Chronical Subdural Hematoma Segmentation Based on Computed Tomography Images Analysis
The aim of the demo is to show our developed system for chronical subdural hematoma segmentation based on analysis of computed tomography images. We used convolutional neural networks to automate the process of subdural hematoma segmentation from DCOM images got from computer tomography device and m...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
FRUCT
2023-05-01
|
Series: | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
Subjects: | |
Online Access: | https://www.fruct.org/publications/volume-33/acm33/files/zzKas.pdf |
_version_ | 1797807519893028864 |
---|---|
author | Alexey Kashevnik Ekaterina Alekseeva Mikhail Haleev Andrey Kitenko Ammar Yaser Ali Konstantin Samochernikh Konstantin Kukanov Arkady Ivanov Andrey Petrov |
author_facet | Alexey Kashevnik Ekaterina Alekseeva Mikhail Haleev Andrey Kitenko Ammar Yaser Ali Konstantin Samochernikh Konstantin Kukanov Arkady Ivanov Andrey Petrov |
author_sort | Alexey Kashevnik |
collection | DOAJ |
description | The aim of the demo is to show our developed system for chronical subdural hematoma segmentation based on analysis of computed tomography images. We used convolutional neural networks to automate the process of subdural hematoma segmentation from DCOM images got from computer tomography device and made a plugin for importing the masks to the OsiriX that one of the most famous DCOM viewer. A training dataset was assembled containing a total of 41 scans consisting of 3306 DCOM images. The presence or absence of subdural hematomas and their area was determined by the radiologist (ground truth). Two architectures are being tested: Unet and FPN (Feature Pyramid Network). For each architecture there are two training options were considered: (1) on separate images, when each image is considered as a separate unit; and (2) pseudo-3D, when images were viewed in blocks and the neural network could make predictions based on predictions for neighboring images. Our best model achieved an average DICE score of 0,7949 on the validation set. We integrated the pretrained model into OsiriX DICOM Viewer as a plugin. The plugin passes images to the model, which returns the segmentation predictions. The plugin converts them to ROI (region of interest) and transfers them to OsiriX, where, if necessary, the radiologist can edit them and get information about hematoma characteristics (such as volume). |
first_indexed | 2024-03-13T06:23:47Z |
format | Article |
id | doaj.art-6df30fbbcfe04be9a4486ec6b0a597f4 |
institution | Directory Open Access Journal |
issn | 2305-7254 2343-0737 |
language | English |
last_indexed | 2024-03-13T06:23:47Z |
publishDate | 2023-05-01 |
publisher | FRUCT |
record_format | Article |
series | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
spelling | doaj.art-6df30fbbcfe04be9a4486ec6b0a597f42023-06-09T11:41:51ZengFRUCTProceedings of the XXth Conference of Open Innovations Association FRUCT2305-72542343-07372023-05-0133242142110.5281/zenodo.8005397Chronical Subdural Hematoma Segmentation Based on Computed Tomography Images AnalysisAlexey Kashevnik0Ekaterina Alekseeva1Mikhail Haleev2Andrey Kitenko3Ammar Yaser Ali4Konstantin Samochernikh5Konstantin Kukanov6Arkady Ivanov7Andrey Petrov8SPIIRASITMO UniversityITMO UniversitySPC RASITMO UniversityAlmozov CenterAlmozov CenterAlmozov CenterAlmozov CenterThe aim of the demo is to show our developed system for chronical subdural hematoma segmentation based on analysis of computed tomography images. We used convolutional neural networks to automate the process of subdural hematoma segmentation from DCOM images got from computer tomography device and made a plugin for importing the masks to the OsiriX that one of the most famous DCOM viewer. A training dataset was assembled containing a total of 41 scans consisting of 3306 DCOM images. The presence or absence of subdural hematomas and their area was determined by the radiologist (ground truth). Two architectures are being tested: Unet and FPN (Feature Pyramid Network). For each architecture there are two training options were considered: (1) on separate images, when each image is considered as a separate unit; and (2) pseudo-3D, when images were viewed in blocks and the neural network could make predictions based on predictions for neighboring images. Our best model achieved an average DICE score of 0,7949 on the validation set. We integrated the pretrained model into OsiriX DICOM Viewer as a plugin. The plugin passes images to the model, which returns the segmentation predictions. The plugin converts them to ROI (region of interest) and transfers them to OsiriX, where, if necessary, the radiologist can edit them and get information about hematoma characteristics (such as volume).https://www.fruct.org/publications/volume-33/acm33/files/zzKas.pdfcomputer vision medical application chronical subdural hematoma segmentation |
spellingShingle | Alexey Kashevnik Ekaterina Alekseeva Mikhail Haleev Andrey Kitenko Ammar Yaser Ali Konstantin Samochernikh Konstantin Kukanov Arkady Ivanov Andrey Petrov Chronical Subdural Hematoma Segmentation Based on Computed Tomography Images Analysis Proceedings of the XXth Conference of Open Innovations Association FRUCT computer vision medical application chronical subdural hematoma segmentation |
title | Chronical Subdural Hematoma Segmentation Based on Computed Tomography Images Analysis |
title_full | Chronical Subdural Hematoma Segmentation Based on Computed Tomography Images Analysis |
title_fullStr | Chronical Subdural Hematoma Segmentation Based on Computed Tomography Images Analysis |
title_full_unstemmed | Chronical Subdural Hematoma Segmentation Based on Computed Tomography Images Analysis |
title_short | Chronical Subdural Hematoma Segmentation Based on Computed Tomography Images Analysis |
title_sort | chronical subdural hematoma segmentation based on computed tomography images analysis |
topic | computer vision medical application chronical subdural hematoma segmentation |
url | https://www.fruct.org/publications/volume-33/acm33/files/zzKas.pdf |
work_keys_str_mv | AT alexeykashevnik chronicalsubduralhematomasegmentationbasedoncomputedtomographyimagesanalysis AT ekaterinaalekseeva chronicalsubduralhematomasegmentationbasedoncomputedtomographyimagesanalysis AT mikhailhaleev chronicalsubduralhematomasegmentationbasedoncomputedtomographyimagesanalysis AT andreykitenko chronicalsubduralhematomasegmentationbasedoncomputedtomographyimagesanalysis AT ammaryaserali chronicalsubduralhematomasegmentationbasedoncomputedtomographyimagesanalysis AT konstantinsamochernikh chronicalsubduralhematomasegmentationbasedoncomputedtomographyimagesanalysis AT konstantinkukanov chronicalsubduralhematomasegmentationbasedoncomputedtomographyimagesanalysis AT arkadyivanov chronicalsubduralhematomasegmentationbasedoncomputedtomographyimagesanalysis AT andreypetrov chronicalsubduralhematomasegmentationbasedoncomputedtomographyimagesanalysis |