[PRE REVIEW]: HoverFast: an accurate, high-throughput, clinically deployable nuclear segmentation tool for brightfield digital pathology images

editorialbot commented 5 months ago

Submitting author: !--author-handle-->@petroslk@sappelhoff<!--end-editor-- Reviewers: @PingjunChen, @NetoPedro Managing EiC: Kevin M. Moerman

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/8587fb20d223790db3cdc903804a398f"><img src="https://joss.theoj.org/papers/8587fb20d223790db3cdc903804a398f/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/8587fb20d223790db3cdc903804a398f/status.svg)](https://joss.theoj.org/papers/8587fb20d223790db3cdc903804a398f)

Author instructions

Thanks for submitting your paper to JOSS @petroslk. Currently, there isn't a JOSS editor assigned to your paper.

@petroslk if you have any suggestions for potential reviewers then please mention them here in this thread (without tagging them with an @). You can search the list of people that have already agreed to review and may be suitable for this submission.

Editor instructions

The JOSS submission bot @editorialbot is here to help you find and assign reviewers and start the main review. To find out what @editorialbot can do for you type:

@editorialbot commands

editorialbot commented 5 months ago

Hello human, I'm @editorialbot, a robot that can help you with some common editorial tasks.

For a list of things I can do to help you, just type:

@editorialbot commands

For example, to regenerate the paper pdf after making changes in the paper's md or bib files, type:

@editorialbot generate pdf

editorialbot commented 5 months ago

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

OK DOIs

- 10.1007/978-3-030-00934-2_30 is OK
- 10.1109/WACV45572.2020.9093435 is OK

MISSING DOIs

- 10.1038/s41592-020-01018-x may be a valid DOI for title: Cellpose: a generalist algorithm for cellular segm...
- 10.1016/j.media.2019.101563 may be a valid DOI for title: Hover-net: Simultaneous segmentation and classific...
- No DOI given, and none found for title: QuPath: Open source software for digital pathology...
- 10.3389/fgene.2021.639930 may be a valid DOI for title: MSU-Net: Multi-scale U-Net for 2D medical image se...
- No DOI given, and none found for title: Automatic differentiation in PyTorch
- No DOI given, and none found for title: Scikit-learn: Machine Learning in Python
- No DOI given, and none found for title: The OpenCV Library
- 10.1038/ng.2764 may be a valid DOI for title: The cancer genome atlas pan-cancer analysis projec...
- No DOI given, and none found for title: Distilling the knowledge in a neural network
- No DOI given, and none found for title: Teacher-student architecture for knowledge learnin...
- 10.1200/cci.18.00157 may be a valid DOI for title: HistoQC: an open-source quality control tool for d...

INVALID DOIs

- None

editorialbot commented 5 months ago

Software report:

github.com/AlDanial/cloc v 1.90  T=0.03 s (537.9 files/s, 70854.7 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
Python                          10            271            126           1102
Markdown                         2             94              0            204
TeX                              1             14              0             98
Dockerfile                       1             12              9             27
INI                              1              1              0             18
-------------------------------------------------------------------------------
SUM:                            15            392            135           1449
-------------------------------------------------------------------------------

Commit count by author:

     6  petroslk
     5  JulienMassonnet
     2  JonatanBonjour
     1  Petros

editorialbot commented 5 months ago

Paper file info:

📄 Wordcount for paper.md is 2199

✅ The paper includes a Statement of need section

editorialbot commented 5 months ago

License info:

🔴 License found: BSD 3-Clause Clear License (Not OSI approved)

editorialbot commented 5 months ago

:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:

petroslk commented 5 months ago

Based on the provided database, publication record and previous reviews, PingjunChen might be a suitable reviewer.

Kevin-Mattheus-Moerman commented 5 months ago

@petroslk thanks for this submission. I have briefly reviewed the above analysis, the paper, and your repository.

Because of the relatively small size and narrow functionality of this work I have just triggered a scope review by the editorial board to determine if this work conforms to our substantial scholarly effort criteria.

Required changes before we can proceed:

[ ] Use an OSI approved open source license.
[ ] Add contributing guidelines to your project.
[ ] Add detailed documentation, the README information seems very basic.
[ ] Add testing instructions and link to them in the README. Automated testing is preferred, is that available?
[ ] Try to address the above DOI issues. You can call @editorialbot check references to check them again once you've amended your .bib file.
[ ] In your affiliations please spell out all country names in full (do not use country acronyms).

petroslk commented 5 months ago

@editorialbot check references

editorialbot commented 5 months ago

Checking the BibTeX entries failed with the following error:

Failed to parse BibTeX on value "publisher" (NAME) [#<BibTeX::Bibliography data=[9]>, "@", #<BibTeX::Entry >, {:title=>["The cancer genome atlas pan-cancer analysis project"], :author=>["Weinstein, John N and Collisson, Eric A and Mills, Gordon B and Shaw, Kenna R and Ozenberger, Brad A and Ellrott, Kyle and Shmulevich, Ilya and Sander, Chris and Stuart, Joshua M"], :journal=>["Nature genetics"], :volume=>["45"], :number=>["10"], :pages=>["1113--1120"], :year=>["2013"], :doi=>["10.1038/ng.2764"]}]

petroslk commented 5 months ago

@editorialbot check references

editorialbot commented 5 months ago

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

OK DOIs

- 10.1007/978-3-030-00934-2_30 is OK
- 10.1109/WACV45572.2020.9093435 is OK
- 10.1038/s41592-020-01018-x is OK
- 10.1016/j.media.2019.101563 is OK
- 10.1038/s41598-017-17204-5 is OK
- 10.3389/fgene.2021.639930 is OK
- 10.1038/ng.2764 is OK
- 10.1200/CCI.18.00157 is OK

MISSING DOIs

- Errored finding suggestions for "Automatic differentiation in PyTorch", please try later
- Errored finding suggestions for "Scikit-learn: Machine Learning in Python", please try later
- Errored finding suggestions for "The OpenCV Library", please try later
- Errored finding suggestions for "Distilling the knowledge in a neural network", please try later
- Errored finding suggestions for "Teacher-student architecture for knowledge learnin...", please try later

INVALID DOIs

- None

petroslk commented 5 months ago

Dear @Kevin-Mattheus-Moerman,

Thank you for your reply and for considering our work. As requested I have addressed your feedback. I have:

Changed the License to BSD-3-Clause (OSI approved)
Added contributing guidelines
Added more in depth documentation with a separate readthedocs page.
Added testing instructions on the readme and on readthedocs. Unfortunately, since the tool is GPU based, I have not yet been able to implement automated testing and run those locally.
I have included correct DOIs for all references that had them.
I have corrected the affiliation acronyms and included full Country names.

Let me know if there is anything missing.

Considering we had to reset the GitHub repository for the submission, most of the commit history is not visible. We also decided to provide the following statement for the editorial board to consider:

Statement of Substantial Scholarly Effort

We, the coauthors, have invested upwards of six months optimizing and iterating over the codebase to achieve the required performance for HoverFast. Our primary focus was to maintain a compact and efficient codebase while ensuring high accuracy and throughput, filling an important niche in the field of digital pathology. Due to the nature of our clinical work and the need to provide a clean repository for this submission, we reset the GitHub repository, which resulted in the loss of the commit history that reflects our extensive development efforts. However, we can attest that the work involved:

Detailed performance optimizations and code refactoring.
Comprehensive testing and validation on various datasets.
Collaborative development efforts among multiple authors, including medical doctors.
Iterative enhancements based on user feedback and practical deployment scenarios.

HoverFast is designed to be feature-complete and adheres to common community standards for Python-based tools. It addresses a critical need for a high-throughput, clinically deployable nuclear segmentation tool for brightfield digital pathology images, representing a substantial scholarly effort and a significant contribution to the available open-source software for digital pathology. We believe that HoverFast meets and exceeds the minimum contribution threshold set by JOSS and will be a valuable tool for researchers and practitioners in the field.

Please let me know if you are in need of any additional information or any feedback to provide! Thank you once again for considering our submission.

Kevin-Mattheus-Moerman commented 5 months ago

@petroslk thanks for the additional information, and for making those changes! We'll be in touch shortly.

Kevin-Mattheus-Moerman commented 5 months ago

@editorialbot check repository

editorialbot commented 5 months ago

Software report:

github.com/AlDanial/cloc v 1.90  T=0.03 s (1125.3 files/s, 137759.2 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
Python                          14            450            669           1194
reStructuredText                 6            315            102            395
Markdown                         3            117              0            259
TeX                              1             14              0            109
Dockerfile                       1             12              9             27
DOS Batch                        1              8              1             26
INI                              1              1              0             18
CSS                              1              3              2             16
YAML                             1              3              0             12
JavaScript                       1              1              1             11
make                             1              4              7              9
-------------------------------------------------------------------------------
SUM:                            31            928            791           2076
-------------------------------------------------------------------------------

Commit count by author:

    20  petroslk
     5  JulienMassonnet
     4  Petros
     2  JonatanBonjour

editorialbot commented 5 months ago

Paper file info:

📄 Wordcount for paper.md is 2202

✅ The paper includes a Statement of need section

editorialbot commented 5 months ago

License info:

✅ License found: BSD 3-Clause "New" or "Revised" License (Valid open source OSI approved license)

Kevin-Mattheus-Moerman commented 5 months ago

@editorialbot check references

editorialbot commented 5 months ago

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

OK DOIs

- 10.1007/978-3-030-00934-2_30 is OK
- 10.1109/WACV45572.2020.9093435 is OK
- 10.1038/s41592-020-01018-x is OK
- 10.1016/j.media.2019.101563 is OK
- 10.1038/s41598-017-17204-5 is OK
- 10.3389/fgene.2021.639930 is OK
- 10.1038/ng.2764 is OK
- 10.1200/CCI.18.00157 is OK

MISSING DOIs

- Errored finding suggestions for "Automatic differentiation in PyTorch", please try later
- No DOI given, and none found for title: Scikit-learn: Machine Learning in Python
- No DOI given, and none found for title: The OpenCV Library
- No DOI given, and none found for title: Distilling the knowledge in a neural network
- No DOI given, and none found for title: Teacher-student architecture for knowledge learnin...

INVALID DOIs

- None

petroslk commented 5 months ago

@Kevin-Mattheus-Moerman Great thanks a lot! Let me know if you need any additional information or modifications!

arfon commented 4 months ago

@editorialbot generate pdf

☝ to generate the most similar paper recommendation list which has been broken for some time.

editorialbot commented 4 months ago

:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:

editorialbot commented 4 months ago

Five most similar historical JOSS papers:

InspectorCell: Finding Ground Truth in Multiplexed Microscopy Images Submitting author: @AndreGosselink Handling editor: @fboehm (Active) Reviewers: @suresh-lab, @cinnetcrash Similarity score: 0.8164

Open-Source Hypothalamic-ForniX (OSHy-X) Atlases and Segmentation Tool for 3T and 7T Submitting author: @Cadaei-Yuvxvs Handling editor: @emdupre (Active) Reviewers: @a3sha2, @kaczmarj Similarity score: 0.8123

Histogram-weighted Networks for Feature Extraction, Connectivity and Advanced Analysis in Neuroscience Submitting author: @raamana Handling editor: @cMadan (Active) Reviewers: @oesteban Similarity score: 0.8100

starfish: scalable pipelines for image-based transcriptomics Submitting author: @neuromusic Handling editor: @csoneson (Active) Reviewers: @giovp, @shazanfar, @vals Similarity score: 0.8034

tissueloc: Whole slide digital pathology image tissue localization Submitting author: @PingjunChen Handling editor: @pjotrp (Retired) Reviewers: @Arafatk Similarity score: 0.8026

⚠️ Note to editors: If these papers look like they might be a good match, click through to the review issue for that paper and invite one or more of the authors before considering asking the reviewers of these papers to review again for JOSS.

Kevin-Mattheus-Moerman commented 4 months ago

@petroslk I've just removed the query-scope label as I'm pleased to confirm that this submission has passed the initial scope review process. We will now be looking for a handling editor.

Kevin-Mattheus-Moerman commented 4 months ago

@petroslk currently all editors in this space are busy handling other submission. I've hence assigned the waitlisted label. this will help ensure you will be next once an editor becomes available.

Kevin-Mattheus-Moerman commented 4 months ago

@sappelhoff I see you are handling several submission already. However, I was wondering, would you be happy to edit this one once you are available? We can keep it waitlisted untill you are.

sappelhoff commented 4 months ago

Hey @Kevin-Mattheus-Moerman thanks, yes I can 👍

Kevin-Mattheus-Moerman commented 4 months ago

@sappelhoff great. I'll assign you now, but feel free to leave it waitlisted for now until you have time.

Kevin-Mattheus-Moerman commented 4 months ago

@editorialbot assign @sappelhoff as editor

editorialbot commented 4 months ago

Assigned! @sappelhoff is now the editor

sappelhoff commented 4 months ago

Hi @petroslk 👋 I will be editing your submission to JOSS. My first question to you is: Can you recommend potentially suitable reviewers from your larger academic network? If yes, please let me know and make sure that they would fulfill the JOSS COI guidelines.

If not, please let me know, too -- then I will try to assemble a team via other databases, or potentially the automatic suggestions.

petroslk commented 4 months ago

Hey there! Here are some potential reviewers that fulfill the requirements and have relevant expertise.

@PingjunChen @NetoPedro @koellerMC

I hope that helps!

sappelhoff commented 4 months ago

Thanks @petroslk.

👋 @PingjunChen, @NetoPedro, @koellerMC, would any of you be willing to review this submission for JOSS? We carry out our checklist-driven reviews here in GitHub issues and follow these guidelines: https://joss.readthedocs.io/en/latest/review_criteria.html

PingjunChen commented 4 months ago

@sappelhoff I am delighted to review HoverFast for JOSS.

sappelhoff commented 4 months ago

@editorialbot add @PingjunChen as reviewer

editorialbot commented 4 months ago

@PingjunChen added to the reviewers list!

NetoPedro commented 3 months ago

I won't mind to do the review too!

sappelhoff commented 3 months ago

@editorialbot add @NetoPredo as reviewer

editorialbot commented 3 months ago

@NetoPredo added to the reviewers list!

sappelhoff commented 3 months ago

@editorialbot add @NetoPedro as reviewer

editorialbot commented 3 months ago

@NetoPedro added to the reviewers list!

sappelhoff commented 3 months ago

@editorialbot remove @NetoPredo from reviewers

editorialbot commented 3 months ago

@NetoPredo removed from the reviewers list!

sappelhoff commented 3 months ago

@editorialbot start review

editorialbot commented 3 months ago

OK, I've started the review over in https://github.com/openjournals/joss-reviews/issues/7022.

openjournals / joss-reviews

[PRE REVIEW]: HoverFast: an accurate, high-throughput, clinically deployable nuclear segmentation tool for brightfield digital pathology images #6792

Status

Statement of Substantial Scholarly Effort