Dual-attention ResNet outperforms transformers in HER2 prediction on DCE-MRI

• URL: http://arxiv.org/abs/2510.13897v1
• Date: Tue, 14 Oct 2025 17:08:17 GMT
• Title: Dual-attention ResNet outperforms transformers in HER2 prediction on DCE-MRI
• Authors: Naomi Fridman, Anat Goldstein,
• Abstract summary: Noninvasive prediction of HER2 status from dynamic contrast-enhanced MRI (DCE-MRI) could streamline diagnostics and reduce reliance on biopsy.<n>We benchmarked intensity normalization strategies using a Triple-Head Dual-Attention ResNet that processes RGB-fused temporal sequences.<n>Our model outperformed transformer-based architectures, achieving 0.75 accuracy and 0.74 AUC on I-SPY test data.
• Score: 1.9336815376402718
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Breast cancer is the most diagnosed cancer in women, with HER2 status critically guiding treatment decisions. Noninvasive prediction of HER2 status from dynamic contrast-enhanced MRI (DCE-MRI) could streamline diagnostics and reduce reliance on biopsy. However, preprocessing high-dynamic-range DCE-MRI into standardized 8-bit RGB format for pretrained neural networks is nontrivial, and normalization strategy significantly affects model performance. We benchmarked intensity normalization strategies using a Triple-Head Dual-Attention ResNet that processes RGB-fused temporal sequences from three DCE phases. Trained on a multicenter cohort (n=1,149) from the I-SPY trials and externally validated on BreastDCEDL_AMBL (n=43 lesions), our model outperformed transformer-based architectures, achieving 0.75 accuracy and 0.74 AUC on I-SPY test data. N4 bias field correction slightly degraded performance. Without fine-tuning, external validation yielded 0.66 AUC, demonstrating cross-institutional generalizability. These findings highlight the effectiveness of dual-attention mechanisms in capturing transferable spatiotemporal features for HER2 stratification, advancing reproducible deep learning biomarkers in breast cancer imaging.

Related papers

• Stage-Specific Benchmarking of Deep Learning Models for Glioblastoma Follow-Up MRI [1.1458853556386799]
  We present the first stage-specific, cross-sectional benchmarking of deep learning models for follow-up MRI.<n>We analyze different post-RT scans independently to test whether architecture performance depends on time-point.<n>These results establish a stage-aware benchmark and motivate future work incorporating longitudinal modeling, multi-sequence MRI, and larger multi-center cohorts.
  arXiv  Detail & Related papers  (2025-11-23T19:38:03Z)
• Large-Scale Pre-training Enables Multimodal AI Differentiation of Radiation Necrosis from Brain Metastasis Progression on Routine MRI [3.291383664051985]
  Differentiating radiation necrosis from tumor progression after radiosurgery is a critical challenge in brain metastases.<n> Conventional supervised deep learning approaches are constrained by scarce biopsy-confirmed training data.<n>Self-supervised learning overcomes this by leveraging the growing availability of largescale unlabeled brain metastases imaging datasets.
  arXiv  Detail & Related papers  (2025-11-22T22:44:50Z)
• Transparent Early ICU Mortality Prediction with Clinical Transformer and Per-Case Modality Attribution [42.85462513661566]
  We present a lightweight, transparent multimodal ensemble that fuses physiological time-series measurements with unstructured clinical notes from the first 48 hours of an ICU stay.<n>A logistic regression model combines predictions from two modality-specific models: a bidirectional LSTM for vitals and a finetuned ClinicalModernBERT transformer for notes.<n>On the MIMIC-III benchmark, our late-fusion ensemble improves discrimination over the best single model while maintaining well-calibrated predictions.
  arXiv  Detail & Related papers  (2025-11-19T20:11:49Z)
• FDP: A Frequency-Decomposition Preprocessing Pipeline for Unsupervised Anomaly Detection in Brain MRI [44.4791295950757]
  We develop an unsupervised anomaly detection (UAD) approach for brain MRI.<n>We conduct the first systematic frequency-domain analysis of pathological signatures.<n>We show that Frequency-Decomposition Preprocessing (FDP) framework can leverage frequency-domain reconstruction for simultaneous pathology suppression and anatomical preservation.
  arXiv  Detail & Related papers  (2025-11-17T02:40:14Z)
• Toward a robust lesion detection model in breast DCE-MRI: adapting foundation models to high-risk women [4.615277920713566]
  We present a classification pipeline that adapts a pretrained foundation model, the Medical Slice Transformer (MST), for breast lesion classification using dynamic contrast-enhanced MRI (DCE-MRI)<n>Our findings highlight the effectiveness of combining foundation model embeddings with advanced classification strategies for building robust and generalizable breast MRI analysis tools.
  arXiv  Detail & Related papers  (2025-09-02T18:11:18Z)
• LGE-Guided Cross-Modality Contrastive Learning for Gadolinium-Free Cardiomyopathy Screening in Cine CMR [51.11296719862485]
  We propose a Contrastive Learning and Cross-Modal alignment framework for gadolinium-free cardiomyopathy screening using cine CMR sequences.<n>By aligning the latent spaces of cine CMR and Late Gadolinium Enhancement (LGE) sequences, our model encodes fibrosis-specific pathology into cine CMR embeddings.
  arXiv  Detail & Related papers  (2025-08-23T07:21:23Z)
• SurgeryLSTM: A Time-Aware Neural Model for Accurate and Explainable Length of Stay Prediction After Spine Surgery [44.119171920037196]
  We develop and evaluate machine learning (ML) models for predicting length of stay (LOS) in elective spine surgery.<n>We compare traditional ML models with our developed model, SurgeryLSTM, a masked bidirectional long short-term memory (BiLSTM) with an attention.<n>Performance was evaluated using the coefficient of determination (R2) and key predictors were identified using explainable AI.
  arXiv  Detail & Related papers  (2025-07-15T01:18:28Z)
• BreastDCEDL: A Comprehensive Breast Cancer DCE-MRI Dataset and Transformer Implementation for Treatment Response Prediction [0.0]
  We present BreastDCEDL, a curated, deep learning-ready dataset comprising pre-treatment 3D Dynamic Contrast-Enhanced MRI (DCE-MRI) scans from 2,070 breast cancer patients.<n>The raw DICOM imaging data were rigorously converted into standardized 3D NIfTI volumes with preserved signal integrity.<n>BreastDCEDL includes predefined benchmark splits, offering a framework for reproducible research and enabling clinically meaningful modeling in breast cancer imaging.
  arXiv  Detail & Related papers  (2025-06-13T19:31:57Z)
• T2-Only Prostate Cancer Prediction by Meta-Learning from Bi-Parametric MR Imaging [39.64252838533947]
  Current imaging-based prostate cancer diagnosis requires both MR T2-weighted (T2w) and diffusion-weighted imaging (DWI) sequences. measuring diffusion patterns in DWI sequences can be time-consuming, prone to artifacts and sensitive to imaging parameters. This study investigates the potential of machine learning (ML) methods using only the T2w sequence as input during inference time.
  arXiv  Detail & Related papers  (2024-11-11T22:38:45Z)
• Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI [58.809276442508256]
  We propose a hybrid network via the combination of convolution neural network (CNN) and transformer layers. The experimental results on private and public DCE-MRI datasets demonstrate that the proposed hybrid network superior performance than the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-11T15:46:00Z)
• Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer [37.55853672333369]
  This paper proposes a novel learnable neural distance that describes the precise relationship between the tumor and vessels in CT images of different patients. The developed risk marker was the strongest predictor of overall survival among preoperative factors.
  arXiv  Detail & Related papers  (2023-08-01T12:46:02Z)
• Moving from 2D to 3D: volumetric medical image classification for rectal cancer staging [62.346649719614]
  preoperative discrimination between T2 and T3 stages is arguably both the most challenging and clinically significant task for rectal cancer treatment. We present a volumetric convolutional neural network to accurately discriminate T2 from T3 stage rectal cancer with rectal MR volumes.
  arXiv  Detail & Related papers  (2022-09-13T07:10:14Z)
• Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction [0.0]
  Data Consistency (DC) is crucial for generalization in multi-modal data and robustness in detecting pathology. This work proposes the Cascades of Independently Recurrent Inference Machines (CIRIM) to assess DC through unrolled optimization. We show that the CIRIM performs best when implicitly enforcing DC, while the E2EVN requires explicitly formulated DC.
  arXiv  Detail & Related papers  (2021-11-30T15:34:30Z)
• Performance of Dual-Augmented Lagrangian Method and Common Spatial Patterns applied in classification of Motor-Imagery BCI [68.8204255655161]
  Motor-imagery based brain-computer interfaces (MI-BCI) have the potential to become ground-breaking technologies for neurorehabilitation. Due to the noisy nature of the used EEG signal, reliable BCI systems require specialized procedures for features optimization and extraction.
  arXiv  Detail & Related papers  (2020-10-13T20:50:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.