Sir Peter MacCallum Department of Oncology - Research Publications
Permanent URI for this collection
Search Results
1 - 2 of 2
-
ItemA Deep Learning Model to Automate Skeletal Muscle Area Measurement on Computed Tomography Images(FRONTIERS MEDIA SA, 2021-05-07)BACKGROUND: Muscle wasting (Sarcopenia) is associated with poor outcomes in cancer patients. Early identification of sarcopenia can facilitate nutritional and exercise intervention. Cross-sectional skeletal muscle (SM) area at the third lumbar vertebra (L3) slice of a computed tomography (CT) image is increasingly used to assess body composition and calculate SM index (SMI), a validated surrogate marker for sarcopenia in cancer. Manual segmentation of SM requires multiple steps, which limits use in routine clinical practice. This project aims to develop an automatic method to segment L3 muscle in CT scans. METHODS: Attenuation correction CTs from full body PET-CT scans from patients enrolled in two prospective trials were used. The training set consisted of 66 non-small cell lung cancer (NSCLC) patients who underwent curative intent radiotherapy. An additional 42 NSCLC patients prescribed curative intent chemo-radiotherapy from a second trial were used for testing. Each patient had multiple CT scans taken at different time points prior to and post- treatment (147 CTs in the training and validation set and 116 CTs in the independent testing set). Skeletal muscle at L3 vertebra was manually segmented by two observers, according to the Alberta protocol to serve as ground truth labels. This included 40 images segmented by both observers to measure inter-observer variation. An ensemble of 2.5D fully convolutional neural networks (U-Nets) was used to perform the segmentation. The final layer of U-Net produced the binary classification of the pixels into muscle and non-muscle area. The model performance was calculated using Dice score and absolute percentage error (APE) in skeletal muscle area between manual and automated contours. RESULTS: We trained five 2.5D U-Nets using 5-fold cross validation and used them to predict the contours in the testing set. The model achieved a mean Dice score of 0.92 and an APE of 3.1% on the independent testing set. This was similar to inter-observer variation of 0.96 and 2.9% for mean Dice and APE respectively. We further quantified the performance of sarcopenia classification using computer generated skeletal muscle area. To meet a clinical diagnosis of sarcopenia based on Alberta protocol the model achieved a sensitivity of 84% and a specificity of 95%. CONCLUSIONS: This work demonstrates an automated method for accurate and reproducible segmentation of skeletal muscle area at L3. This is an efficient tool for large scale or routine computation of skeletal muscle area in cancer patients which may have applications on low quality CTs acquired as part of PET/CT studies for staging and surveillance of patients with cancer.
-
ItemSingle-arm prospective interventional study assessing feasibility of using gallium-68 ventilation and perfusion PET/CT to avoid functional lung in patients with stage III non-small cell lung cancer(BMJ PUBLISHING GROUP, 2020)BACKGROUND: In the curative-intent treatment of locally advanced lung cancer, significant morbidity and mortality can result from thoracic radiation therapy. Symptomatic radiation pneumonitis occurs in one in three patients and can lead to radiation-induced fibrosis. Local failure occurs in one in three patients due to the lungs being a dose-limiting organ, conventionally restricting tumour doses to around 60 Gy. Functional lung imaging using positron emission tomography (PET)/CT provides a geographic map of regional lung function and preclinical studies suggest this enables personalised lung radiotherapy. This map of lung function can be integrated into Volumetric Modulated Arc Therapy (VMAT) radiotherapy planning systems, enabling conformal avoidance of highly functioning regions of lung, thereby facilitating increased doses to tumour while reducing normal tissue doses. METHODS AND ANALYSIS: This prospective interventional study will investigate the use of ventilation and perfusion PET/CT to identify highly functioning lung volumes and avoidance of these using VMAT planning. This single-arm trial will be conducted across two large public teaching hospitals in Australia. Twenty patients with stage III non-small cell lung cancer will be recruited. All patients enrolled will receive dose-escalated (69 Gy) functional avoidance radiation therapy. The primary endpoint is feasibility with this achieved if ≥15 out of 20 patients meet pre-defined feasibility criteria. Patients will be followed for 12 months post-treatment with serial imaging, biomarkers, toxicity assessment and quality of life assessment. DISCUSSION: Using advanced techniques such as VMAT functionally adapted radiation therapy may enable safe moderate dose escalation with an aim of improving local control and concurrently decreasing treatment related toxicity. If this technique is proven feasible, it will inform the design of a prospective randomised trial to assess the clinical benefits of functional lung avoidance radiation therapy. ETHICS AND DISSEMINATION: This study was approved by the Peter MacCallum Human Research Ethics Committee. All participants will provide written informed consent. Results will be disseminated via publications. TRIALS REGISTRATION NUMBER: NCT03569072; Pre-results.