Department of Gastrointestinal Oncology, Osaka International Cancer Institute (formerly Osaka Medical Center for Cancer and Cardiovascular Diseases), Osaka, Japan.
Department of Internal Medicine, National Taiwan University Hospital and College of Medicine, National Taiwan University, Taipei, Taiwan.
Gastrointest Endosc. 2018 May;87(5):1339-1344. doi: 10.1016/j.gie.2017.11.029. Epub 2017 Dec 7.
Magnifying narrow-band imaging (M-NBI) is important in the diagnosis of early gastric cancers (EGCs) but requires expertise to master. We developed a computer-aided diagnosis (CADx) system to assist endoscopists in identifying and delineating EGCs.
We retrospectively collected and randomly selected 66 EGC M-NBI images and 60 non-cancer M-NBI images into a training set and 61 EGC M-NBI images and 20 non-cancer M-NBI images into a test set. After preprocessing and partition, we determined 8 gray-level co-occurrence matrix (GLCM) features for each partitioned 40 × 40 pixel block and calculated a coefficient of variation of 8 GLCM feature vectors. We then trained a support vector machine (SVM) based on variation vectors from the training set and examined in the test set. Furthermore, we collected 2 determined P and Q GLCM feature vectors from cancerous image blocks containing irregular microvessels from the training set, and we trained another SVM (SVM) to delineate cancerous blocks, which were compared with expert-delineated areas for area concordance.
The diagnostic performance revealed accuracy of 96.3%, precision (positive predictive value [PPV]) of 98.3%, recall (sensitivity) of 96.7%, and specificity of 95%, at a rate of 0.41 ± 0.01 seconds per image. The performance of area concordance, on a block basis, demonstrated accuracy of 73.8% ± 10.9%, precision (PPV) of 75.3% ± 20.9%, recall (sensitivity) of 65.5% ± 19.9%, and specificity of 80.8% ± 17.1%, at a rate of 0.49 ± 0.04 seconds per image.
This pilot study demonstrates that our CADx system has great potential in real-time diagnosis and delineation of EGCs in M-NBI images.
放大窄带成像（M-NBI）在早期胃癌（EGC）的诊断中很重要，但需要专业知识才能掌握。我们开发了一种计算机辅助诊断（CADx）系统，以协助内镜医师识别和描绘 EGC。
我们回顾性地收集并随机选择了 66 例 EGC M-NBI 图像和 60 例非癌 M-NBI 图像作为训练集，以及 61 例 EGC M-NBI 图像和 20 例非癌 M-NBI 图像作为测试集。经过预处理和分区，我们为每个分区的 40×40 像素块确定了 8 个灰度共生矩阵（GLCM）特征，并计算了 8 个 GLCM 特征向量的变异系数。然后，我们基于训练集中的变异向量训练了一个支持向量机（SVM），并在测试集中进行了检查。此外，我们从训练集中包含不规则微血管的癌性图像块中收集了 2 个确定的 P 和 Q GLCM 特征向量，并训练了另一个 SVM（SVM）来描绘癌性块，然后与专家描绘的区域进行面积一致性比较。
诊断性能显示，在 0.41±0.01 秒/张的速度下，准确率为 96.3%，阳性预测值（PPV）为 98.3%，召回率（敏感性）为 96.7%，特异性为 95%。在基于块的面积一致性方面，准确率为 73.8%±10.9%，PPV 为 75.3%±20.9%，召回率（敏感性）为 65.5%±19.9%，特异性为 80.8%±17.1%，速度为 0.49±0.04 秒/张。
这项初步研究表明，我们的 CADx 系统在实时诊断和描绘 M-NBI 图像中的 EGC 方面具有很大的潜力。
