发表机构
Van Lang University（Van Lang大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究在泄漏控制、病变不相交协议下评估皮肤镜预处理，发现最小处理加在线增强比复杂预处理在YOLO26上取得更好的准确率-效率权衡。
AI 中文摘要
手工预处理被广泛用于自动化皮肤镜分析中，以抑制成像伪影并增强病变可见性。然而，其对现代实时模型的实际贡献仍不清楚，尤其是在评估协议未能充分控制同一病变图像间相关性时。本研究提出了一种泄漏控制、病变不相交的皮肤镜预处理与增强评估方法，使用固定的纳尺度YOLO26分割模型（YOLO26n-seg）进行联合多类病变分类和实例分割。从HAM10000（10,015张图像）中，质量控制得到来自7,468个独特病变的10,013个有效图像-掩膜对，按病变身份划分为互斥集合。在架构、分辨率、训练预算和评估协议固定的条件下，我们比较了最小处理图像加在线增强与离线类别平衡、DullRazor-CLAHE预处理以及原始-处理混合视图，跨越三个随机种子。在病变不相交测试集上，原始基线实现了掩膜mAP$_{50:95}$为$0.5636 \pm 0.0234$，Dice分数为$0.9356 \pm 0.0024$，宏F1分数为$0.6917 \pm 0.0202$。离线增强并未提高平均性能，而组合和混合策略降低了类别感知的分割和分类准确性。模型仅2.69百万参数，运行速度约为每秒50帧。在泄漏控制、病变不相交协议下，所有非输入因素固定，最小处理的皮肤镜图像结合标准在线增强比日益复杂的确定性预处理提供了更好的准确率-效率权衡，后者在HAM10000上的三个种子中未产生一致的联合收益。
英文摘要
Handcrafted preprocessing is widely employed in automated dermoscopic analysis to suppress imaging artifacts and enhance lesion visibility. Nevertheless, its actual contribution to modern real-time models remains unclear, particularly when evaluation protocols do not adequately control correlations among images of the same lesion. This study presents a leakage-controlled, lesion-disjoint evaluation of dermoscopic preprocessing and augmentation for joint multi-class lesion classification and instance segmentation using a fixed nano-scale YOLO26 segmentation model (YOLO26n-seg). From HAM10000 (10,015 images), quality control yields 10,013 valid image-mask pairs from 7,468 unique lesions, partitioned into mutually exclusive sets by lesion identity. With the architecture, resolution, training budget, and evaluation protocol held fixed, we compare minimally processed images plus online augmentation against offline class balancing, DullRazor-CLAHE preprocessing, and raw-processed hybrid views, over three random seeds. On the lesion-disjoint test set, the raw baseline achieves a mask mAP$_{50:95}$ of $0.5636 \pm 0.0234$, a Dice score of $0.9356 \pm 0.0024$, and a macro-F1 score of $0.6917 \pm 0.0202$. Offline augmentation does not improve the mean performance, while the combined and hybrid strategies reduce both class-aware segmentation and classification accuracy. At only 2.69 million parameters, the model runs at approximately 50 frames per second. Under a leakage-controlled, lesion-disjoint protocol with all non-input factors held fixed, minimally processed dermoscopic images combined with standard online augmentation deliver a better accuracy-efficiency trade-off than increasingly complex deterministic preprocessing, which yields no consistent joint benefit across three seeds on HAM10000.
Comments6 pages, 3 figures, 5 tables
