對於腹膜後腫瘤分割中 U-Net 修改版性能的研究

A Study on the Performance of U-Net Modifications in Retroperitoneal Tumor Segmentation

February 1, 2025

作者: Moein Heidari, Ehsan Khodapanah Aghdam, Alexander Manzella, Daniel Hsu, Rebecca Scalabrino, Wenjin Chen, David J. Foran, Ilker Hacihaliloglu

cs.AI

摘要

腹膜後區域存在各種腫瘤，包括罕見的良性和惡性類型，由於其罕見性和與重要結構的接近，對其進行診斷和治療具有挑戰性。由於這些腫瘤形狀不規則，估算腫瘤體積很困難，而手動分割則耗時。使用 U-Net 及其變體進行自動分割，並納入 Vision Transformer (ViT) 元素，已顯示出有希望的結果，但面臨著高計算需求的困難。為了應對這一問題，像 Mamba State Space Model (SSM) 和 Extended Long-Short Term Memory (xLSTM) 這樣的架構提供了有效的解決方案，通過處理長距離依賴性來降低資源消耗。本研究評估了 U-Net 的增強功能，包括 CNN、ViT、Mamba 和 xLSTM，在一個新的內部 CT 資料集和一個公共器官分割資料集上。提出的 ViLU-Net 模型集成了 Vi-blocks 以改善分割效果。結果突出了 xLSTM 在 U-Net 框架中的效率。代碼可在 GitHub 上公開訪問。

English

The retroperitoneum hosts a variety of tumors, including rare benign and malignant types, which pose diagnostic and treatment challenges due to their infrequency and proximity to vital structures. Estimating tumor volume is difficult due to their irregular shapes, and manual segmentation is time-consuming. Automatic segmentation using U-Net and its variants, incorporating Vision Transformer (ViT) elements, has shown promising results but struggles with high computational demands. To address this, architectures like the Mamba State Space Model (SSM) and Extended Long-Short Term Memory (xLSTM) offer efficient solutions by handling long-range dependencies with lower resource consumption. This study evaluates U-Net enhancements, including CNN, ViT, Mamba, and xLSTM, on a new in-house CT dataset and a public organ segmentation dataset. The proposed ViLU-Net model integrates Vi-blocks for improved segmentation. Results highlight xLSTM's efficiency in the U-Net framework. The code is publicly accessible on GitHub.