ICHOR: A Robust Representation Learning Approach for ASL CBF Maps with Self-Supervised Masked Autoencoders

• URL: http://arxiv.org/abs/2603.05247v1
• Date: Thu, 05 Mar 2026 15:01:11 GMT
• Title: ICHOR: A Robust Representation Learning Approach for ASL CBF Maps with Self-Supervised Masked Autoencoders
• Authors: Xavier Beltran-Urbano, Yiran Li, Xinglin Zeng, Katie R. Jobson, Manuel Taso, Christopher A. Brown, David A. Wolk, Corey T. McMillan, Ilya M. Nashrallah, Paul A. Yushkevich, Ze Wang, John A. Detre, Sudipto Dolui,
• Abstract summary: Arterial spin labeling (ASL) perfusion MRI allows direct quantification of regional cerebral blood flow.<n>ICHOR is a self supervised pre-training approach for ASL CBF maps that learns transferable representations using 3D masked autoencoders.<n>We curated one of the largest ASL datasets to date, comprising 11,405 ASL CBF scans from 14 studies spanning multiple sites and acquisition protocols.
• Score: 2.7089571884047783
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Arterial spin labeling (ASL) perfusion MRI allows direct quantification of regional cerebral blood flow (CBF) without exogenous contrast, enabling noninvasive measurements that can be repeated without constraints imposed by contrast injection. ASL is increasingly acquired in research studies and clinical MRI protocols. Building on successes in structural imaging, recent efforts have implemented deep learning based methods to improve image quality, enable automated quality control, and derive robust quantitative and predictive biomarkers with ASL derived CBF. However, progress has been limited by variable image quality, substantial inter-site, vendor and protocol differences, and limited availability of labeled datasets needed to train models that generalize across cohorts. To address these challenges, we introduce ICHOR, a self supervised pre-training approach for ASL CBF maps that learns transferable representations using 3D masked autoencoders. ICHOR is pretrained via masked image modeling using a Vision Transformer backbone and can be used as a general-purpose encoder for downstream ASL tasks. For pre-training, we curated one of the largest ASL datasets to date, comprising 11,405 ASL CBF scans from 14 studies spanning multiple sites and acquisition protocols. We evaluated the pre-trained ICHOR encoder on three downstream diagnostic classification tasks and one ASL CBF map quality prediction regression task. Across all evaluations, ICHOR outperformed existing neuroimaging self-supervised pre-training methods adapted to ASL. Pre-trained weights and code will be made publicly available.

Related papers

• Latent Anomaly Detection: Masked VQ-GAN for Unsupervised Segmentation in Medical CBCT [0.47587112043038626]
  This study aims to develop an unsupervised training approach for automatically identifying anomalies in ONJ imaging scans.<n>In the first stage, a VQ-GAN is trained to accurately reconstruct normal subjects.<n>In the second stage, random cube masking and ONJ-specific masking are applied to train a new encoder capable of recovering the data.
  arXiv  Detail & Related papers  (2025-06-17T05:58:04Z)
• The Efficacy of Semantics-Preserving Transformations in Self-Supervised Learning for Medical Ultrasound [60.80780313225093]
  This study systematically investigated the impact of data augmentation and preprocessing strategies in self-supervised learning for lung ultrasound.<n>Three data augmentation pipelines were assessed: a baseline pipeline commonly used across imaging domains, a novel semantic-preserving pipeline designed for ultrasound, and a distilled set of the most effective transformations from both pipelines.
  arXiv  Detail & Related papers  (2025-04-10T16:26:47Z)
• Self-Supervised Multiple Instance Learning for Acute Myeloid Leukemia Classification [1.1874560263468232]
  Diseases like Acute Myeloid Leukemia (AML) pose challenges due to scarce and costly annotations on a single-cell level. Multiple Instance Learning (MIL) addresses weakly labeled scenarios but necessitates powerful encoders typically trained with labeled data. In this study, we explore Self-Supervised Learning (SSL) as a pre-training approach for MIL-based subtype AML classification from blood smears.
  arXiv  Detail & Related papers  (2024-03-08T15:16:15Z)
• Self-supervised learning for skin cancer diagnosis with limited training data [0.196629787330046]
  Self-supervised learning (SSL) is an alternative to the standard supervised pre-training on ImageNet for scenarios with limited training data. We consider textitfurther SSL pre-training on task-specific datasets, where our implementation is motivated by supervised transfer learning. We find minimal further SSL pre-training on task-specific data can be as effective as large-scale SSL pre-training on ImageNet for medical image classification tasks with limited labelled data.
  arXiv  Detail & Related papers  (2024-01-01T08:11:38Z)
• Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images [1.883452979588382]
  Self-supervised learning (SSL) can be applied to chest radiographs to learn robust features. We tested our approach on over 800,000 chest radiographs from six large global datasets.
  arXiv  Detail & Related papers  (2023-08-15T10:37:13Z)
• Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training [51.16994853817024]
  This work focuses on designing an effective pre-training framework for 3D radiology images. We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations. The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-07-31T17:59:42Z)
• Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation [57.206129938611454]
  Self-supervised representation learning (SSL) methods have outperformed the ImageNet classification pre-training for vision tasks such as object detection. We empirically study and analyze the effects of SSL and compare it with other pre-training alternatives for 3DHPSE. Our observations challenge the naive application of the current SSL pre-training to 3DHPSE and relight the value of other data types in the pre-training aspect.
  arXiv  Detail & Related papers  (2023-03-09T16:17:52Z)
• Dissecting Self-Supervised Learning Methods for Surgical Computer Vision [51.370873913181605]
  Self-Supervised Learning (SSL) methods have begun to gain traction in the general computer vision community. The effectiveness of SSL methods in more complex and impactful domains, such as medicine and surgery, remains limited and unexplored. We present an extensive analysis of the performance of these methods on the Cholec80 dataset for two fundamental and popular tasks in surgical context understanding, phase recognition and tool presence detection.
  arXiv  Detail & Related papers  (2022-07-01T14:17:11Z)
• Medical Instrument Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning [62.13520959168732]
  We propose a semi-supervised learning framework for instrument segmentation in 3D US. To achieve the SSL learning, a Dual-UNet is proposed to segment the instrument. Our proposed method achieves Dice score of about 68.6%-69.1% and the inference time of about 1 sec. per volume.
  arXiv  Detail & Related papers  (2021-07-30T07:59:45Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)
• Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning [21.902313057142905]
  Self-supervised learning (SSL) is a potential solution for deficient annotated data. We propose a novel SSL approach for 3D medical image classification, namely Task-related Contrastive Prediction Coding ( TCPC) TCPC embeds task knowledge into training 3D neural networks.
  arXiv  Detail & Related papers  (2020-06-10T12:37:39Z)

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.