Evaluation of Multi-Scale Multiple Instance Learning to Improve Thyroid Cancer Classification

04/22/2022
by   Maximilian E. Tschuchnig, et al.
0

Thyroid cancer is currently the fifth most common malignancy diagnosed in women. Since differentiation of cancer sub-types is important for treatment and current, manual methods are time consuming and subjective, automatic computer-aided differentiation of cancer types is crucial. Manual differentiation of thyroid cancer is based on tissue sections, analysed by pathologists using histological features. Due to the enormous size of gigapixel whole slide images, holistic classification using deep learning methods is not feasible. Patch based multiple instance learning approaches, combined with aggregations such as bag-of-words, is a common approach. This work's contribution is to extend a patch based state-of-the-art method by generating and combining feature vectors of three different patch resolutions and analysing three distinct ways of combining them. The results showed improvements in one of the three multi-scale approaches, while the others led to decreased scores. This provides motivation for analysis and discussion of the individual approaches.

READ FULL TEXT
research
07/09/2019

Learning from Thresholds: Fully Automated Classification of Tumor Infiltrating Lymphocytes for Multiple Cancer Types

Deep learning classifiers for characterization of whole slide tissue mor...
research
02/18/2020

Dataset of Segmented Nuclei in Hematoxylin and Eosin Stained Histopathology Images of 10 Cancer Types

The distribution and appearance of nuclei are essential markers for the ...
research
02/28/2022

Using Multi-scale SwinTransformer-HTC with Data augmentation in CoNIC Challenge

Colorectal cancer is one of the most common cancers worldwide, so early ...
research
11/10/2022

MixUp-MIL: Novel Data Augmentation for Multiple Instance Learning and a Study on Thyroid Cancer Diagnosis

Multiple instance learning exhibits a powerful approach for whole slide ...
research
07/26/2021

A Multiple-Instance Learning Approach for the Assessment of Gallbladder Vascularity from Laparoscopic Images

An important task at the onset of a laparoscopic cholecystectomy (LC) op...
research
09/27/2022

A Pathologist-Informed Workflow for Classification of Prostate Glands in Histopathology

Pathologists diagnose and grade prostate cancer by examining tissue from...
research
11/10/2020

Glioma Classification Using Multimodal Radiology and Histology Data

Gliomas are brain tumours with a high mortality rate. There are various ...

Please sign up or login with your details

Forgot password? Click here to reset