GSoC 2020 project idea 15: OpenDevoCell Integration

This project will focus on improving the data science and machine learning infrastructure of the DevoWorm group. The work will focus on an extension of the Summer of Code projects completed in 2017 [1] and 2019 [2]. The first two aims are to improve upon the OpenDevoCell web interface ( and to improve segmentation techniques overall. While the OpenDevoCell interface has been implemented as a Heroku app, we would like to develop a dashboard for interpretation as well as tighter integration with DevoZoo’s ( collection of open-source microscopy data. The third aim is to deploy the code package as a unified Python library, which would be done in concert with the improvement of segmentation techniques.

The priority for this Summer is to improve the web interface both in terms of interactivity and functionality. Ideally, we would like to provide users with multiple options for analysis. This includes the ability to incorporate new forms of analysis as well as algorithms for new types of data. Currently, our web app is optimized for microscopy images acquired using the SPIM technique. However, we would also like to segment microscopy images acquired using a wide range of technologies. Feeding into this is the ability to segment and obtain features for the data in our DevoZoo. The ability to extract quantitative data from these movie images is key to conducting the comparative and time-series analysis. The development of a dashboard would ideally enable users to employ various machine learning and simulation techniques in one place.

These improvements are meant to increase participation in our open science initiative and make sophisticated analytical techniques more accessible to students and potential collaborators alike. We are looking for someone who can work with programming tools, including HTML/CSS, TensorFlow, ReactJS, and Python. Improvements to segmentation performance might include the implementation of a pre-trained model such as Deeplab [3] or a means to plug in new components as they are developed. You will join the DevoWorm group, a project within the OpenWorm Foundation (, where we are trying to build the first virtual organism.

Mentors: Bradly Alicea ( and Vinay Varma (, OpenWorm Foundation.


[1] Siddharth Yadav, 2017:

[2] Vinay Varma, 2019: 187265128652/semantic-image-processing-for-developmental-data

[3] see our group’s work on implementing image segmentation using DeepLabv3 in TensorFlow:

Hello ,

I’m Abhishek Bvs currently pursuing my under graduation in the field of Computer Science and Engineering from Amrita Vishwa Vidyapeetham, Kerala, India. I’m adept at problem-solving and application development and eager to refine and utilize skills in real-world projects for the common good. My technical interests mostly lie in web application development. I have a very good fundamentals in computer programming, object oriented programming, data structures, designing and modeling of database, networking and so no. I have developed few web applications in Python, PHP & JAVA and familar with ReactJS and enjoying learning image processsing as part of my curriculum. My projects can be found in Github

Having worked on many projects, I have experience collaborating and working in teams. I am highly creative with extensive experience in designing. I would like to work on this project and am looking forward to discuss ideas about the project with mentors. I expect that I could learn many new things from the community

Thanks & have a nice day !

Hi @Abhishek_Bvs,

Thanks for your interest.
If you are interested in working towards your project proposal and also getting more insight about which issues/bugs you can start working on to dive deeper into the project, then please follow some of the steps listed below :

  1. Leverage the links that have been shared above. They link the past work done on the project by our (INCF’s) past GSoC students. You might do well to understand their code and how it fits into the larger picture of this project idea.
  2. To get better feedback and faster replies from the two mentors of this project, please follow the Openworm foundation link - You will find there is a procedure to join their slack channel. Please join the slack channel if possible as mentors from OpenWorm community are much more active their and you will find better suggestions about your project proposal and steps that you take.


Thanks @arnab1896 for guiding me. Right now I’m going through the proposals and presentations of last year GSoC Students. Will look into the procedures and join openworm slack channel asap.


Sounds like you would be a good candidate for this project. This builds on projects from previous years, so please see our previous project presentations for some context. You might also be interested in the DevoWormML course, which was held last Fall and covers some of the topics our group is interested in.

As Arnab has suggested, please join the OpenWorm Slack, and join #devoworm and #devowormml. The blog post (mentioned in the project description) and DevoWormML materials should give you a better idea of what we are looking for. I can guide you with proposal development, so send me a draft version for feedback when you get to that stage. Good luck!

Will contact you soon. Thanks @b.alicea

Hi all, I just wanted to add a small detail here. The algorithm behind the web app ( is supported by a combination of morphological image processing techniques like dilation, erosion and also smoothening, thresholding and noise reduction. The deep learning model (W-net) which was implemented was integrated into ImageJ as a plugin. We did not have any labeled data and we had to go in with an unsupervised approach and I kinda struggled to make it work properly inside the java tool. Any new interesting ideas involving semi-supervised learning or self-supervised learning or any other technique which the student believes to be practical are welcome.

Also, for the integration of additional features into the app and UI/UX improvements, please put yourself into the shoes of the user and think about what features you would like to have. The current version can be improved in a lot of ways. One good place to start will be to add the feature to upload videos and provide cell tracking capability (will require redesigning of the algorithm) and adding a login/signup feature to support a dashboard. Please feel free to post here in case if you are uncertain about anything. All the best!

1 Like

Thanks, @nvinayvarma189. I have a few queries and things to be discussed. As given in the idea description the suggested model that can be tried is Deeplab (or any semi-supervised and self-supervised) model needs labelled data for improving the segmentation. So, Is it possible to get the labelled data or Is there any chance where images are manually annotated for getting this done? Regarding the improvement of the present application, I’m working on the ideas once they are refined I will contact you. Thanks for helping me out.

Hello everybody,
My name is Kush Aggarwal, I am a third year student and have been working with web development from past one year with languages like NodeJS, ReactJS and Flask and currently learning and working in the field of Machine Learning and deep learning. I would really like to work in this project and mentors to learn new skills as well as grow more in the ones I have.
Although I suppose I have begun a bit late but would love to be a part and participate in the same
Kush Aggarwal

Hello Everyone!
My name is Osama and I am in my final year, pursuing a bachelor’s degree in Computer Science from University of Karachi, Karachi, Pakistan. I have been working on web related technologies for the past one year (Node, React, Django) and also like coding in C++. I enjoy Machine learning algorithms and algorithms ,in general, and have a keen interest in learning new technologies and implement them on ideas. I have worked with tensorflow a few times and I’m excited to use it in greater detail through such projects. Thanks!