arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.08699cs.CV
收藏

II-FCN用于黑素瘤检测的皮肤病变分析

II-FCN for skin lesion analysis towards melanoma detection

University of Electronic Science and Technology of China(电子科技大学)

Hongdiao Wen

摘要:

皮肤镜图像检测由于目标的可区分性较弱而一直是一项艰巨的任务。尽管近年来深度卷积神经网络在流行的计算机视觉任务中的性能得到了显著提升,但对于低对比度图像分割问题,仍然存在探索更鲁棒和精确模型的空间。面对ISBI 2017中病变分割的挑战,我们建立了一个基于仅10个可逆起始块的对称恒等起始全卷积网络,每个分块由四个不同层深和核大小的卷积分支组成,提取语义特征,然后提出一个Jaccard指标的近似损失函数来训练我们的为了克服传统卷积方法的不足,我们采用了膨胀卷积和条件随机场方法来校正分割,并引入了多种方法来防止过拟合问题。实验结果表明,我们的模型达到了0.82的jaccard指数,并保持了从一个时期到另一个时期的学习。

英文摘要:

Dermoscopy image detection stays a tough task due to the weak distinguishable property of the object.Although the deep convolution neural network signifigantly boosted the performance on prevelance computer vision tasks in recent years,there remains a room to explore more robust and precise models to the problem of low contrast image segmentation.Towards the challenge of Lesion Segmentation in ISBI 2017,we built a symmetrical identity inception fully convolution network which is based on only 10 reversible inception blocks,every block composed of four convolution branches with combination of different layer depth and kernel size to extract sundry semantic features.Then we proposed an approximate loss function for jaccard index metrics to train our model.To overcome the drawbacks of traditional convolution,we adopted the dilation convolution and conditional random field method to rectify our segmentation.We also introduced multiple ways to prevent the problem of overfitting.The experimental results shows that our model achived jaccard index of 0.82 and kept learning from epoch to epoch.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑