@eelvira

Signed up since Sept. 30, 2017

Points

Timestamp Points Contributor Ad-hoc References
Jan. 26, 2018 5 @eelvira No PR #297
Jan. 26, 2018 6 @eelvira No Issues #230
Jan. 24, 2018 3 @eelvira No Issues #274
PR #293
Dec. 28, 2017 40 @eelvira No Issues #138
PR #267

Activity

@eelvira commented on issue #230: Ask a Clinician! (add a question, get points)

1. Does it make sense to save false-positives as well to check their locations on the next timestamp of the patient's CT? 2. What is the first thing radiologists notice if the pathologies are barely noticeable, and the algorithm did not mark these areas as probably pathological? 3. Where is it planned to run the program: directly on the computers of doctors or remotely on the server? Whether it's worth to implement algorithms with worse performance, but if they are also less resource consuming?
10 months, 3 weeks ago

@eelvira opened a new pull request: #297: Refactoring lungs separation

Refactoring of lungs separation: `remove_trash`, `if_separate` ## CLA - [x] I have signed the CLA; if other committers are in the commit history, they have signed the CLA as well
10 months, 3 weeks ago

@eelvira commented on PR #293: #274 Add doc strings

@reubano, thank you for reviewing, done and rebased!
10 months, 3 weeks ago

@eelvira opened a new pull request: #293: #274 Add doc strings

Adding docstrings and refactoring. ##Reference to official issue #274 ## CLA - [x] I have signed the CLA; if other committers are in the commit history, they have signed the CLA as well
10 months, 3 weeks ago

@eelvira commented on PR #267: Improved lungs segmentation algorithm

@reubano, @lamby, all rebased and squashed, can you take a look, please?
11 months, 3 weeks ago

@eelvira commented on PR #267: Improved lungs segmentation algorithm

Initially the separation of the lungs was implemented [the method](http://ieeexplore.ieee.org/abstract/document/929615/?reload=true), which chose the search area on a two-dimensional slice. Two-dimensional morphological erosion with a diamond-shaped nucleus was used for separation and successively was extended to other slices. It wasn't work perfect for some cases. ![good](https://user-images.githubusercontent.com/22271721/34329172-4568ac22-e906-11e7-87ba-eca19ed3b287.png) In order to avoid such situations, it was decided to apply the method was described in [this preprint](https://www.researchgate.net/publication/322041883_Lungs%27_Junction_Dilation_Propagation) by @vessemer. The main idea of the algorithm is to select reference binary image of the lungs in a one slice which further will be propagated over all adjacent slices, that have not yet been visited, by comparison of its complements. This process will be repeated, taking adjacent slices from previous step, as new reference images until lungs are not separated. ![sep_good](https://user-images.githubusercontent.com/22271721/34329173-463e3342-e906-11e7-8802-0d42238fb17d.png)
11 months, 3 weeks ago

@eelvira commented on PR #267: Improved lungs segmentation algorithm

@reubano , thank you for your comment and remarks! I will provide everything as soon as possible :)
12 months ago

@eelvira commented on PR #267: Improved lungs segmentation algorithm

@WGierke , thank you for your comment! I will try to provide all the necessary tests this weekend after some changes in the code base
1 year ago

@eelvira opened a new pull request: #267: Improved lungs segmentation algorithm

## Description The threshold method consists of 3 steps: 1) removal large airways from the lung; 2) lung segmentation; 3) morphological smoothing. ## Reference to official issue I have solved issue #138, there it was proposed to improve lung segmentation: https://github.com/concept-to-clinic/concept-to-clinic/issues/138 ## Motivation and Context The algorithm includs errors in lung segmentation, which often occur at the borders of the lungs, when the contrast between the lung parenchyma and the surrounding tissue is low due to pathologic abnormalities that show up as dense regions. In normal lung anatomy, the shape of the costal lung surface is convex. When an error occurs at the costal border, the surface is typically not convex anymore. This problem was fixed with method, which was described in issue #138. Also bronches and trachea were indicated and segmented in this method. ## How Has This Been Tested? I've tested the algorithm over the cases with nodules and compare output with basic segmentation algorithm. For check: first_patient = load_scan(INPUT_FOLDER) first_patient_pixels = get_pixels_hu(first_patient) lungs, trachea = detection_lung_error(first_patient_pixels) ## Screenshots : You can see that the algorithm includes pathologies, whereas the ventricle isn't included in lungs area: ![1](https://user-images.githubusercontent.com/22271721/33984220-e6e6d4e4-e0c7-11e7-80fc-8d6ffe50621c.png) ![3](https://user-images.githubusercontent.com/22271721/33984234-f4c3883c-e0c7-11e7-8814-83b724546266.png) Segmented lungs and trachea (bronchi) in frontal projection: ![2](https://user-images.githubusercontent.com/22271721/33984311-313e580a-e0c8-11e7-9f33-88188887c5f3.png) ![mesh_applied 3 -min](https://user-images.githubusercontent.com/22271721/33988348-32c6cb0a-e0d5-11e7-8b8a-b7a1cbfac080.gif)
1 year ago
1 year, 2 months ago