바로가기  >

Abstract
Purpose: Basal/acetazolamide brain perfusion single-photon emission computed tomography (SPECT) has been used to evaluate functional hemodynamics in patients with carotid artery stenosis. We aimed to develop a deep learning model as a support system for interpreting brain perfusion SPECT leveraging unstructured text reports.

Methods: In total, 7345 basal/acetazolamide brain perfusion SPECT images and their text reports were retrospectively collected. A long short-term memory (LSTM) network was trained using 500 randomly selected text reports to predict manually labeled structured information, including abnormalities of basal perfusion and vascular reserve for each vascular territory. Using this trained LSTM model, we extracted structured information from the remaining 6845 text reports to develop a deep learning model for interpreting SPECT images. The model was based on a 3D convolutional neural network (CNN), and the performance was tested on the other 500 cases by measuring the area under the receiver-operating characteristic curve (AUC). We then applied the model to patients who underwent revascularization (n = 33) to compare the estimated output of the CNN model for pre- and post-revascularization SPECT and clinical outcomes.

Results: The AUC of the LSTM model for extracting structured labels was 1.00 for basal perfusion and 0.99 for vascular reserve for all 9 brain regions. The AUC of the CNN model designed to identify abnormal perfusion was 0.83 for basal perfusion and 0.89 for vascular reserve. The output of the CNN model was significantly improved according to the revascularization in the target vascular territory, and its changes in brain territories were concordant with clinical outcomes.

Conclusion: We developed a deep learning model to support the interpretation of brain perfusion SPECT by converting unstructured text reports into structured labels. This model can be used as a support system not only to identify perfusion abnormalities but also to provide quantitative scores of abnormalities, particularly for patients who require revascularization.

그림 1> 뇌혈류 SPECT 딥러닝 모델의 전체 모식도 (a) 구조화되지 않은 영상 판독문으로부터 뇌혈류 상태에 대한 구조화된 정보를 학습 및 추출하기 위한 LSTM 모델. (b) LSTM 모델을 이용하여 판독문으로부터 영상에 대한 구조화된 레이블을 추출하고, (c) SPECT 영상에서 영역별 기저 뇌혈류 및 혈류 예비능 상태에 대한 비정상 스코어를 학습 및 예측하기 위한 3D CNN 모델.

그림 2> 뇌혈관 재개통술 전-후 표적-비표적 뇌혈관 영역에 대한 임상적 결과와 딥러닝 기반 뇌혈류 SPECT 영상 비정상 스코어가 일치하는 경향을 보임 (a: 기저 뇌혈류, b: 혈류 예비능, c: heatmap).

Affiliations
1 Department of Nuclear Medicine, Seoul National University Hospital, 28 Yongon-Dong, Jongno-Gu, Seoul, 110-744, South Korea.
2 Department of Molecular Medicine and Biopharmaceutical Sciences, Graduate School of Convergence Science and Technology, and College of Medicine or College of Pharmacy, Seoul National University, Seoul, Republic of Korea.
3 Department of Nuclear Medicine, Seoul National University Hospital, 28 Yongon-Dong, Jongno-Gu, Seoul, 110-744, South Korea. chy1000@snu.ac.kr.
4 Department of Nuclear Medicine, Seoul National University Hospital, 28 Yongon-Dong, Jongno-Gu, Seoul, 110-744, South Korea. dsl@plaza.snu.ac.kr.
5 Department of Molecular Medicine and Biopharmaceutical Sciences, Graduate School of Convergence Science and Technology, and College of Medicine or College of Pharmacy, Seoul National University, Seoul, Republic of Korea. dsl@plaza.snu.ac.kr.