Deep learning-based automatic segmentation of cardiac substructures for lung cancers.

PURPOSE: Accurate and comprehensive segmentation of cardiac substructures is crucial for minimizing the risk of radiation-induced heart disease in lung cancer radiotherapy. We sought to develop and validate deep learning-based auto-segmentation models for cardiac substructures. MATERIALS AND METHODS: Nineteen cardiac substructures (whole heart, 4 heart chambers, 6 great vessels, 4 valves, and 4 coronary arteries) in 100 patients treated for non-small cell lung cancer were manually delineated by two radiation oncologists. The valves and coronary arteries were delineated as planning risk volumes. An nnU-Net auto-segmentation model was trained, validated, and tested on this dataset with a split ratio of 75:5:20. The auto-segmented contours were evaluated by comparing them with manually drawn contours in terms of Dice similarity coefficient (DSC) and dose metrics extracted from clinical plans. An independent dataset of 42 patients was used for subjective evaluation of the auto-segmentation model by 4 physicians. RESULTS: The average DSCs were 0.95 (+/- 0.01) for the whole heart, 0.91 (+/- 0.02) for 4 chambers, 0.86 (+/- 0.09) for 6 great vessels, 0.81 (+/- 0.09) for 4 valves, and 0.60 (+/- 0.14) for 4 coronary arteries. The average absolute errors in mean/max doses to all substructures were 1.04 (+/- 1.99) Gy and 2.20 (+/- 4.37) Gy. The subjective evaluation revealed that 94% of the auto-segmented contours were clinically acceptable. CONCLUSION: We demonstrated the effectiveness of our nnU-Net model for delineating cardiac substructures, including coronary arteries. Our results indicate that this model has promise for studies regarding radiation dose to cardiac substructures.

Automated Contouring and Planning in Radiation Therapy: What Is 'Clinically Acceptable'?

Developers and users of artificial-intelligence-based tools for automatic contouring and treatment planning in radiotherapy are expected to assess clinical acceptability of these tools. However, what is 'clinical acceptability'? Quantitative and qualitative approaches have been used to assess this ill-defined concept, all of which have advantages and disadvantages or limitations. The approach chosen may depend on the goal of the study as well as on available resources. In this paper, we discuss various aspects of 'clinical acceptability' and how they can move us toward a standard for defining clinical acceptability of new autocontouring and planning tools.

Multi-organ segmentation of abdominal structures from non-contrast and contrast enhanced CT images.

Manually delineating upper abdominal organs at risk (OARs) is a time-consuming task. To develop a deep-learning-based tool for accurate and robust auto-segmentation of these OARs, forty pancreatic cancer patients with contrast-enhanced breath-hold computed tomographic (CT) images were selected. We trained a three-dimensional (3D) U-Net ensemble that automatically segments all organ contours concurrently with the self-configuring nnU-Net framework. Our tool's performance was assessed on a held-out test set of 30 patients quantitatively. Five radiation oncologists from three different institutions assessed the performance of the tool using a 5-point Likert scale on an additional 75 randomly selected test patients. The mean (± std. dev.) Dice similarity coefficient values between the automatic segmentation and the ground truth on contrast-enhanced CT images were 0.80 ± 0.08, 0.89 ± 0.05, 0.90 ± 0.06, 0.92 ± 0.03, 0.96 ± 0.01, 0.97 ± 0.01, 0.96 ± 0.01, and 0.96 ± 0.01 for the duodenum, small bowel, large bowel, stomach, liver, spleen, right kidney, and left kidney, respectively. 89.3% (contrast-enhanced) and 85.3% (non-contrast-enhanced) of duodenum contours were scored as a 3 or above, which required only minor edits. More than 90% of the other organs' contours were scored as a 3 or above. Our tool achieved a high level of clinical acceptability with a small training dataset and provides accurate contours for treatment planning.

Radiomics features of the primary tumor fail to improve prediction of overall survival in large cohorts of CT- and PET-imaged head and neck cancer patients.

Radiomics studies require many patients in order to power them, thus patients are often combined from different institutions and using different imaging protocols. Various studies have shown that imaging protocols affect radiomics feature values. We examined whether using data from cohorts with controlled imaging protocols improved patient outcome models. We retrospectively reviewed 726 CT and 686 PET images from head and neck cancer patients, who were divided into training or independent testing cohorts. For each patient, radiomics features with different preprocessing were calculated and two clinical variables-HPV status and tumor volume-were also included. A Cox proportional hazards model was built on the training data by using bootstrapped Lasso regression to predict overall survival. The effect of controlled imaging protocols on model performance was evaluated by subsetting the original training and independent testing cohorts to include only patients whose images were obtained using the same imaging protocol and vendor. Tumor volume, HPV status, and two radiomics covariates were selected for the CT model, resulting in an AUC of 0.72. However, volume alone produced a higher AUC, whereas adding radiomics features reduced the AUC. HPV status and one radiomics feature were selected as covariates for the PET model, resulting in an AUC of 0.59, but neither covariate was significantly associated with survival. Limiting the training and independent testing to patients with the same imaging protocol reduced the AUC for CT patients to 0.55, and no covariates were selected for PET patients. Radiomics features were not consistently associated with survival in CT or PET images of head and neck patients, even within patients with the same imaging protocol.

Knee and Hip Joint Cartilage Damage from Combined Spaceflight Hazards of Low-Dose Radiation Less than 1 Gy and Prolonged Hindlimb Unloading.

Reduced weight bearing, and to a lesser extent radiation, during spaceflight have been shown as potential hazards to astronaut joint health. These hazards combined effect to the knee and hip joints are not well defined, particularly with low-dose exposure to radiation. In this study, we examined the individual and combined effects of varying low-dose radiation (≤1 Gy) and reduced weight bearing on the cartilage of the knee and hip joints. C57BL/6J mice (n = 80) were either tail suspended via hindlimb unloading (HLU) or remained full-weight bearing (ground). On day 6, each group was divided and irradiated with 0 Gy (sham), 0.1 Gy, 0.5 Gy or 1.0 Gy (n = 10/group), yielding eight groups: ground-sham; ground-0.1 Gy; ground-0.5 Gy; ground-1.0 Gy; HLU-sham; HLU-0.1 Gy; HLU-0.5 Gy; and HLU-1.0 Gy. On day 30, the hindlimbs, hip cartilage and serum were collected from the mice. Significant differences were identified statistically between treatment groups and the ground-sham control group, but no significant differences were observed between HLU and/or radiation groups. Contrast-enhanced micro-computed tomography (microCECT) demonstrated decrease in volume and thickness at the weight-bearing femoral-tibial cartilage-cartilage contact point in all treatment groups compared to ground-sham. Lower collagen was observed in all groups compared to ground-sham. Circulating serum cartilage oligomeric matrix protein (sCOMP), a biomarker for ongoing cartilage degradation, was increased in all of the irradiated groups compared to ground-sham, regardless of unloading. Mass spectrometry of the cartilage lining the femoral head and subsequent Ingenuity Pathway Analysis (IPA) identified a decrease in cartilage compositional proteins indicative of osteoarthritis. Our findings demonstrate that both individually and combined, HLU and exposure to spaceflight relevant radiation doses lead to cartilage degradation of the knee and hip with expression of an arthritic phenotype. Moreover, early administration of low-dose irradiation (0.1, 0.5 or 1.0 Gy) causes an active catabolic response in cartilage 24 days postirradiation. Further research is warranted with a focus on the prevention of cartilage degradation from long-term periods of reduced weight bearing and spaceflight-relevant low doses and qualities of radiation.

Operational consistency of medical linear accelerators manufactured and commissioned in series.

The purpose of this study was to determine if medical linear accelerators (linac) produced by the same manufacturer exhibit operational consistency within their subsystems and components. Two linacs that were commissioned together and installed at the same facility were monitored. Each machine delivered a daily robust quality assurance (QA) irradiation. Linacs and their components operate consistently, but have different operational parameter levels even when produced by the same manufacturer and commissioned in series. These findings have implications on the feasibility of true clinical beam matching.