17 Matching Annotations
  1. Jun 2024
    1. virtually stained images are intrinsically denoised because the models cannot learn to predict random noise.

      Intrinsically denoised, sure, but noisy training data may still lead to a smoothed/blurred prediction. Are there techniques you have experimented with to sharpen predictions or has this not been an issue in your experience?

    2. Virtually and experimentally stained nuclei and membranes are segmented using the same Cellpose model.

      For many applications the virtual staining could be seen as a means to an end: segmentation. Is the intermediate step of predicting the virtual stain necessary or would it be feasible to skip straight to the segmentation by e.g. merging the Cellpose segmentation model?

    3. trade-offs between spatial resolution, temporal resolution, number of channels, and photodamage

      not to mention dataset sizes.

  2. Mar 2024
    1. The predicted classes agreed well with the class representations and the fluorescence images themselves

      Can this claim be quantified without deferring to a figure?

    2. Figure 1

      The class representations of cell type 1 and cell type K are not very well differentiated.

    3. Supplementary Figures 1-2

      IMO Supplemental figures 1 and 2 would be more clear and succinct as heatmaps than line plots.

    4. ideal

      You provide a clear explanation of how you generate the pseudospectra in the methods, but I question the use of "ideal" in describing them. I get that you mean idealized, but it sounds as if they are perfect and in no way subjective which is misleading.

    5. In a test set of 50 image tiles per dataset

      Could you please clarify if this test was done by using manual segmentation as ground truth? If not, what was the source of ground truth data used to compute F1-scores?

      An F1-score of 0.7 is not generally seen as very high. Could emphasize more strongly in your discussion the power of your approach (combining the instance segmentation with class maps for classification) given that this seems to be a non-trivial segmentation problem.

  3. Feb 2024
    1. The extended exposure time can also achieve an even better SNR than that in coherent Raman microscopy [1].

      Is this claim quantitatively verified?

    2. Exposure times were 5 s/line and 30 s/line for imaging the live and cryofixed samples, respectively.

      How is this a fair comparison for comparing SNR between live and cryofixed conditions? I understand your point that exposure time for live Raman is limited due to photodamage, but would still be interesting to see 30s/line for live Raman (albeit with drift artifacts) for the sake of comparison.

    3. exposure with compensating

      *exposure, compensating

    4. We confirmed the band width of 3.9 cm-1 at 1001 cm-1, assigned as phenylalanine, in the cryofixed conditions, whereas the same peak was observed to be 8.6 cm-1 under a practical Raman measurement condition at room temperature (Fig. 1F).

      This is a nice example of benchmarks for band widths for certain spectral peaks to differentiate between low and high SNR!

    5. high-SNR Raman imaging

      Can you more clearly define what constitutes "high-SNR" Raman? Of course it is high relative to "low-SNR" Raman, but how can someone know if they are doing high- vs low-SNR Raman? Are there thresholds that are (or can be) defined on the width of certain spectral peaks?

    6. fused silica coverslip

      Is fused silica necessary to prevent autofluorescence from surface defects in normal glass coverslips? Is it typical/recommended to used fused silica for Raman microscopy generally or only for very high sensitivity measurements?

    7. shows


    8. wavelengthdispersion

      *wavelength dispersion

    9. Additionally, the utility of the chemical fixation is limited in fixing biological activities in motion [24], and there are molecular species that cannot be fixed by the current chemical fixation techniques [25].

      Would be helpful to cite a couple specific examples of biological activities and/or molecular species for which fixation is insufficient to bolster motivation for cryogenic freezing.