Multi-View Hypercomplex Learning for Breast Cancer Screening (2022-04-12T00:00:00.000000Z)

TL;DR

Multi-view hypercomplex learning is introduced, a novel learning paradigm for multi-view breast cancer classification based on parameterized hypercomplex neural networks (PHNNs) that consistently outperforms state-of-the-art multi-view models, while also generalizing across radiographic modalities and tasks such as disease classification from chest X-rays and multimodal brain tumor segmentation.

Abstract

Radiologists interpret mammography exams by jointly analyzing all four views, as correlations among them are crucial for accurate diagnosis. Recent methods employ dedicated fusion blocks to capture such dependencies, but these are often hindered by view dominance, training instability, and computational overhead. To address these challenges, we introduce multi-view hypercomplex learning, a novel learning paradigm for multi-view breast cancer classification based on parameterized hypercomplex neural networks (PHNNs). Thanks to hypercomplex algebra, our models intrinsically capture both intra- and inter-view relations. We propose PHResNets for two-view exams and two complementary four-view architectures: PHYBOnet, optimized for efficiency, and PHYSEnet, optimized for accuracy. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art multi-view models, while also generalizing across radiographic modalities and tasks such as disease classification from chest X-rays and multimodal brain tumor segmentation. Full code and pretrained models are available at https://github.com/ispamm/PHBreast.

Authors

D. Comminiello

6 papers

E. Lopez

1 papers

Eleonora Grassucci

2 papers

TL;DR

Abstract

Authors

References95 items

UX-Net Based Speech Separation Scheme using Parameterized Hypercomplex Convolutions

Parameterized hypercomplex convolutional network for accurate protein backbone torsion angle prediction

A comprehensive investigation of multimodal deep learning fusion strategies for breast cancer classification

PHemoNet: A Multimodal Network for Physiological Signals

Hierarchical Hypercomplex Network for Multimodal Emotion Recognition

Visual speech recognition using compact hypercomplex neural networks

Deep Hypercomplex Networks for Spatiotemporal Data Processing: Parameter efficiency and superior performance [Hypercomplex Signal and Image Processing]

Deep Location Soft-Embedding-Based Network With Regional Scoring for Mammogram Classification

Towards Explaining Hypercomplex Neural Networks

Harnessing the power of radiomics and deep learning for improved breast cancer diagnosis with multiparametric breast mammography

MV-Swin-T: Mammogram Classification with Multi-View Swin Transformer

HRadNet: A Hierarchical Radiomics-Based Network for Multicenter Breast Cancer Molecular Subtypes Prediction

Attention-Map Augmentation for Hypercomplex Breast Cancer Classification

A systematic review of machine and deep learning techniques for the identification and classification of breast cancer through medical image modalities

Hypercomplex Multimodal Emotion Recognition from EEG and Peripheral Physiological Signals

Ipsilateral Lesion Detection Refinement for Tomosynthesis

BTS-ST: Swin transformer network for segmentation and classification of multimodality breast cancer images

Efficient ECG-Based Atrial Fibrillation Detection via Parameterised Hypercomplex Neural Networks

Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation

HoVer-Trans: Anatomy-Aware HoVer-Transformer for ROI-Free Breast Cancer Diagnosis in Ultrasound Images

Efficient Sound Event Localization and Detection in the Quaternion Domain

Breast cancer detection using artificial intelligence techniques: A systematic literature review

Multimodal deep learning for biomedical data fusion: a review

Cancer statistics, 2022

Diagnose Like a Radiologist: Hybrid Neuro-Probabilistic Reasoning for Attribute-Based Medical Image Diagnosis

Reducing False-Positive Biopsies using Deep Neural Networks that Utilize both Local and Global Image Context of Screening Mammograms

PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions

WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification

Breast Cancer Diagnosis in Two-View Mammography Using End-to-End Trained EfficientNet-Based Convolutional Network

MommiNet-v2: Mammographic multi-view mass identification networks

Triage of 2D Mammographic Images Using Multi-view Multi-task Convolutional Neural Networks

Act Like a Radiologist: Towards Reliable Multi-View Correspondence Reasoning for Mammogram Mass Detection

Multi-scale attention-based convolutional neural network for classification of breast masses in mammograms.

Multiview multimodal network for breast cancer diagnosis in contrast-enhanced spectral mammography images

Quaternion Generative Adversarial Networks

Multi-view analysis of unregistered medical images using cross-view transformers

Post-Hoc Overall Survival Time Prediction From Brain MRI

Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameters

Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification

Quaternion Neural Networks for 3D Sound Source Localization in Reverberant Environments

New convolutional neural network model for screening and diagnosis of mammograms

Cross-View Correspondence Reasoning Based on Bipartite Graph Convolutional Network for Mammogram Mass Detection

Cross-View Attention Network for Breast Cancer Screening from Multi-View Mammograms

Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI

An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization

Deep Learning Computer-Aided Diagnosis for Breast Lesion in Digital Mammogram.

Hypercomplex-Valued Recurrent Correlation Neural Networks

Improving the Ability of Deep Neural Networks to Use Information from Multiple Views in Breast Cancer Screening

Stand-alone artificial intelligence - The future of breast cancer screening?

Multi-View Feature Fusion Based Four Views Model for Mammogram Classification Using Convolutional Neural Network

Streaming Convolutional Neural Networks for End-to-End Learning With Multi-Megapixel Images

Multi-View Convolutional Neural Networks for Mammographic Image Classification

A survey of quaternion neural networks

Cross-View Relation Networks for Mammogram Mass Detection

Deep convolutional neural networks for mammography: advances, challenges and applications

What Makes Training Multi-Modal Classification Networks Hard?

Deep learning-based breast cancer classification through medical imaging modalities: state of the art and research challenges

Deep Neural Networks Improve Radiologists’ Performance in Breast Cancer Screening

Survey on deep learning with class imbalance

Automatic mass detection in mammograms using deep convolutional neural networks

Transfusion: Understanding Transfer Learning for Medical Imaging

CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison

Learning from Imbalanced Data Sets with Weighted Cross-Entropy Function

Quaternion Convolutional Neural Networks for Detection and Localization of 3D Sound Events

Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

Quaternion Convolutional Neural Networks for Heterogeneous Image Processing

MAMMO: A Deep Learning Solution for Facilitating Radiologist-Machine Collaboration in Breast Cancer Diagnosis

Deep Learning to Distinguish Recalled but Benign Mammography Images in Breast Cancer Screening

Quaternion Recurrent Neural Networks

Large Scale Automated Reading of Frontal and Lateral Chest X-Rays using Dual Convolutional Neural Networks

A curated mammography data set for use in computer-aided detection and diagnosis research

Deep Quaternion Networks

Deep Multimodal Learning: A Survey on Recent Advances and Trends

Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features

Deep Learning to Improve Breast Cancer Detection on Screening Mammography

Multimodal Machine Learning: A Survey and Taxonomy