Automatic assessment of nailfold capillaroscopy software: a pilot study
Introduction Capillaroscopy is a simple method of nailfold capillary imaging, used to diagnose diseases from the systemic sclerosis spectrum. However, the assessment of the capillary image is time-consuming and subjective. This makes it difficult to use for a detailed comparison of studies assessed...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Termedia Publishing House
2024-11-01
|
| Series: | Rheumatology |
| Subjects: | |
| Online Access: | https://reu.termedia.pl/Automatic-assessment-of-nailfold-capillaroscopy-software-a-pilot-study,194040,0,2.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832584783096446976 |
|---|---|
| author | Olga Elżbieta Brzezińska Krzysztof Andrzej Rychlicki-Kicior Joanna Samanta Makowska |
| author_facet | Olga Elżbieta Brzezińska Krzysztof Andrzej Rychlicki-Kicior Joanna Samanta Makowska |
| author_sort | Olga Elżbieta Brzezińska |
| collection | DOAJ |
| description | Introduction
Capillaroscopy is a simple method of nailfold capillary imaging, used to diagnose diseases from the systemic sclerosis spectrum. However, the assessment of the capillary image is time-consuming and subjective. This makes it difficult to use for a detailed comparison of studies assessed by various physicians. This pilot study aimed to validate software used for automatic capillary counting and image classification as normal or pathological.
Material and methods
The study was based on the assessment of 200 capillaroscopic images obtained from patients suffering from systemic sclerosis or scleroderma spectrum diseases and healthy people. Dinolite MEDL4N Pro was used to perform capillaroscopy. Each image was analysed manually and described using working software. The neural network was trained using the fast.ai library (based on PyTorch). The ResNet-34 deep residual neural network was chosen; 10-fold cross-validation with the validation and test set was performed, using the Darknet-YoloV3 state of the art neural network in a GPU-optimized (P5000 GPU) environment. For the calculation of 1 mm capillaries, an additional detection mechanism was designed.
Results
The results obtained under neural network training were compared to the results obtained in manual analysis. The sensitivity of the automatic tool relative to manual assessment in classification of correct vs. pathological images was 89.0%, specificity 89.4% for the training group, in validation 89.0% and 86.9% respectively. For the average number of capillaries in 1 mm the precision of real images detected within the region of interest was 96.48%.
Conclusions
The pilot software for fully automatic capillaroscopic image assessment can be a useful tool for the rapid classification of a normal and altered capillaroscopy pattern. In addition, it allows one to quickly calculate the number of capillaries. In the future, the tool will be developed and will make it possible to obtain full imaging characteristics independent of the experience of the examiner. |
| format | Article |
| id | doaj-art-47a54c1dc4624f2a865f1bb6b1dad9a7 |
| institution | Kabale University |
| issn | 0034-6233 2084-9834 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Termedia Publishing House |
| record_format | Article |
| series | Rheumatology |
| spelling | doaj-art-47a54c1dc4624f2a865f1bb6b1dad9a72025-01-27T11:20:37ZengTermedia Publishing HouseRheumatology0034-62332084-98342024-11-0162534635010.5114/reum/194040194040Automatic assessment of nailfold capillaroscopy software: a pilot studyOlga Elżbieta Brzezińska0https://orcid.org/0000-0002-3885-8497Krzysztof Andrzej Rychlicki-Kicior1https://orcid.org/0000-0002-3419-745XJoanna Samanta Makowska2https://orcid.org/0000-0003-2036-375XDepartment of Rheumatology, Medical University of Lodz, PolandUniversity of Economics and Human Sciences in Warsaw, PolandDepartment of Rheumatology, Medical University of Lodz, PolandIntroduction Capillaroscopy is a simple method of nailfold capillary imaging, used to diagnose diseases from the systemic sclerosis spectrum. However, the assessment of the capillary image is time-consuming and subjective. This makes it difficult to use for a detailed comparison of studies assessed by various physicians. This pilot study aimed to validate software used for automatic capillary counting and image classification as normal or pathological. Material and methods The study was based on the assessment of 200 capillaroscopic images obtained from patients suffering from systemic sclerosis or scleroderma spectrum diseases and healthy people. Dinolite MEDL4N Pro was used to perform capillaroscopy. Each image was analysed manually and described using working software. The neural network was trained using the fast.ai library (based on PyTorch). The ResNet-34 deep residual neural network was chosen; 10-fold cross-validation with the validation and test set was performed, using the Darknet-YoloV3 state of the art neural network in a GPU-optimized (P5000 GPU) environment. For the calculation of 1 mm capillaries, an additional detection mechanism was designed. Results The results obtained under neural network training were compared to the results obtained in manual analysis. The sensitivity of the automatic tool relative to manual assessment in classification of correct vs. pathological images was 89.0%, specificity 89.4% for the training group, in validation 89.0% and 86.9% respectively. For the average number of capillaries in 1 mm the precision of real images detected within the region of interest was 96.48%. Conclusions The pilot software for fully automatic capillaroscopic image assessment can be a useful tool for the rapid classification of a normal and altered capillaroscopy pattern. In addition, it allows one to quickly calculate the number of capillaries. In the future, the tool will be developed and will make it possible to obtain full imaging characteristics independent of the experience of the examiner.https://reu.termedia.pl/Automatic-assessment-of-nailfold-capillaroscopy-software-a-pilot-study,194040,0,2.htmlmicroangiopathycapillaroscopydeep learningartificial intelligence |
| spellingShingle | Olga Elżbieta Brzezińska Krzysztof Andrzej Rychlicki-Kicior Joanna Samanta Makowska Automatic assessment of nailfold capillaroscopy software: a pilot study Rheumatology microangiopathy capillaroscopy deep learning artificial intelligence |
| title | Automatic assessment of nailfold capillaroscopy software: a pilot study |
| title_full | Automatic assessment of nailfold capillaroscopy software: a pilot study |
| title_fullStr | Automatic assessment of nailfold capillaroscopy software: a pilot study |
| title_full_unstemmed | Automatic assessment of nailfold capillaroscopy software: a pilot study |
| title_short | Automatic assessment of nailfold capillaroscopy software: a pilot study |
| title_sort | automatic assessment of nailfold capillaroscopy software a pilot study |
| topic | microangiopathy capillaroscopy deep learning artificial intelligence |
| url | https://reu.termedia.pl/Automatic-assessment-of-nailfold-capillaroscopy-software-a-pilot-study,194040,0,2.html |
| work_keys_str_mv | AT olgaelzbietabrzezinska automaticassessmentofnailfoldcapillaroscopysoftwareapilotstudy AT krzysztofandrzejrychlickikicior automaticassessmentofnailfoldcapillaroscopysoftwareapilotstudy AT joannasamantamakowska automaticassessmentofnailfoldcapillaroscopysoftwareapilotstudy |