Diagnosis of non-polypoid neoplasia of the colon with CT colonography

描述（由申请人提供）： 结肠癌是美国男性和女性癌症死亡的第二大原因，如果发现并切除结肠前病变，结肠癌是可以预防的。该项目的长期目标是开发一种基于图像的诊断方法，以促进结肠癌的早期检测。计算机断层结肠成像（CTC），或虚拟结肠镜检查，是一种新兴的替代筛查工具，结肠癌的平均风险患者。基于最近的大规模，多中心临床试验（包括国家CT结肠造影试验）证明的在检测临床显著息肉方面的高患者敏感性和特异性，CTC现在被美国癌症协会，美国多学会工作组和美国放射学会的联合指南列为结直肠癌的可行筛查选择。在Soetikno等人最近报道的美国系列中，很明显，亚洲人和西方人都可能发生非息肉样结直肠瘤形成，其占所有早期结直肠癌的54%，并且往往与原位或粘膜下浸润性癌相关。形态学上平坦的病变具有高的严重病理学比率，这一发现表明需要有效的筛查方法来准确地识别这些病变。CTC作为筛查工具目前的问题是，其检测扁平病变的性能在研究中存在差异，因此仍未确定。拟议项目的短期目标是开发和评估一种计算机辅助扁平病变检测（CAfD）方案，该方案可自动检测高分辨率CTC图像中的扁平病变，并开发和评估一种扁平病变解释系统，以帮助放射科医生快速准确地检测扁平病变。我们假设CAfD方案将产生临床上可接受的平坦病变的高检测性能，并且平坦病变解释系统将提高放射科医生在CTC图像中检测平坦病变的性能。该系统的成功开发将极大地推动基于CT的结肠癌筛查在大规模人群中的临床实施，提高筛查率，促进结肠癌的早期诊断，并最终降低结肠癌的死亡率。

DESCRIPTION (provided by applicant): Colon cancer, the second leading cause of cancer deaths for men and women in the United States, can be prevented if precursor colonic lesions are detected and removed. The long-term goal of the proposed project is to develop an image-based diagnostic method that advances the early detection of colon cancer. Computed tomographic colonography (CTC), or virtual colonoscopy, is an emerging alternative screening tool for colon cancer in average risk patients. Based on the high per-patient sensitivity and specificity in the detection of clinically significant polyps that were demonstrated by the recent large-scale, multi-center clinical trials, including the National CT Colonography Trial, CTC is now listed as a viable screening option for colorectal cancer in the joint guideline from the American Cancer Society, the U.S. Multi-Society Task Force, and the American College of Radiology. In a recent U.S. series reported by Soetikno et al., it became clear that both Asian and Western populations may develop non-polypoidal colorectal neoplasia, which contribute to 54% of all early colorectal cancers and tend to be associated with in situ or submucosal invasive carcinomas. The finding that morphologically flat lesions have high rates of serious pathology suggests that effective screening methods will need to accurately identify these lesions. Current problem with CTC as a screening tool is that its performance for the detection of flat lesions varies across studies and thus remains undetermined. The short-term goal of the proposed project is to develop and evaluate a computer-aided flat-lesion detection (CAfD) scheme that automatically detects flat lesions in high-resolution CTC images, and to develop and evaluate a flat-lesion interpretation system that assists radiologists in detecting flat lesions quickly and accurately. We hypothesize that the CAfD scheme will yield clinically acceptable high detection performance for flat lesions, and that the flat-lesion interpretation system will improve radiologists' performance in the detection of flat lesions in CTC images. Successful development of the proposed flat-lesion interpretation system will substantially advance the clinical implementation of CT-based colon cancer screening in large populations, lead to an increased screening rate, promote the early diagnosis of colon cancer, and ultimately reduce the mortality due to colon cancer.