[PRE REVIEW]: Volume Segmantics: A Python Package for Semantic Segmentation of Volumetric Data Using Pre-trained PyTorch Deep Learning Models

[editorialbot]

Submitting author: @OllyK (Oliver N. F. King)
Repository: https://github.com/DiamondLightSource/volume-segmantics
Branch with paper.md (empty if default branch): paper
Version: v0.2.6
Editor: @osorensen
Reviewers: @jingpengw, @estenhl
Managing EiC: Arfon Smith

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/cb6e86a01006b487a09e41a9fc5b4e5e"><img src="https://joss.theoj.org/papers/cb6e86a01006b487a09e41a9fc5b4e5e/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/cb6e86a01006b487a09e41a9fc5b4e5e/status.svg)](https://joss.theoj.org/papers/cb6e86a01006b487a09e41a9fc5b4e5e)

Author instructions

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

@OllyK if you have any suggestions for potential reviewers then please mention them here in this thread (without tagging them with an @). In addition, this list of people have already agreed to review for JOSS and may be suitable for this submission (please start at the bottom of the list).

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]

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]

Software report:

github.com/AlDanial/cloc v 1.88  T=0.07 s (787.1 files/s, 120419.9 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
HTML                             5            551              0           3284
Python                          36            602            517           2555
Markdown                         6            140              0            471
YAML                             6             12             27            198
TeX                              1              7              0            103
TOML                             1              5              0             50
JavaScript                       1              3              3             40
-------------------------------------------------------------------------------
SUM:                            56           1320            547           6701
-------------------------------------------------------------------------------


gitinspector failed to run statistical information for the repository

[editorialbot]

Wordcount for paper.md is 989

[editorialbot]

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

OK DOIs

- 10.1007/s11263-015-0816-y is OK
- 10.1007/978-3-030-32245-8_4 is OK
- 10.3390/info11020125 is OK
- 10.1002/essoar.10506807.2 is OK
- 10.1098/rsif.2021.0140 is OK
- 10.3389/fcell.2022.842342 is OK

MISSING DOIs

- None

INVALID DOIs

- None

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[OllyK]

Dear Editors,

Some ideas for potential reviewers:
jingpengw
abhi-glitchhg
surajpaib
mohammadul
agi-codes
vasudev-sharma
michaelberks
hofmannu
vs74

Best Wishes.

[arfon]

@OllyK – thanks for your submission to JOSS. We're currently managing a large backlog of submissions and the editor most appropriate for your area is already rather busy.

For now, we will need to waitlist this paper and process it as the queue reduces. Thanks for your patience! We should have a new editor joining the team soon who could take on this submission for us.

[OllyK]

@arfon – Thanks for the heads up, look forward to continuing the process when the backlog reduces.

[danielskatz]

👋 @osorensen - would you be able to edit this submission?

[danielskatz]

@editorialbot invite @osorensen as editor

[editorialbot]

Invitation to edit this submission sent!

[osorensen]

@editorialbot add @osorensen as editor

[editorialbot]

Assigned! @osorensen is now the editor

[osorensen]

👋 @jingpengw @abhi-glitchhg @surajpaib 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

[xiuliren]

could you also provide the github repo link? Best, Jingpeng

…

On Tue, Aug 9, 2022 at 2:01 AM Øystein Sørensen ***@***.***> wrote: 👋 @jingpengw <https://github.com/jingpengw> @abhi-glitchhg <https://github.com/abhi-glitchhg> @surajpaib <https://github.com/surajpaib> 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 — Reply to this email directly, view it on GitHub <#4645 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AB2MB5OFGQO3LJ57CGE2YYTVYHX25ANCNFSM55QBZ5AA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[osorensen]

@jingpengw, the GitHub repo is https://github.com/DiamondLightSource/volume-segmantics.

[xiuliren]

I am happy to review it, but there exists a package, called pytorch_connectomics, that is pretty well made. By quick browsing of this repo, I did not find the uniqueness of this repo compared to it. https://github.com/zudi-lin/pytorch_connectomics Best, Jingpeng

…

On Tue, Aug 9, 2022 at 8:36 AM Øystein Sørensen ***@***.***> wrote: @jingpengw <https://github.com/jingpengw>, the GitHub repo is https://github.com/DiamondLightSource/volume-segmantics. — Reply to this email directly, view it on GitHub <#4645 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AB2MB5N4AWZQNUWY44Z4GN3VYJGEHANCNFSM55QBZ5AA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[osorensen]

I am happy to review it, but there exists a package, called pytorch_connectomics, that is pretty well made. By quick browsing of this repo, I did not find the uniqueness of this repo compared to it. https://github.com/zudi-lin/pytorch_connectomics Best, Jingpeng
…
On Tue, Aug 9, 2022 at 8:36 AM Øystein Sørensen @.> wrote: @jingpengw https://github.com/jingpengw, the GitHub repo is https://github.com/DiamondLightSource/volume-segmantics. — Reply to this email directly, view it on GitHub <#4645 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AB2MB5N4AWZQNUWY44Z4GN3VYJGEHANCNFSM55QBZ5AA . You are receiving this because you were mentioned.Message ID: @.>

@OllyK could you please provide a comment to this issue?

[OllyK]

@jingpengw @osorensen Yes certainly. I was just holding off since the invitiation to review hasn't been accepted yet and was unsure if reacting to pre-judgement before the process has started would be constructive 😃
Thanks for pointing out the pytorch_connectectomics repo Jingpeng, it certainly looks impressive and appears to have a strong team behind it. Having just looked at it briefly, there are a number of differences that I can see.

1. pytorch_connectomics is much more complicated, both in the functionality it offers and the useage. There are many options to configure and the commandline invocations appear to be complex. My package focusses on simplicity and has one main purpose - fast and straightforward training of models for volumetric semantic segmentation with minimal configuration.
2. In pytorch_connectomics 2D or 3D models are generally trained from scratch, a time and resource heavy process requiring large training datasets, hence why their examples often distribute training across multiple large GPUs. My library is intended to be used in situations where the user doesn't have access to these resources and does not want to wait much longer than 5 minutes to train a model - the library has been incorporated into a GUI application (SuRVoS2) where users (people completely unfamiliar with computer science) expect to be able to perform steps in a reasonable timeframe. Also we want syncrotron users to quickly train models for use in their current experiments.
3. Although the authors of pytorch_connectomics state that their package can be used on all kinds of data their focus appears to be heavily weighted towards EM data and segmentation techniques useful for connectomics. My package is generic to volumetric image data from any modality and discipline.
4. Swapping out and trying different pre-trained encoder types and models appears to be more straightforward in my library, simply change a string in a YAML file. This is thanks to functionality afforded by the segmentation-models.pytorch library that is utilised in my package. Therefore a smaller, lightweight encoder could be used to save resources, for example. Perhaps I haven't looked in enough detail but couldn't see the option to change encoder in pytorch_connectomics.
5. As previously mentioned, it is hoped that the simple API for volume_segmantics would allow the package to be incorporated into other applications (as it is in SuRVoS2). This does not appear to be such a consideration for pytorch_connectomics.

Apologies for the long answer, I expect I'll wake up in the middle of the night with some other reasons on my mind 😄 These are the only comments I can make, to the best of my knowledge since I haven't had time to try the pytorch_connectomics package out yet and am unlikely to do so in the near future,

Best Wishes,

Olly

[osorensen]

Thanks for the detailed answer, @OllyK. I have looked a bit at your repository myself, and my impression is that this is within scope for a review.

[osorensen]

@editorialbot add @jingpengw as reviewer

[editorialbot]

@jingpengw added to the reviewers list!

[osorensen]

👋 @michaelberks @hofmannu 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

[xiuliren]

Review checklist for @jingpengw

Conflict of interest

• I confirm that I have read the JOSS conflict of interest (COI) policy and that: I have no COIs with reviewing this work or that any perceived COIs have been waived by JOSS for the purpose of this review.

Code of Conduct

• I confirm that I read and will adhere to the JOSS code of conduct.

General checks

• Repository: Is the source code for this software available at the https://github.com/DiamondLightSource/volume-segmantics?
• License: Does the repository contain a plain-text LICENSE file with the contents of an OSI approved software license?
• Contribution and authorship: Has the submitting author (@OllyK) made major contributions to the software? Does the full list of paper authors seem appropriate and complete?
• Substantial scholarly effort: Does this submission meet the scope eligibility described in the JOSS guidelines

Functionality

• Installation: Does installation proceed as outlined in the documentation?
• Functionality: Have the functional claims of the software been confirmed?
• Performance: If there are any performance claims of the software, have they been confirmed? (If there are no claims, please check off this item.)

Documentation

• A statement of need: Do the authors clearly state what problems the software is designed to solve and who the target audience is?
• Installation instructions: Is there a clearly-stated list of dependencies? Ideally these should be handled with an automated package management solution.
• Example usage: Do the authors include examples of how to use the software (ideally to solve real-world analysis problems).
• Functionality documentation: Is the core functionality of the software documented to a satisfactory level (e.g., API method documentation)?
• Automated tests: Are there automated tests or manual steps described so that the functionality of the software can be verified?
• Community guidelines: Are there clear guidelines for third parties wishing to 1) Contribute to the software 2) Report issues or problems with the software 3) Seek support

Software paper

• Summary: Has a clear description of the high-level functionality and purpose of the software for a diverse, non-specialist audience been provided?
• A statement of need: Does the paper have a section titled 'Statement of need' that clearly states what problems the software is designed to solve, who the target audience is, and its relation to other work?
• State of the field: Do the authors describe how this software compares to other commonly-used packages?
• Quality of writing: Is the paper well written (i.e., it does not require editing for structure, language, or writing quality)?
• References: Is the list of references complete, and is everything cited appropriately that should be cited (e.g., papers, datasets, software)? Do references in the text use the proper citation syntax?

[osorensen]

Thanks for starting your review @jingpengw, but since this is a pre review issue, you'll unfortunately have to do it again once I start the actual review issue. I'll start that review once we have 1-2 more reviewers confirmed. You'll be notified.

[osorensen]

👋 @agi-codes @vasudev-sharma @mohammadul 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

[osorensen]

@editorialbot add @estenhl as reviewer

[editorialbot]

@estenhl added to the reviewers list!

[osorensen]

@editorialbot start review

[editorialbot]

OK, I've started the review over in #4691.