查詢結果分析
相關文獻
- 基於腦質造影影像建置腦中風診斷預後輔助系統
- 卷積神經網路技術輔助診斷失智症腦部灌注影像
- 腦中風患者吞嚥功能臨床評估可靠性之探討
- 上矢狀竇栓塞併雙側偏癱:病例報告
- 運動後低血壓反應與血壓控制之探討
- The Effect of Sphenopalatine Postganglionic Neurotomy on the Alteration of Local Cerebral Blood Flow of Normotensive and Hypertensive Rats in Acute Cold Stress
- 以動脈注射血栓溶劑治療急性缺血性腦中風:七例報告
- 成功使用血栓溶解劑治療急性缺血性腦中風:一病例報告暨文獻回顧
- 臺北市機構式長期照護體系之腦中風物理治療服務需求調查
- 糖尿病與腦中風
頁籤選單縮合
題 名 | 基於腦質造影影像建置腦中風診斷預後輔助系統=Constructing a Stroke Diagnosis and Prognosis System Based on the BPN Algorithm Using Tc-99m-ECD SPECT Images |
---|---|
作 者 | 陳瑞仁; 張簡鴻年; 張雁翔; | 書刊名 | Annals of Nuclear Medicine and Molecular Imaging |
卷 期 | 37:1 2024.03[民113.03] |
頁 次 | 頁1-11 |
分類號 | 415.922 |
關鍵詞 | 腦中風; 腦部灌注影像; 遷移學習; 倒傳遞神經網路; 核子醫學; Back-propagation neural network; Cerebral perfusion image; Nuclear medical; Stroke diseases; Transfer learning; |
語 文 | 中文(Chinese) |
DOI | 10.6332/ANMMI.202403_37(1).0001 |
中文摘要 | 目的:人工智慧(artificial intelligence,AI)深度學習之技術,逐漸被應用於不同的醫學影像辨識,多著重於computed tomography(CT)或magnetic resonance imaging(MRI)影像分析上,鮮少有應用於核子醫學影像的研究。SPECT是少數能在早期靈敏反應出腦內異常的檢查工具,除了診斷腦血管疾病,還可做為預後評估的工具,故開發一套腦中風診斷輔助系統為本研究目標。方法:本研究收集高雄長庚紀念醫院2017~2021年,5年內所有Tc-99m ECD SPECT腦部影像,符合ICD-10-Code I60-I69腦血管疾病萃取規則,共收集144例病歷,去除雜訊及瑕疵影像並使用資料擴增技術,避免因資料量小產生過度擬合或無法訓練,並獲取更多新的圖像及增加泛化等問題。利用倒傳遞神經網路(back-propagation neural network,BPN)的演算法對腦中風影像進行訓練,依照腦部血流分布擷取出重要特徵。結果:本研究模型藉由遷移學習與VGG16模型進行比較,影像辨識準確率94.4%提升了1.3%,腦中風敏感性90.3%提升了5.4%,召回率及皮氏分數各為90.3%、94.2%。ROC接收者操作特徵曲線,平均AUC面積為0.89±0.08,故本訓練模型有極佳的鑑別力。結論:基於BPN算法的優勢,本研究建立了一個腦中風診斷輔助系統,以支持腦中風影像的辨識和評估可能出現第二次中風的可能性,該系統還可以協助醫生進行快速診斷,減少錯誤,最後希望所開發出的軟體功能,能移植到輔助醫療診斷系統即時測試,以便連接理論與實務的真實情形。 |
英文摘要 | Background: The technology of deep learning in artificial intelligence (AI) is increasingly applied to medical image recognition. These applications are focused mainly on the analysis of computed tomography (CT) or magnetic resonance imaging (MRI) images and seldom intended to support research of nuclear medical images. Single-photon emission computed tomography (SPECT) is one of the few examination tools that can sensitively reflect abnormalities in the brain at an early stage. In addition to diagnosing cerebrovascular diseases, it can also be used as a tool for prognostic evaluation. Therefore, constructing a stroke image recognition system for diagnosis and prognosis is the goal of this study. Method: We collected all the Tc-99m ECD SPECT brain images from Kaohsiung Chang Gung Memorial Hospital over a period of five years from 2017 to 2021. A total of 144 medical records that met the ICD-10-Code I60-I69 cerebrovascular disease extraction rules were obtained. In the preprocessing of data, noise and defective images were removed. Data augmentation technology was exploited to avoid overfitting and underfitting due to the small amount of data and obtain more new images for higher generalization ability. The back-propagation neural network (BPN) algorithm was adopted to train stroke images and extract important features according to the distribution of blood flows in the brain Result: The proposed model is compared with the VGG16 through transfer training. It delivers an accuracy of 94.4% (1.3% higher) and a sensitivity of 90.3% (5.4% higher). Its recall rate and F-score reach 90.3% and 94.2% respectively. The receiver operating characteristic (ROC) curve and average area under the ROC curve (0.89 ± 0.08) indicate that this model has an excellent discrimination capability. Conclusion: Based on the strengths of the BPN algorithm, we construct a stroke image recognition system to support stroke image recognition, assessment of the possibility of a second stroke, and prognostic evaluation. This system can also assist physicians in performing a rapid diagnosis and reduce errors. It is hoped that the developed software can be ported to real-world medical systems for testing, so as to connect the theory with practical situations. |
本系統中英文摘要資訊取自各篇刊載內容。