Singapore Bioimaging Consortium, Agency for Science, Technology and Research, 30 Biopolis Street, #07-01, Matrix, Singapore 138671.
Med Phys. 2013 Oct;40(10):103502. doi: 10.1118/1.4820539.
Characterization of focal liver lesions with various imaging modalities can be very challenging in the clinical practice and is experience-dependent. The authors' aim is to develop an automatic method to facilitate the characterization of focal liver lesions (FLLs) using multiphase computed tomography (CT) images by radiologists.
A multiphase-image retrieval system is proposed to retrieve a preconstructed database of FLLs with confirmed diagnoses, which can assist radiologists' decision-making in FLL characterization. It first localizes the FLL on multiphase CT scans using a hybrid generative-discriminative FLL detection method and a nonrigid B-spline registration method. Then, it extracts the multiphase density and texture features to numerically represent the FLL. Next, it compares the query FLL with the model FLLs in the database in terms of the feature and measures their similarities using the L1-norm based similarity scores. The model FLLs are ranked by similarities and the top results are finally provided to the users for their evidence studies.
The system was tested on a database of 69 four-phase contrast-enhanced CT scans, consisting of six classes of liver lesions, and evaluated in terms of the precision-recall curve and the Bull's Eye Percentage Score (BEP). It obtained a BEP score of 78%. Compared with any single-phase based representation, the multiphase-based representation increased the BEP scores of the system, from 63%-65% to 78%. In a pilot study, two radiologists performed characterization of FLLs without and with the knowledge of the top five retrieved results. The results were evaluated in terms of the diagnostic accuracy, the receiver operating characteristic (ROC) curve and the mean diagnostic confidence. One radiologist's accuracy improved from 75% to 92%, the area under ROC curves (AUC) from 0.85 to 0.95 (p = 0.081), and the mean diagnostic confidence from 4.6 to 7.3 (p = 0.039). The second radiologist's accuracy did not change, at 75%, with AUC increasing from 0.72 to 0.75 (p = 0.709), and the mean confidence from 4.5 to 4.9 (p = 0.607).
Multiphase CT images can be used in content-based image retrieval for FLL's categorization and result in good performance in comparison with single-phase CT images. The proposed method has the potential to improve the radiologists' diagnostic accuracy and confidence by providing visually similar lesions with confirmed diagnoses for their interpretation of clinical studies.
在临床实践中，利用各种成像方式对肝脏局灶性病变进行特征描述极具挑战性，而且这种描述很大程度上依赖于医生的经验。作者旨在开发一种自动方法，通过多期 CT 图像来辅助放射科医生对肝脏局灶性病变（FLL）进行特征描述。
提出了一种多期图像检索系统，以检索具有明确诊断的 FLL 的预构建数据库，从而辅助放射科医生进行 FLL 特征描述的决策。该系统首先使用混合生成式-判别式 FLL 检测方法和非刚性 B 样条配准方法，在多期 CT 扫描图像上定位 FLL。然后，提取多期密度和纹理特征，以数值方式表示 FLL。接下来，根据特征，比较查询 FLL 与数据库中的模型 FLL，并使用基于 L1 范数的相似度得分来衡量它们之间的相似度。根据相似度对模型 FLL 进行排序，并将前几个结果提供给用户，供其进行证据研究。
该系统在一个由 69 例四期增强 CT 扫描组成的数据库上进行了测试，该数据库包含六种肝脏病变类型，基于精确-召回曲线和“Bull's Eye 百分比评分（BEP）”对其进行了评估。它获得了 78%的 BEP 评分。与任何单期的表示方法相比，多期表示方法提高了系统的 BEP 评分，从 63%到 65%提高到了 78%。在一项试点研究中，两位放射科医生分别在不了解和了解前五个检索结果的情况下对 FLL 进行了特征描述。使用诊断准确性、受试者工作特征（ROC）曲线和平均诊断置信度来评估结果。一位放射科医生的准确性从 75%提高到了 92%，ROC 曲线下面积（AUC）从 0.85 提高到了 0.95（p=0.081），平均诊断置信度从 4.6 提高到了 7.3（p=0.039）。第二位放射科医生的准确性没有变化，仍为 75%，但 AUC 从 0.72 提高到了 0.75（p=0.709），平均置信度从 4.5 提高到了 4.9（p=0.607）。
多期 CT 图像可用于 FLL 的基于内容的图像检索，与单期 CT 图像相比，其表现良好。该方法有可能通过为放射科医生提供具有明确诊断的视觉相似病变，以辅助其对临床研究进行解释，从而提高诊断准确性和信心。
