Artificial Intelligence Now Classifies Lung Cancer as well as Pathologists
Towards AI-assisted healthcare
Lung cancer is the leading case of cancer death in the western world. Pathologists examine tissue slides under the microscope and classify them to determine grade and treatment for a tumor. But every cancer is different, so reading these slides can be hard. Like really hard. Can artificial intelligence help out?
Yes, yes, and…
Deep Learning
Recently, deep learning has produced a set of image analysis techniques that automatically extract relevant features called Convolutional Neural Networks (CNNs), transforming the field of computer vision. CNNs use a data-driven approach to automatically learn feature representations for images, achieving super-human performance on benchmark image classification datasets such as ImageNet and CIFAR-10. By collecting large amounts of lung cancer images and having pathologists annotate them, a CNN can be trained to classify different types of cancer lung cancer slides, facilitating the identification and grading of lung adenocarcinoma.