Wieslander H, Forslid G, Bengtsson E, Wählby C, Hirsch J, Runow Stark C, Kecheril Sadanandan S
The IEEE International Conference on Computer Vision (ICCV), 2017 - (-) - [2017-11-01; online 2017-09-13]
Discovering cancer at an early stage is an effective way to increase the chance of survival. However, since most screening processes are done manually it is time inefﬁcient and thus a costly process. One way of automizing the screening process could be to classify cells using Convolutional Neural Networks. Convolutional Neural Networks have been proven to be accurate for image classiﬁcation tasks. Two datasets containing oral cells and two datasets containing cervical cells were used. For the cervical cancer dataset the cells were classiﬁed by medical experts as normal or abnormal. For the oral cell dataset we only used the diagnosis of the patient. All cells obtained from a patient with malignancy were thus considered malignant even though most of them looked normal. The performance was evaluated for two different network architectures, ResNet and VGG. For the oral datasets the accuracy varied between 78-82% correctly classiﬁed cells depending on the dataset and network. For the cervical datasets the accuracy varied between 84-86% correctly classiﬁed cells depending on the dataset and network. The results indicate a high potential for detecting abnormalities in oral cavity and in uterine cervix. ResNet was shown to be the preferable network, with a higher accuracy and a smaller standard deviation.
QC bibliography QC xrefs