# Project: Low Powered Models for disease detection and classification for Radiology Images **URL:** \ **Category:** Radiology\ **Tags:** gsoc2020-project, radiology, gsoc2020\ **Created:** [May 5, 2020, 12:27am UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706 "2020-05-05T00:27:11Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![r0bby](https://forums.librehealth.io/user_avatar/forums.librehealth.io/r0bby/32/1781_2.png) [@r0bby](https://forums.librehealth.io/u/r0bby)\ **Post date:** [May 5, 2020, 12:27am UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/1 "2020-05-05T00:27:11Z")
This is the thread to be used for [Project: Low Powered Models for disease detection and classification for Radiology Images](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3300) ---
**Author:** ![r0bby](https://forums.librehealth.io/user_avatar/forums.librehealth.io/r0bby/32/1781_2.png) [@r0bby](https://forums.librehealth.io/u/r0bby)\ **Post date:** [May 5, 2020, 12:27am UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/2 "2020-05-05T00:27:34Z")
@aishwhereya use this thread for your project, please. ---
**Author:** ![aishwhereya](https://forums.librehealth.io/user_avatar/forums.librehealth.io/aishwhereya/32/1264_2.png) [@aishwhereya](https://forums.librehealth.io/u/aishwhereya)\ **Post date:** [May 5, 2020, 11:07am UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/3 "2020-05-05T11:07:15Z")
Yes @r0bby. Roger that. ---
**Author:** ![aishwhereya](https://forums.librehealth.io/user_avatar/forums.librehealth.io/aishwhereya/32/1264_2.png) [@aishwhereya](https://forums.librehealth.io/u/aishwhereya)\ **Post date:** [May 5, 2020, 11:20am UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/4 "2020-05-05T11:20:25Z")
@r0bby I have a doubt. I had applied for the the project “Automatic Labelling of Radiology Images”. On the main GSoC website, my project title is the same. But here on the forums, it is " Low Powered Models for disease detection and classification for Radiology Images". You have mentioned this new title in this recent post too - [Congratulations our accepted Students for GSoC 2020](https://forums.librehealth.io/t/congratulations-our-accepted-students-for-gsoc-2020/3680). Is this an error ? Or am I supposed to work under this project title using my original proposal? Or am I supposed to alter my proposal to fit this new project? ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [May 5, 2020, 3:09pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/5 "2020-05-05T15:09:22Z")
@aishwhereya, First of all Congratulations!! There will be some modification in your projects, which falls into this category, so @r0bby has asked you to use this thread. I will let you know how to proceed on this soon. Till then brush up your skills on `Qunatization` of models. 🙂 ---
**Author:** ![aishwhereya](https://forums.librehealth.io/user_avatar/forums.librehealth.io/aishwhereya/32/1264_2.png) [@aishwhereya](https://forums.librehealth.io/u/aishwhereya)\ **Post date:** [May 5, 2020, 3:14pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/6 "2020-05-05T15:14:26Z")
Ok got it. I will start reading about it. @pri2si17 we need to set up a constant time per week for conversations regarding updates and queries. How do you propose to go about it? Would it be okay to use librehealth chat instead of the forum? ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [May 5, 2020, 3:46pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/7 "2020-05-05T15:46:38Z")
I will let you know how to proceed. ---
**Author:** ![r0bby](https://forums.librehealth.io/user_avatar/forums.librehealth.io/r0bby/32/1781_2.png) [@r0bby](https://forums.librehealth.io/u/r0bby)\ **Post date:** [May 6, 2020, 12:08am UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/8 "2020-05-06T00:08:30Z")
> [@aishwhereya](#): > > @pri2si17 we need to set up a constant time per week for conversations regarding updates and queries. How do you propose to go about it? Would it be okay to use librehealth chat instead of the forum? While I prefer asynchronous communication as it can be seen by all, I allow the use of the Jitsi Meet room in the first post. ---
**Author:** ![aishwhereya](https://forums.librehealth.io/user_avatar/forums.librehealth.io/aishwhereya/32/1264_2.png) [@aishwhereya](https://forums.librehealth.io/u/aishwhereya)\ **Post date:** [May 6, 2020, 4:10pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/9 "2020-05-06T16:10:34Z")
Hello @pri2si17 @judywawira, I realized that I have only interacted with @pri2si17 before and that too only regarding the project. So as a starter for the Community Bonding period, here is a short introduction about me - [Google Summer of Code 2020 Student Meet and Greet](https://forums.librehealth.io/t/google-summer-of-code-2020-student-meet-and-greet/3681/7) ---
**Author:** ![r0bby](https://forums.librehealth.io/user_avatar/forums.librehealth.io/r0bby/32/1781_2.png) [@r0bby](https://forums.librehealth.io/u/r0bby)\ **Post date:** [May 6, 2020, 8:26pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/10 "2020-05-06T20:26:54Z")
> [@aishwhereya](#): > > I realized that I have only interacted with @pri2si17 before and that too only regarding the project. So as a starter for the Community Bonding period, here is a short introduction about me - [Google Summer of Code 2020 Student Meet and Greet](https://forums.librehealth.io/t/google-summer-of-code-2020-student-meet-and-greet/3681/7) You’re fine – thanks for doing that. ---
**Author:** ![aishwhereya](https://forums.librehealth.io/user_avatar/forums.librehealth.io/aishwhereya/32/1264_2.png) [@aishwhereya](https://forums.librehealth.io/u/aishwhereya)\ **Post date:** [May 11, 2020, 9:12pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/11 "2020-05-11T21:12:58Z")
Hello @pri2si17 @judywawira It has been a week since the community bonding period has started and I think we are lacking communication about how to go ahead regarding this project. I think we can have more discussions about the contents of this project starting with the instructions that @pri2si17 was going to give me. I am going to have a lot of queries due to the change of title and will probably have to set up a new timeline too. I am sorry if I am being impatient. Till then, I have read about quantization as @pri2si17 had said. And I have also gone through this thread for understanding the basic requirements [Project: Low Powered Models for disease detection and classification for Radiology Images](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3300) ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [May 12, 2020, 5:25am UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/12 "2020-05-12T05:25:47Z")
Hi @aishwhereya Yes it is delay on my part. Sorry for that. But please be rest assured, you will have complete plan before coding period begins. 🙂 I am giving you brief overview, of the modifications, and will make a detailed outline in coming days. Please bear with me. The whole idea of this project is to develop models which can run on low powered machines like andriod, ios and even embedded ARM boards. So : - You will have to develop models for classification and detection as you were doing it earlier. - Apply optimisation techniques (quantization/prunning). - Qunatization to be applied : 16-bit/8-bit/4-bit/Integer/binary - Observe the power consumption (possibly you need to search for it), inference time, model size. (Will provide details for it) - Run it on emulators. (Qemu is there) With quantization, we wanted to have a model whose accuracy is comparable to deep models, but much faster and light weight. Tasks you can look for is : - Fork the repository : [LibreHealth / LibreHealth Radiology / lh-radiology-mobile-models · GitLab](https://gitlab.com/librehealth/radiology/lh-radiology-mobile-models) - Build the docker image. (Let me know if you have issues, I haven’t added instructions yet, but you can find it on internet) - Try to run and emulate Raspberry PI from Qemu inside docker container. One more point, explore student-teacher paradigm ([https://arxiv.org/pdf/1804.06332.pdf](https://arxiv.org/pdf/1804.06332.pdf)) and see if you can replicate it. Let me know in case of any issue. 🙂 @judywawira Please see to it. ---
**Author:** ![aishwhereya](https://forums.librehealth.io/user_avatar/forums.librehealth.io/aishwhereya/32/1264_2.png) [@aishwhereya](https://forums.librehealth.io/u/aishwhereya)\ **Post date:** [May 12, 2020, 5:44am UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/13 "2020-05-12T05:44:57Z")
Thank you @pri2si17 I will set up the environment and complete these tasks. I will get back to you after that. Also, is my project going to be integrated with lh-radiology ? Do I have to look into the code-base of any particular module apart from the one that you mentioned? ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [May 12, 2020, 4:02pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/14 "2020-05-12T16:02:29Z")
Nopes. Just this repository. ---
**Author:** ![aishwhereya](https://forums.librehealth.io/user_avatar/forums.librehealth.io/aishwhereya/32/1264_2.png) [@aishwhereya](https://forums.librehealth.io/u/aishwhereya)\ **Post date:** [May 14, 2020, 3:40pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/15 "2020-05-14T15:40:28Z")
Hello @pri2si17 I have completed the following tasks. - Forked the lh-radiology-mobile-modules repo - Built the docker image from the given Dockerfile and ran it successfully. - Emulated Raspberry Pi from Qemu on my local machine as well as inside a docker container. I have written the Dockerfile for the same. I have used the base image of Ubuntu-18.04 and emulated Rasbian-Stretch on the Pi. I read the paper ([https://arxiv.org/pdf/1804.06332.pdf](https://arxiv.org/pdf/1804.06332.pdf)) that you suggested to implement the student-teacher paradigm. They have not released the code for the mathematics that they have used. The only thing that they have mentioned is that they have used MXNet Library for implementation. I am exploring techniques to evaluate models based on - Memory Usage (Model size can be found easily. Looking for methods to find number of parameters) - Computation Time (This is a simple piece of code) - Power Consumption (Looking for methods for this factor) Waiting for more instructions from you. PS : I have to update my project title and abstract on the main GSoC website. Any suggestions for the abstract? May I write the brief introduction that you gave me in the previous message? ---
**Author:** ![sunbiz](https://forums.librehealth.io/user_avatar/forums.librehealth.io/sunbiz/32/395_2.png) [@sunbiz](https://forums.librehealth.io/u/sunbiz)\ **Post date:** [May 14, 2020, 8:44pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/16 "2020-05-14T20:44:25Z")
I hope we can see some Ultrasound (US) or IVUS focused low-powered models through this project… and many of the use-cases probably have some kind of real-time detection from these. You know a lot of people call portable US the future stethoscopes. ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [May 16, 2020, 1:12pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/17 "2020-05-16T13:12:40Z")
Hi @aishwhereya > [@aishwhereya](#): > > I have to update my project title and abstract on the main GSoC website. Any suggestions for the abstract? @sunbiz @judywawira can you please clear this. Regarding abstract, yes you can put that. > [@aishwhereya](#): > > They have not released the code for the mathematics that they have used. The only thing that they have mentioned is that they have used MXNet Library for implementation. Yes they haven’t provided the code, but I think you can take reference of knowledge distillation github repos. > [@aishwhereya](#): > > Emulated Raspberry Pi from Qemu on my local machine as well as inside a docker container. I have written the Dockerfile for the same. I have used the base image of Ubuntu-18.04 and emulated Rasbian-Stretch on the Pi. Perfect! Can you raise a PR to my repo? I am assuming that you made changes to the same Dockerfile. ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [May 16, 2020, 1:13pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/18 "2020-05-16T13:13:18Z")
Hi @sunbiz Can you please provide more details about it. ---
**Author:** ![aishwhereya](https://forums.librehealth.io/user_avatar/forums.librehealth.io/aishwhereya/32/1264_2.png) [@aishwhereya](https://forums.librehealth.io/u/aishwhereya)\ **Post date:** [May 16, 2020, 4:06pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/19 "2020-05-16T16:06:34Z")
Sure I’ll do the needful this week. ---
**Author:** ![sunbiz](https://forums.librehealth.io/user_avatar/forums.librehealth.io/sunbiz/32/395_2.png) [@sunbiz](https://forums.librehealth.io/u/sunbiz)\ **Post date:** [May 18, 2020, 6:15pm UTC](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706/20 "2020-05-18T18:15:18Z")
This will need more research, but please have a look at the following research papers and the models used here: - [https://arxiv.org/abs/1904.02843](https://arxiv.org/abs/1904.02843) - [https://www.sciencedirect.com/science/article/pii/S1077314217300620](https://www.sciencedirect.com/science/article/pii/S1077314217300620) - [https://ieeexplore.ieee.org/abstract/document/8421260](https://ieeexplore.ieee.org/abstract/document/8421260) - [https://ieeexplore.ieee.org/abstract/document/7875138](https://ieeexplore.ieee.org/abstract/document/7875138) [Next page](https://forums.librehealth.io/t/project-low-powered-models-for-disease-detection-and-classification-for-radiology-images/3706.md?page=2)