基于卷积神经网络的小细胞型肺癌辅助检测方法

Small Cell Lung Cancer Auxiliary Detection Method Based on Convolution Neural Network

肺癌是世界上患病率并且死亡率最高的疾病之一,而小细胞型肺癌由于密度差最大以及涉及较多的图像因素,是脏器中最容易诊断的癌症。创新性地提出一种新的辅助检测方法,即采取卷积神经网络算法辅助检测小细胞型肺癌,该算法已经在人脸识别、车辆识别和文字判别等领域取得了丰硕的成果。卷积神经网络很好地结合了之前检测算法的优点,又能兼顾准确性,更好地减少误诊率,提高学习效率。此外当有新的学习样本加入,在保持原有学习结果的基础上,只调整神经元的权值就能明显提高诊断率。

Lung cancer is one of the highest mortality in the world, due to its largest density and a lot of image factors, small cell lung cancer is the best to diagnose. This paper introduces a new method-Deep Learning which belongs to machine learning to diagnose small cell lung cancer. Convolution Neural Networks （CNN） has gained a lot of fame in Face recognition, vehicle identification and text discrimination fields. With the mode of Convolution Neural Networks, we can reduce the ratio of misdiagnosis largely. Moreover, if appending new complementing samples, the detection rate can be improved significantly, only adjusting a few adding neurons＇ weights while keeping previous weights unchanging.