REVIEW 10 cited by
nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image 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
nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation
read the original abstract
The release of nnU-Net marked a paradigm shift in 3D medical image segmentation, demonstrating that a properly configured U-Net architecture could still achieve state-of-the-art results. Despite this, the pursuit of novel architectures, and the respective claims of superior performance over the U-Net baseline, continued. In this study, we demonstrate that many of these recent claims fail to hold up when scrutinized for common validation shortcomings, such as the use of inadequate baselines, insufficient datasets, and neglected computational resources. By meticulously avoiding these pitfalls, we conduct a thorough and comprehensive benchmarking of current segmentation methods including CNN-based, Transformer-based, and Mamba-based approaches. In contrast to current beliefs, we find that the recipe for state-of-the-art performance is 1) employing CNN-based U-Net models, including ResNet and ConvNeXt variants, 2) using the nnU-Net framework, and 3) scaling models to modern hardware resources. These results indicate an ongoing innovation bias towards novel architectures in the field and underscore the need for more stringent validation standards in the quest for scientific progress.
Forward citations
Cited by 10 Pith papers
-
Complete virtual unwrapping and reading of a rolled Herculaneum papyrus
First complete digital unwrapping and reading of a Herculaneum papyrus scroll (PHerc. 1667) via synchrotron X-ray CT, virtual unrolling, and machine learning.
-
SubsurfaceGen: Procedural Generation of Field-Scale Earth Models and Seismic Data
The paper introduces SubsurfaceGen, a procedural generator for field-scale 3D velocity models and seismic data, releases a dataset of 4276 2D slices from 42 models across six geological settings, and evaluates neural ...
-
BenchX: Benchmarking AI Models for Cancer Detection and Localization with Demographic and Protocol Biases
BenchX supplies an 85k-scan benchmark that exposes poor performance of 12 tumor-detection models on underrepresented demographic and protocol subgroups.
-
MonoUNet: A Robust Tiny Neural Network for Automated Knee Cartilage Segmentation on Point-of-Care Ultrasound Devices
MonoUNet achieves 92.62-94.82% Dice and 0.133-0.254 mm MASD on multi-device knee cartilage ultrasound while using 10-700x fewer parameters than prior lightweight models by adding a trainable monogenic phase block and ...
-
MonoUNet: A Robust Tiny Neural Network for Automated Knee Cartilage Segmentation on Point-of-Care Ultrasound Devices
MonoUNet is a tiny segmentation network that achieves 92-95% Dice scores on multi-device knee cartilage ultrasound while using 10-700x fewer parameters than prior lightweight models by injecting trainable local phase ...
-
GLOW-FDG: Generalized cancer LesiOn Whole-body segmentation model for $^{18}$F-FDG-PET/CT
An open multi-cancer FDG-PET/CT lesion segmentation model trained on 1,563 scans outperforms public benchmarks on 185 external scans with fewer false positives and robust TTB/TLG.
-
Towards Interactive Lesion Segmentation in Whole-Body PET/CT with Promptable Models
Adding click prompts encoded as Euclidean distance transforms to an nnU-Net improves interactive whole-body PET/CT lesion segmentation over Gaussian encodings and baseline autoPET III models.
-
Advanced Tumor Segmentation in PET/CT Imaging: A Training Strategy Study with nnU-Net for AutoPET III
nnU-Net with ResNet encoder, intensity normalization, batch dice loss, and CraveMix augmentation reaches Dice 0.80 and third place in AutoPET III.
-
AMO-ENE: Attention-based Multi-Omics Fusion Model for Outcome Prediction in Extra Nodal Extension and HPV-associated Oropharyngeal Cancer
An attention-based fusion model combining semi-supervised CT segmentation, radiomics, and clinical features predicts metastatic recurrence, overall survival, and disease-free survival in HPV+ oropharyngeal cancer with...
-
autoPET IV challenge: Incorporating organ supervision and human guidance for lesion segmentation in PET/CT
Combining tracer classification, organ supervision, and stochastic click sampling makes an nnU-Net model segment PET/CT lesions robustly without guidance and progressively better with clicks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.