Department of Electronics and Communication Engineering (ECE), Kamaraj college of engineering and technology (Autonomous), Virudhunagar, India.
BMC Med Inform Decis Mak. 2020 Oct 31;20(1):282. doi: 10.1186/s12911-020-01220-z.
A proposed computer aided detection (CAD) scheme faces major issues during subtle nodule recognition. However, radiologists have not noticed subtle nodules in beginning stage of lung cancer while a proposed CAD scheme recognizes non subtle nodules using x-ray images.
Such an issue has been resolved by creating MANN (Massive Artificial Neural Network) based soft tissue technique from the lung segmented x-ray image. A soft tissue image recognizes nodule candidate for feature extortion and classification. X-ray images are downloaded using Japanese society of radiological technology (JSRT) image set. This image set includes 233 images (140 nodule x-ray images and 93 normal x-ray images). A mean size for a nodule is 17.8 mm and it is validated with computed tomography (CT) image. Thirty percent (42/140) abnormal represents subtle nodules and it is split into five stages (tremendously subtle, very subtle, subtle, observable, relatively observable) by radiologists.
A proposed CAD scheme without soft tissue technique attained 66.42% (93/140) sensitivity and 66.76% accuracy having 2.5 false positives per image. Utilizing soft tissue technique, many nodules superimposed by ribs as well as clavicles have identified (sensitivity is 72.85% (102/140) and accuracy is 72.96% at one false positive rate).
In particular, a proposed CAD system determine sensitivity and accuracy in support of subtle nodules (sensitivity is 14/42 = 33.33% and accuracy is 33.66%) is statistically higher than CAD (sensitivity is 13/42 = 30.95% and accuracy is 30.97%) scheme without soft tissue technique. A proposed CAD scheme attained tremendously minimum false positive rate and it is a promising technique in support of cancerous recognition due to improved sensitivity and specificity.
在识别细微结节时，一种提出的计算机辅助检测 (CAD) 方案面临重大问题。然而，放射科医生在肺癌早期阶段并未注意到细微结节，而 CAD 方案使用 X 射线图像识别非细微结节。
通过从肺部分割的 X 射线图像中创建基于大规模人工神经网络 (MANN) 的软组织技术，解决了这一问题。软组织图像识别结节候选特征提取和分类。使用日本放射技术学会 (JSRT) 图像集下载 X 射线图像。该图像集包括 233 张图像（140 张结节 X 射线图像和 93 张正常 X 射线图像）。结节的平均大小为 17.8mm，并通过计算机断层扫描 (CT) 图像进行验证。30%（42/140）异常代表细微结节，由放射科医生分为五个阶段（非常细微、非常细微、细微、可观察、相对可观察）。
没有软组织技术的 CAD 方案的敏感性为 66.42%（93/140），准确性为 66.76%，每张图像有 2.5 个假阳性。利用软组织技术，已经识别出许多肋骨和锁骨叠加的结节（敏感性为 72.85%（102/140），假阳性率为 1 时准确性为 72.96%）。
特别是，提出的 CAD 系统支持细微结节的敏感性和准确性（敏感性为 14/42=33.33%，准确性为 33.66%）在统计学上高于没有软组织技术的 CAD（敏感性为 13/42=30.95%，准确性为 30.97%）方案。提出的 CAD 方案实现了极低的假阳性率，由于敏感性和特异性的提高，它是一种支持癌症识别的有前途的技术。
