Automatic Detection of Visceral Arterial Aneurysms on Computed Tomography Angiography Using Artificial Intelligence Based Segmentation of the Vascular System
Introduction: Visceral arterial aneurysms (VAAs) are life threatening. Due to the paucity of symptoms and rarity of the disease, VAAs are underdiagnosed and underestimated. Artificial intelligence (AI) offers new insights into segmentation of the vascular system, and opportunities to better detect V...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | EJVES Vascular Forum |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666688X23000497 |
| _version_ | 1827908235059789824 |
|---|---|
| author | Fabien Lareyre Caroline Caradu Arindam Chaudhuri Cong Duy Lê Gilles Di Lorenzo Cédric Adam Marion Carrier Juliette Raffort Raphaël Coscas Jérémie Jayet Raphaël Soler Lucie Salomon du Mont |
| author_facet | Fabien Lareyre Caroline Caradu Arindam Chaudhuri Cong Duy Lê Gilles Di Lorenzo Cédric Adam Marion Carrier Juliette Raffort Raphaël Coscas Jérémie Jayet Raphaël Soler Lucie Salomon du Mont |
| author_sort | Fabien Lareyre |
| collection | DOAJ |
| description | Introduction: Visceral arterial aneurysms (VAAs) are life threatening. Due to the paucity of symptoms and rarity of the disease, VAAs are underdiagnosed and underestimated. Artificial intelligence (AI) offers new insights into segmentation of the vascular system, and opportunities to better detect VAAs. This pilot study aimed to develop an AI based method to automatically detect VAAs from computed tomography angiography (CTA). Methods: A hybrid method combining a feature based expert system with a supervised deep learning algorithm (convolutional neural network) was used to enable fully automatic segmentation of the abdominal vascular tree. Centrelines were built and reference diameters of each visceral artery were calculated. An abnormal dilatation (VAAs) was defined as a substantial increase in diameter at the pixel of interest compared with the mean diameter of the reference portion. The automatic software provided 3D rendered images with a flag on the identified VAA areas. The performance of the method was tested in a dataset of 33 CTA scans and compared with the ground truth provided by two human experts. Results: Forty-three VAAs were identified by human experts (32 in the coeliac trunk branches, eight in the superior mesenteric artery, one in the left renal, and two in the right renal arteries). The automatic system accurately detected 40 of the 43 VAAs, with a sensitivity of 0.93 and a positive predictive value of 0.51. The mean number of flag areas per CTA was 3.5 ± 1.5 and they could be reviewed and checked by a human expert in less than 30 seconds per CTA. Conclusion: Although the specificity needs to be improved, this study demonstrates the potential of an AI based automatic method to develop new tools to improve screening and detection of VAAs by automatically attracting clinicians’ attention to suspicious dilatations of the visceral arteries. |
| first_indexed | 2024-03-13T01:19:05Z |
| format | Article |
| id | doaj.art-08e90e154bae401fa55aba6dd92a7cca |
| institution | Directory Open Access Journal |
| issn | 2666-688X |
| language | English |
| last_indexed | 2024-03-13T01:19:05Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EJVES Vascular Forum |
| spelling | doaj.art-08e90e154bae401fa55aba6dd92a7cca2023-07-05T05:17:12ZengElsevierEJVES Vascular Forum2666-688X2023-01-01591519Automatic Detection of Visceral Arterial Aneurysms on Computed Tomography Angiography Using Artificial Intelligence Based Segmentation of the Vascular SystemFabien Lareyre0Caroline Caradu1Arindam Chaudhuri2Cong Duy Lê3Gilles Di Lorenzo4Cédric Adam5Marion Carrier6Juliette Raffort7Raphaël Coscas8Jérémie Jayet9Raphaël Soler10Lucie Salomon du Mont11Department of Vascular Surgery, Hospital of Antibes Juan-les-Pins, France; Université Côte d'Azur, CHU, Inserm U1065, C3M, Nice, France; Corresponding author. Department of Vascular Surgery, Hospital of Antibes-Juan-les-Pins, 107 avenue de Nice, 06 600, Antibes, France.Department of Vascular Surgery, University Hospital of Bordeaux, FranceBedfordshire - Milton Keynes Vascular Centre, Bedford Hospital NHS Trust, Bedford, UKDepartment of Vascular Surgery, Hospital of Antibes Juan-les-Pins, FranceDepartment of Vascular Surgery, Hospital of Antibes Juan-les-Pins, FranceLaboratory of Applied Mathematics and Computer Science (MICS), CentraleSupélec, Université Paris-Saclay, FranceLaboratory of Applied Mathematics and Computer Science (MICS), CentraleSupélec, Université Paris-Saclay, FranceUniversité Côte d'Azur, CHU, Inserm U1065, C3M, Nice, France; Institute 3IA Côte d’Azur, Université Côte d’Azur, France; Clinical Chemistry Laboratory, University Hospital of Nice, FranceDepartment of Vascular Surgery, Ambroise Paré University Hospital, AP-HP, Boulogne-Billancourt, FranceDepartment of Vascular Surgery, Ambroise Paré University Hospital, AP-HP, Boulogne-Billancourt, FranceDepartment of Vascular and Endovascular Surgery, Hôpital Saint Joseph, Marseille, FranceDepartment of Vascular Surgery, University Hospital of Besançon, FranceIntroduction: Visceral arterial aneurysms (VAAs) are life threatening. Due to the paucity of symptoms and rarity of the disease, VAAs are underdiagnosed and underestimated. Artificial intelligence (AI) offers new insights into segmentation of the vascular system, and opportunities to better detect VAAs. This pilot study aimed to develop an AI based method to automatically detect VAAs from computed tomography angiography (CTA). Methods: A hybrid method combining a feature based expert system with a supervised deep learning algorithm (convolutional neural network) was used to enable fully automatic segmentation of the abdominal vascular tree. Centrelines were built and reference diameters of each visceral artery were calculated. An abnormal dilatation (VAAs) was defined as a substantial increase in diameter at the pixel of interest compared with the mean diameter of the reference portion. The automatic software provided 3D rendered images with a flag on the identified VAA areas. The performance of the method was tested in a dataset of 33 CTA scans and compared with the ground truth provided by two human experts. Results: Forty-three VAAs were identified by human experts (32 in the coeliac trunk branches, eight in the superior mesenteric artery, one in the left renal, and two in the right renal arteries). The automatic system accurately detected 40 of the 43 VAAs, with a sensitivity of 0.93 and a positive predictive value of 0.51. The mean number of flag areas per CTA was 3.5 ± 1.5 and they could be reviewed and checked by a human expert in less than 30 seconds per CTA. Conclusion: Although the specificity needs to be improved, this study demonstrates the potential of an AI based automatic method to develop new tools to improve screening and detection of VAAs by automatically attracting clinicians’ attention to suspicious dilatations of the visceral arteries.http://www.sciencedirect.com/science/article/pii/S2666688X23000497Artificial intelligenceAutomated segmentationMachine learningVascularVisceral arterial aneurysm |
| spellingShingle | Fabien Lareyre Caroline Caradu Arindam Chaudhuri Cong Duy Lê Gilles Di Lorenzo Cédric Adam Marion Carrier Juliette Raffort Raphaël Coscas Jérémie Jayet Raphaël Soler Lucie Salomon du Mont Automatic Detection of Visceral Arterial Aneurysms on Computed Tomography Angiography Using Artificial Intelligence Based Segmentation of the Vascular System EJVES Vascular Forum Artificial intelligence Automated segmentation Machine learning Vascular Visceral arterial aneurysm |
| title | Automatic Detection of Visceral Arterial Aneurysms on Computed Tomography Angiography Using Artificial Intelligence Based Segmentation of the Vascular System |
| title_full | Automatic Detection of Visceral Arterial Aneurysms on Computed Tomography Angiography Using Artificial Intelligence Based Segmentation of the Vascular System |
| title_fullStr | Automatic Detection of Visceral Arterial Aneurysms on Computed Tomography Angiography Using Artificial Intelligence Based Segmentation of the Vascular System |
| title_full_unstemmed | Automatic Detection of Visceral Arterial Aneurysms on Computed Tomography Angiography Using Artificial Intelligence Based Segmentation of the Vascular System |
| title_short | Automatic Detection of Visceral Arterial Aneurysms on Computed Tomography Angiography Using Artificial Intelligence Based Segmentation of the Vascular System |
| title_sort | automatic detection of visceral arterial aneurysms on computed tomography angiography using artificial intelligence based segmentation of the vascular system |
| topic | Artificial intelligence Automated segmentation Machine learning Vascular Visceral arterial aneurysm |
| url | http://www.sciencedirect.com/science/article/pii/S2666688X23000497 |
| work_keys_str_mv | AT fabienlareyre automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT carolinecaradu automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT arindamchaudhuri automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT congduyle automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT gillesdilorenzo automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT cedricadam automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT marioncarrier automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT julietteraffort automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT raphaelcoscas automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT jeremiejayet automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT raphaelsoler automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem AT luciesalomondumont automaticdetectionofvisceralarterialaneurysmsoncomputedtomographyangiographyusingartificialintelligencebasedsegmentationofthevascularsystem |