透過您的圖書館登入
IP:3.237.65.102
  • 學位論文

肺部電腦斷層掃描之毛玻璃狀肺結節侵犯性區別診斷:低實質比、深度學習與放射體學方法

Classification of the Invasiveness of Ground Glass Nodule on CT images: low solid ratio, deep learning and radiomics method

指導教授 : 陳中明

摘要


根據衛生福利部於109年國人死因統計結果[1],癌症的死亡率在十大死因中排序第一,而又以氣管、支氣管、肺癌位於癌症中的第一且已蟬聯多年,是一項不可輕忽的疾病,若能及早給予患者相應的治療的話,可以相對提高存活率。較早期的肺部腫瘤在電腦斷層掃描上通常會呈現毛玻璃狀,毛玻璃狀定義即為腫瘤呈現霧狀並且不會遮擋住穿越之血管或是蓋住氣管等組織。另外,於2011年有三個協會:國際肺癌協會(IASLC)、美國胸科協會(ATS)及歐洲呼吸協會(ERS),共同從病理角度針對毛玻璃狀肺腺癌做分類,以他們對人體所造成的威脅程度可以分成三大類,分別為較不具威脅性的pre-invasive lesions,包含非典型腺瘤樣增生(AAH)與原位肺腺癌(AIS),以及另外兩類:微浸潤腺癌(MIA)和浸潤腺癌(IA)[2],而不同分類的肺腺癌所需的開刀方式與存活率也不盡相同,其中AIS/MIA有些醫生的準則會選擇先以追蹤為主,或使用次肺葉切除術(楔狀切除術或是肺節切除術),在術後五年的存活率是接近100%,反觀浸潤腺癌(IA)的存活率則有所降低(依照不同的亞型而有不同的存活率)[3]。所以若能從電腦斷層掃描上將早期毛玻璃狀腫瘤中的原位肺腺癌與微浸潤線癌從浸潤腺癌中分出來可以給予醫生應進行手術還是應先觀察的一個參考,是相當重要的事。 於本論文,將採用實質比小於0.25且小於三公分的毛玻璃狀原位肺腺癌(AIS)、微浸潤線癌(MIA)與浸潤腺癌(IA)當作研究材料,經醫師判斷後其須符合腫瘤實質區域之最大直徑與腫瘤本體之最大徑比值小於0.25,並將AIS與MIA歸類為不具侵犯性的肺腺癌,而IA屬於具侵犯性的肺腺癌。研究目的為利用放射體學與深度學習的方法將具侵犯性的肺腺癌與不具侵犯性的肺腺癌給區分出來。

並列摘要


According to the report from Ministry of the health and welfare in 2020[1], cancer ranked first in the cause of death statistics. Among all cancer cause of death, cancers of trachea, bronchus and lung were placed first for a long time. Apparently, it’s important to have an early detection in order to lead to cure and enhance the survival rate since lung cancer is a force to be reckoned with. Early-stage lung adenocarcinoma nodules often manifest as ground-glass opacity (GGO) which is defined as lesions showing hazy, increased attenuation that does not obscure underlying bronchial structures or pulmonary vessels. In 2011, the International Association for the Study of Lung Cancer (IASLC), the American Thoracic Society(ATS), and the European Respiratory Society (ERS) classified lung adenocarcinomas manifest as GGO into three groups of type:(1)pre-invasive lesions, including atypical adenomatous hyperplasias (AAH) and adenocarcinoma on situ (AIS), (2)minimally invasive adenocarcinoma (MIA), and(3)invasive adenocarcinoma (IA)[2]. The lung adenocarcinomas from each groups are suggested for different therapeutic strategy. AIS and MIA can be tracked at first or treated with sublobar resection (wedge or segmental resection) with a 100% or nearly 100% of 5-year survival-rate[3]. On the other hand, the invasive adenocarcinoma causes a reduction in survival-rate (Which depends on the subtype of the adenocarcinoma). As stated above, classifying AIS and MIA from IA which manifest as GGO on computed tomography is crucial that either gives the doctors an option to track first or to perform the operation. In this study, the inclusion criteria are the maximum diameter is less than 3 cm and the solid ratio of the ground-glass nodules must be less than 0.25 which judged by the doctor, indicates the ratio of max diameter of the solid lesion to max diameter of the whole lesion need to be less than 0.25. Furthermore, AIS and MIA are classified as non-invasive adenocarcinoma while IAs are invasive adenocarcinoma. The purpose of the study is to use radiomics and deep learning to build up classification model so as to make a precise precision to the classification problem.

參考文獻


[1] 衛生福利部109年國人死因統計結果
[2] Travis, W. D., Brambilla, E., Noguchi, M., Nicholson, A. G., Geisinger, K. R., Yatabe, Y., Beer, D. G., Powell, C. A., Riely, G. J., Van Schil, P. E. (2011). International association for the study of lung cancer/american thoracic society/european respiratory society international multidisciplinary classification of lung adenocarcinoma. Journal of Thoracic Oncology, 6(2), 244-285.
[3] Liu, S., Wang, R., Zhang, Y., Li, Y., Cheng, C., Pan, Y., Xiang, J., Zhang, Y., Chen, H., Sun, Y. (2016). Precise diagnosis of intraoperative frozen section is an effective method to guide resection strategy for peripheral small-sized lung adenocarcinoma. Journal of clinical oncology, 34(4), 307-313.
[4] Nesbitt, J. C., Putnam Jr, J. B., Walsh, G. L., Roth, J. A., Mountain, C. F. (1995). Survival in early-stage non-small cell lung cancer. The Annals of thoracic surgery, 60(2), 466-472.
[5] Jemal, A., Siegel, R., Xu, J., Ward, E. (2010). Cancer statistics, 2010. CA: a cancer journal for clinicians, 60(5), 277-300.

延伸閱讀