Fast and Low-GPU-memory abdomen CT organ segmentation: The FLARE challenge.

Automatic segmentation of abdominal organs in CT scans plays an important role in clinical practice. However, most existing benchmarks and datasets only focus on segmentation accuracy, while the model efficiency and its accuracy on the testing cases from different medical centers have not been evaluated. To comprehensively benchmark abdominal organ segmentation methods, we organized the first Fast and Low GPU memory Abdominal oRgan sEgmentation (FLARE) challenge, where the segmentation methods were encouraged to achieve high accuracy on the testing cases from different medical centers, fast inference speed, and low GPU memory consumption, simultaneously. The winning method surpassed the existing state-of-the-art method, achieving a 19× faster inference speed and reducing the GPU memory consumption by 60% with comparable accuracy. We provide a summary of the top methods, make their code and Docker containers publicly available, and give practical suggestions on building accurate and efficient abdominal organ segmentation models. The FLARE challenge remains open for future submissions through a live platform for benchmarking further methodology developments at https://flare.grand-challenge.org/.

Transfer learning for data-efficient abdominal muscle segmentation with convolutional neural networks.

BACKGROUND: Skeletal muscle segmentation is an important procedure for assessing sarcopenia, an emerging imaging biomarker of patient frailty. Data annotation remains the bottleneck for training deep learning auto-segmentation models. PURPOSE: There is a need to define methodologies for applying models to different domains (e.g., anatomical regions or imaging modalities) without dramatically increasing data annotation. METHODS: To address this problem, we empirically evaluate the generalizability of various source tasks for transfer learning: natural image classification, natural image segmentation, unsupervised image reconstruction, and self-supervised jigsaw solving. Axial CT slices at L3 were extracted from PET-CT scans for 204 oesophago-gastric cancer patients and the skeletal muscle manually delineated by an expert. Features were transferred and segmentation models trained on subsets ( n = 5 , 10 , 25 , 50 , 75 , 100 , 125 $n=5,10,25,50,75,100,125$ ) of the manually annotated training set. Four-fold cross-validation was performed to evaluate model generalizability. Human-level performance was established by performing an inter-observer study consisting of ten trained radiographers. RESULTS: We find that accurate segmentation models can be trained on a fraction of the data required by current approaches. The Dice similarity coefficient and root mean square distance-to-agreement were calculated for each prediction and used to assess model performance. Models pre-trained on a segmentation task and fine-tuned on 10 images produce delineations that are comparable to those from trained observers and extract reliable measures of muscle health. CONCLUSIONS: Appropriate transfer learning can generate convolutional neural networks for abdominal muscle segmentation that achieve human-level performance while decreasing the required data by an order of magnitude, compared to previous methods ( n = 160 → 10 $n=160 \rightarrow 10$ ). This work enables the development of future models for assessing skeletal muscle at other anatomical sites where large annotated data sets are scarce and clinical needs are yet to be addressed.

A self-supervised workflow for particle picking in cryo-EM.

High-resolution single-particle cryo-EM data analysis relies on accurate particle picking. To facilitate the particle picking process, a self-supervised workflow has been developed. This includes an iterative strategy, which uses a 2D class average to improve training particles, and a progressively improved convolutional neural network for particle picking. To automate the selection of particles, a threshold is defined (%/Res) using the ratio of percentage class distribution and resolution as a cutoff. This workflow has been tested using six publicly available data sets with different particle sizes and shapes, and can automatically pick particles with minimal user input. The picked particles support high-resolution reconstructions at 3.0 Šor better. This workflow is a step towards automated single-particle cryo-EM data analysis at the stage of particle picking. It may be used in conjunction with commonly used single-particle analysis packages such as Relion, cryoSPARC, cisTEM, SPHIRE and EMAN2.