International Journal of Computer Assisted Radiology and Surgery

Tissues margin-based analytical anisotropic algorithm boosting method via deep learning attention mechanism with cervical cancer

Speed and accuracy are two critical factors in dose calculation for radiotherapy. Analytical Anisotropic Algorithm (AAA) is a rapid dose calculation algorithm but has dose errors in tissue margin area. Acuros XB (AXB) has high accuracy but takes long time to calculate. To improve the dose accuracy on the tissue margin area for AAA, we proposed a novel deep learning-based dose accuracy improvement method using Margin-Net combined with Margin-Loss. A novel model 'Margin-Net' was designed with a Margin Attention Mechanism to generate special margin-related features. Margin-Loss was introduced to consider the dose errors and dose gradients in tissues margin area. Ninety-five VMAT cervical cancer cases with paired AAA and AXB dose were enrolled in our study: 76 cases for training and 19 cases for testing. Tissues Margin Masks were generated from RT contours with 6 mm extension. Tissues Margin Mask, AAA dose and CTs were input data; AXB dose was used as reference dose for model training and evaluation. Comparison experiments were performed to evaluated effectiveness of Margin-Net and Margin-Loss. Compared to AXB dose, the 3D gamma passing rate (1%/1 mm, 10% threshold) for 19 test cases 95.75 ± 1.05% using Margin-Net with Margin-Loss, which was significantly higher than the original AAA dose (73.64 ± 3.46%). The passing rate reduced to 94.07 ± 1.16% without Margin-Loss and 87.3 ± 1.18% if Margin-Net key structure 'MAM' was also removed. The proposed novel tissues margin-based dose conversion method can significantly improve the dose accuracy of Analytical Anisotropic Algorithm to be comparable to AXB algorithm. It can potentially improve the efficiency of treatment planning process with low demanding of computation resources.

Multi-task deep learning for automatic image segmentation and treatment response assessment in metastatic ovarian cancer

Abstract Purpose:  High-grade serous ovarian carcinoma (HGSOC) is characterised by significant spatial and temporal heterogeneity, often presenting at an advanced metastatic stage. One of the most common treatment approaches involves neoadjuvant chemotherapy (NACT), followed by surgery. However, the multi-scale complexity of HGSOC poses a major challenge in evaluating response to NACT. Methods:  Here, we present a multi-task deep learning approach that facilitates simultaneous segmentation of pelvic/ovarian and omental lesions in contrast-enhanced computerised tomography (CE-CT) scans, as well as treatment response assessment in metastatic ovarian cancer. The model combines multi-scale feature representations from two identical U-Net architectures, allowing for an in-depth comparison of CE-CT scans acquired before and after treatment. The network was trained using 198 CE-CT images of 99 ovarian cancer patients for predicting segmentation masks and evaluating treatment response. Results:  It achieves an AUC of 0.78 (95% CI [0.70–0.91]) in an independent cohort of 98 scans of 49 ovarian cancer patients from a different institution. In addition to the classification performance, the segmentation Dice scores are only slightly lower than the current state-of-the-art for HGSOC segmentation. Conclusion:  This work is the first to demonstrate the feasibility of a multi-task deep learning approach in assessing chemotherapy-induced tumour changes across the main disease burden of patients with complex multi-site HGSOC, which could be used for treatment response evaluation and disease monitoring.