Abstract

Mining algorithms for Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) of breast tissue are discussed. The algorithms are based on recent advances in multi-dimensional signal processing and aim to advance current state-of-the-art computer-aided detection and analysis of breast tumours when these are observed at various states of development. The topics discussed include image feature extraction, information fusion using radiomics, multi-parametric computer-aided classification and diagnosis using information fusion of tensorial datasets as well as Clifford algebra based classification approaches and convolutional neural network deep learning methodologies. The discussion also extends to semi-supervised deep learning and self-supervised strategies as well as generative adversarial networks and algorithms using generated confrontational learning approaches. In order to address the problem of weakly labelled tumour images, generative adversarial deep learning strategies are considered for the classification of different tumour types. The proposed data fusion approaches provide a novel Artificial Intelligence (AI) based framework for more robust image registration that can potentially advance the early identification of heterogeneous tumour types, even when the associated imaged organs are registered as separate entities embedded in more complex geometric spaces. Finally, the general structure of a high-dimensional medical imaging analysis platform that is based on multi-task detection and learning is proposed as a way forward. The proposed algorithm makes use of novel loss functions that form the building blocks for a generated confrontation learning methodology that can be used for tensorial DCE-MRI. Since some of the approaches discussed are also based on time-lapse imaging, conclusions on the rate of proliferation of the disease can be made possible. The proposed framework can potentially reduce the costs associated with the interpretation of medical images by providing automated, faster and more consistent diagnosis.

Highlights

  • Incidences of breast cancer have dramatically increased over the past 30 years, with the maximum number of incidents having gradually shifted from the 40–44 age group in the past 20 years to the50–54 age group over the past decade

  • We explore relevant research on histology-based imaging, and discuss annotation issues encountered in magnetic resonance and Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-magnetic resonance imaging (MRI))

  • diffusion-weighted imaging (DWI) of breast cancer patients, the mean apparent diffusion coefficient (ADC) value of ER-negative tumours was significantly higher than that of ER-positive tumours (p = 0.005), which suggested that the ADC values on tumour and peritumoural stroma allow a good distinction of different biological labels

Read more

Summary

Introduction

Incidences of breast cancer have dramatically increased over the past 30 years, with the maximum number of incidents having gradually shifted from the 40–44 age group in the past 20 years to the. The specificity of diagnosis is being constantly improved and gradually becoming an indispensable means of inspection for breast cancer screening Such advances have been making a significant impact in the field of tumour diagnosis, where increasingly refined tumour images in terms of contrast and resolution provide a lot of additional information, enabling experts to identify disease types and rate of proliferation, as well as verify the efficacy of different types of treatment. In traditional high-dimensional DCE-MRI analysis, time domain signals and spatial domain characteristics in the image are processed separately to make a final diagnosis Such approach results in low specificity of lesion detection, i.e., in a range of 40–80% [5,6].

Radiomic
Integration of Radiomics with DCE-MRI Datasets
Overview of Computer Aided Classification Algorithms for Cancer Diagnosis
Tensor Based MRI Image Analysis and Classification
Illustration
High-Dimensional
Deepfor
Flowchart
Self-Supervised Learning
Generative Adversarial Networks for MRI
Semi-Supervised Knowledge Transfer for Deep Learning
High-Dimensional Medical Imaging Analysis by Multi-Task Detection
Findings
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call