Bio Joo1, Sung Soo Ahn2, Pyeong Ho Yoon3, Sohi Bae3, Beomseok Sohn1,4, Yong Eun Lee5, Jun Ho Bae5, Moo Sung Park5, Hyun Seok Choi1, Seung-Koo Lee1. 1. Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Yonsei University College of Medicine, 50 Yonsei-ro, Seodaemun-gu, Seoul, 120-752, Korea. 2. Department of Radiology, Research Institute of Radiological Science and Center for Clinical Image Data Science, Yonsei University College of Medicine, 50 Yonsei-ro, Seodaemun-gu, Seoul, 120-752, Korea. SUNGSOO@yuhs.ac. 3. Department of Radiology, National Health Insurance Service Ilsan Hospital, Goyang-si, Gyeonggi-do, Korea. 4. Department of Radiology, Hongik Hospital, Seoul, Korea. 5. DEEPNOID, Seoul, Korea.
Abstract
OBJECTIVES: To develop a deep learning algorithm for automated detection and localization of intracranial aneurysms on time-of-flight MR angiography and evaluate its diagnostic performance. METHODS: In a retrospective and multicenter study, MR images with aneurysms based on radiological reports were extracted. The examinations were randomly divided into two data sets: training set of 468 examinations and internal test set of 120 examinations. Additionally, 50 examinations without aneurysms were randomly selected and added to the internal test set. External test data set consisted of 56 examinations with intracranial aneurysms and 50 examinations without aneurysms, which were extracted based on radiological reports from a different institution. After manual ground truth segmentation of aneurysms, a deep learning algorithm based on 3D ResNet architecture was established with the training set. Its sensitivity, positive predictive value, and specificity were evaluated in the internal and external test sets. RESULTS: MR images included 551 aneurysms (mean diameter, 4.17 ± 2.49 mm) in the training, 147 aneurysms (mean diameter, 3.98 ± 2.11 mm) in the internal test, 63 aneurysms (mean diameter, 3.23 ± 1.69 mm) in the external test sets. The sensitivity, the positive predictive value, and the specificity were 87.1%, 92.8%, and 92.0% for the internal test set and 85.7%, 91.5%, and 98.0% for the external test set, respectively. CONCLUSION: A deep learning algorithm detected intracranial aneurysms with a high diagnostic performance which was validated using external data set. KEY POINTS: • A deep learning-based algorithm for the automated diagnosis of intracranial aneurysms demonstrated a high sensitivity, positive predictive value, and specificity. • The high diagnostic performance of the algorithm was validated using external test data set from a different institution with a different scanner. • The algorithm might be robust and effective for general use in real clinical settings.
OBJECTIVES: To develop a deep learning algorithm for automated detection and localization of intracranial aneurysms on time-of-flight MR angiography and evaluate its diagnostic performance. METHODS: In a retrospective and multicenter study, MR images with aneurysms based on radiological reports were extracted. The examinations were randomly divided into two data sets: training set of 468 examinations and internal test set of 120 examinations. Additionally, 50 examinations without aneurysms were randomly selected and added to the internal test set. External test data set consisted of 56 examinations with intracranial aneurysms and 50 examinations without aneurysms, which were extracted based on radiological reports from a different institution. After manual ground truth segmentation of aneurysms, a deep learning algorithm based on 3D ResNet architecture was established with the training set. Its sensitivity, positive predictive value, and specificity were evaluated in the internal and external test sets. RESULTS: MR images included 551 aneurysms (mean diameter, 4.17 ± 2.49 mm) in the training, 147 aneurysms (mean diameter, 3.98 ± 2.11 mm) in the internal test, 63 aneurysms (mean diameter, 3.23 ± 1.69 mm) in the external test sets. The sensitivity, the positive predictive value, and the specificity were 87.1%, 92.8%, and 92.0% for the internal test set and 85.7%, 91.5%, and 98.0% for the external test set, respectively. CONCLUSION: A deep learning algorithm detected intracranial aneurysms with a high diagnostic performance which was validated using external data set. KEY POINTS: • A deep learning-based algorithm for the automated diagnosis of intracranial aneurysms demonstrated a high sensitivity, positive predictive value, and specificity. • The high diagnostic performance of the algorithm was validated using external test data set from a different institution with a different scanner. • The algorithm might be robust and effective for general use in real clinical settings.
Entities:
Keywords:
Artificial intelligence; Deep learning; Intracranial aneurysm; Magnetic resonance angiography
Authors: Vittorio Stumpo; Victor E Staartjes; Giuseppe Esposito; Carlo Serra; Luca Regli; Alessandro Olivi; Carmelo Lucio Sturiale Journal: Acta Neurochir Suppl Date: 2022
Authors: B Sohn; K-Y Park; J Choi; J H Koo; K Han; B Joo; S Y Won; J Cha; H S Choi; S-K Lee Journal: AJNR Am J Neuroradiol Date: 2021-08-12 Impact factor: 4.966
Authors: Bio Joo; Hyun Seok Choi; Sung Soo Ahn; Jihoon Cha; So Yeon Won; Beomseok Sohn; Hwiyoung Kim; Kyunghwa Han; Hwa Pyung Kim; Jong Mun Choi; Sang Min Lee; Tae Gyu Kim; Seung-Koo Lee Journal: Yonsei Med J Date: 2021-11 Impact factor: 2.759
Authors: Jun Hyong Ahn; Heung Cheol Kim; Jong Kook Rhim; Jeong Jin Park; Dick Sigmund; Min Chan Park; Jae Hoon Jeong; Jin Pyeong Jeon Journal: J Pers Med Date: 2021-03-24