Are you planning on attending the APTOS Symposium to share your work? Express your interest via this survey and we will notify you if we can provide a free pass.
\n\nAt the 4th APTOS Symposium, experts will share how emerging, innovative digital technologies are used in different parts of the world to enhance ophthalmic care. The theme of this year’s meeting will be the evolution, validation, and sustainability of AI. We will see how far AI has evolved from the inaugural APTOS Symposium in 2016 and look at what it is next in this exciting field. A goal of this competition is to capture algorithms across the world and train new data scientists.
\n\nWe would like to invite investigators, hospitals and/or companies to participate in the Challenge either as an individual or a group. Through friendly competition, we can improve and strengthen our computer models as well as friendships. Winning teams will be recognized at APTOS 2019. We will also further our roundtable discussions on the practicality and the regulatory implications of emerging digital technologies as well as ethical considerations.
", "messages": [ { "id": 618363, "postDate": "2019-09-05T06:43:09.810Z", "content": "@maggiemd , @sohier To clear up one mystery on my mind (in order to understand the significance of this problem),\ncould you please explain me why we have quite few number of training data in this competition?
\n\nWe all know that Google AI team also have similar models but trained on like 100,000 examples and have high accuracy, so what is the usage of our models in this competition?
", "rawMarkdown": "@maggiemd , @sohier To clear up one mystery on my mind (in order to understand the significance of this problem),\ncould you please explain me why we have quite few number of training data in this competition?\n\nWe all know that Google AI team also have similar models but trained on like 100,000 examples and have high accuracy, so what is the usage of our models in this competition?", "votes": 12, "replies": [ { "id": 618410, "postDate": "2019-09-05T07:32:11.260Z", "rawMarkdown": "", "votes": 2, "isDeleted": true }, { "id": 618423, "postDate": "2019-09-05T07:42:37.777Z", "content": "You/we will find innovative ways to tackle this task. Then, Google will add more data and build better models. Having better models gets you more market share. Simple :)
\n\nLong version: although eye scanning will likely be free of charge for final user there are a lot of costs which will be covered by hospitals/Governments such as lenses etc which is essentially our tax money so we will be paying for it indirectly. To use the software you need to buy equipment, and that is where the money is coming from. This means that having the exact same supplier for equipment would not make you competitive on the market because of your weaker model.
\n\nDATA RULES and IT'S ALL ABOUT THE MONEY
", "rawMarkdown": "You/we will find innovative ways to tackle this task. Then, Google will add more data and build better models. Having better models gets you more market share. Simple :)\n\n**Long version**: although eye scanning will likely be free of charge for final user there are a lot of costs which will be covered by hospitals/Governments such as lenses etc which is essentially our tax money so we will be paying for it indirectly. To use the software you need to buy equipment, and that is where the money is coming from. This means that having the exact same supplier for equipment would not make you competitive on the market because of your weaker model.\n\n**DATA RULES** and **IT'S ALL ABOUT THE MONEY**", "votes": 3 }, { "id": 618485, "postDate": "2019-09-05T08:43:33.113Z", "content": "\n\n\nwhat is the usage of our models in this competition?
\n
\n\n\n\n\nThen, Google will add more data and build better models.
\n
", "rawMarkdown": "> what is the usage of our models in this competition?\n\n\n> Then, Google will add more data and build better models. \n\n", "votes": 5 }, { "id": 618896, "postDate": "2019-09-05T15:54:45.847Z", "content": "@neuronengineer This effort is focused on taking the winning solutions from this competition and sharing them at the APTOS symposium. The images for this competition came directly from Aravind and the ground truth came from their clinical staff. The license type for winning models is Open Source so that any other opthamologist organizations can benefit.
", "rawMarkdown": "@neuronengineer This effort is focused on taking the winning solutions from this competition and sharing them at the APTOS symposium. The images for this competition came directly from Aravind and the ground truth came from their clinical staff. The license type for winning models is Open Source so that any other opthamologist organizations can benefit. ", "votes": 6 }, { "id": 618942, "postDate": "2019-09-05T17:06:18.040Z", "content": "Thanks maggie\nBut one more q..\nWhy kagglers & not Google who has already got more brains,resources to come up with more precise and accurate Deep NN model...
", "rawMarkdown": "Thanks maggie\nBut one more q..\nWhy kagglers & not Google who has already got more brains,resources to come up with more precise and accurate Deep NN model...", "votes": -1 } ] }, { "id": 618147, "postDate": "2019-09-04T23:23:10.473Z", "content": "Are you planning on attending the APTOS Symposium to share your work? Express your interest via this survey and we will notify you if we can provide a free pass.
\n\nAt the 4th APTOS Symposium, experts will share how emerging, innovative digital technologies are used in different parts of the world to enhance ophthalmic care. The theme of this year’s meeting will be the evolution, validation, and sustainability of AI. We will see how far AI has evolved from the inaugural APTOS Symposium in 2016 and look at what it is next in this exciting field. A goal of this competition is to capture algorithms across the world and train new data scientists.
\n\nWe would like to invite investigators, hospitals and/or companies to participate in the Challenge either as an individual or a group. Through friendly competition, we can improve and strengthen our computer models as well as friendships. Winning teams will be recognized at APTOS 2019. We will also further our roundtable discussions on the practicality and the regulatory implications of emerging digital technologies as well as ethical considerations.
", "rawMarkdown": "Are you planning on attending the APTOS Symposium to share your work? Express your interest via [this survey](https://forms.gle/KZf4WXRcHNHn8GrA6) and we will notify you if we can provide a free pass. \n\nAt the [4th APTOS Symposium](http://2019.asiateleophth.org/), experts will share how emerging, innovative digital technologies are used in different parts of the world to enhance ophthalmic care. The theme of this year’s meeting will be the evolution, validation, and sustainability of AI. We will see how far AI has evolved from the inaugural APTOS Symposium in 2016 and look at what it is next in this exciting field. A goal of this competition is to capture algorithms across the world and train new data scientists. \n\nWe would like to invite investigators, hospitals and/or companies to participate in the Challenge either as an individual or a group. Through friendly competition, we can improve and strengthen our computer models as well as friendships. Winning teams will be recognized at [APTOS 2019](https://www.kaggle.com/c/aptos2019-blindness-detection/overview/prizes). We will also further our roundtable discussions on the practicality and the regulatory implications of emerging digital technologies as well as ethical considerations.", "votes": 9 }, { "id": 629659, "postDate": "2019-09-19T03:28:11.117Z", "content": "@maggiemd Hello, I have participated in the competition. I want to continue my further research on this. Can I use Kaggle dataset(APTOS 2019 Blindness Detection) for training my new model and for publishing my work based on the outcome.
", "rawMarkdown": "@maggiemd Hello, I have participated in the competition. I want to continue my further research on this. Can I use Kaggle dataset(APTOS 2019 Blindness Detection) for training my new model and for publishing my work based on the outcome.", "replies": [ { "id": 1034034, "postDate": "2020-10-01T12:53:44.053Z", "content": "I want to konw too
", "rawMarkdown": "I want to konw too" }, { "id": 1038145, "postDate": "2020-10-05T15:30:33.270Z", "content": "You can always look up the data use terms in the Competition Rules under Section 7 A - I pasted the section from the rules below.
\nA. Data Access and Use. Competition Use and Non-Commercial & Academic Research: You may access and use the Competition Data for non-commercial purposes only, including for participating in the Competition and on Kaggle.com forums, and for academic research and education. The Competition Sponsor reserves the right to disqualify any participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.
", "rawMarkdown": "You can always look up the data use terms in the Competition Rules under Section 7 A - I pasted the section from the rules below. \n\n7. COMPETITION DATA.\n\"Competition Data\" means the data or datasets available from the Competition Website for the purpose of use in the Competition, including any prototype or executable code provided on the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to participants.\n\nA. Data Access and Use. Competition Use and Non-Commercial & Academic Research: You may access and use the Competition Data for non-commercial purposes only, including for participating in the Competition and on Kaggle.com forums, and for academic research and education. The Competition Sponsor reserves the right to disqualify any participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.", "votes": 2, "replies": [ { "id": 1038931, "postDate": "2020-10-06T07:18:06.807Z", "content": "How can I refer to this data set in my research? I can't find the writing method of the references that refer to the data set
", "rawMarkdown": "How can I refer to this data set in my research? I can't find the writing method of the references that refer to the data set\n\n" } ] }, { "id": 1075391, "postDate": "2020-11-11T17:06:22.623Z", "content": "Hi Maggie @maggiemd
\nit is a great option to have the train data at hand for research, thank you
@maggiemd , @sohier To clear up one mystery on my mind (in order to understand the significance of this problem),\ncould you please explain me why we have quite few number of training data in this competition?
\n\nWe all know that Google AI team also have similar models but trained on like 100,000 examples and have high accuracy, so what is the usage of our models in this competition?
", "votes": 12, "replies": [ { "id": 618410, "author_name": "", "author_url": "", "post_date": "2019-09-05T07:32:11.260000", "content": "", "votes": 2, "replies": [] }, { "id": 618423, "author_name": "Miroslav Valan", "author_url": "", "post_date": "2019-09-05T07:42:37.777000", "content": "You/we will find innovative ways to tackle this task. Then, Google will add more data and build better models. Having better models gets you more market share. Simple :)
\n\nLong version: although eye scanning will likely be free of charge for final user there are a lot of costs which will be covered by hospitals/Governments such as lenses etc which is essentially our tax money so we will be paying for it indirectly. To use the software you need to buy equipment, and that is where the money is coming from. This means that having the exact same supplier for equipment would not make you competitive on the market because of your weaker model.
\n\nDATA RULES and IT'S ALL ABOUT THE MONEY
", "votes": 3, "replies": [] }, { "id": 618485, "author_name": "Kiran Kunapuli", "author_url": "", "post_date": "2019-09-05T08:43:33.113000", "content": "\n\n\nwhat is the usage of our models in this competition?
\n
\n\n\n\n\nThen, Google will add more data and build better models.
\n
", "votes": 5, "replies": [] }, { "id": 618896, "author_name": "Maggie", "author_url": "", "post_date": "2019-09-05T15:54:45.847000", "content": "@neuronengineer This effort is focused on taking the winning solutions from this competition and sharing them at the APTOS symposium. The images for this competition came directly from Aravind and the ground truth came from their clinical staff. The license type for winning models is Open Source so that any other opthamologist organizations can benefit.
", "votes": 6, "replies": [] }, { "id": 618942, "author_name": "Jaideep", "author_url": "", "post_date": "2019-09-05T17:06:18.040000", "content": "Thanks maggie\nBut one more q..\nWhy kagglers & not Google who has already got more brains,resources to come up with more precise and accurate Deep NN model...
", "votes": -1, "replies": [] } ] }, { "id": 629659, "author_name": "Rupa", "author_url": "", "post_date": "2019-09-19T03:28:11.117000", "content": "@maggiemd Hello, I have participated in the competition. I want to continue my further research on this. Can I use Kaggle dataset(APTOS 2019 Blindness Detection) for training my new model and for publishing my work based on the outcome.
", "votes": 0, "replies": [ { "id": 1034034, "author_name": "sjjswu", "author_url": "", "post_date": "2020-10-01T12:53:44.053000", "content": "I want to konw too
", "votes": 0, "replies": [] }, { "id": 1038145, "author_name": "Maggie", "author_url": "", "post_date": "2020-10-05T15:30:33.270000", "content": "You can always look up the data use terms in the Competition Rules under Section 7 A - I pasted the section from the rules below.
\nA. Data Access and Use. Competition Use and Non-Commercial & Academic Research: You may access and use the Competition Data for non-commercial purposes only, including for participating in the Competition and on Kaggle.com forums, and for academic research and education. The Competition Sponsor reserves the right to disqualify any participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.
", "votes": 2, "replies": [ { "id": 1038931, "author_name": "sjjswu", "author_url": "", "post_date": "2020-10-06T07:18:06.807000", "content": "How can I refer to this data set in my research? I can't find the writing method of the references that refer to the data set
", "votes": 0, "replies": [] } ] }, { "id": 1075391, "author_name": "yassine marrakchi", "author_url": "", "post_date": "2020-11-11T17:06:22.623000", "content": "Hi Maggie @maggiemd
\nit is a great option to have the train data at hand for research, thank you
![https://media.giphy.com/media/1hM5ljbq5Y9Udki5sU/giphy.gif](\"https://media.giphy.com/media/1hM5ljbq5Y9Udki5sU/giphy.gif\"){kind=link}
![https://media.giphy.com/media/OZICOqOsT1lhC/giphy.gif](\"https://media.giphy.com/media/OZICOqOsT1lhC/giphy.gif\"){kind=link}