Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Introduction to deep learning and recent research topics in medical field

(1) Brief introduction to deep learning
(2) Recent research topics in medical field

  • Be the first to comment

Introduction to deep learning and recent research topics in medical field

  1. 1. Radiological Physics Lab Seoul National University Jimin Lee
  2. 2. Contents 2 1. Artificial Intelligence & Deep Learning 2. Research Topics
  3. 3. Artificial Intelligence & Deep Learning 3
  4. 4. Artificial Intelligence 4 1. http://smartfutures.net/02/seeding-the-ai-in-your-life/ https://www.paysa.com/blog/2018/02/01/how-ai-is-revolutionizing-medical-diagnosis/
  5. 5. Artificial Intelligence  To develop a model to do a specific task by learning from big data 5 1. https://adgefficiency.com
  6. 6. Artificial Intelligence 6 1. https://medium.com/aws-activate-startup-blog/adapting-deep-learning-to-medicine-with-behold-ai-e60c37eb966a ?  To develop a model to do a specific task by learning from big data
  7. 7. Deep Learning  Artificial Intelligence, Machine Learning and Deep Learning 7 1. https://www.gettingsmart.com/2017/03/the-technologies-reshaping-life-and-livelihood/
  8. 8. Deep Learning  Artificial Neural Networks (인공 신경망) 8 1. cs231n: Convolutional Neural Networks for Visual Recognition The number of hidden layers = Depth of the network How can we learn the optimal 𝝎𝒊,𝒋,𝒌?
  9. 9. Deep Learning  Artificial Neural Networks (인공 신경망) learning process 9 1.
  10. 10. Deep Learning  Artificial Neural Networks (인공 신경망) learning process 10 1.
  11. 11. Deep Learning  Artificial Neural Networks (인공 신경망) learning process 11 1.
  12. 12. Deep Learning  Artificial Neural Networks (인공 신경망) learning process 12 1.
  13. 13. Deep Learning  Artificial Neural Networks (인공 신경망) learning process 13 1.
  14. 14. Deep Learning  Artificial Neural Networks (인공 신경망) learning process 14 1.
  15. 15. Deep Learning  Artificial Neural Networks (인공 신경망) learning process 15 1.
  16. 16. Deep Learning  Artificial Neural Networks (인공 신경망) learning process 16 1.
  17. 17. Deep Learning 17 1.
  18. 18. Deep Learning 18 1.
  19. 19. Deep Learning 19 1.
  20. 20. Deep Learning 20 1.
  21. 21. Deep Learning 21 1.
  22. 22. Deep Learning 22 1.
  23. 23. Deep Learning 23 1.
  24. 24. Deep Learning 24 1.
  25. 25. Deep Learning  Artificial Neural Networks (인공 신경망) learning process 25 1. https://theclevermachine.wordpress.com/tag/backpropagation , http://sebastianraschka.com/Articles/2015_singlelayer_neurons.html
  26. 26. Deep Learning  Artificial Neural Networks (인공 신경망) = “Deep” Learning 26 1.
  27. 27. Deep Learning  Convolutional Neural Networks (CNN) 27 1. cs231n: Convolutional Neural Networks for Visual Recognition
  28. 28. Deep Learning  Convolutional Neural Networks (CNN) 28 1. cs231n: Convolutional Neural Networks for Visual Recognition
  29. 29. Deep Learning  Convolutional Neural Networks (CNN) 29 1. cs231n: Convolutional Neural Networks for Visual Recognition
  30. 30. Deep Learning  Convolutional Neural Networks (CNN) 30 1. cs231n: Convolutional Neural Networks for Visual Recognition
  31. 31. Deep Learning  Convolutional Neural Networks (CNN) 31 1. cs231n: Convolutional Neural Networks for Visual Recognition
  32. 32. Deep Learning  Vision 32 적용 분야 1. cs231n: Convolutional Neural Networks for Visual Recognition
  33. 33. Deep Learning  Autonomous driving (자율 주행) 33 1. https://www.youtube.com/watch?v=HbPhvct5kvs
  34. 34. Deep Learning  Neural Style Transfer 34 1. Leon, et al. Image Style Transfer Using Convolutional Neural Networks
  35. 35. Deep Learning  Natural language processing (자연어 처리) • Translation • Chat bot • Caption generation • Document summarization • Voice synthesis  http://tv.naver.com/v/2292650 (35:00 ~ )  https://carpedm20.github.io/tacotron/en.html 35 1.
  36. 36. Research Topics 36
  37. 37. Research Topics  Chest X-ray • Lunit Insight : https://www.youtube.com/watch?v=ZkWBVyNuE3A (1:20 - ) • Diagnosis of major lung diseases (식약처 의료기기 허가) 37 Medical Images 2. 기흉 폐결핵 폐암 https://insight.lunit.io/#examples
  38. 38. Research Topics  X-ray • VUNO-MED BoneAge • Software for measuring age of bones (식약처 의료기기 허가) 38 Medical Images 2. https://www.youtube.com/watch?v=cI9nCVL40LM
  39. 39. Research Topics  Low-Dose CT 39 Medical Images 2. Kang, et al. A Deep Convolutional Neural Network using Directional Wavelets for Low-dose X-ray CT Reconstruction
  40. 40. Research Topics  Low-Dose CT 40 Medical Images 2. Kang, et al. A Deep Convolutional Neural Network using Directional Wavelets for Low-dose X-ray CT Reconstruction
  41. 41. Research Topics  Low-Dose CT 41 Medical Images 2. Kang, et al. A Deep Convolutional Neural Network using Directional Wavelets for Low-dose X-ray CT Reconstruction
  42. 42. Research Topics  CT • Liver and liver tumor segmentation 42 Medical Images 2. Li, et al. H-DenseUNet: Hybrid densely connected UNet for liver and liver tumor segmentation from CT volumes
  43. 43. Research Topics  CT • Liver and liver tumor segmentation 43 Medical Images 2. Li, et al. H-DenseUNet: Hybrid densely connected UNet for liver and liver tumor segmentation from CT volumes
  44. 44. Research Topics  CT • Liver and liver tumor segmentation 44 Medical Images 2. Li, et al. H-DenseUNet: Hybrid densely connected UNet for liver and liver tumor segmentation from CT volumes
  45. 45. Research Topics  CT • Liver and liver tumor segmentation 45 Medical Images 2. Li, et al. H-DenseUNet: Hybrid densely connected UNet for liver and liver tumor segmentation from CT volumes 𝐷𝑆𝐶 𝐴, 𝐵 = 2 × |𝐴 ∩ 𝐵| 𝐴 + |𝐵|
  46. 46. Research Topics  Segmentation of the prostate and OAR in CT 46 Radiation Treatment 2. Samaneh, et al. Segmentation of the prostate and organs at risk in male pelvic CT images using deep learning bladder prostate rectum
  47. 47. Research Topics  Segmentation of the prostate and OAR in CT • Prostate segmentation results 47 Radiation Treatment 2. Samaneh, et al. Segmentation of the prostate and organs at risk in male pelvic CT images using deep learning
  48. 48. Research Topics  Segmentation of the prostate and OAR in CT • Bladder, rectum segmentation results 48 Radiation Treatment 2. Samaneh, et al. Segmentation of the prostate and organs at risk in male pelvic CT images using deep learning
  49. 49. Research Topics  MR-only Radiotherapy (MR-LINAC) 49 Radiation Treatment 2. https://avaloninnovation.com/en/mr-linac-en
  50. 50. Research Topics  MR-only Radiotherapy (MR-LINAC) • Pseudo CT generation from MR images 50 Radiation Treatment 2. Matteo, et al. Fast synthetic CT generation with deep learning for general pelvis MR-only Radiotherapy
  51. 51. Research Topics  MR-only Radiotherapy (MR-LINAC) • Difference of dose calculation results from real CT and pseudo CT : -3 ~ 3 % 51 Radiation Treatment 2. Matteo, et al. Fast synthetic CT generation with deep learning for general pelvis MR-only Radiotherapy
  52. 52. Research Topics  Isotope identification • Input : Gamma-ray spectra (Contains up to 5 random isotopes among 33 isotopes in total) • Target : Relative count contributions from each radioisotope 52 Radiation Detection 2. M. Kamuda, et al. Automated Isotope Identification Algorithm Using Artificial Neural Networks
  53. 53. Q & A 53
  54. 54. Thank you. 54

    Be the first to comment

    Login to see the comments

  • SaikiranBandla1

    Jan. 9, 2019
  • JiminLee36

    Aug. 8, 2020

(1) Brief introduction to deep learning (2) Recent research topics in medical field

Views

Total views

413

On Slideshare

0

From embeds

0

Number of embeds

2

Actions

Downloads

42

Shares

0

Comments

0

Likes

2

×