Panic Jovana, Defeudis Arianna, Mazzetti Simone, Rosati Samanta, Giannetto Giuliana, Vassallo Lorenzo, Regge Daniele, Balestra Gabriella, Giannini Valentina
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:1675-1678. doi: 10.1109/EMBC44109.2020.9175804.
The aim of the study is to present a new Convolutional Neural Network (CNN) based system for the automatic segmentation of the colorectal cancer. The algorithm implemented consists of several steps: a pre-processing to normalize and highlights the tumoral area, the classification based on CNNs, and a post-processing aimed at reducing false positive elements. The classification is performed using three CNNs: each of them classifies the same regions of interest acquired from three different MR sequences. The final segmentation mask is obtained by a majority voting. Performances were evaluated using a semi-automatic segmentation revised by an experienced radiologist as reference standard. The system obtained Dice Similarity Coefficient (DSC) of 0.60, Precision (Pr) of 0.76 and Recall (Re) of 0.55 on the testing set. After applying the leave-one-out validation, we obtained a median DSC=0.58, Pr=0.74, Re=0.54. The promising results obtained by this system, if validated on a larger dataset, could strongly improve personalized medicine.
本研究的目的是提出一种基于卷积神经网络（CNN）的用于结直肠癌自动分割的新系统。所实施的算法包括几个步骤：进行预处理以归一化并突出肿瘤区域，基于卷积神经网络进行分类，以及进行旨在减少假阳性元素的后处理。分类使用三个卷积神经网络进行：每个网络对从三个不同的磁共振序列获取的相同感兴趣区域进行分类。最终的分割掩码通过多数投票获得。使用由经验丰富的放射科医生修订的半自动分割作为参考标准来评估性能。该系统在测试集上获得的骰子相似系数（DSC）为0.60，精度（Pr）为0.76，召回率（Re）为0.55。应用留一法验证后，我们获得的中位数DSC = 0.58，Pr = 0.74，Re = 0.54。如果在更大的数据集上得到验证，该系统所取得的有前景的结果可能会极大地改善个性化医疗。
