REVIEW 9 cited by
nnFormer: Interleaved Transformer for Volumetric Segmentation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
nnFormer: Interleaved Transformer for Volumetric Segmentation
read the original abstract
Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community. Given the ability to exploit long-term dependencies, transformers are promising to help atypical convolutional neural networks to overcome their inherent shortcomings of spatial inductive bias. However, most of recently proposed transformer-based segmentation approaches simply treated transformers as assisted modules to help encode global context into convolutional representations. To address this issue, we introduce nnFormer, a 3D transformer for volumetric medical image segmentation. nnFormer not only exploits the combination of interleaved convolution and self-attention operations, but also introduces local and global volume-based self-attention mechanism to learn volume representations. Moreover, nnFormer proposes to use skip attention to replace the traditional concatenation/summation operations in skip connections in U-Net like architecture. Experiments show that nnFormer significantly outperforms previous transformer-based counterparts by large margins on three public datasets. Compared to nnUNet, nnFormer produces significantly lower HD95 and comparable DSC results. Furthermore, we show that nnFormer and nnUNet are highly complementary to each other in model ensembling.
Forward citations
Cited by 9 Pith papers
-
SAM+D: Parameter-Efficient Dimensional Lifting of SAM-Family Models via Depth-Routed LoRA and Depth Shifting
Depth-routed LoRA and a depth-shift module lift frozen SAM and SAM2 to 3D and 3D+T segmentation using less than ~3.7% trainable parameters.
-
One-for-All Adaptive Radiotherapy Planning Agent: A Foundation Framework for Daily CBCT-guided Radiotherapy
A unified agentic model performs online adaptive radiotherapy planning from daily CBCT in under two minutes with target dose errors generally within 2.0 Gy of clinical reference plans.
-
Super-Generalist: Towards Comprehensive and Accurate Medical Image Understanding via Generalist-Specialist Synergy
Injecting multi-expert anatomy/lesion segmentation priors into vision–language alignment and calibrating text attention with lesion masks yields broad CT diagnosis plus specialist-level tumor performance and lesion grounding.
-
MS-DKC: A Dataset Knowledge Card Framework for Designing and Adapting Medical Image Segmentation Models
MS-DKC is a dataset knowledge card framework that maps image, morphology, supervision, context, and risk descriptors to design priors and failure modes, shown to produce dataset-specific model adaptations with improve...
-
Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning
A unified autoregressive vision-language framework integrates segmentation, detection, and appearance reasoning for CT images via task-routing tokens and progressive refinement, with gains on public benchmarks.
-
MHMamba: Multi-Head Mamba for 3D Brain Tumor Segmentation
MHMamba combines a U-Net with multi-head Mamba, channel calibration, and adaptive skip fusion to improve 3D brain tumor segmentation accuracy and small-lesion sensitivity on BraTS datasets while retaining linear complexity.
-
A Positron Range Correction with Texture Preservation Framework in PET Imaging
PRC-TP combines an nnFormer network trained on Monte Carlo simulations with Model-consistent Texture Re-Injection to correct positron range effects in 82Rb PET while restoring acquisition-consistent texture.
-
Focal Modulation and Bidirectional Feature Fusion Network for Medical Image Segmentation
FM-BFF-Net combines focal modulation attention with bidirectional encoder-decoder fusion in a CNN-transformer architecture and reports higher Dice and Jaccard scores than recent methods across eight medical image datasets.
-
Improving Prostate Gland Segmentation Using Transformer based Architectures
SwinUNETR outperforms 3D UNet with Dice scores up to 0.902 on larger gland subsets using mixed-cohort five-fold training, while UNETR performs poorly on the same subsets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.