1
|
Li Y, Zhang H, Sun Y, Fan Q, Wang L, Ji C, HuiGu, Chen B, Zhao S, Wang D, Yu P, Li J, Yang S, Zhang C, Wang X. Deep learning-based platform performs high detection sensitivity of intracranial aneurysms in 3D brain TOF-MRA: An external clinical validation study. Int J Med Inform 2024; 188:105487. [PMID: 38761459 DOI: 10.1016/j.ijmedinf.2024.105487] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2023] [Revised: 05/06/2024] [Accepted: 05/15/2024] [Indexed: 05/20/2024]
Abstract
PURPOSE To evaluate the diagnostic efficacy of a developed artificial intelligence (AI) platform incorporating deep learning algorithms for the automated detection of intracranial aneurysms in time-of-flight (TOF) magnetic resonance angiography (MRA). METHOD This retrospective study encompassed 3D TOF MRA images acquired between January 2023 and June 2023, aiming to validate the presence of intracranial aneurysms via our developed AI platform. The manual segmentation results by experienced neuroradiologists served as the "gold standard". Following annotation of MRA images by neuroradiologists using InferScholar software, the AI platform conducted automatic segmentation of intracranial aneurysms. Various metrics including accuracy (ACC), balanced ACC, area under the curve (AUC), sensitivity (SE), specificity (SP), F1 score, Brier Score, and Net Benefit were utilized to evaluate the generalization of AI platform. Comparison of intracranial aneurysm identification performance was conducted between the AI platform and six radiologists with experience ranging from 3 to 12 years in interpreting MR images. Additionally, a comparative analysis was carried out between radiologists' detection performance based on independent visual diagnosis and AI-assisted diagnosis. Subgroup analyses were also performed based on the size and location of the aneurysms to explore factors impacting aneurysm detectability. RESULTS 510 patients were enrolled including 215 patients (42.16 %) with intracranial aneurysms and 295 patients (57.84 %) without aneurysms. Compared with six radiologists, the AI platform showed competitive discrimination power (AUC, 0.96), acceptable calibration (Brier Score loss, 0.08), and clinical utility (Net Benefit, 86.96 %). The AI platform demonstrated superior performance in detecting aneurysms with an overall SE, SP, ACC, balanced ACC, and F1 score of 91.63 %, 92.20 %, 91.96 %, 91.92 %, and 90.57 % respectively, outperforming the detectability of the two resident radiologists. For subgroup analysis based on aneurysm size and location, we observed that the SE of the AI platform for identifying tiny (diameter<3mm), small (3 mm ≤ diameter<5mm), medium (5 mm ≤ diameter<7mm) and large aneurysms (diameter ≥ 7 mm) was 87.80 %, 93.14 %, 95.45 %, and 100 %, respectively. Furthermore, the SE for detecting aneurysms in the anterior circulation was higher than that in the posterior circulation. Utilizing the AI assistance, six radiologists (i.e., two residents, two attendings and two professors) achieved statistically significant improvements in mean SE (residents: 71.40 % vs. 88.37 %; attendings: 82.79 % vs. 93.26 %; professors: 90.07 % vs. 97.44 %; P < 0.05) and ACC (residents: 85.29 % vs. 94.12 %; attendings: 91.76 % vs. 97.06 %; professors: 95.29 % vs. 98.82 %; P < 0.05) while no statistically significant change was observed in SP. Overall, radiologists' mean SE increased by 11.40 %, mean SP increased by 1.86 %, and mean ACC increased by 5.88 %, mean balanced ACC promoted by 6.63 %, mean F1 score grew by 7.89 %, and Net Benefit rose by 12.52 %, with a concurrent decrease in mean Brier score declined by 0.06. CONCLUSIONS The deep learning algorithms implemented in the AI platform effectively detected intracranial aneurysms on TOF-MRA and notably enhanced the diagnostic capabilities of radiologists. This indicates that the AI-based auxiliary diagnosis model can provide dependable and precise prediction to improve the diagnostic capacity of radiologists.
Collapse
Affiliation(s)
- Yuanyuan Li
- Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, China; Department of Radiology, Liaocheng People's Hospital, Shandong First Medical University & Shandong Academy of Medical Sciences, China; Department of Radiology, Shandong Provincial Hospital, Cheeloo College of Medicine, Shandong University, China
| | - Huiling Zhang
- Institute of Research, Infervision Medical Technology Co., Ltd, China
| | - Yun Sun
- Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, China
| | - Qianrui Fan
- Institute of Research, Infervision Medical Technology Co., Ltd, China
| | - Long Wang
- Department of Cardiovascular Surgery, Shandong Provincial Hospital Affiliated to Shandong First Medical University, China
| | - Congshan Ji
- Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, China
| | - HuiGu
- Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, China; Department of Radiology, Liaocheng People's Hospital, Shandong First Medical University & Shandong Academy of Medical Sciences, China; Department of Radiology, Shandong Provincial Hospital, Cheeloo College of Medicine, Shandong University, China
| | - Baojin Chen
- Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, China
| | - Shuo Zhao
- Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, China; Department of Radiology, Liaocheng People's Hospital, Shandong First Medical University & Shandong Academy of Medical Sciences, China; Department of Radiology, Shandong Provincial Hospital, Cheeloo College of Medicine, Shandong University, China
| | - Dawei Wang
- Institute of Research, Infervision Medical Technology Co., Ltd, China
| | - Pengxin Yu
- Institute of Research, Infervision Medical Technology Co., Ltd, China
| | - Junchen Li
- Department of Radiology, Changshu Hospital Affiliated to Nanjing University of Chinese Medicine, China
| | - Shifeng Yang
- Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, China.
| | - Chuanchen Zhang
- Department of Radiology, Liaocheng People's Hospital, Shandong First Medical University & Shandong Academy of Medical Sciences, China.
| | - Ximing Wang
- Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, China; Department of Radiology, Shandong Provincial Hospital, Cheeloo College of Medicine, Shandong University, China.
| |
Collapse
|
2
|
Frączek MJ, Krzyżewski RM, Kliś KM, Kwinta BM, Popiela TJ, Stachura K. Unruptured intracranial aneurysms: Why should we focus on small aneurysms? A comprehensive update of recent findings. Pol J Radiol 2024; 89:e13-e23. [PMID: 38371893 PMCID: PMC10867953 DOI: 10.5114/pjr.2024.134424] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2023] [Accepted: 12/21/2023] [Indexed: 02/20/2024] Open
Abstract
Intracranial aneurysms (IAs) are a significant public health concern because they have the potential to cause deva-stating consequences, including death and disability. Despite advances in diagnostic and treatment modalities, the outcomes for patients with aneurysmal subarachnoid haemorrhage (aSAH) remain poor, with high rates of rebleeding, vasospasm, and cerebral ischaemia. IAs are a significant risk factor for aSAH, and it is estimated that up to 3% of the general population have IAs. Recent studies using novel imaging modalities have shown that the prevalence of IAs may be much higher, with 6.6% of adults aged 40-84 years having intradural saccular IAs ≥ 2 mm. The risk of rupture for IAs is difficult to predict, and the decision to treat them invasively is based on a balance between the estimated rupture risk and the procedural risks of the treatment. However, the mortality and morbidity rates among patients treated for IAs can be as high as 5%. There is a need for clear guidelines on the treatment of IAs, and this review aims to provide an update on recent findings in this area. To achieve this goal, the authors identified and summarized recent, high-impact studies on IAs. The review focuses on the diagnostic and treatment options for IAs, as well as the risks associated with these interventions. The authors also provide an overview of the natural history of IAs and discuss the challenges and uncertainties in managing these patients.
Collapse
Affiliation(s)
- Maciej Jakub Frączek
- Department of Neurosurgery and Neurotraumatology, Faculty of Medicine, Jagiellonian University Medical College, Krakow, Poland
- Doctoral School of Medical and Health Sciences, Jagiellonian University Medical College, Krakow, Poland
| | - Roger Marek Krzyżewski
- Department of Neurosurgery and Neurotraumatology, Faculty of Medicine, Jagiellonian University Medical College, Krakow, Poland
| | - Kornelia Maria Kliś
- Department of Neurosurgery and Neurotraumatology, Faculty of Medicine, Jagiellonian University Medical College, Krakow, Poland
| | - Borys Maria Kwinta
- Department of Neurosurgery and Neurotraumatology, Faculty of Medicine, Jagiellonian University Medical College, Krakow, Poland
| | - Tadeusz Jan Popiela
- Chair of Radiology, Faculty of Medicine, Jagiellonian University Medical College, Krakow, Poland
| | - Krzysztof Stachura
- Department of Neurosurgery and Neurotraumatology, Faculty of Medicine, Jagiellonian University Medical College, Krakow, Poland
| |
Collapse
|
3
|
Ma J, Zheng Y, Li P, Zhou T, Sun Z, Ju T, Li A. Risk factors for the rupture of intracranial aneurysms: a systematic review and meta-analysis. Front Neurol 2023; 14:1268438. [PMID: 38146438 PMCID: PMC10749344 DOI: 10.3389/fneur.2023.1268438] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2023] [Accepted: 11/09/2023] [Indexed: 12/27/2023] Open
Abstract
Purpose The study aimed to identify potential risk factors for aneurysm rupture by performing a systematic review and meta-analysis. Materials and methods We systematically searched the PubMed, Embase, and Cochrane Library electronic databases for eligible studies from their inception until June 2023. Results Eighteen studies involving 17,069 patients with unruptured intracranial aneurysm (UIA) and 2,699 aneurysm ruptures were selected for the meta-analysis. Hyperlipidemia [odds ratio (OR): 0.47; 95% confidence interval (CI): 0.39-0.56; p < 0.001] and a family history of subarachnoid hemorrhage (SAH) (OR: 0.81; 95% CI: 0.71-0.91; p = 0.001) were associated with a reduced risk of aneurysm rupture. In contrast, a large-size aneurysm (OR: 4.49; 95% CI: 2.46-8.17; p < 0.001), ACA (OR: 3.34; 95% CI: 1.94-5.76; p < 0.001), MCA (OR: 2.16; 95% CI: 1.73-2.69; p < 0.001), and VABA (OR: 2.20; 95% CI: 1.24-3.91; p = 0.007) were associated with an increased risk of aneurysm rupture. Furthermore, the risk of aneurysm rupture was not affected by age, sex, current smoking, hypertension, diabetes mellitus, a history of SAH, and multiple aneurysms. Conclusion This study identified the predictors of aneurysm rupture in patients with UIAs, including hyperlipidemia, a family history of SAH, a large-size aneurysm, ACA, MCA, and VABA; patients at high risk for aneurysm rupture should be carefully monitored. Systematic Review Registration Our study was registered in the INPLASY platform (INPLASY202360062).
Collapse
Affiliation(s)
- Jinyuan Ma
- Department of Neurosurgery, Qingdao Binhai University Affiliated Hospital, Qingdao, China
| | - Yuehua Zheng
- Department of Neurosurgery, Weifang People’s Hospital Shandong Province, Weifang, China
| | - Puxian Li
- Department of Neurosurgery, Qingdao Binhai University Affiliated Hospital, Qingdao, China
| | - Tao Zhou
- Department of Neurosurgery, Weifang People’s Hospital Shandong Province, Weifang, China
| | - Zhen Sun
- Department of Neurosurgery, Qingdao Binhai University Affiliated Hospital, Qingdao, China
| | - Tongze Ju
- Department of Neurosurgery, Qingdao Binhai University Affiliated Hospital, Qingdao, China
| | - Aijun Li
- Department of Neurosurgery, Qingdao Binhai University Affiliated Hospital, Qingdao, China
| |
Collapse
|
4
|
Siller S, Kunz M, Lauseker M, Dimitriadis K, Dorn F, Tonn JC, Schichor C. The impact of initial counselling for patients' decision-making and the accuracy of interdisciplinary neurovascular board evaluation in elective treatment of unruptured intracranial aneurysms - a German single-centre retrospective study. Clin Neurol Neurosurg 2023; 232:107896. [PMID: 37454599 DOI: 10.1016/j.clineuro.2023.107896] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2023] [Revised: 07/10/2023] [Accepted: 07/11/2023] [Indexed: 07/18/2023]
Abstract
OBJECTIVE Interdisciplinary-neurovascular-boards (INVB) are deemed to find the patient's optimum treatment-modality in elective unruptured intracranial aneurysm-repair (EUIAR). If INVB judges risk/success estimation similar for microsurgical/endovascular EUIAR, the choice for either modality is up to the informed patient. However, it is unknown if the patients' decision-making might be biased by the discipline of initial counselling prior to INVB and if INVB's equal risk/success estimation is finally accurate. METHODS We analysed all our patients with EUIAR after INVB-discussion between 2007 and 2017 and identified those patients where INVB-recommendation estimated similar risk/success rates for both treatment-modalities. We investigated the procedural/outcome parameters and determined if the mode of initial counselling prior to INVB influenced the patients' choice of EUIAR and if INVB's equal risk/success estimation was accurate. RESULTS Within altogether 572 patients with EUIAR during our study period, we identified 99 patients (agemean:58 yrs; m:f=1:2) in whom pre-treatment INVB-discussion estimated risk/success rates for both modalities of EUIAR to be similar. Prior to INVB-discussion, 80 of the 99 patients had been initially counselled in the neurosurgical discipline and 19 patients in the endovascular discipline. The final patients' decision rates for surgical vs. endovascular EUIAR (after secondary consultation of each patient in both disciplines after INVB-discussion) were 67% vs. 33% in the first and 58% vs. 42% in the latter group (no significant difference: p = 0.345). Uni- and multivariate analysis did not show any hints for a bias in patients' decision-making caused by the discipline of initial counselling prior to INVB/secondary bilateral consultations. Clinical and procedural outcome at last follow-up (median:18mos) did not differ between those 66 patients that eventually decided for microsurgical and those 33 patients that eventually decided for endovascular EUIAR, underlining the high accuracy of INVB's pre-treatment risk/success estimations. CONCLUSION Only in a small number of patients, INVB estimates both disciplines to be of equal value for EUIAR which proves to be highly accurate at long-term outcome measures. Initial contact to one or the other neurovascular discipline does not appear to play a significant role in the final patient's decision-making process.
Collapse
Affiliation(s)
- Sebastian Siller
- Neurosurgical Clinic, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany; Department of Neuroradiology, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany.
| | - Mathias Kunz
- Neurosurgical Clinic, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany; Department of Neuroradiology, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany
| | - Michael Lauseker
- Institute for Medical Information Processing, Biometry and Epidemiology, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany; Department of Neuroradiology, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany
| | - Konstantinos Dimitriadis
- Neurological Clinic, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany; Department of Neuroradiology, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany
| | - Franziska Dorn
- Institute for Medical Information Processing, Biometry and Epidemiology, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany; Department of Neuroradiology, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany; Department of Neuroradiology, University Hospital of Bonn, Venusberg Campus 1, 53127 Bonn, Germany
| | - Joerg-Christian Tonn
- Neurosurgical Clinic, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany; Department of Neuroradiology, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany
| | - Christian Schichor
- Neurosurgical Clinic, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany; Department of Neuroradiology, Clinic of the University of Munich (LMU), Campus Grosshadern, Marchioninistrasse 15, 81377 Munich, Germany
| |
Collapse
|