Assessment of heart-substructures auto-contouring accuracy for application in heart-sparing radiotherapy for lung cancer.

Objectives: We validated an auto-contouring algorithm for heart substructures in lung cancer patients, aiming to establish its accuracy and reliability for radiotherapy (RT) planning. We focus on contouring an amalgamated set of subregions in the base of the heart considered to be a new organ at risk, the cardiac avoidance area (CAA), to enable maximum dose limit implementation in lung RT planning. Methods: The study validates a deep-learning model specifically adapted for auto-contouring the CAA (which includes the right atrium, aortic valve root, and proximal segments of the left and right coronary arteries). Geometric, dosimetric, quantitative, and qualitative validation measures are reported. Comparison with manual contours, including assessment of interobserver variability, and robustness testing over 198 cases are also conducted. Results: Geometric validation shows that auto-contouring performance lies within the expected range of manual observer variability despite being slightly poorer than the average of manual observers (mean surface distance for CAA of 1.6 vs 1.2 mm, dice similarity coefficient of 0.86 vs 0.88). Dosimetric validation demonstrates consistency between plans optimized using auto-contours and manual contours. Robustness testing confirms acceptable contours in all cases, with 80% rated as "Good" and the remaining 20% as "Useful." Conclusions: The auto-contouring algorithm for heart substructures in lung cancer patients demonstrates acceptable and comparable performance to human observers. Advances in knowledge: Accurate and reliable auto-contouring results for the CAA facilitate the implementation of a maximum dose limit to this region in lung RT planning, which has now been introduced in the routine setting at our institution.

Low muscle mass measured at T12 is a prognostic biomarker in unresectable oesophageal cancers receiving chemoradiotherapy.

BACKGROUND AND PURPOSE: Low muscle mass is an imaging biomarker of patient frailty that has been associated with increased toxicity and decreased survival in a number of cancers. Patients with unresectable oesophageal cancer receive chemoradiotherapy as standard of care. Muscle mass is not yet an established prognostic marker in this population. Muscle mass is usually assessed by segmenting skeletal muscle at the L3 vertebral level. But radiotherapy planning scans for oesophageal cancers do not always image this level, which has limited previous studies of body composition. Skeletal muscle is known to regulate immune function, but the association of muscle mass with lymphopenia in cancer patients has not been shown. MATERIALS AND METHODS: We retrospectively analyse 135 oesophageal cancer patients who received chemoradiotherapy and investigate the prognostic value of skeletal muscle area assessed at T12. We also examine the association between muscle mass and radiation-induced lymphopenia. RESULTS: We find that low muscle mass is associated with poorer overall survival (hazard ratio [95% confidence interval]: 0.72 [0.53-0.97]). However, this effect interacts with body mass index (BMI) such that the prognostic value of low muscle mass is removed by high BMI. In our study, patients with low muscle mass were more prone to radiation-induced lymphopenia (75% vs. 50% in patients with high muscle mass). A significant decrease in circulating lymphocytes was associated with poorer overall survival (hazard ratio [95% confidence interval]: 0.68 [0.47-0.99]). CONCLUSION: Our study shows that assessing muscle mass at T12 is feasible and provides prognostic information. Low muscle mass at T12 is associated with poorer overall survival and increased risk of radiation-induced lymphopenia. Muscle mass provides additional information over performance status and BMI. Low BMI patients are most affected by low muscle mass, highlighting the importance of close nutritional support in this population.

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.