結合髖關節X光影像特徵萃取及機器學習建構骨質疏鬆之預測模式

Combination Hip X-ray Image Features Extraction and Machine Learning Predictive Osteopenia and Osteoporosis

洪詩凱(Shih-Kai Hung)

指導教授 ： 許巍嚴 ； 胡雅涵

國立中正大學/管理學院/資訊管理系醫療資訊管理研究所/碩士(2015年)

摘要

雙能量X光吸收儀為目前診斷骨質疏鬆症的標準工具，但考量不同臨床需求，各種不同的檢查方法都被嘗試做為診斷的參考依據，例如理學檢查、X光攝影、定量電腦斷層攝影掃描、定量超音波、周邊骨密度測量儀、骨生化代謝指標等，在醫療資源有限的情況下，臨床醫師通常會先評估病患臨床危險因子或初篩檢查數據，針對危險性高的族群再以雙能量X光吸收儀進一步確診。本研究使用骨質疏鬆症的重要臨床危險因子，並結合影像萃取髖關節股骨頸影像特徵，嘗試使用機器學習技術找出具有代表性的數值來幫助分類，進而發展骨質疏鬆初步篩檢的預測模型。
本研究使用X光數位影像並採用回溯性方式收集50歲以上男性及停經女性的髖關節X光影像，並依照世界衛生組織所訂定的骨質疏鬆症診斷標準，依T値分為正常與具骨鬆風險兩類。通過圖像形態特徵萃取的方法，直接計算X光片上的骨小梁型態，將所得參數結合骨鬆重要危險因子，並應用類神經網路、支援向量機以及邏輯斯迴歸的分類技術，透過人工智慧的演算來建構骨質疏鬆症之預測模式，並與雙能量X光吸收儀的結果進行比較。本研究結果以類神經網路ANN為最佳分類器，其中停經婦女正確率為86.20%、敏感性為84.71%、特異性為87.66%、ROC為0.929；男性50歲以上正確率為85.82%、敏感性為81.64%、特異性為90.02%、ROC為0.953。本研究提供另一種有別於以往的方法作為未來臨床醫師評估骨質疏鬆之初步篩檢的參考，協助找潛在具骨鬆風險之患者，必要時再轉介雙能量X光吸收儀以確立診斷。

關鍵字

機器學習 ； 骨質疏鬆症 ； 雙能量X光吸收儀 ； 特徵萃取

並列摘要

Dual energy X-ray absorptiometry (DXA) is typically used to diagnose osteoporosis. To meet different clinical demands, there are many distinct means used for predicting osteoporosis. These methods include physical examination, X-ray, quantitative computed tomography (QCT), quantitative ultrasound (QUS), peripheral dual-energy X-ray absorptiometry (pDXA) and bone biochemical metabolite markers. Due to limited medical resources, clinical risk factors (CRFs) and initial screening results are usually assessed by clinicians for the very beginning. For patients with high risk of osteoporosis, a further diagnosis using DXA will be made. In order to develop a prediction model for initial screening of osteoporosis, we used CRFs and features extraction of femoral neck in combination with machine learning to find the most representative factors, which can help for further classification.
We retrospectively collected the hip X-ray from male individuals with ages over 50 year’s old and female individuals with postmenopausal women, respectively. According to osteoporosis diagnostic criteria established by World Health Organization, T-score was divided into two cohorts. Combination hip X-ray image features extraction and machine learning predictive osteopenia and osteoporosis. By using artificial neural network (ANN), support vector machine (SVM) and logistic regression (LR), these scores along with important risk factors of osteoporosis were analyzed by machine learning algorithm to construct a prediction model for osteoporosis. These prediction results were compared with the results of DXA. The results show that the best prediction model is artificial neural network (ANN).
Regarding the prediction model for postmenopausal women, the accuracy, sensitivity, specificity, and ROC were 86.20%, 84.71%, 87.66% and 0.929, respectively. Regarding the prediction model for the men ages over 50 years old, the accuracy, sensitivity, specificity, and ROC were 85.82%, 81.64%, 90.02% and 0.953, respectively. Our method provides an alternative of initial prognosis for osteoporosis, especially for asymptomatic patients and those with high fracture risk.

並列關鍵字

machine learning ； Osteoporosis ； Dual energy X-ray absorptiometry ； features extraction

參考文獻

吳文生, 顏智培, 蔡燿隆, 黃佰璋, & 周淑芬. (2011). 超音波檢查與亞太骨質疏鬆風險評估工具OSTA之比較研究－以南台灣某區域敎學醫院體檢民眾. 嘉南學報（科技類）(37), 53-60.

李欣岱, 蘇千田, & 林茂榮. (2008). 骨質疏鬆症性骨折之預防篩檢. 台灣老年醫學暨老年學雜誌, 3(2), 64-77.

李俊秀. (2012). 骨質密度檢測值與相關危險因子預測骨質疏鬆症發生率. 臺灣大學.

李燕鳴, 曾慶孝, & 劉淑馨. (2009). 預測中老年期停經婦女低骨質密度的危險因素. 台灣老年醫學暨老年學雜誌, 4(1), 39-50.

范光中, & 許永河. (2010). 台灣人口高齡化的社經衝擊. 台灣老年醫學暨老年學雜誌, 5(3), 149-168.