Comparison and practical review of segmentation approaches for label-free microscopy

<p>This dataset contains microscopic images of PNT1A cell line captured by multiple microcopic without use of any labeling and a manually annotated ground truth for subsequent use in segmentation algorithms. Dataset also includes images reconstructed according to the methods described below in order to ease further segmentation. </p> <p><strong>Materials and methods </strong></p> <p>Cells were cultured in RPMI-1640 medium supplemented with antibiotics (penicillin 100 U/ml and streptomycin 0.1 mg/ml) with 10% fetal bovine serum. Prior microscopy acquisition, cells were maintained at 37 cenigrade in a humidified incubator with 5% CO2. Intentionally, high passage number of cells was used (>30) in order to describe distinct morphological heterogeneity of cells (rounded and spindle-shaped, relatively small to large polyploid cells). For acquisition purposes, cells were cultivated in Flow chambers µ-Slide I Luer Family (Ibidi, Martinsried, Germany).</p> <p>Quantitative phase imaging (QPI) microscopy was performed on Tescan Q-PHASE (Tescan, Brno, Czech republic), with objective Nikon CFI Plan Fluor 10x/0.30 captured by Ximea MR4021MC (Ximea, Münster, Germany). Imaging is based on the original concept of coherence-controlled holographic microscope \cite{Kolman:10,Slaby:13}, images are shown in grayscale with units of pg/µm2.</p> <p>DIC microscopy was performed on microscope Nikon A1R (Nikon, Tokyo, Japan), with objective Nikon CFI Plan Apo VC 20x/0.75 captured by CCD camera Jenoptik ProgRes MF (Jenoptik, Jena, Germany). </p> <p>HMC microscopy was performed on microscope Olympus IX71 (Olympus, Tokyo, Japan), with objective Olympus CplanFL N 10x/0.3 RC1 captured by CCD camera Hamamatsu Photonics ORCA-R2 (Hamamatsu Photonics K.K., Hamamatsu, Japan).</p> <p>PC microscopy was performed on a Nikon Eclipse TS100-F microscope, with a Nikon CFI Achro ADL 10x/0.25 objective captured by CCD camera Jenoptik ProgRes MF.</p> <p><strong>Folder structure and file and filename description</strong><br> <br> <em>folder "source data+groundtruth"</em><br> - includes raw microscopic data <br> (uncompressed 16-bit for DIC, HMC and PC, 32-bit for QPI)<br> - includes manualy annotated groundtruth (zip file - imageJ ROI file, 1bit png mask)</p> <p>e.g. <br> DIC_01_raw.tif<br> DIC_01_groundtruth_imagejROI.zip<br> DIC_01_groundtruth_mask.png</p> <p><br> <em>folder "reconstructions"</em></p> <p>includes reconstructed images using reconstructions with highest dice coefficient achieved. </p> <p>for DIC and HMC: rDIC-Koos, rDIC-Yin, and rWeka<br> for PC: rPC-Top-Hat, rDIC-Yin, and rWeka<br> for QPI: rWeka</p> <p>note that for rWeka images numbered 01 for DIC, HMC and PC and 01-03 for QPI were used for learning.</p> <p><strong>Abbreviations</strong><br> DIC, differential image contrast<br> HMC, Hoffman modulation contrast<br> PC, phase contrast<br> QPI, quantitative phase imaging<br> rDIC-Koos, DIC/HMC image reconstruction according to Koos et al, Sci Rep. 2016;6:30420<br> rDIC-Yin, DIC/HMC image reconstruction according to Yin et al, Inf Process Med Imaging. 2011;22:384-97.<br> rPC-Yin, PC image reconstruction according to Yin et al, Med Im Anal. 2012; 16(5):1047<br> rPC-Top-Hat, Top-Hat filter according to Dewan et al, IEEE Transactions on Biomedical Circuits and<br> Systems.2014;8(5):716-728<br> rWeka, probability map using Trainable Weka segmentation according to Arganda-Carreras et al. Bioinformatics. 2017