# DNA Damage Microscopy Image Classification Project **URL:** \ **Category:** AIML AWG Open Projects\ **Tags:** aiml, radiation\ **Created:** [May 29, 2024, 1:23am UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429 "2024-05-29T01:23:14Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![evartsb](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/evartsb/32/250_2.png) [@evartsb](https://awg.osdr.space/u/evartsb)\ **Post date:** [May 29, 2024, 1:23am UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/1 "2024-05-29T01:23:14Z")
This project focuses on the analysis and classification of fluorescence microscopy images of mouse fibroblast cells irradiated with either Fe particles or X-ray, and the characterization of DNA damage indicated by 53BP1 foci presence related to radiation exposure. We are analyzing the NASA Open Science Data Repository: OSD-366 (DOI: 10.26030/v8w4-rg83) available here: [https://registry.opendata.aws/bps\_microscopy/](https://registry.opendata.aws/bps_microscopy/) ---
**Author:** ![rtscott2001](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/rtscott2001/32/5_2.png) [@rtscott2001](https://awg.osdr.space/u/rtscott2001)\ **Post date:** [May 29, 2024, 2:16am UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/2 "2024-05-29T02:16:12Z")
@tbv1 here’s the project, led by @evartsb along with @svcostes ---
**Author:** ![anuiris](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/anuiris/32/1358_2.png) [@anuiris](https://awg.osdr.space/u/anuiris)\ **Post date:** [May 30, 2024, 5:12pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/4 "2024-05-30T17:12:44Z")
Thanks for the info. We’re also working on the same OSDR and have just begun manual quantification of the foci. Is there a specific tool which is user friendly and efficient at the same time to label the foci? Best, Anu ---
**Author:** ![dave](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/dave/32/123_2.png) [@dave](https://awg.osdr.space/u/dave)\ **Post date:** [May 30, 2024, 11:05pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/5 "2024-05-30T23:05:13Z")
Hi @anuiris this might be helpful: Meta’s Segment Anything Model (SAM). [https://segment-anything.com/](https://segment-anything.com/) ---
**Author:** ![dave](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/dave/32/123_2.png) [@dave](https://awg.osdr.space/u/dave)\ **Post date:** [May 30, 2024, 11:09pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/6 "2024-05-30T23:09:56Z")
@evartsb i don’t know how to access the images via the AWS S3 bucket, so if you could attach some sample images from several strains here that would be great. My company’s software can measure shapes in very unique ways. Example: **Video [15 min]: Shape Analysis Detects Malaria Without Giemsa Staining** [![](https://us1.discourse-cdn.com/flex001/uploads/osdr/original/1X/d1097e1149aac8165d4a870aa95b37c805d4dac6.jpeg "Shape Analysis Detects Malaria Without Giemsa Staining") ](https://www.youtube.com/watch?v=Og5eEmOv9fU) Slides from video: > **[Shape Analysis Detects Malaria Without Giemsa Staining.pdf](https://drive.google.com/file/d/1i-YuwMC2NrFL513xKa82oEW4sJjWptZY/view?usp=sharing)** > > Google Drive file. ---
**Author:** ![anuiris](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/anuiris/32/1358_2.png) [@anuiris](https://awg.osdr.space/u/anuiris)\ **Post date:** [May 31, 2024, 9:18am UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/7 "2024-05-31T09:18:49Z")
Thank you very much. Let us try with this. ---
**Author:** ![evartsb](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/evartsb/32/250_2.png) [@evartsb](https://awg.osdr.space/u/evartsb)\ **Post date:** [May 31, 2024, 2:52pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/8 "2024-05-31T14:52:23Z")
Hi @anuiris ! I evaluated several tools and the issue I came across was .tif file format compatibility with many labeling tools. I ended up finding a python script that runs in Jupyter Lab that I was able to modify to fit our purposes. If you come across any _free_ tools that can be used to quickly label a large quantity of images, please let me know! ---
**Author:** ![evartsb](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/evartsb/32/250_2.png) [@evartsb](https://awg.osdr.space/u/evartsb)\ **Post date:** [May 31, 2024, 2:59pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/9 "2024-05-31T14:59:05Z")
Hi @dave ! I used aws cli to download the files. steps: 1. download awscli client: [https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.html](https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.html) 2. download the files from s3 to your local machine: [https://docs.aws.amazon.com/AmazonS3/latest/userguide/download-objects.html](https://docs.aws.amazon.com/AmazonS3/latest/userguide/download-objects.html) 3. alternatively, you can download files from aws s3 using the python boto3 library: [Downloading files - Boto3 1.34.115 documentation](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/s3-example-download-file.html) I hope this helps! Let me know if you have any issues and as always, stack overflow can probably explain it 100 ways better than I can 😉 ---
**Author:** ![svcostes](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/svcostes/32/33_2.png) [@svcostes](https://awg.osdr.space/u/svcostes)\ **Post date:** [June 1, 2024, 4:34pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/10 "2024-06-01T16:34:51Z")
Hi @anuiris Anu, I have developed different tools to quantify foci. What coding language do you use? ---
**Author:** ![anuiris](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/anuiris/32/1358_2.png) [@anuiris](https://awg.osdr.space/u/anuiris)\ **Post date:** [June 4, 2024, 7:37am UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/11 "2024-06-04T07:37:42Z")
We had the same issue. However, my colleague Dr Josef has now written a script for a tool that allows us to mark the foci quite well. We’re in the process of refining it. There’s a group from Belgium that suggested Focinator but I haven’t tried it. As of now, I have LabelMe which isn’t quite user friendly. ---
**Author:** ![anuiris](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/anuiris/32/1358_2.png) [@anuiris](https://awg.osdr.space/u/anuiris)\ **Post date:** [June 4, 2024, 7:40am UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/12 "2024-06-04T07:40:52Z")
Hi, we were about to send you an email regarding this @svcostes Dr Gianluca is building the AI model, Dr Josef Borg has now created a tool to help with identification of the foci. They’re using Python. My current role is in manually labelling the images and LabelMe was suggested which is not quite efficient in my opinion. Do you have an easier and efficient tool for manually labelling the foci?? Thanks in advance! ---
**Author:** ![svcostes](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/svcostes/32/33_2.png) [@svcostes](https://awg.osdr.space/u/svcostes)\ **Post date:** [June 4, 2024, 9:53pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/13 "2024-06-04T21:53:16Z")
Hi Anu @evartsb has a labeling tool. For spot detection, I recommend to stay away from threshold and top hat. Wavelet works best. I’m currently testing AI-driven spot detection as a non signal processing approach. ---
**Author:** ![anuiris](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/anuiris/32/1358_2.png) [@anuiris](https://awg.osdr.space/u/anuiris)\ **Post date:** [June 5, 2024, 7:12am UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/14 "2024-06-05T07:12:59Z")
Thank you for that lead! @evartsb would you be able to share the same with our team? @svcostes would you be available for a short meeting sometime with our IRIF team: PI @joseph.j.borg PI Gianluca and Bioinformatician Josef Borg ? It appears that our project is along the same lines as your work with few ramifications. Best, Anu ---
**Author:** ![svcostes](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/svcostes/32/33_2.png) [@svcostes](https://awg.osdr.space/u/svcostes)\ **Post date:** [June 5, 2024, 3:49pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/15 "2024-06-05T15:49:39Z")
Sure, always happy to meet Joseph ---
**Author:** ![evartsb](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/evartsb/32/250_2.png) [@evartsb](https://awg.osdr.space/u/evartsb)\ **Post date:** [June 10, 2024, 6:58pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/16 "2024-06-10T18:58:14Z")
@anuiris I cna share the python scripts. There are issues with the update function since Jupyter Notebooks update to newest version and the screen refresh leaves some artifacts from the previous batch of images (just affecting image border and image text description.) but the script works just find. It loads 40 images into a viewer in Jupyter Lab, then you right click, or left click on an image to label it. What is your email so I can email it to you? Also, are you interested in joining our project team bi-weekly meetings every other Monday at 2-3 PM ET ? ---
**Author:** ![anuiris](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/anuiris/32/1358_2.png) [@anuiris](https://awg.osdr.space/u/anuiris)\ **Post date:** [June 10, 2024, 7:34pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/17 "2024-06-10T19:34:00Z")
@evartsb Thank you. Could you please share it to Dr Josef Borg as well? josef.borg@um.edu.mt My email ID is [anuevangelineiris@gmail.com](mailto:anuevangelineiris@gmail.com) Yes, I’d like to join your group and attend the meetings as well. Thank you very much. ---
**Author:** ![anuiris](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/anuiris/32/1358_2.png) [@anuiris](https://awg.osdr.space/u/anuiris)\ **Post date:** [June 11, 2024, 4:05pm UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/18 "2024-06-11T16:05:59Z")
@evartsb @svcostes @rtscott2001 Is there an inclusion criteria for manually labelling an IRIF? Some images have multiple foci of varying intensities that generate confusion as to which is a true foci and which are Artifacts. ---
**Author:** ![svcostes](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/svcostes/32/33_2.png) [@svcostes](https://awg.osdr.space/u/svcostes)\ **Post date:** [June 12, 2024, 1:18am UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/19 "2024-06-12T01:18:01Z")
IRIF intensity cannot be used as a cutoff alone. You need to accept lower intensity foci as well. We typically use the 0 Gy control to tune detection and intensity threshold. Having said that, expect to also see foci in non-irradiated samples. They reflect real DNA DSB due to other stressors than Ionizing Radiation. But if you set intensity very low, then you also start detecting chromatin patterns, often punctuated as well. That is the reason why I typically use pattern recognition signal processing for detection. It is not as sensitive on intensity and does a great work differentiating irradiated vs non irradiated. Also, always tune the detection based on the highest dose and shortest time point. Here a few more pointers: [Spatiotemporal characterization of ionizing radiation induced DNA damage foci and their relation to chromatin organization - ScienceDirect](https://www.sciencedirect.com/science/article/abs/pii/S1383574210000037) [Image-Based Modeling Reveals Dynamic Redistribution of DNA Damage into Nuclear Sub-Domains | PLOS Computational Biology](https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.0030155) [Imaging Features that Discriminate between Foci Induced by High- and Low-LET Radiation in Human Fibroblasts | Radiation Research (allenpress.com)](https://meridian.allenpress.com/radiation-research/article-abstract/165/5/505/42380/Imaging-Features-that-Discriminate-between-Foci) ---
**Author:** ![anuiris](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/anuiris/32/1358_2.png) [@anuiris](https://awg.osdr.space/u/anuiris)\ **Post date:** [June 17, 2024, 9:01am UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/20 "2024-06-17T09:01:42Z")
Thank you for the pointers. The dataset that we are using for the project is OSDR366. We couldn’t find 0Gy control images from the public domain. Is it available? We tried LabelMe and it offsets the foci boundary quite a lot. Currently Josef has created a tool with pattern and intensity combined recognition. Once we have few images labelled well, we shall show them to you for your expert opinion. Thank you! ---
**Author:** ![anuiris](https://sea1.discourse-cdn.com/flex001/user_avatar/awg.osdr.space/anuiris/32/1358_2.png) [@anuiris](https://awg.osdr.space/u/anuiris)\ **Post date:** [June 17, 2024, 9:03am UTC](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429/21 "2024-06-17T09:03:52Z")
@evartsb Could you please share the meeting link? Thank you. [Next page](https://awg.osdr.space/t/dna-damage-microscopy-image-classification-project/429.md?page=2)