C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation

Yu, Qihang; Yang, Dong; Roth, Holger R.; Bai, Yang; Zhang, Yixiao; Yuille, Alan; Xu, Daguang

doi:10.1109/cvpr42600.2020.00418

Cited by 141 publications

(92 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most 10 top teams used model ensembles to reduce outliers and improved their performance by collecting the consensus segmentation from separately trained models. This observation also shows that the training pipeline can potentially be further improved based on novel concepts like AutoML 59,60 or neural architectures search [61][62][63] algorithms.…”

Section: Performance Of Algorithmsmentioning

confidence: 80%

Rapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge

Roth¹,

Díez

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge - 2020.

show abstract

Section: Performance Of Algorithmsmentioning

confidence: 80%

Rapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge

Roth¹,

Díez

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Meanwhile, the pre-trained encoder can benefit the transfer learning of various medical imaging analysis tasks, such as classification and detection. In MSD pancreas segmentation task, Swin UNETR with pre-trained weights outperforms AutoML algorithms such as DiNTS [27] and C2FNAS [59] that are specifically designed for searching the optimal network architectures on the same segmentation task. Currently, Swin UNETR has only been pre-trained using CT images, and our experiments have not demonstrated enough transferability when applied directly to other medical imaging modalities such as MRI.…”

Section: Discussion and Limitationsmentioning

confidence: 99%

Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis

Tang¹,

Yang²,

Li³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Vision Transformers (ViT)s have shown great performance in self-supervised learning of global and local representations that can be transferred to downstream applications. Inspired by these results, we introduce a novel self-supervised learning framework with tailored proxy tasks for medical image analysis. Specifically, we propose: (i) a new 3D transformer-based model, dubbed Swin UNEt TRansformers (Swin UNETR), with a hierarchical encoder for self-supervised pre-training; (ii) tailored proxy tasks for learning the underlying pattern of human anatomy. We demonstrate successful pre-training of the proposed model on 5,050 publicly available computed tomography (CT) images from various body organs. The effectiveness of our approach is validated by fine-tuning the pre-trained models on the Beyond the Cranial Vault (BTCV) Segmentation Challenge with 13 abdominal organs and segmentation tasks from the Medical Segmentation Decathlon (MSD) dataset. Our model is currently the state-of-the-art (i.e. ranked 1st) on the public test leaderboards of both MSD 1 and BTCV 2 datasets. Code: https://monai.io/research/swin-unetr

show abstract

“…To investigate the interplay between image complexity, input downsampling, and network depth, we designed two baseline encoder-decoder networks: a light-weight (shallow) network (LW-Net) consisting of only 45 layers, and a deep (large-scale) network (LS-Net) with 10 times more layers. The reason for designing new architectures instead of using popular networks for medical image segmentation such as the U-Net variants [26], [27] and neural architecture search approaches [17], [19], [20] is computational constraints. The prevalent architectures in this domain are resource hungry and training such networks on typical hardware is not always feasible.…”

Section: Segmentation Networkmentioning

confidence: 99%

Leveraging Image Complexity in Macro-Level Neural Network Design for Medical Image Segmentation

Naqvi¹,

Meijering²

2021

Preprint

View full text Add to dashboard Cite

Recent progress in encoder-decoder neural network architecture design has led to significant performance improvements in a wide range of medical image segmentation tasks. However, state-of-the-art networks for a given task may be too computationally demanding to run on affordable hardware, and thus users often resort to practical workarounds by modifying various macro-level design aspects. Two common examples are downsampling of the input images and reducing the network depth to meet computer memory constraints. In this paper we investigate the effects of these changes on segmentation performance and show that image complexity can be used as a guideline in choosing what is best for a given dataset. We consider four statistical measures to quantify image complexity and evaluate their suitability on ten different public datasets. For the purpose of our experiments we also propose two new encoder-decoder architectures representing shallow and deep networks that are more memory efficient than currently popular networks. Our results suggest that median frequency is the best complexity measure in deciding about an acceptable input downsampling factor and network depth. For high-complexity datasets, a shallow network running on the original images may yield better segmentation results than a deep network running on downsampled images, whereas the opposite may be the case for low-complexity images.

show abstract

C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation

Cited by 141 publications

References 23 publications

Rapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge

Rapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge

Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis

Leveraging Image Complexity in Macro-Level Neural Network Design for Medical Image Segmentation

Contact Info

Product

Resources

About