Se ha denunciado esta presentación.
Utilizamos tu perfil de LinkedIn y tus datos de actividad para personalizar los anuncios y mostrarte publicidad más relevante. Puedes cambiar tus preferencias de publicidad en cualquier momento.

Active Deep Learning for Medical Imaging

6.203 visualizaciones

Publicado el

https://imatge.upc.edu/web/publications/active-deep-learning-medical-imaging-segmentation

This thesis proposes a novel active learning framework capable to train eectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our approach tries to apply in segmentation existing active learning techniques, which is becoming an important topic today because of the many problems caused by the lack of large amounts of data. We explore dierent strategies to study the image information and introduce a previously used cost-eective active learning method based on the selection of high condence predictions to assign automatically pseudo-labels with the aim of reducing the manual annotations. First, we made a simple application for handwritten digit classication to get started to the methodology and then we test the system with a medical image database for the treatment of melanoma skin cancer. Finally, we compared the traditional training methods with our active learning proposals, specifying the conditions and parameters required for it to be optimal.

Publicado en: Datos y análisis
  • Inicia sesión para ver los comentarios

Active Deep Learning for Medical Imaging

  1. 1. ACTIVE DEEP LEARNING FOR MEDICAL IMAGING Marc Górriz Xavier Giró-i-Nieto Axel Carlier Emmanuel Faure
  2. 2. 2 OUTLINE 1. Motivation 2. State of the art 3. Methodology 4. Results 5. Conclusions
  3. 3. 3 MOTIVATION GOAL. Use active learning methodology to train a convolutional neural network for semantic segmentation of lesion areas in medical images. Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)
  4. 4. 4 MOTIVATION Manual pixel-wise annotation: ▹ Medical expert ▹ 1 image ~ 30 min 2,000images x 25 €/h x 30min/image = = 25,000 €/database
  5. 5. 5 MOTIVATION ▹ Millions of trainable parameters. ▹ Optimization process during training. ▹ Large amounts of labeled data to prevent convergence in local minima. Deep Convolutional Neural Network
  6. 6. 6 MOTIVATION Active Learning solution “ auto-selection of useful instances to be labeled in order to achieve similar performance with few data ” Computer Vision Laboratory CVLAB. Machine Learning for Biomedical Imaging. Active Learning
  7. 7. 7 Toy example: 2D classifier red & black classifier. Select the best discriminator with as few labeled data as possible. Unlabeled dataset ▹ Ground truth in light color ▹ Random labeling initialization accuracy: red: black: ? : ? % 0 / 29 0 / 29 29 / 29
  8. 8. 8 Toy example: 2D classifier red & black classifier. Select the best discriminator with as few labeled data as possible. Active Learning approach: ▹ 4 new labels per iteration ▹ Most uncertain selection accuracy: red: black: ? : 85% 04 / 29 04 / 29 21 / 29
  9. 9. 9 Toy example: 2D classifier red & black classifier. Select the best discriminator with as few labeled data as possible. Active Learning approach: ▹ 4 new labels per iteration ▹ Most uncertain selection accuracy: red: black: ? : 85% 04 / 29 04 / 29 21 / 29
  10. 10. 10 Toy example: 2D classifier red & black classifier. Select the best discriminator with as few labeled data as possible. Active Learning approach: ▹ 4 new labels per iteration ▹ Most uncertain selection accuracy: red: black: ? : 85% 06 / 29 06 / 29 17 / 29
  11. 11. 11 Toy example: 2D classifier red & black classifier. Select the best discriminator with as few labeled data as possible. Active Learning approach: ▹ 4 new labels per iteration ▹ Most uncertain selection accuracy: red: black: ? : 90% 06 / 29 06 / 29 17 / 29
  12. 12. 12 Toy example: 2D classifier red & black classifier. Select the best discriminator with as few labeled data as possible. Active Learning approach: ▹ 4 new labels per iteration ▹ Most uncertain selection accuracy: red: black: ? : 90% 06 / 29 06 / 29 17 / 29
  13. 13. 13 Toy example: 2D classifier red & black classifier. Select the best discriminator with as few labeled data as possible. Active Learning approach: ▹ 4 new labels per iteration ▹ Most uncertain selection accuracy: red: black: ? : 90% 08 / 29 09 / 29 12 / 29
  14. 14. 14 Toy example: 2D classifier red & black classifier. Select the best discriminator with as few labeled data as possible. Active Learning approach: ▹ 4 new labels per iteration ▹ Most uncertain selection accuracy: red: black: ? : 100% 08 / 29 09 / 29 12 / 29
  15. 15. 15 Toy example: 2D classifier Goal completed: best (same) accuracy with few labeled data. Active Learning Approach Fully Labeled Approach
  16. 16. 16 OUTLINE 1. Motivation 2. State of the art 3. Methodology 4. Results 5. Conclusions
  17. 17. 17 STATE OF THE ART Uncertain. Samples near border between classes. More dubitative for the classifier. Labeled by human. Certain. Samples far from the border between classes. Easier for the classifier. Labeled by itself (Pseudo Labeling). Cost effective Active Learning algorithm (CEAL) Keze Wang, Dongyu Zhang, Ya Li, Ruimao Zhang, and Liang Lin. Cost-effective active learning for deep image classification. CoRR, abs/1701.03551, 2017.
  18. 18. 18 U-NET MODEL ▹ Convolutional Neural Network for biomedical image segmentation. Olaf Ronneberger et al., U-Net: Convolutional Networks for Biomedical Image Segmentation. CoRR, abs/1505.04597, 2015.
  19. 19. 19 OUTLINE 1. Motivation 2. State of the art 3. Methodology 4. Results 5. Conclusions
  20. 20. 20 ISIC ARCHIVE DATASET ▹ ISIC 2016 Challenge dataset (modified) for Skin Lesion Analysis towards melanoma detection. Training set 1600 images Test set 400 images ➡
  21. 21. 21 METHODOLOGY SCHEME
  22. 22. 22 METHODOLOGY SCHEME Initialization
  23. 23. 23 INITIALIZATION Initial datasets definition ISIC training dataset Initial labeled set Initial unlabeled set Labeled size Labeled size Initialevaluation ▹ Initial labeled size depending only on the real world application specifications.
  24. 24. 24 INITIALIZATION Data augmentation ▹ Random transformations to generate new initial data instances. ▹ Increases the variability of the initial data to prevent overfitting. ▹ Helps to achieve a fast great initial performance.
  25. 25. 25 METHODOLOGY SCHEME Complementary Sample selection
  26. 26. 26 UNCERTAINTY COMPUTATION Monte Carlo Dropout methodology ▹ Prediction uncertainty will be the variance of T step predictions by applying dropout to change randomly the weights setup. Original image Step predictions Pixel-wise (PW) uncertainty
  27. 27. 27 UNCERTAINTY COMPUTATION Monte Carlo Dropout methodology ▹ We need a numerical index to rank all the input data. ▹ Overall uncertainty as pixel-wise sum. ▹ A size normalization is needed to decorrelate the uncertainty component around the cell contour. U = 162.22 U = 235.21
  28. 28. 28 DIAGRAM DATA ANALYSIS Complementary Data Selection Unlabeled set predictions + uncertainty maps Uncertainty vs dice coefficient (unlabeled data)
  29. 29. 29 DIAGRAM DATA ANALYSIS Complementary Data Selection Unlabeled set predictions Human manually labeling ▹ Most uncertain samples. ▹ No-detections. Uncertainty vs dice coefficient (unlabeled data) No-detections
  30. 30. 30 DIAGRAM DATA ANALYSIS Complementary Data Selection Unlabeled set predictions System automatic labeling ▹ Best accurate predictions. ▹ Most certain samples. Uncertainty vs dice coefficient (unlabeled data)
  31. 31. 31 DIAGRAM DATA ANALYSIS Complementary Data Selection Uncertainty axis projection Uncertainty vs dice coefficient (unlabeled data)
  32. 32. 32 DIAGRAM DATA ANALYSIS Complementary Data Selection ▹ Candidates for pseudo-labeling Uncertainty vs dice coefficient (unlabeled data) Uncertainty axis projection
  33. 33. 33 DIAGRAM DATA ANALYSIS Complementary Data Selection ▹ Interfering samples for the pseudo-labeling selection Uncertainty vs dice coefficient (unlabeled data) Uncertainty axis projection
  34. 34. 34 DIAGRAM DATA ANALYSIS Complementary Data Selection Unlabeled set predictions ▹ Interfering samples for the pseudo-labeling selection Uncertainty vs dice coefficient (unlabeled data) Solution. Random selection ▹ Select K random samples in the region to be manually annotated.
  35. 35. 35 OUTLINE 1. Motivation 2. State of the art 3. Methodology 4. Results 5. Conclusions
  36. 36. 36 CEAL APPROACH Initialization Initial labeled set Initial unlabeled set Test set 600 samples 1000 samples 400 samples Active Learning Loop (sample selection per iteration) Human Labeling Pseudo LabelingNo-detections Most uncertain Random 10 samples 10 samples 15 samples 20 + 20 x it (> 5 it ) samples
  37. 37. 37 RESULTS Initial training Active Learning Loop (10 iterations)
  38. 38. 38 RESULTS ▹ Regions diagram evolution. ▹ Red samples: human annotations.
  39. 39. 39 RESULTS Qualitative evaluation Original image Active Learning model Fully Labeled model
  40. 40. 40 RESULTS Qualitative evaluation Original image Active Learning model Fully Labeled model
  41. 41. 41 RESULTS Qualitative evaluation Original image Active Learning model Fully Labeled model
  42. 42. 42 OUTLINE 1. Motivation 2. State of the art 3. Methodology 4. Results 5. Conclusions
  43. 43. 43 CONCLUSIONS Active Deep Learning for semantic segmentation is few discussed today due to the network complexity. Tested. Cost-Effective Active Learning methodology is able for segmentation. Satisfactory qualitative results. Imperfect segmentations but enough in many real world applications.
  44. 44. 44 CONCLUSIONS ▹ Save of time and money in the labeling process if the application not requires a contour perfection. Labeled data Time cost Money cost Fully Labeled model 2,000 samples 1,000 h 25,000 € Active Learning model 900 samples 450 h 11,250 € Savings 550 h 13,750 €
  45. 45. 45 FUTURE WORK ▹ Improve the complementary sample selection in order to take more advantage to the pseudo labeling process.
  46. 46. 46 THANKS! Any questions? You can find me at
  47. 47. APPENDIX SLIDES
  48. 48. 48 U-NET MODEL ▹ ConvNet weights randomly initialized. ▹ Loss function: Dice coefficient. ▹ Adam optimizer (stochastic gradient-based optimization) ▸ Learning rate: 10e-5 ▹ Batch size: 32 samples Training parameters
  49. 49. 49 UNCERTAINTY COMPUTATION Cell size correlation problem ▹ Correlation between cell size and the overall uncertainty value. ▹ We need a cell size normalization. Overall uncertainty = 163.22 Overall uncertainty = 235.21
  50. 50. 50 UNCERTAINTY COMPUTATION Euclidean Distance Transform x Prediction Distance map {0,1} Size-normalized uncertainty map Uncertainty map

×