Moragheb Mohammad Amin, Badie Ali, Noshad Ali
MSc, Department of Computer Engineering, Faculty of Engineering, Mamasani Higher Education Center, Mamasani, Iran.
MSc, Department of Computer Engineering, Faculty of Engineering, Salman Farsi University of Kazerun, Kazerun, Iran.
J Biomed Phys Eng. 2022 Aug 1;12(4):377-386. doi: 10.31661/jbpe.v0i0.2110-1412. eCollection 2022 Aug.
Pulmonary or benign nodules are classified as nodules with a diameter of 3 cm or less and defined as non-cancerous nodules. The early diagnosis of malignant lung nodules is important for a more reliable prognosis of lung cancer and less invasive chemotherapy and radiotherapy procedures.
This study aimed to introduce an improved hybrid approach for efficient nodule mask generation and false-positive reduction.
In this experimental study, nodule segmentation preprocessing was conducted to prepare the input computed tomography (CT) scans for the U-Net convolutional neural network (CNN) model, and includes the normalization of CT scans and transfer of pixel values corresponding to the radiodensity of Hounsfield Units (HU). A U-Net CNN was developed based on lung CT scans for nodule identification.
The U-net model converged to a dice coefficient of 0.678 with a sensitivity of 75%. Many false positives were considered in every real positive, at 11.1, reduced in the proposed CNN to 2.32 FPs (False Positive) per TP (True Positive).
Based on the disadvantages of the largest nodule, the similarity of extracted features of the current study with those of others was imperative. The improved hybrid approach introduced was useful for other image classification tasks as expected.
肺结节或良性结节是指直径3厘米及以下的结节，被定义为非癌性结节。恶性肺结节的早期诊断对于肺癌更可靠的预后以及侵入性更小的化疗和放疗程序至关重要。
本研究旨在引入一种改进的混合方法，以高效生成结节掩码并减少假阳性。
在本实验研究中，进行了结节分割预处理，为U-Net卷积神经网络（CNN）模型准备输入的计算机断层扫描（CT）图像，包括CT图像的归一化以及对应于亨氏单位（HU）放射密度的像素值转换。基于肺部CT图像开发了一个U-Net CNN用于结节识别。
U-net模型的骰子系数收敛到0.678，灵敏度为75%。每个真实阳性中存在许多假阳性，最初为11.1，在所提出的CNN中降低到每个真阳性（TP）有2.32个假阳性（FP）。
基于最大结节的缺点，当前研究提取特征与其他研究的相似性势在必行。所引入的改进混合方法如预期的那样对其他图像分类任务有用。
