A breast cancer chat robot is used to provide medical information to patients and soothe their anxiety. Many researches are focusing on the chatbots' important conversational skills in breast cancer consultation. However, most current breast cancer chatbots ignore breast cancer diagnosis, which is one of the main reasons for patients' anxiety. In this paper, we present a chat robot to perform the breast cancer diagnosis, generate responses to users, and provide them with information related to breast cancer. Our chat robot consists of three parts, breast cancer detection, chatting function, and user interface. In breast cancer detection, we first resize, rotate and normalize the images, and then load and fine-tune the pre-trained Resnet-152 with SGDM. For the chatting function, we normalize the texts and use TF-IDF to find the true answer in the whole list for users. At last, we encapsulate breast cancer detection and chatting functions into the user interface. The experimental results show that the chat robot could detect breast cancer accurately and give true responses to users. Our analyses illustrate that our chat robot can assist in diagnosis and treatment by saving time, sharing more information with patients, and analyzing images of slices.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.