Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography.
A non-contrast cranial computer tomography (ncCT) is often employed for the diagnosis of the early stage of the ischemic stroke. However, the number of false negatives is high. More accurate results are obtained by an MRI. However, the MRI is not available in every hospital. Moreover, even if it is...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0277573 |
| _version_ | 1797956066249539584 |
|---|---|
| author | Natsuda Kaothanthong Kamin Atsavasirilert Soawapot Sarampakhul Pantid Chantangphol Dittapong Songsaeng Stanislav Makhanov |
| author_facet | Natsuda Kaothanthong Kamin Atsavasirilert Soawapot Sarampakhul Pantid Chantangphol Dittapong Songsaeng Stanislav Makhanov |
| author_sort | Natsuda Kaothanthong |
| collection | DOAJ |
| description | A non-contrast cranial computer tomography (ncCT) is often employed for the diagnosis of the early stage of the ischemic stroke. However, the number of false negatives is high. More accurate results are obtained by an MRI. However, the MRI is not available in every hospital. Moreover, even if it is available in the clinic for the routine tests, emergency often does not have it. Therefore, this paper proposes an end-to-end framework for detection and segmentation of the brain infarct on the ncCT. The computer tomography perfusion (CTp) is used as the ground truth. The proposed ensemble model employs three deep convolution neural networks (CNNs) to process three end-to-end feature maps and a hand-craft features characterized by specific contra-lateral features. To improve the accuracy of the detected infarct area, the spatial dependencies between neighboring slices are employed at the postprocessing step. The numerical experiments have been performed on 18 ncCT-CTp paired stroke cases (804 image-pairs). The leave-one-out approach is applied for evaluating the proposed method. The model achieves 91.16% accuracy, 65.15% precision, 77.44% recall, 69.97% F1 score, and 0.4536 IoU. |
| first_indexed | 2024-04-10T23:44:06Z |
| format | Article |
| id | doaj.art-d4c9cf6f43ba46899ca2e94e2c80b8f3 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-10T23:44:06Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-d4c9cf6f43ba46899ca2e94e2c80b8f32023-01-11T05:32:42ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-011712e027757310.1371/journal.pone.0277573Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography.Natsuda KaothanthongKamin AtsavasirilertSoawapot SarampakhulPantid ChantangpholDittapong SongsaengStanislav MakhanovA non-contrast cranial computer tomography (ncCT) is often employed for the diagnosis of the early stage of the ischemic stroke. However, the number of false negatives is high. More accurate results are obtained by an MRI. However, the MRI is not available in every hospital. Moreover, even if it is available in the clinic for the routine tests, emergency often does not have it. Therefore, this paper proposes an end-to-end framework for detection and segmentation of the brain infarct on the ncCT. The computer tomography perfusion (CTp) is used as the ground truth. The proposed ensemble model employs three deep convolution neural networks (CNNs) to process three end-to-end feature maps and a hand-craft features characterized by specific contra-lateral features. To improve the accuracy of the detected infarct area, the spatial dependencies between neighboring slices are employed at the postprocessing step. The numerical experiments have been performed on 18 ncCT-CTp paired stroke cases (804 image-pairs). The leave-one-out approach is applied for evaluating the proposed method. The model achieves 91.16% accuracy, 65.15% precision, 77.44% recall, 69.97% F1 score, and 0.4536 IoU.https://doi.org/10.1371/journal.pone.0277573 |
| spellingShingle | Natsuda Kaothanthong Kamin Atsavasirilert Soawapot Sarampakhul Pantid Chantangphol Dittapong Songsaeng Stanislav Makhanov Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography. PLoS ONE |
| title | Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography. |
| title_full | Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography. |
| title_fullStr | Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography. |
| title_full_unstemmed | Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography. |
| title_short | Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography. |
| title_sort | artificial intelligence for localization of the acute ischemic stroke by non contrast computed tomography |
| url | https://doi.org/10.1371/journal.pone.0277573 |
| work_keys_str_mv | AT natsudakaothanthong artificialintelligenceforlocalizationoftheacuteischemicstrokebynoncontrastcomputedtomography AT kaminatsavasirilert artificialintelligenceforlocalizationoftheacuteischemicstrokebynoncontrastcomputedtomography AT soawapotsarampakhul artificialintelligenceforlocalizationoftheacuteischemicstrokebynoncontrastcomputedtomography AT pantidchantangphol artificialintelligenceforlocalizationoftheacuteischemicstrokebynoncontrastcomputedtomography AT dittapongsongsaeng artificialintelligenceforlocalizationoftheacuteischemicstrokebynoncontrastcomputedtomography AT stanislavmakhanov artificialintelligenceforlocalizationoftheacuteischemicstrokebynoncontrastcomputedtomography |