不透明液体疫苗的自动检测
The Automated Inspection of Opaque Liquid Vaccines
摘要:
在制药工业中,含有悬浮液的不透明疫苗的筛选目前是由受过训练的人类视觉检查员进行的人工任务。我们表明,深度学习可以用来有效地自动化这一过程。需要移动的对比度来区分异常与其他粒子,反射和灰尘停留在一个小瓶的表面。我们训练3D-ConvNets来预测包含异常的20帧视频样本的可能性。我们的未增强数据集由手工标记的样本组成,使用制药公司HAL Allergy Group提供的小瓶记录。我们训练了10个随机初始化的3D-ConvNets来提供基准,观察到阳性样本(包含异常)和阴性样本(无异常)的平均AUROC分数分别为0.94和0.93。使用帧完成生成对抗网络,我们:(i)引入一种计算显着图的算法,我们使用它来验证3D-ConvNets确实识别异常;(ii)提出一种新的自训练方法,使用显着图来确定多个网络是否同意异常的位置。我们的自我训练方法允许我们通过标记217,888个额外的样本来扩展我们的数据集。使用我们的增强数据集训练的3D-ConvNets改进了我们仅在未增强数据集上进行训练时得到的结果。
英文摘要:
In the pharmaceutical industry the screening of opaque vaccines containing suspensions is currently a manual task carried out by trained human visual inspectors. We show that deep learning can be used to effectively automate this process. A moving contrast is required to distinguish anomalies from other particles, reflections and dust resting on a vial's surface. We train 3D-ConvNets to predict the likelihood of 20-frame video samples containing anomalies. Our unaugmented dataset consists of hand-labelled samples, recorded using vials provided by the HAL Allergy Group, a pharmaceutical company. We trained ten randomly initialized 3D-ConvNets to provide a benchmark, observing mean AUROC scores of 0.94 and 0.93 for positive samples (containing anomalies) and negative (anomaly-free) samples, respectively. Using Frame-Completion Generative Adversarial Networks we: (i) introduce an algorithm for computing saliency maps, which we use to verify that the 3D-ConvNets are indeed identifying anomalies; (ii) propose a novel self-training approach using the saliency maps to determine if multiple networks agree on the location of anomalies. Our self-training approach allows us to augment our data set by labelling 217,888 additional samples. 3D-ConvNets trained with our augmented dataset improve on the results we get when we train only on the unaugmented dataset.
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。