Data augmentation for training deep regression for in vitro cell detection

2019 ◽  
Author(s):  
Olivier Debeir ◽  
Christine Decaestecker
Keyword(s):  
Data Augmentation ◽  
Cell Detection

scholarly journals Integration of autopatching with automated pipette and cell detection in vitro

2016 ◽  
Vol 116 (4) ◽  
pp. 1564-1578 ◽  
Author(s):  
Qiuyu Wu (吴秋雨) ◽  
Ilya Kolb ◽  
Brendan M. Callahan ◽  
Zhaolun Su ◽  
William Stoy ◽  
...  
Keyword(s):  
Computer Vision ◽  
Cell Membrane ◽  
Patch Clamp ◽  
Brain Slices ◽  
Cell Detection ◽  
Trial Duration ◽  
Electrophysiological Recordings ◽  
Main Technique ◽  
Simplex Virus

Patch clamp is the main technique for measuring electrical properties of individual cells. Since its discovery in 1976 by Neher and Sakmann, patch clamp has been instrumental in broadening our understanding of the fundamental properties of ion channels and synapses in neurons. The conventional patch-clamp method requires manual, precise positioning of a glass micropipette against the cell membrane of a visually identified target neuron. Subsequently, a tight “gigaseal” connection between the pipette and the cell membrane is established, and suction is applied to establish the whole cell patch configuration to perform electrophysiological recordings. This procedure is repeated manually for each individual cell, making it labor intensive and time consuming. In this article we describe the development of a new automatic patch-clamp system for brain slices, which integrates all steps of the patch-clamp process: image acquisition through a microscope, computer vision-based identification of a patch pipette and fluorescently labeled neurons, micromanipulator control, and automated patching. We validated our system in brain slices from wild-type and transgenic mice expressing channelrhodopsin 2 under the Thy1 promoter (line 18) or injected with a herpes simplex virus-expressing archaerhodopsin, ArchT. Our computer vision-based algorithm makes the fluorescent cell detection and targeting user independent. Compared with manual patching, our system is superior in both success rate and average trial duration. It provides more reliable trial-to-trial control of the patching process and improves reproducibility of experiments.

Deep Learning–Based Detection of Endothelial Tip Cells in the Oxygen-Induced Retinopathy Model

2020 ◽  
pp. 019262332097296
Author(s):  
Igor Zingman ◽  
Nina Zippel ◽  
Gerald Birk ◽  
Sebastian Eder ◽  
Leo Thomas ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Neuronal Damage ◽  
Mouse Retina ◽  
Cell Detection ◽  
Single Shot ◽  
Training Procedure ◽  
Oxygen Induced Retinopathy ◽  
Detection Of Objects ◽  
Proliferative Retinopathies ◽  
Tip Cells

Proliferative retinopathies, such as diabetic retinopathy and retinopathy of prematurity, are leading causes of vision impairment. A common feature is a loss of retinal capillary vessels resulting in hypoxia and neuronal damage. The oxygen-induced retinopathy model is widely used to study revascularization of an ischemic area in the mouse retina. The presence of endothelial tip cells indicates vascular recovery; however, their quantification relies on manual counting in microscopy images of retinal flat mount preparations. Recent advances in deep neural networks (DNNs) allow the automation of such tasks. We demonstrate a workflow for detection of tip cells in retinal images using the DNN-based Single Shot Detector (SSD). The SSD was designed for detection of objects in natural images. We adapt the SSD architecture and training procedure to the tip cell detection task and retrain the DNN using labeled tip cells in images of fluorescently stained retina flat mounts. Transferring knowledge from the pretrained DNN and extensive data augmentation reduced the amount of required labeled data. Our system shows a performance comparable to the human level, while providing highly consistent results. Therefore, such a system can automate counting of tip cells, a readout frequently used in retinopathy research, thereby reducing routine work for biomedical experts.

A novel fibroblast activation protein-targeted near-infrared fluorescent off–on probe for cancer cell detection, in vitro and in vivo imaging

2018 ◽  
Vol 6 (10) ◽  
pp. 1449-1451 ◽  
Author(s):  
Jie Xing ◽  
Qiuyu Gong ◽  
Ruifen Zou ◽  
Zihou Li ◽  
Yuanzhi Xia ◽  
...  
Keyword(s):  
Fluorescent Probe ◽  
In Vivo Imaging ◽  
Near Infrared ◽  
Fibroblast Activation Protein ◽  
Cell Detection ◽  
Fibroblast Activation ◽  
Design And Synthesis ◽  
Cancer Cell Detection

Design and synthesis of a novel fibroblast activation protein “off–on” near-infrared fluorescent probe for cell detection, in vitro and in vivo imaging.

69 QUALITY OF IN VITRO PRODUCED AND CRYOPRESERVED PORCINE EMBRYOS ASSESSED BY CELL NUMBER, TUNEL-POSITIVE NUCLEI, AND CASPASE-3 ACTIVITY

2011 ◽  
Vol 23 (1) ◽  
pp. 140
Author(s):  
M. Bryla ◽  
M. Trzcinska ◽  
B. Gajda
Keyword(s):  
In Vitro Culture ◽  
Caspase 3 ◽  
Preimplantation Embryos ◽  
Lower Percentage ◽  
Cell Detection ◽  
Large White ◽  
Number Of Cells

The aim of this experiment was to investigate the quality of in vitro cultured and cryopreserved porcine expanded blastocysts from Day 5, 6, and 7 of culture. The quality of the preimplantation embryos was determined by counting the number of cells, observing a TUNEL-positive reaction (TUNEL reagent; In Situ Cell Detection kit, Roche Diagnostics, Germany) and by caspase-3 labelling (PhiPhiLuxG2D2 Kit, Calbiochem, Germany). Embryos were collected from 32 superovulated donor gilts. All were crossbreds of Polish Landrace and Large White, age 6–8 months, weighing 90–100 kg. The experiment was done on 2–4 cell embryos produced in vivo and cultured in vitro for 7 days in NCSU-23 medium until expanding blastocyst stage. The embryos of this stage were obtained on Day 5, 6, and 7 of in vitro culture and divided into two groups: control-(1) 210 nonvitrified (NV) embryos and -(2) vitrified/thawed (VT) 169 embryos. The expanded blastocysts were vitrified the open pulled straw (OPS) method (Vajta 2000 Anim. Reprod. Sci. 60–61, 357–364). The results were analyzed by Student’s t-test, and all values were significant at P ≤ 0.05. The NV group of embryos showed significant differences in the number of cells (66.5 ± 24.0 v. 54.8 ± 15.9) and in TUNEL-positive nuclei (8.8 ± 12.5 v. 16.2 ± 14.9) between Day 5 and Day 7 of culture, respectively. Analysis of VT embryos also revealed significant differences in the number of cells (65.2 ± 17.4 v. 55.5 ± 14.3) and in TUNEL-positive nuclei (25.5 ± 16.4 v. 35.8 ± 19.3) between Day 5 and Day 7 of culture, respectively. Lower percentage of NT and VT blastocysts produced on Day 5 of culture revealed caspase-3 activity (51.3 v. 64.8%) compared with embryos on Day 7 (76.8 v. 89.3%), respectively. In conclusion, blastocysts cultured in vitro for 5 days consist of a high number of nuclei, have a low incidence of TUNEL-positive nuclei, and low caspase-3 activity compared with blastocysts cultured for 6 and 7 days in all analysed groups. Our results revealed that expanding blastocysts produced on Day 5 of in vitro culture had higher ability to survive vitrification/thawing procedure. This work was supported by Grant NR 12 0036 06 from the National Centre of Research and Development, Poland.

scholarly journals Genetically encoded cell-death indicators (GEDI) to detect an early irreversible commitment to neurodegeneration

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Jeremy W. Linsley ◽  
Kevan Shah ◽  
Nicholas Castello ◽  
Michelle Chan ◽  
Dominik Haddad ◽  
...  
Keyword(s):  
Cell Death ◽  
Time Lapse ◽  
Death Process ◽  
Cell Detection ◽  
High Throughput Analysis ◽  
Time Resolved ◽  
Single Cell Detection ◽  
Human Neurons

AbstractCell death is a critical process that occurs normally in health and disease. However, its study is limited due to available technologies that only detect very late stages in the process or specific death mechanisms. Here, we report the development of a family of fluorescent biosensors called genetically encoded death indicators (GEDIs). GEDIs specifically detect an intracellular Ca2+ level that cells achieve early in the cell death process and that marks a stage at which cells are irreversibly committed to die. The time-resolved nature of a GEDI delineates a binary demarcation of cell life and death in real time, reformulating the definition of cell death. We demonstrate that GEDIs acutely and accurately report death of rodent and human neurons in vitro, and show that GEDIs enable an automated imaging platform for single cell detection of neuronal death in vivo in zebrafish larvae. With a quantitative pseudo-ratiometric signal, GEDIs facilitate high-throughput analysis of cell death in time-lapse imaging analysis, providing the necessary resolution and scale to identify early factors leading to cell death in studies of neurodegeneration.

Expression of MUC-1 Epitopes on Normal Bone Marrow: Implications for the Detection of Micrometastatic Tumor Cells

1999 ◽  
Vol 17 (5) ◽  
pp. 1535-1535 ◽  
Author(s):  
Wolfram Brugger ◽  
Hans-Jörg Bühring ◽  
Frank Grünebach ◽  
Wichard Vogel ◽  
Sepp Kaul ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Tumor Cell ◽  
Western Blotting ◽  
Mononuclear Cells ◽  
Cell Detection ◽  
Tumor Cell Detection ◽  
Peripheral Blood Progenitor Cells ◽  
Normal Human ◽  
Positive Results

PURPOSE: The expression of the carcinoma-associated mucin MUC-1 is thought to be restricted to epithelial cells and is used for micrometastatic tumor cell detection in patients with solid tumors, including those with breast cancer. Little is known, however, about the expression of MUC-1 epitopes in normal hematopoietic cells. MATERIALS AND METHODS: MUC-1 expression was analyzed by flow cytometry and immunocytology on bone marrow (BM) mononuclear cells and purified CD34+ cells from healthy volunteers, using different anti-MUC-1–specific monoclonal antibodies. In addition, Western blotting of MUC-1 proteins was performed. RESULTS: Surprisingly, 2% to 10% of normal human BM mononuclear cells expressed MUC-1, as defined by the anti–MUC-1 antibodies BM-2 (2E11), BM-7, 12H12, MAM-6, and HMFG-1. In contrast, two antibodies recognizing the BM-8 and the HMFG-2 epitopes of MUC-1 were not detected. MUC-1+ cells from normal BM consisted primarily of erythroblasts and normoblasts. In agreement with this, normal CD34+ cells cultured in vitro to differentiate into the erythroid lineage showed a strong MUC-1 expression on day 7 proerythroblasts. Western blotting of these cells confirmed that the reactive species is the known high molecular weight MUC-1 protein. CONCLUSION: Our data demonstrate that some MUC-1 epitopes are expressed on normal BM cells and particularly on cells of the erythroid lineage. Hence the application of anti–MUC-1 antibodies for disseminated tumor cell detection in BM or peripheral blood progenitor cells may provide false-positive results, and only carefully evaluated anti–MUC-1 antibodies (eg, HMFG-2) might be selected. Furthermore, MUC-1–targeted immunotherapy in cancer patients might be hampered by the suppression of erythropoiesis.

scholarly journals Automatic deep learning driven label-free image guided patch clamp system for human and rodent in vitro slice physiology

2020 ◽  
Author(s):  
Krisztian Koos ◽  
Gáspár Oláh ◽  
Tamas Balassa ◽  
Norbert Mihut ◽  
Márton Rózsa ◽  
...  
Keyword(s):  
Image Analysis ◽  
Deep Learning ◽  
Patch Clamp ◽  
Brain Research ◽  
Brain Slices ◽  
Cell Detection ◽  
Label Free ◽  
Patch Clamp Recording ◽  
Tissue Slices

ABSTRACTPatch clamp recording of neurons is a labor-intensive and time-consuming procedure. We have developed a tool that fully automatically performs electrophysiological recordings in label-free tissue slices. The automation covers the detection of cells in label-free images, calibration of the micropipette movement, approach to the cell with the pipette, formation of the whole-cell configuration, and recording. The cell detection is based on deep learning. The model was trained on a new image database of neurons in unlabeled brain tissue slices. The pipette tip detection and approaching phase use image analysis techniques for precise movements. High-quality measurements were performed on hundreds of human and rodent neurons. We also demonstrate that further molecular and anatomical analysis can be performed on the recorded cells. The software has a diary module that automatically logs patch clamp events. Our tool can multiply the number of daily measurements to help brain research.ONE SENTENCE SUMMARYNovel deep learning and image analysis algorithms for automated patch clamp systems to reliably measure neurons in human and rodent brain slices.

scholarly journals Genetically encoded cell-death indicators (GEDI) to detect an early irreversible commitment to neurodegeneration

2019 ◽  
Author(s):  
Jeremy W. Linsley ◽  
Kevan Shah ◽  
Nicholas Castello ◽  
Michelle Chan ◽  
Dominic Haddad ◽  
...  
Keyword(s):  
Cell Death ◽  
Time Lapse ◽  
Death Process ◽  
Cell Detection ◽  
High Throughput Analysis ◽  
Time Resolved ◽  
Single Cell Detection ◽  
Human Neurons

AbstractCell death is a critical process that occurs normally in health and disease. However, its study is limited due to available technologies that only detect very late stages in the process or specific death mechanisms. Here, we report the development of a new fluorescent biosensor called genetically encoded death indicator (GEDI). GEDI specifically detects an intracellular Ca2+ level that cells achieve early in the cell death process and marks a stage at which cells are irreversibly committed to die. The time-resolved nature of GEDI delineates a binary demarcation of cell life and death in real time, reformulating the definition of cell death. We demonstrate that GEDI acutely and accurately reports death of rodent and human neurons in vitro, and show GEDI enables a novel automated imaging platform for single cell detection of neuronal death in vivo in zebrafish larvae. With a quantitative pseudo-ratiometric signal, GEDI facilitates high-throughput analysis of cell death in time lapse imaging analysis, providing the necessary resolution and scale to identify early factors leading to cell death in studies of neurodegeneration.

A lysosome-specific near-infrared fluorescent probe for in vitro cancer cell detection and non-invasive in vivo imaging

2019 ◽  
Vol 55 (94) ◽  
pp. 14182-14185 ◽  
Author(s):  
Rakesh Mengji ◽  
Chiranjit Acharya ◽  
Venugopal Vangala ◽  
Avijit Jana
Keyword(s):  
Clinical Practice ◽  
Fluorescent Probe ◽  
Fluorescent Probes ◽  
In Vivo Imaging ◽  
Near Infrared ◽  
Cell Detection ◽  
Non Invasive ◽  
Cancer Cell Detection

Near-infrared (NIR) fluorescent probes have been developed as potential bio-materials having profound applications in diagnosis and clinical practice.

Sign in / Sign up

Export Citation Format

Share Document