• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

He, Xuehai (He, Xuehai.) | Cai, Zhuo (Cai, Zhuo.) | Wei, Wenlan (Wei, Wenlan.) | Zhang, Yichen (Zhang, Yichen.) | Mou, Luntian (Mou, Luntian.) | Xing, Eric (Xing, Eric.) | Xie, Pengtao (Xie, Pengtao.)

Indexed by:

CPCI-S CPCI-SSH

Abstract:

Pathology imaging is broadly used for identifying the causes and effects of diseases or injuries. Given a pathology image, being able to answer questions about the clinical findings contained in the image is very important for medical decision making. In this paper, we aim to develop a pathological visual question answering framework to analyze pathology images and answer medical questions related to these images. To build such a framework, we create PathVQA, a pathology VQA dataset with 32,795 questions asked from 4,998 pathology images. We also propose a three-level optimization framework which performs self-supervised pretraining and VQA finetuning end-to-end to learn powerful visual and textual representations jointly and automatically identifies and excludes noisy self-supervised examples from pretraining. We perform experiments on our created PathVQA dataset and the results demonstrate the effectiveness of our proposed methods. The datasets and code are available at https://github.com/UCSD-AI4H/PathVQA

Keyword:

Author Community:

  • [ 1 ] [He, Xuehai]Univ Calif San Diego, La Jolla, CA 92093 USA
  • [ 2 ] [Zhang, Yichen]Univ Calif San Diego, La Jolla, CA 92093 USA
  • [ 3 ] [Xie, Pengtao]Univ Calif San Diego, La Jolla, CA 92093 USA
  • [ 4 ] [Cai, Zhuo]Tsinghua Univ, Beijing, Peoples R China
  • [ 5 ] [Wei, Wenlan]Wuhan Univ, Wuhan, Hubei, Peoples R China
  • [ 6 ] [Mou, Luntian]Beijing Univ Technol, Beijing, Peoples R China
  • [ 7 ] [Xing, Eric]MBZUAI, Abu Dhabi, U Arab Emirates
  • [ 8 ] [Xing, Eric]CMU, Pittsburgh, PA USA

Reprint Author's Address:

  • [Xie, Pengtao]Univ Calif San Diego, La Jolla, CA 92093 USA

Show more details

Related Keywords:

Related Article:

Source :

ACL-IJCNLP 2021: THE 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 2

Year: 2021

Page: 708-718

Language: English

Cited Count:

WoS CC Cited Count: 22

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 2

Affiliated Colleges:

Online/Total:647/5450166
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.