通过逐级细化感知，用低分辨率起步提升高分辨医学图像分类效率与准确率。
CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classification
- 从低分辨率全局开始，动态定位需细化区域并逐步融合高分辨率细节
- 在相同精度下，计算量减少19.6倍，最高比次优方法提升2.27个百分点
- 适合追求高精度与低资源消耗的医学图像分析场景
高分辨率医学图像包含关键但空间稀疏的细粒度线索，但全分辨率处理会带来巨大计算与内存开销。多数深度模型统一处理图像，导致冗余计算或下采样后诊断细节丢失。本文提出链式感知精炼（CPR），一种从粗到细的框架，将医学图像分析建模为逐级的全局到局部决策过程。从低分辨率全局视图出发，CPR动态预测需细化区域的位置与范围，从原始图像提取高分辨率证据，并逐步融合全局上下文。在保持主干网络输入尺寸不变的同时缩小感知范围，CPR以恒定峰值显存实现诊断保真度。在五个医学影像数据集和多种主干架构上的实验表明，CPR始终优于固定分辨率与多尺度的最先进方法，在匹配精度下实现最高19.6倍的GFLOPs降低，准确率提升达2.27个百分点，确立了高分辨率医学图像分析中卓越的精度-效率权衡。代码已开源。
原文摘要 · Abstract (English)
High resolution medical images contain fine grained, spatially sparse cues that are critical for diagnosis, yet preserving full resolution incurs substantial computational and memory costs. Most deep models process images uniformly, leading to redundant computation or loss of diagnostic detail under downsampling. We propose Chained Perceptual Refinement, CPR, a coarse to fine framework that formulates medical image analysis as a sequential global to local decision process. Starting from a low resolution global view, CPR dynamically predicts the location and spatial extent of refinement regions, extracts high resolution evidence from the original image, and incrementally integrates it with global context. By keeping the backbone input size fixed while contracting the perceptual field, CPR preserves diagnostic fidelity with constant peak GPU memory. Extensive experiments on five medical imaging datasets and multiple backbone architectures demonstrate that CPR consistently outperforms both fixed resolution and multi scale state of the art baselines, achieving improvements of up to 2.27 percentage points over the second best method. It also achieves up to a 19.6 fold reduction in GFLOPs at matched accuracy, establishing a superior accuracy and efficiency trade off for high resolution medical image analysis. The code is available on GitHub.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。