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.
-
ItemTherapeutic options for mucinous ovarian carcinoma(ACADEMIC PRESS INC ELSEVIER SCIENCE, 2020-03)OBJECTIVE: Mucinous ovarian carcinoma (MOC) is an uncommon ovarian cancer histotype that responds poorly to conventional chemotherapy regimens. Although long overall survival outcomes can occur with early detection and optimal surgical resection, recurrent and advanced disease are associated with extremely poor survival. There are no current guidelines specifically for the systemic management of recurrent MOC. We analyzed data from a large cohort of women with MOC to evaluate the potential for clinical utility from a range of systemic agents. METHODS: We analyzed gene copy number (n = 191) and DNA sequencing data (n = 184) from primary MOC to evaluate signatures of mismatch repair deficiency and homologous recombination deficiency, and other genetic events. Immunohistochemistry data were collated for ER, CK7, CK20, CDX2, HER2, PAX8 and p16 (n = 117-166). RESULTS: Molecular aberrations noted in MOC that suggest a match with current targeted therapies include amplification of ERBB2 (26.7%) and BRAF mutation (9%). Observed genetic events that suggest potential efficacy for agents currently in clinical trials include: KRAS/NRAS mutations (66%), TP53 missense mutation (49%), RNF43 mutation (11%), ARID1A mutation (10%), and PIK3CA/PTEN mutation (9%). Therapies exploiting homologous recombination deficiency (HRD) may not be effective in MOC, as only 1/191 had a high HRD score. Mismatch repair deficiency was similarly rare (1/184). CONCLUSIONS: Although genetically diverse, MOC has several potential therapeutic targets. Importantly, the lack of response to platinum-based therapy observed clinically corresponds to the lack of a genomic signature associated with HRD, and MOC are thus also unlikely to respond to PARP inhibition.