Mastering the Game of Go – slides [paper explained]

This week I presented to our weekly reading group, this work:

Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., … Hassabis, D. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587), 484–489.

To quickly summarize this work…

Basically, they create a policy network, which is a convolutional neural network, that predicts the next move a human player would do from a board state. They create a value network, also a convolutional neural network, that predicts the outcome (win or lose) of the game given the current board state.
Continue reading “Mastering the Game of Go – slides [paper explained]”

Dermofit 10-class – differences in ISBI and MLMI accuracy explained

I just got a great question asking why there is a discrepancy in the accuracy reported in our two works:

[ISBI paper, we report 81.8% accuracy over 10 classes]
Kawahara, J., BenTaieb, A., & Hamarneh, G. (2016). Deep features to classify skin lesions. In IEEE ISBI (pp. 1397–1400). Summary and slides here.

[MICCAI MLMI paper, we report 74.1% accuracy over 10 classes]
Kawahara, J., & Hamarneh, G. (2016). Multi-Resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers. In MLMI. Summary and slides here.

We use the same Dermofit dataset, so it seems surprising the accuracy we report in the papers are different. So I thought I would elaborate on why here.
Continue reading “Dermofit 10-class – differences in ISBI and MLMI accuracy explained”

multi-resolution-tract CNN with hybrid pretrained and skin-lesion trained layers

Our paper entitled: “Multi-resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers” was accepted and presented as an oral talk in the Machine Learning in Medical Imaging (MLMI) Workshop (part of the MICCAI conference).

In this work, we used a convolutional neural network (CNN) to classify 10 different types of skin lesions, including melanoma and non-melanoma types.

The key technical contribution was to use multiple tracts (or paths) within the neural network, to train (and test) the network on an image using multiple image resolutions simultaneously. Additionally, we extended a CNN pretrained on a single image resolution to work for multiple image resolutions.

Here are our slides presented at MLMI (thanks AΓ―cha!) showing our deep learning approach to classify skin disease:
Continue reading “multi-resolution-tract CNN with hybrid pretrained and skin-lesion trained layers”

Deep features to classify skin lesions – summary and slides

Here I'm nervously just starting our talk on our approach to skin lesion classification
Me nervously just starting to talk about our approach to skin lesion classification.

We presented our work, “Deep Features to Classify Skin Lesions” at ISBI 2016 in Prague! And I’m happy to report that our work was awarded runner-up for the Best Student Paper Award πŸ™‚

In this work, we looked at how to classify skin lesions from images captured with a digital camera (i.e., non-dermoscopy). Our approach was able to distinguish among 10 different types of skin diseases over 1300 images and achieved an accuracy higher than what was previously reported over the same dataset. We did this by applying deep learning (i.e., pretrained convolutional neural networks) to melanoma and non-melanoma skin images.

Continue reading “Deep features to classify skin lesions – summary and slides”

How to segment the spinal cord and predict disability in multiple sclerosis patients

So I have officially finished my Master’s work πŸ™‚ and I’ve written up a more extended abstract of the thesis with less technical terms below. This hopefully can give you some concise intuition on the work without the technical details. This page is meant to be a summary of all things related to this work and links to other relevant articles that I wrote.

The thesis is available here and is entitled:
Spinal cord segmentation and disability prediction in multiple sclerosis using novel optimization and machine learning methods

This thesis examines a) how toΒ segment the spinal cord from 3D magnetic resonance images (MRI) using computer-aided methods, and b) how to predict the level of clinical disability in multiple sclerosis (MS) patients using spinal cord segmentations and corresponding MRIs.

Continue reading “How to segment the spinal cord and predict disability in multiple sclerosis patients”

Predicting Disability in Patients with Multiple Sclerosis using MRI – MICCAI CSI

Our work on predicting the physical disability level of patients was accepted for an oral presentation at the MICCAI 2013 workshop on, Computational Methods and Clinical Applications for Spine Image, in Nagoya, Japan.

The paper itself you can read here and is called:
Novel morphological and appearance features for predicting physical disability from MR images in multiple sclerosis patients

Spinal Cord Segmentation using an A* search

Our paper was accepted in ISBI 2013! πŸ™‚

The paper is called:

Globally Optimal Spinal Cord Segmentation Using a Minimal Path in High Dimensions

I think the title really summarizes the work pretty nicely so I’ll break down each part of the title to give you a brief overview of the paper.

“Spinal Cord Segmentation” = this is the goal of the work. Given a 3D MRI, we want a method that can mark those voxels that belong to the spinal cord. Segmentation means to label the voxels as spinal cord or background.

“High Dimensions” = we represented the segmented spinal cord by a list of 6 numbers. I’ll explain this a bit more since this a bit tricky to understand. We used principle component analysis (PCA) to represent the “shape” of a 2D slice of the spinal cord. PCA allows us to represent each shape by its center point (x,y,z) and three principle components (giving us a total of 6 numbers per 2D slice). We can represent our spinal cord as a stack of these 2D shapes, or equivalently, a list of 6 numbers.

Now the question is, how to find this list of 6 numbers? Well we can search for them. This is similar to finding the shortest path in between 2 points, but instead of searching over 2 or 3 (spatial) dimensions, we search over the 6 dimensions (3 spatial and 3 shape).

“Minimal Path” = a minimal path finds the shortest path in between two points. In our methods, a user enters the start and end point of the spinal cord, and we find the minimal path in 6D between these two points. We use a slightly modified version of the A* search to find this minimal path. A path is defined to be “short” if the shapes “fits” well (e.g. the borders match) with what is in the MRI.

“Globally Optimal” = means that we can find the best segmentation that exists based on how we defined how well the shape “fits”. Our method will always find the global minimum and will not get stuck in any local minima.

You can take a look at the paper here.

Here’s the poster we did for the ISBI conference.

ISBI 2013 poster
Spinal Cord Segmentation Poster

The nice PDF can be viewed here.