发表机构
Northeastern University; LDRP Institute of Technology and Research; Kadi Sarva Vishwavidyalaya（东北大学; LDRP技术与研究学院; 卡迪萨尔瓦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出VGG16-MCA UNet，结合预训练编码器与多通道注意力解码器及Focal Tversky损失，在BraTS 2020和LGG上实现95.10%和88.32%的像素级Dice，提供可复现的二维FLAIR全肿瘤分割基线。
AI 中文摘要
自动化脑肿瘤分割有助于诊断、治疗规划和疾病进展监测，但构建能够泛化到异质性肿瘤且标注数据有限的模型仍然困难。我们提出了VGG16-MCA UNet，一种混合架构，将ImageNet预训练的VGG16编码器与解码器配对，在解码器中，多通道注意力（MCA）模块在每次跳跃连接融合后重新校准特征，并使用Focal Tversky损失进行训练以应对严重的前景-背景不平衡。我们将该模型作为二维、仅FLAIR的全肿瘤分割器，在两个公共数据集的肿瘤阳性切片上进行评估：BraTS 2020基准和LGG MRI分割数据集。使用5折交叉验证和通过对五个折模型的权重取平均形成的单一网络，该方法在我们留出的BraTS 2020分割上达到95.10%的聚合像素级Dice（F1），在LGG上达到88.32%。这些分数是在将所有测试像素汇集成单个混淆矩阵后计算的，而不是按病例平均，因此不能直接与BraTS挑战协议中使用的按病例平均Dice进行比较。所有划分均基于单个切片而非患者进行，因此每位患者的切片同时出现在训练和测试中；上述数字衡量的是已知患者内的插值，应视为上限而非对新患者的泛化。该模型在单个6 GB NVIDIA RTX 2060上分割一个256x256切片耗时66.32毫秒，比没有MCA的等效VGG16-UNet多约8毫秒。我们发布了划分记录并完整报告了协议，旨在提供一个精确定义且可复现的二维FLAIR基线。
英文摘要
Automated brain tumor segmentation supports diagnosis, treatment planning, and monitoring of disease progression, but building models that generalize across heterogeneous tumors and limited annotated data remains difficult. We present VGG16-MCA UNet, a hybrid architecture pairing an ImageNet-pretrained VGG16 encoder with a decoder in which a Multi-Channel Attention (MCA) module recalibrates features after each skip-connection fusion, trained with the Focal Tversky loss to counter severe foreground-background imbalance. We evaluate the model as a 2D, FLAIR-only, whole-tumor segmenter on tumor-positive slices from two public datasets: the BraTS 2020 benchmark and the LGG MRI Segmentation dataset. Using 5-fold cross-validation and a single network formed by averaging the weights of the five fold models, the method attains an aggregate pixel-level Dice (F1) of 95.10% on our held-out BraTS 2020 split and 88.32% on LGG. These scores are computed over all test pixels pooled into a single confusion matrix rather than averaged per case, and are therefore not directly comparable to the per-case mean Dice used in the BraTS challenge protocol. All partitions were drawn over individual slices rather than over patients, so every patient contributes slices to both training and test; the figures above therefore measure interpolation within known patients and should be read as an upper bound rather than as generalization to new ones. The model segments a 256x256 slice in 66.32 ms on a single 6 GB NVIDIA RTX 2060, approximately 8 ms more than an equivalent VGG16-UNet without MCA. We release the split records and report the protocol in full, with the aim of providing a precisely specified and reproducible 2D FLAIR baseline.
Comments22 pages, 7 figures, 4 tables. Code and data splits: https://github.com/ShubhamGajjar/vgg16-mca-unet
