A study on the performance of U-Net modifications in retroperitoneal tumor segmentation
Bibliographic record
Abstract
The retroperitoneum presents a diverse array of pathologies, encompassing both rare benign tumors and malignant neoplasms, which can be either primary or metastatic. Diagnosing and treating these tumors can be challenging due to their infrequency, late presentation, and their close association with critical structures in the retroperitoneal space. Estimating the volume of retroperitoneal tumors is often challenging due to their large dimensions and irregular shape. Automatic semantic segmentation of tumors is crucial for comprehensive medical image analysis, impacting accurate cancer diagnosis and treatment planning due to manual segmentation’s time-consuming and tedious nature. U-Net and its variants incorporate the various convolutions of Vision Transformer (ViT) designs and have delivered top-notch results in 2D and 3D medical image segmentation tasks across diverse imaging modalities. ViTs excel at extracting global information, yet face scalability issues due to high computational and memory costs, making them challenging to use in medical applications with hardware constraints. Recently, architectures like the Mamba State Space Model (SSM) have been developed to address the quadratic computational demands of Transformers. Additionally, Extended Long-Short Term Memory (xLSTM) has emerged as a noteworthy successor to traditional LSTMs, offering a competitive edge in sequence modeling. Like SSMs, xLSTM excels at managing long-range dependencies while maintaining linear computational and memory efficiency. This study aimed to evaluate the U-Net-based modifications from the convolutional neural networks (CNNs), ViT, mamba, and the new xLSTM companions over the newly introduced in-house CT dataset along a publicly available organ segmentation dataset. Specifically, we introduce ViLU-Net designed by incorporating Vi-blocks into the encoder-decoder framework to advance biomedical image segmentation. The results point out the efficacy of xLSTM within the U-Net structure.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".