Visual Language Pretrained Multiple Instance Zero-Shot
Transfer for Histopathology Images
Name
lu-mingylu-sm-eecs-2023-thesis.pdf
Description
Thesis PDF
Size
7.22 MB
Format
Adobe PDF
Checksum (MD5)
b60e6b3e62ba907a346944d9101c181c
Author(s)
Lu, Ming Yang (Max)
Advisor(s)
Mahmood, Faisal
Date Issued
June 2023
Publisher
Massachusetts Institute of Technology
Abstract
Contrastive visual language pretraining has emerged as a powerful method for either training new language-aware image encoders or augmenting existing pretrained models with zero-shot visual recognition capabilities. However, existing works typically train on large datasets of image-text pairs and have been designed to perform downstream tasks involving only small to medium sized-images, neither of which are applicable to the emerging field of computational pathology where there are limited publicly available paired image-text datasets and each image can span up to 100,000 x 100,000 pixels. In this paper we present MI-Zero, a simple and intuitive framework for unleashing the zero-shot transfer capabilities of contrastively aligned image and text models on gigapixel histopathology whole slide images, enabling multiple downstream diagnostic tasks to be carried out by pretrained encoders without requiring any additional labels. MI-Zero reformulates zero-shot transfer under the framework of multiple instance learning to overcome the computational challenge of inference on extremely large images. We used over 550k pathology reports and other available in-domain text corpora to pretrain our text encoder. By effectively leveraging strong pretrained encoders, our best model pretrained on over 33k histopathology image-caption pairs achieves an average median zero-shot accuracy of 70.2% across three different real-world cancer subtyping tasks.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
