 hot spot scoring and global scoring using different digital image analysis (DIA) platforms. METHODS An ER+/HER2- breast cancer cohort (n = 139) with whole slide images of sequential sections stained for hematoxylin-eosin, pancytokeratin and Ki67, was analyzed using two DIA platforms. For hot spot analysis virtual dual staining was applied, aligning pancytokeratin and Ki67 images and 22 hot spot algorithms with different features were designed. For global Ki67 scoring an automated QuPath algorithm was applied on Ki67-stained whole slide images. Clinicopathological data included overall survival (OS) and recurrence-free survival (RFS) along with PAM50 molecular subtypes. RESULTS We show significant variations in Ki67 hot spot scoring depending on number of included tumor cells, hot spot size, shape and location. The higher the number of scored tumor cells, the higher the reproducibility of Ki67 proliferation values. Hot spot scoring had greater prognostic potential for RFS in high versus low Ki67 subgroups (hazard ratio (HR) 6.88, CI 2.07-22.87, p = 0.002), compared to global scoring (HR 3.13, CI 1.41-6.96, p = 0.005). Regarding OS, global scoring (HR 7.46, CI 2.46-22.58, p < 0.001) was slightly better than hot spot scoring (HR 6.93, CI 1.61-29.91, p = 0.009). In adjusted multivariate analysis, only global scoring was an independent prognostic marker for both RFS and OS. In addition, global Ki67-based surrogate subtypes reached higher concordance with PAM50 molecular subtype for luminal A and B tumors (66.3% concordance rate, κ = 0.345), than using hot spot scoring (55.8% concordance rate, κ = 0.250). CONCLUSIONS We conclude that the automated global Ki67 scoring is feasible and shows clinical validity, which, however, needs to be confirmed in a larger cohort before clinical implementation.
Collapse
Affiliation(s)
- Stephanie Robertson
- Department of Oncology and Pathology, CCK, Karolinska Institutet, R8:04, 17176, Stockholm, Sweden.
- Department of Clinical Pathology and Cytology, Karolinska University Laboratory, Stockholm, Sweden.
| | - Balazs Acs
- Department of Oncology and Pathology, CCK, Karolinska Institutet, R8:04, 17176, Stockholm, Sweden
- Department of Clinical Pathology and Cytology, Karolinska University Laboratory, Stockholm, Sweden
| | | | - Johan Hartman
- Department of Oncology and Pathology, CCK, Karolinska Institutet, R8:04, 17176, Stockholm, Sweden
- Department of Clinical Pathology and Cytology, Karolinska University Laboratory, Stockholm, Sweden
| |
Collapse
|
37
|
Ma L, Halicek M, Zhou X, Dormer J, Fei B. Hyperspectral Microscopic Imaging for Automatic Detection of Head and Neck Squamous Cell Carcinoma Using Histologic Image and Machine Learning. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2020; 11320. [PMID: 32476708 DOI: 10.1117/12.2549369] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/14/2022]
Abstract
The purpose of this study is to develop hyperspectral imaging (HSI) for automatic detection of head and neck cancer cells on histologic slides. A compact hyperspectral microscopic system is developed in this study. Histologic slides from 15 patients with squamous cell carcinoma (SCC) of the larynx and hypopharynx are imaged with the system. The proposed nuclei segmentation method based on principle component analysis (PCA) can extract most nuclei in the hyperspectral image without extracting other sub-cellular components. Both spectra-based support vector machine (SVM) and patch-based convolutional neural network (CNN) are used for nuclei classification. CNNs were trained with both hyperspectral images and pseudo RGB images of extracted nuclei, in order to evaluate the usefulness of extra information provided by hyperspectral imaging. The average accuracy of spectra-based SVM classification is 68%. The average AUC and average accuracy of the HSI patch-based CNN classification is 0.94 and 82.4%, respectively. The hyperspectral microscopic imaging and classification methods provide an automatic tool to aid pathologists in detecting SCC on histologic slides.
Collapse
Affiliation(s)
- Ling Ma
- Univ. of Texas at Dallas, Department of Bioengineering, Richardson, TX 75080
| | - Martin Halicek
- Univ. of Texas at Dallas, Department of Bioengineering, Richardson, TX 75080
| | - Ximing Zhou
- Univ. of Texas at Dallas, Department of Bioengineering, Richardson, TX 75080
| | - James Dormer
- Univ. of Texas at Dallas, Department of Bioengineering, Richardson, TX 75080
| | - Baowei Fei
- Univ. of Texas at Dallas, Department of Bioengineering, Richardson, TX 75080.,Univ. of Texas Southwestern Medical Center, Advanced Imaging Research Center, Dallas, TX.,Univ. of Texas Southwestern Medical Center, Department of Radiology, Dallas, TX
| |
Collapse
|
38
|
Baiyasi R, Gallagher MJ, McCarthy LA, Searles EK, Zhang Q, Link S, Landes CF. Quantitative Analysis of Nanorod Aggregation and Morphology from Scanning Electron Micrographs Using SEMseg. J Phys Chem A 2020; 124:5262-5270. [DOI: 10.1021/acs.jpca.0c03190] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/04/2023]
Affiliation(s)
- Rashad Baiyasi
- Department of Electrical and Computer Engineering, Rice University, MS 366, Houston, Texas 77005, United States
| | - Miranda J. Gallagher
- Department of Chemistry, Rice University, MS 60, Houston, Texas 77005, United States
| | - Lauren A. McCarthy
- Department of Chemistry, Rice University, MS 60, Houston, Texas 77005, United States
| | - Emily K. Searles
- Department of Chemistry, Rice University, MS 60, Houston, Texas 77005, United States
| | - Qingfeng Zhang
- Department of Chemistry, Rice University, MS 60, Houston, Texas 77005, United States
- Smalley-Curl Institute, Rice University, Houston, Texas 77005, United States
| | - Stephan Link
- Department of Electrical and Computer Engineering, Rice University, MS 366, Houston, Texas 77005, United States
- Department of Chemistry, Rice University, MS 60, Houston, Texas 77005, United States
- Smalley-Curl Institute, Rice University, Houston, Texas 77005, United States
| | - Christy F. Landes
- Department of Electrical and Computer Engineering, Rice University, MS 366, Houston, Texas 77005, United States
- Department of Chemistry, Rice University, MS 60, Houston, Texas 77005, United States
- Smalley-Curl Institute, Rice University, Houston, Texas 77005, United States
- Department of Chemical and Biomolecular Engineering, Rice University, Houston, Texas 77005, United States
| |
Collapse
|
39
|
The Prediction of Fine Sediment Distribution in Gravel-Bed Rivers Using a Combination of DEM and FNN. WATER 2020. [DOI: 10.3390/w12061515] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Large amounts of fine sediment infiltration into void spaces of coarse bed material have the ability to alter the morphodynamics of rivers and their aquatic ecosystems. Modelling the mechanisms of fine sediment infiltration in gravel-bed is therefore of high significance. We proposed a framework for calculating the sediment exchange in two layers. On the basis of the conventional approaches, we derived a two-layer fine sediment sorting, which considers the transportation of fine sediment in the form of infiltration into the void spaces of the gravel-bed. The relationship between the fine sediment exchange and the affected factors was obtained by using the discrete element method (DEM) in combination with feedforward neural networks (FNN). The DEM model was validated and applied for gravel-bed flumes with different sizes of fine sediments. Further, we developed algorithms for extracting information in terms of gravel-bed packing, grain size distribution, and porosity variation. On the basis of the DEM results with this extracted information, we developed an FNN model for fine sediment sorting. Analyzing the calculated results and comparing them with the available measurements showed that our framework can successfully simulate the exchange of fine sediment in gravel-bed rivers.
Collapse
|
40
|
Weiss T, Semmler L, Millesi F, Mann A, Haertinger M, Salzmann M, Radtke C. Automated image analysis of stained cytospins to quantify Schwann cell purity and proliferation. PLoS One 2020; 15:e0233647. [PMID: 32442229 PMCID: PMC7244157 DOI: 10.1371/journal.pone.0233647] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2019] [Accepted: 05/10/2020] [Indexed: 11/18/2022] Open
Abstract
In response to injury, adult Schwann cells (SCs) re-enter the cell cycle, change their expression profile, and exert repair functions important for wound healing and the re-growth of axons. While this phenotypical instability of SCs is essential for nerve regeneration, it has also been implicated in cancer progression and de-myelinating neuropathies. Thus, SCs became an important research tool to study the molecular mechanisms involved in repair and disease and to identify targets for therapeutic intervention. A high purity of isolated SC cultures used for experimentation must be demonstrated to exclude that novel findings are derived from a contaminating fibroblasts population. In addition, information about the SC proliferation status is an important parameter to be determined in response to different treatments. The evaluation of SC purity and proliferation, however, usually depends on the time consuming, manual assessment of immunofluorescence stainings or comes with the sacrifice of a large amount of SCs for flow cytometry analysis. We here show that rat SC culture derived cytospins stained for SC marker SOX10, proliferation marker EdU, intermediate filament vimentin and DAPI allowed the determination of SC identity and proliferation by requiring only a small number of cells. Furthermore, the CellProfiler software was used to develop an automated image analysis pipeline that quantified SCs and proliferating SCs from the obtained immunofluorescence images. By comparing the results of total cell count, SC purity and SC proliferation rate between manual counting and the CellProfiler output, we demonstrated applicability and reliability of the established pipeline. In conclusion, we here combined the cytospin technique, a multi-colour immunofluorescence staining panel, and an automated image analysis pipeline to enable the quantification of SC purity and SC proliferation from small cell aliquots. This procedure represents a solid read-out to simplify and standardize the quantification of primary SC culture purity and proliferation.
Collapse
Affiliation(s)
- Tamara Weiss
- Research Laboratory of the Division of Plastic and Reconstructive Surgery, Department of Surgery, Medical University of Vienna, Vienna, Austria
- * E-mail:
| | - Lorenz Semmler
- Research Laboratory of the Division of Plastic and Reconstructive Surgery, Department of Surgery, Medical University of Vienna, Vienna, Austria
| | - Flavia Millesi
- Research Laboratory of the Division of Plastic and Reconstructive Surgery, Department of Surgery, Medical University of Vienna, Vienna, Austria
| | - Anda Mann
- Research Laboratory of the Division of Plastic and Reconstructive Surgery, Department of Surgery, Medical University of Vienna, Vienna, Austria
| | - Maximilian Haertinger
- Research Laboratory of the Division of Plastic and Reconstructive Surgery, Department of Surgery, Medical University of Vienna, Vienna, Austria
| | - Manuel Salzmann
- Institute of Vascular Biology and Thrombosis Research, Medical University of Vienna, Vienna, Austria
| | - Christine Radtke
- Research Laboratory of the Division of Plastic and Reconstructive Surgery, Department of Surgery, Medical University of Vienna, Vienna, Austria
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Medical University of Vienna, Vienna, Austria
| |
Collapse
|
41
|
Iriya R, Jing W, Syal K, Mo M, Chen C, Yu H, Haydel SE, Wang S, Tao N. Rapid antibiotic susceptibility testing based on bacterial motion patterns with long short-term memory neural networks. IEEE SENSORS JOURNAL 2020; 20:4940-4950. [PMID: 32440258 PMCID: PMC7241544 DOI: 10.1109/jsen.2020.2967058] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/16/2023]
Abstract
Antibiotic resistance is an increasing public health threat. To combat it, a fast method to determine the antibiotic susceptibility of infecting pathogens is required. Here we present an optical imaging-based method to track the motion of single bacterial cells and generate a model to classify active and inactive cells based on the motion patterns of the individual cells. The model includes an image-processing algorithm to segment individual bacterial cells and track the motion of the cells over time, and a deep learning algorithm (Long Short-Term Memory network) to learn and determine if a bacterial cell is active or inactive. By applying the model to human urine specimens spiked with an Escherichia coli lab strain, we show that the method can accurately perform antibiotic susceptibility testing as fast as 30 minutes for five commonly used antibiotics.
Collapse
Affiliation(s)
- Rafael Iriya
- School of Electrical, Computer and Energy engineering, Arizona State University, Tempe, AZ, 85287, USA
| | - Wenwen Jing
- The Biodesign Center for Biosensors and Bioelectronics, Arizona State University, Tempe, AZ, 85287, USA
| | - Karan Syal
- The Biodesign Center for Biosensors and Bioelectronics, Arizona State University, Tempe, AZ, 85287, USA
| | - Manni Mo
- The Biodesign Center for Biosensors and Bioelectronics, Arizona State University, Tempe, AZ, 85287, USA
| | - Chao Chen
- The Biodesign Center for Biosensors and Bioelectronics, Arizona State University, Tempe, AZ, 85287, USA
| | - Hui Yu
- Institute for Personalized Medicine, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China
| | - Shelley E Haydel
- School of Life Sciences, Arizona State University, Tempe, AZ, 85287, USA
| | - Shaopeng Wang
- The Biodesign Center for Biosensors and Bioelectronics, Arizona State University, Tempe, AZ, 85287, USA
| | - Nongjian Tao
- School of Electrical, Computer and Energy engineering, Arizona State University, Tempe, AZ, 85287, USA
| |
Collapse
|
42
|
Baum D, Weaver JC, Zlotnikov I, Knötel D, Tomholt L, Dean MN. High-Throughput Segmentation of Tiled Biological Structures using Random-Walk Distance Transforms. Integr Comp Biol 2020; 59:1700-1712. [PMID: 31282926 PMCID: PMC6907396 DOI: 10.1093/icb/icz117] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022] Open
Abstract
Various 3D imaging techniques are routinely used to examine biological materials, the results of which are usually a stack of grayscale images. In order to quantify structural aspects of the biological materials, however, they must first be extracted from the dataset in a process called segmentation. If the individual structures to be extracted are in contact or very close to each other, distance-based segmentation methods utilizing the Euclidean distance transform are commonly employed. Major disadvantages of the Euclidean distance transform, however, are its susceptibility to noise (very common in biological data), which often leads to incorrect segmentations (i.e., poor separation of objects of interest), and its limitation of being only effective for roundish objects. In the present work, we propose an alternative distance transform method, the random-walk distance transform, and demonstrate its effectiveness in high-throughput segmentation of three microCT datasets of biological tilings (i.e., structures composed of a large number of similar repeating units). In contrast to the Euclidean distance transform, the random-walk approach represents the global, rather than the local, geometric character of the objects to be segmented and, thus, is less susceptible to noise. In addition, it is directly applicable to structures with anisotropic shape characteristics. Using three case studies—tessellated cartilage from a stingray, the dermal endoskeleton of a starfish, and the prismatic layer of a bivalve mollusc shell—we provide a typical workflow for the segmentation of tiled structures, describe core image processing concepts that are underused in biological research, and show that for each study system, large amounts of biologically-relevant data can be rapidly segmented, visualized, and analyzed.
Collapse
Affiliation(s)
- Daniel Baum
- Department of Visual Data Analysis, Zuse Institute Berlin, Berlin, Germany
| | - James C Weaver
- Wyss Institute for Biologically Inspired Engineering, Harvard University, Cambridge, MA, USA
| | - Igor Zlotnikov
- B CUBE-Center for Molecular Bioengineering, Technische Universität Dresden, Dresden, Germany
| | - David Knötel
- Department of Visual Data Analysis, Zuse Institute Berlin, Berlin, Germany
| | - Lara Tomholt
- Wyss Institute for Biologically Inspired Engineering, Harvard University, Cambridge, MA, USA.,Harvard Graduate School of Design, Harvard University, Cambridge, MA, USA
| | - Mason N Dean
- Max Planck Institute of Colloids and Interfaces, Department of Biomaterials, Research Campus Golm, Potsdam, Germany
| |
Collapse
|
43
|
Pandey S, Singh PR, Tian J. An image augmentation approach using two-stage generative adversarial network for nuclei image segmentation. Biomed Signal Process Control 2020. [DOI: 10.1016/j.bspc.2019.101782] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
44
|
Xu Y, Wu T, Gao F, Charlton JR, Bennett KM. Improved small blob detection in 3D images using jointly constrained deep learning and Hessian analysis. Sci Rep 2020; 10:326. [PMID: 31941994 PMCID: PMC6962386 DOI: 10.1038/s41598-019-57223-y] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2019] [Accepted: 12/20/2019] [Indexed: 12/23/2022] Open
Abstract
Imaging biomarkers are being rapidly developed for early diagnosis and staging of disease. The development of these biomarkers requires advances in both image acquisition and analysis. Detecting and segmenting objects from images are often the first steps in quantitative measurement of these biomarkers. The challenges of detecting objects in images, particularly small objects known as blobs, include low image resolution, image noise and overlap between the blobs. The Difference of Gaussian (DoG) detector has been used to overcome these challenges in blob detection. However, the DoG detector is susceptible to over-detection and must be refined for robust, reproducible detection in a wide range of medical images. In this research, we propose a joint constraint blob detector from U-Net, a deep learning model, and Hessian analysis, to overcome these problems and identify true blobs from noisy medical images. We evaluate this approach, UH-DoG, using a public 2D fluorescent dataset for cell nucleus detection and a 3D kidney magnetic resonance imaging dataset for glomerulus detection. We then compare this approach to methods in the literature. While comparable to the other four comparing methods on recall, the UH-DoG outperforms them on both precision and F-score.
Collapse
Affiliation(s)
- Yanzhe Xu
- School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, 699S Mill Ave, Tempe, AZ, 85281, USA
| | - Teresa Wu
- School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, 699S Mill Ave, Tempe, AZ, 85281, USA.
| | - Fei Gao
- School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, 699S Mill Ave, Tempe, AZ, 85281, USA
| | - Jennifer R Charlton
- Department of Pediatrics, Division Nephrology, University of Virginia, Charlottesville, VA, 22908, USA
| | - Kevin M Bennett
- Department of Radiology, Washington University, St. Louis, MO, 63130, USA
| |
Collapse
|
45
|
Caicedo JC, Goodman A, Karhohs KW, Cimini BA, Ackerman J, Haghighi M, Heng C, Becker T, Doan M, McQuin C, Rohban M, Singh S, Carpenter AE. Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl. Nat Methods 2019; 16:1247-1253. [PMID: 31636459 PMCID: PMC6919559 DOI: 10.1038/s41592-019-0612-7] [Citation(s) in RCA: 238] [Impact Index Per Article: 47.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/02/2018] [Accepted: 09/13/2019] [Indexed: 01/15/2023]
Abstract
Segmenting the nuclei of cells in microscopy images is often the first step in the quantitative analysis of imaging data for biological and biomedical applications. Many bioimage analysis tools can segment nuclei in images but need to be selected and configured for every experiment. The 2018 Data Science Bowl attracted 3,891 teams worldwide to make the first attempt to build a segmentation method that could be applied to any two-dimensional light microscopy image of stained nuclei across experiments, with no human interaction. Top participants in the challenge succeeded in this task, developing deep-learning-based models that identified cell nuclei across many image types and experimental conditions without the need to manually adjust segmentation parameters. This represents an important step toward configuration-free bioimage analysis software tools.
Collapse
Affiliation(s)
| | - Allen Goodman
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
| | | | - Beth A Cimini
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
| | | | | | | | - Tim Becker
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
| | - Minh Doan
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
| | - Claire McQuin
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
| | | | | | | |
Collapse
|
46
|
Acs B, Ahmed FS, Gupta S, Wong PF, Gartrell RD, Sarin Pradhan J, Rizk EM, Gould Rothberg B, Saenger YM, Rimm DL. An open source automated tumor infiltrating lymphocyte algorithm for prognosis in melanoma. Nat Commun 2019; 10:5440. [PMID: 31784511 PMCID: PMC6884485 DOI: 10.1038/s41467-019-13043-2] [Citation(s) in RCA: 54] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2019] [Accepted: 10/15/2019] [Indexed: 12/15/2022] Open
Abstract
Assessment of tumor infiltrating lymphocytes (TILs) as a prognostic variable in melanoma has not seen broad adoption due to lack of standardization. Automation could represent a solution. Here, using open source software, we build an algorithm for image-based automated assessment of TILs on hematoxylin-eosin stained sections in melanoma. Using a retrospective collection of 641 melanoma patients comprising four independent cohorts; one training set (N = 227) and three validation cohorts (N = 137, N = 201, N = 76) from 2 institutions, we show that the automated TIL scoring algorithm separates patients into favorable and poor prognosis cohorts, where higher TILs scores were associated with favorable prognosis. In multivariable analyses, automated TIL scores show an independent association with disease-specific overall survival. Therefore, the open source, automated TIL scoring is an independent prognostic marker in melanoma. With further study, we believe that this algorithm could be useful to define a subset of patients that could potentially be spared immunotherapy.
Collapse
Affiliation(s)
- Balazs Acs
- Department of Pathology, Yale School of Medicine, New Haven, CT, 06510, USA.,Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden
| | | | - Swati Gupta
- Department of Pathology, Yale School of Medicine, New Haven, CT, 06510, USA
| | - Pok Fai Wong
- Department of Pathology, Yale School of Medicine, New Haven, CT, 06510, USA
| | - Robyn D Gartrell
- Department of Medicine, Division of Hematology/Oncology, Columbia University Medical Center/New York Presbyterian, New York, NY, USA
| | - Jaya Sarin Pradhan
- Department of Pathology and Cell Biology, Division of Oral and Maxillofacial Pathology, Columbia University Irving Medical Center/New York Presbyterian, New York, NY, USA
| | - Emanuelle M Rizk
- Department of Medicine, Division of Hematology/Oncology, Columbia University Irving Medical Center/New York Presbyterian, New York, NY, USA
| | | | - Yvonne M Saenger
- Department of Medicine, Division of Hematology/Oncology, Columbia University Irving Medical Center/New York Presbyterian, New York, NY, USA
| | - David L Rimm
- Department of Pathology, Yale School of Medicine, New Haven, CT, 06510, USA. .,Department of Medicine, Yale School of Medicine, New Haven, CT, 06510, USA.
| |
Collapse
|
47
|
Vinegoni C, Feruglio PF, Gryczynski I, Mazitschek R, Weissleder R. Fluorescence anisotropy imaging in drug discovery. Adv Drug Deliv Rev 2019; 151-152:262-288. [PMID: 29410158 PMCID: PMC6072632 DOI: 10.1016/j.addr.2018.01.019] [Citation(s) in RCA: 37] [Impact Index Per Article: 7.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2017] [Revised: 01/29/2018] [Accepted: 01/30/2018] [Indexed: 12/15/2022]
Abstract
Non-invasive measurement of drug-target engagement can provide critical insights in the molecular pharmacology of small molecule drugs. Fluorescence polarization/fluorescence anisotropy measurements are commonly employed in protein/cell screening assays. However, the expansion of such measurements to the in vivo setting has proven difficult until recently. With the advent of high-resolution fluorescence anisotropy microscopy it is now possible to perform kinetic measurements of intracellular drug distribution and target engagement in commonly used mouse models. In this review we discuss the background, current advances and future perspectives in intravital fluorescence anisotropy measurements to derive pharmacokinetic and pharmacodynamic measurements in single cells and whole organs.
Collapse
Affiliation(s)
- Claudio Vinegoni
- Center for System Biology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
| | - Paolo Fumene Feruglio
- Center for System Biology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA; Department of Neurological, Biomedical and Movement Sciences, University of Verona, Verona, Italy
| | - Ignacy Gryczynski
- University of North Texas Health Science Center, Institute for Molecular Medicine, Fort Worth, TX, United States
| | - Ralph Mazitschek
- Center for System Biology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Ralph Weissleder
- Center for System Biology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| |
Collapse
|
48
|
Abstract
Embryonic development is highly complex and dynamic, requiring the coordination of numerous molecular and cellular events at precise times and places. Advances in imaging technology have made it possible to follow developmental processes at cellular, tissue, and organ levels over time as they take place in the intact embryo. Parallel innovations of in vivo probes permit imaging to report on molecular, physiological, and anatomical events of embryogenesis, but the resulting multidimensional data sets pose significant challenges for extracting knowledge. In this review, we discuss recent and emerging advances in imaging technologies, in vivo labeling, and data processing that offer the greatest potential for jointly deciphering the intricate cellular dynamics and the underlying molecular mechanisms. Our discussion of the emerging area of “image-omics” highlights both the challenges of data analysis and the promise of more fully embracing computation and data science for rapidly advancing our understanding of biology.
Collapse
Affiliation(s)
- Francesco Cutrale
- Department of Biomedical Engineering, University of Southern California, Los Angeles, California 90089, USA
- Translational Imaging Center, University of Southern California, Los Angeles, California 90089, USA
| | - Scott E. Fraser
- Department of Biomedical Engineering, University of Southern California, Los Angeles, California 90089, USA
- Translational Imaging Center, University of Southern California, Los Angeles, California 90089, USA
- Division of Molecular and Computational Biology, Department of Biological Sciences, University of Southern California, Los Angeles, California 90089, USA
| | - Le A. Trinh
- Translational Imaging Center, University of Southern California, Los Angeles, California 90089, USA
- Division of Molecular and Computational Biology, Department of Biological Sciences, University of Southern California, Los Angeles, California 90089, USA
| |
Collapse
|
49
|
Klauschen F, Müller KR, Binder A, Bockmayr M, Hägele M, Seegerer P, Wienert S, Pruneri G, de Maria S, Badve S, Michiels S, Nielsen T, Adams S, Savas P, Symmans F, Willis S, Gruosso T, Park M, Haibe-Kains B, Gallas B, Thompson A, Cree I, Sotiriou C, Solinas C, Preusser M, Hewitt S, Rimm D, Viale G, Loi S, Loibl S, Salgado R, Denkert C. Scoring of tumor-infiltrating lymphocytes: From visual estimation to machine learning. Semin Cancer Biol 2018; 52:151-157. [DOI: 10.1016/j.semcancer.2018.07.001] [Citation(s) in RCA: 61] [Impact Index Per Article: 10.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2018] [Revised: 07/01/2018] [Accepted: 07/02/2018] [Indexed: 12/12/2022]
|
50
|
IFN-γ-response mediator GBP-1 represses human cell proliferation by inhibiting the Hippo signaling transcription factor TEAD. Biochem J 2018; 475:2955-2967. [PMID: 30120107 PMCID: PMC6156764 DOI: 10.1042/bcj20180123] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2018] [Revised: 08/03/2018] [Accepted: 08/17/2018] [Indexed: 12/28/2022]
Abstract
Interferon-gamma (IFN-γ) is a pleiotropic cytokine that exerts important functions in inflammation, infectious diseases, and cancer. The large GTPase human guanylate-binding protein 1 (GBP-1) is among the most strongly IFN-γ-induced cellular proteins. Previously, it has been shown that GBP-1 mediates manifold cellular responses to IFN-γ including the inhibition of proliferation, spreading, migration, and invasion and through this exerts anti-tumorigenic activity. However, the mechanisms of GBP-1 anti-tumorigenic activities remain poorly understood. Here, we elucidated the molecular mechanism of the human GBP-1-mediated suppression of proliferation by demonstrating for the first time a cross-talk between the anti-tumorigenic IFN-γ and Hippo pathways. The α9-helix of GBP-1 was found to be sufficient to inhibit proliferation. Protein-binding and molecular modeling studies revealed that the α9-helix binds to the DNA-binding domain of the Hippo signaling transcription factor TEA domain protein (TEAD) mediated by the 376VDHLFQK382 sequence at the N-terminus of the GBP-1-α9-helix. Mutation of this sequence resulted in abrogation of both TEAD interaction and suppression of proliferation. Further on, the interaction caused inhibition of TEAD transcriptional activity associated with the down-regulation of TEAD-target genes. In agreement with these results, IFN-γ treatment of the cells also impaired TEAD activity, and this effect was abrogated by siRNA-mediated inhibition of GBP-1 expression. Altogether, this demonstrated that the α9-helix is the proliferation inhibitory domain of GBP-1, which acts independent of the GTPase activity through the inhibition of the Hippo transcription factor TEAD in mediating the anti-proliferative cell response to IFN-γ.
Collapse
|