臺灣博碩士論文加值系統

顱內出血（intracranial hemorrhage; ICH）是腦血管疾病的一種，腦血管因高血壓等慢性病變，突發血管破裂使血液滲漏至大腦內。約三分之一的病人在出血早期會有神經症狀惡化的現象，其中約有半數的所有倖存者因此失去功能性，需長期照護及復健治療。然而，ICH的患者是否需手術以及手術的時機尚未有明確的定論。手術的主要目標是減少腦內血塊所產生的併發症。臨床上以ABC/2公式來計算血塊體積，但不精確且不適用於所有類型的出血。

本實驗以建構自動化影像切割模式，目的是希望藉此精確計算出血體積也減少了手動圈選的時間。另一目標則利用資料探勘建立腦出血預後的預測模式。實驗結果顯示，半自動切割模式以規則性出血未破裂至腦室有較高的準確性，而建立預測預後模式則以Random Forest為最佳分類器，3個月與6個月預後曲線下面積為0.89~0.901，皆達到最佳鑑別力。

Intracranial hemorrhage (ICH) is a subtype of cerebrovascular diseases, defined as rupture of a intracranial vessel, resulting in blood leakage into brain parenchyma. Approximately, one third of ICH patients have the early deterioration of neurological function after ICH. Accordingly, about half of survivors are likely to be functionally impaired and need long-term care and physiotherapy. However, neither the absolute indications nor the most optimal time point for surgery are determined yet. The major goal of the surgery is to reduce the potential complications of blood clots in brain. In clinical research, the formula ABC/2 is most commonly used to measure the volume of the hematoma; however, the formula less accurate and is not applicable to all types of hematomas.

In this study, we aimed to construct automatic segmentation technique model to calculate the hematoma size more accurately and also to reduce the time needed in manual process. Furthermore, we utilized data mining to construct the prognosis model of cerebral hemorrhage. The results showed that the semi-automatic segmentation technique model had higher accuracy to measure the ellipsoid-shaped hematoma and non-intraventricular hemorrhage. The Random Forest had the best discriminating power with an AUC of 0.89~0.90，the test model provided the best predictive performance for functional outcome at 3 and 6 months.

第一章、緒論 1
1.1研究背景 1
1.2研究動機 3
1.3研究目的 5
1.4預期之成果及貢獻 5
第二章、文獻探討 6
2.1 原發性腦出血的相關因子 6
2.2原發性腦出血的部位影響 8
2.3原發性腦出血體積的探討 8
2.4 原發性腦出血的預後 10
2.5原發性腦中風之相關研究 14
第三章、研究方法 19
3.1影像資料來源 19
3.2影像資料前處理 19
3.3影像分析處理 20
3.3.1臨床測量血腫體積ABC/2 20
3.3.2手動圈選 22
3.3.3自動切割 23
3.4研究變項及操作型定義 24
3.5 機器學習 29
3.5.1資料前處理 29
3.5.2自動weka(Auto-weka) 30
3.6研究工具與效能評估 30
第四章、結果與討論 32
4.1 自動切割影像結果 32
4.2變項重要性排序 35
4.3分類器結果 44
第五章、結論 45
5.1研究結論 45
5.2與過去的研究比較 46
5.3未來研究方向與建議 46
5.4研究限制 47
5.5主要貢獻 47
參考文獻 48

台灣腦中風學會. (民 97). Taiwan Guidelines for the Management of Stroke 2008. 台灣腦中風學會.
Retrieved from http://www.stroke.org.tw/guideline/guideline_1.asp
洪晟翔(民 101). 基於正交變動動差特徵及K-means 分群演算法之多重物件追蹤技術.國立屏東教育大學資訊科學系碩士論文，未出版，屏東市。Retrieved from http://140.127.82.166/retrieve/12622/17.pdf
梁蕙雯. (民 98). 腦中風之障礙與失能評估量表簡介. 台北市醫師公會會刊, 20–23.
Amini, L., Azarpazhouh, R., Farzadfar, M. T., Mousavi, S. A., Jazaieri, F., Khorvash, F., …Toghianfar, N. (2013). Prediction and control of stroke by data mining. International Journal of Preventive Medicine, 4(Suppl 2), S245-9.
Andersen, K. K., Olsen, T. S., Dehlendorff, C., &Kammersgaard, L. P. (2009). Hemorrhagic and ischemic strokes compared: Stroke severity, mortality, and risk factors. Stroke, 40(6), 2068–2072.
Ariesen, M. J., Claus, S. P., Rinkel, G. J. E., &Algra, A. (2003). Risk factors for intracerebral hemorrhage in the general population: A systematic review. Stroke, 34(8), 2060–2065.
Arslan, A. K., Colak, C., &Sarihan, M. E. (2016). Different medical data mining approaches based prediction of ischemic stroke. Computer Methods and Programs in Biomedicine, 130, 87–92.
Asadi, H., Dowling, R., Yan, B., &Mitchell, P. (2014). Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy. PLoS ONE, 9(2), 14–19.
Baltes, P. B., &Smith, J. (2003). New frontiers in the future of aging: From successful aging of the young old to the dilemmas of the fourth age. Gerontology, 49(2), 123–135.
Boulanger, M., Poon, M. T. C., Wild, S. H., &Al-Shahi Salman, R. (2016). Association between diabetes mellitus and the occurrence and outcome of intracerebral hemorrhage. Neurology, 87(9), 870–8.
Carcel, C., Sato, S., &Anderson, C. S. (2016). Blood Pressure Management in Intracranial Hemorrhage: Current Challenges and Opportunities. Current Treatment Options in Cardiovascular Medicine, 18(4), 1–11.
Cheng, B., Forkert, N. D., Zavaglia, M., Hilgetag, C. C., Golsari, A., Siemonsen, S., …Thomalla, G. (2014). Influence of stroke infarct location on functional outcome measured by the modified rankin scale. Stroke, 45(6), 1695–1702.
Choo, Y. S., Chung, J., Joo, J.-Y., Kim, Y. B., &Hong, C.-K. (2016). Borderline basal ganglia hemorrhage volume: patient selection for good clinical outcome after stereotactic catheter drainage. Journal of Neurosurgery, 125(November), 1–7.
Colak,C.,Karaman,E.,&Turtay,M. G.(2015).Application of knowledge discovery process on the prediction of stroke. Computer Methods and Programs in Biomedicine , 119(3), 181 - 185
Deogaonkar, A., DeGeorgia, M., Bae, C., Abou-Chebl, A., &Andrefsky, J. (2005). Fever is associated with third ventricular shift after intracerebral hemorrhage: pathophysiologic implications. Neurology India, 53(2), 202-6-7.
Divani, A. A., Majidi, S., Luo, X., Souslian, F. G., Zhang, J., Abosch, A., &Tummala, R. P. (2011). The ABCs of accurate volumetric measurement of cerebral hematoma. Stroke, 42(6), 1569–1574.
Easton, J. F., Stephens, C. R., &Angelova, M. (2014). Risk factors and prediction of very short term versus short/intermediate term post-stroke mortality: A data mining approach. Computers in Biology and Medicine, 54, 199–210.
Flaherty, M. L., Tao, H., Haverbusch, M., Sekar, P., Kleindorfer, D., Kissela, B., …Woo, D. (2008). Warfarin use leads to larger intracerebral hematomas. Neurology, 71(14), 1084–1089.
Hemphill, J. C., Greenberg, S. M., Anderson, C. S., Becker, K., Bendok, B. R., Cushman, M., …Woo, D. (2015). Guidelines for the Management of Spontaneous Intracerebral Hemorrhage: A Guideline for Healthcare Professionals from the American Heart Association/American Stroke Association. Stroke (Vol. 46). James, P. A., Oparil, S., Carter, B. L., Cushman, W. C., Dennison-Himmelfarb, C., Handler, J., …Ortiz, E. (2014). 2014 Evidence-Based Guideline for the Management of High Blood Pressure in Adults. Jama, 311(5), 1–14. Kase, C. S., Shoamanesh, A., Greenberg, S. M., &Caplan, L. R. (2016). Intracerebral Hemorrhage. In Stroke (Sixth Edit, p. 466–515.e12). Elsevier.
Khan, N. A., Quan, H., Hill, M. D. M., Pilote, L., McAlister, F. A., Palepu, A., …Anderson, C. (2013). Risk factors, quality of care and prognosis in South Asian, East Asian and White patients with stroke. BMC Neurology, 13(1), 74.
Kothari, R. U., Brott, T., Broderick, J. P., Barsan, W. G., Sauerbeck, L. R., Zuccarello, M., &Khoury, J. (1996). The ABCs of measuring intracerebral hemorrhage volumes. Stroke, 27(8), 1304–1305.
Leppälä, J. M., Virtamo, J., Fogelholm, R., Albanes, D., Olli, P., &Pressure, B. (2010). Different Risk Factors for Different Stroke Subtypes, 41(Mannerheimintie 172).
Lewington, S., Clarke, R., Qizilbash, N., Peto, R., &Collins, R. (2002). Age-specific relevance of usual blood pressure to vascular mortality: A meta-analysis of individual data for one million adults in 61 prospective studies. Lancet, 360(9349), 1903–1913.
Liu, H., Zen, Y., Li, J., Wang, X., Li, H., Xu, J., &You, C. (2014). Optimal treatment determination on the basis of haematoma volume and intra-cerebral haemorrhage score in patients with hypertensive putaminal haemorrhages: a retrospective analysis of 310 patients. BMC Neurology, 14(1), 141.
Lu,H.Y., Li,T.C., Tu,Y.K., Tsai,J.C.,Lai,H.S.,&Kuo,L.T.(2015).Traumatic brain injury using repeated measurements of glasgow coma scale and data mining methods.Journal of Medical Systems, 39(2), 14
Murthy, S. B., Moradiya, Y., Dawson, J., Lees, K. R., Hanley, D. F., &Ziai, W. C. (2015). Perihematomal Edema and Functional Outcomes in Intracerebral Hemorrhage: Influence of Hematoma Volume and Location. Stroke, 46(11), 3088–3092.
Nag, C., Das, K., Ghosh, M., &Khandakar, M. R. (2012). Prediction of clinical outcome in acute hemorrhagic stroke from a single CT scan on admission. North American Journal of Medical Sciences, 4(10), 463–467.
O’Donnell, M. J., Denis, X., Liu, L., Zhang, H., Chin, S. L., Rao-Melacini, P., …Yusuf, S. (2010). Risk factors for ischaemic and intracerebral haemorrhagic stroke in 22 countries (the INTERSTROKE study): A case-control study. The Lancet, 376(9735), 112–123.
Quinn, T. J., Dawson, J., Walters, M. R., &Lees, K. R. (2009). Functional outcome measures in contemporary stroke trials. International Journal of Stroke, 4(3), 200–205.
Roquer, J., Rodríguez-Campello, A., Jiménez-Conde, J., Cuadrado-Godia, E., Giralt-Steinhauer, E., Vivanco Hidalgo, R. M., …Ois, A. (2016). Sex-related differences in primary intracerebral hemorrhage. Neurology, 87(3), 257–262.
Rosand, J., Eckman, M. H., Knudsen, K. A., Singer, D. E., &Greenberg, S. M. (2004). The effect of warfarin and intensity of anticoagulation on outcome of intracerebral hemorrhage. Archives of Internal Medicine, 164(8), 880–4.
Samarasekera, N., Fonville, A., Lerpiniere, C., Farrall, A. J., Wardlaw, J. M., White, P. M., …Todd, I. (2015). Influence of intracerebral hemorrhage location on incidence, characteristics, and outcome: Population-based study. Stroke, 46(2), 361–368.
Strotzer, M. (2009). One century of brain mapping using Brodmann areas. Clinical Neuroradiology, 19(3), 179–186.
Sulter, G., Steen, C., &Jacques De Keyser. (1999). Use of the Barthel Index and Modified Rankin Scale in Acute Stroke Trials. Stroke, 30(8), 1538–1541.
The Emerging Risk Factors Collaboration. (2010). Diabetes mellitus, fasting blood glucose concentration, and risk of vascular disease: a collaborative meta-analysis of 102 prospective studies. The Lancet, 375(9733), 2215–2222.
VanAsch, C. J., Luitse, M. J., Rinkel, G. J., van derTweel, I., Algra, A., &Klijn, C. J. (2010). Incidence, case fatality, and functional outcome of intracerebral haemorrhage over time, according to age, sex, and ethnic origin: a systematic review and meta-analysis. The Lancet Neurology, 9(2), 167–176.
Zia, E., Hedblad, B., Pessah-Rasmussen, H., Berglund, G., Janzon, L., &Engström, G. (2007). Blood pressure in relation to the incidence of cerebral infarction and intracerebral hemorrhage. Hypertensive hemorrhage: debated nomenclature is still relevant. Stroke, 38(10), 2681–5.