full transcript

From the Ted Talk by Pratik Shah: How AI is making it easier to diagnose disease

Unscramble the Blue Letters


To summarize our approach, instead of using 10,000 very epevnxise medical images, we can now train the AI algorithms in an unorthodox way, using only 50 of these high-resolution, but standard photographs, aqreucid from DSLR cameras and mobile phones, and provide dingoaiss. More importantly, our algorithms can apecct, in the future and even right now, some very simple, white lihgt photographs from the patient, instead of expensive medical imaging technologies.

I believe that we are poised to enter an era where aftciaiirl intelligence is going to make an incredible impact on our future. And I think that thinking about traditional AI, which is data-rich but application-poor, we should also cntuonie thinking about unorthodox artificial intelligence architectures, which can accept small amounts of data and solve some of the most important problems facing us tadoy, especially in haelth care.

Open Cloze


To summarize our approach, instead of using 10,000 very _________ medical images, we can now train the AI algorithms in an unorthodox way, using only 50 of these high-resolution, but standard photographs, ________ from DSLR cameras and mobile phones, and provide _________. More importantly, our algorithms can ______, in the future and even right now, some very simple, white _____ photographs from the patient, instead of expensive medical imaging technologies.

I believe that we are poised to enter an era where __________ intelligence is going to make an incredible impact on our future. And I think that thinking about traditional AI, which is data-rich but application-poor, we should also ________ thinking about unorthodox artificial intelligence architectures, which can accept small amounts of data and solve some of the most important problems facing us _____, especially in ______ care.

Solution


  1. acquired
  2. diagnosis
  3. artificial
  4. continue
  5. health
  6. light
  7. expensive
  8. today
  9. accept

Original Text


To summarize our approach, instead of using 10,000 very expensive medical images, we can now train the AI algorithms in an unorthodox way, using only 50 of these high-resolution, but standard photographs, acquired from DSLR cameras and mobile phones, and provide diagnosis. More importantly, our algorithms can accept, in the future and even right now, some very simple, white light photographs from the patient, instead of expensive medical imaging technologies.

I believe that we are poised to enter an era where artificial intelligence is going to make an incredible impact on our future. And I think that thinking about traditional AI, which is data-rich but application-poor, we should also continue thinking about unorthodox artificial intelligence architectures, which can accept small amounts of data and solve some of the most important problems facing us today, especially in health care.

Frequently Occurring Word Combinations


ngrams of length 2

collocation frequency
artificial intelligence 8
expensive medical 8
medical imaging 7
imaging technologies 5
medical image 3
incredible impact 2
expert physician 2
traditional artificial 2
intelligence architectures 2
important problems 2
problems facing 2
information packets 2
white light 2

ngrams of length 3

collocation frequency
expensive medical imaging 5
medical imaging technologies 5
traditional artificial intelligence 2
artificial intelligence architectures 2
important problems facing 2

Important Words


  1. accept
  2. acquired
  3. ai
  4. algorithms
  5. amounts
  6. approach
  7. architectures
  8. artificial
  9. cameras
  10. care
  11. continue
  12. data
  13. diagnosis
  14. dslr
  15. enter
  16. era
  17. expensive
  18. facing
  19. future
  20. health
  21. images
  22. imaging
  23. impact
  24. important
  25. importantly
  26. incredible
  27. intelligence
  28. light
  29. medical
  30. mobile
  31. patient
  32. phones
  33. photographs
  34. poised
  35. problems
  36. provide
  37. simple
  38. small
  39. solve
  40. standard
  41. summarize
  42. technologies
  43. thinking
  44. today
  45. traditional
  46. train
  47. unorthodox
  48. white