Search

Byline: Keya. Amarsee, Prabhakar. Ramachandran, Andrew. Fielding, Margot. Lehman, Christopher. Noble, Ben. Perrett, Daryl. Ning Purpose: Fiducial marker seeds are often used as a surrogate to identify and track the [...]

Purpose: Optimizers are widely utilized across various domains to enhance desired outcomes by either maximizing or minimizing objective functions. In the context of deep learning, they help to minimize the loss function and improve model’s performance. This study aims to evaluate the accuracy of different optimizers employed for autosegmentation of non‑small cell lung cancer (NSCLC) target volumes on thoracic computed tomography images utilized in oncology. Materials and Methods: The study utilized 112 patients, comprising 92 patients from “The Cancer Imaging Archive” (TCIA) and 20 of our local clinical patients, to evaluate the efficacy of various optimizers. The gross tumor volume was selected as the foreground mask for training and testing the models. Of the 92 TCIA patients, 57 were used for training and validation, and the remaining 35 for testing using nnU‑Net. The performance of the final model was further evaluated on the 20 local clinical patient datasets. Six different optimizers, namely AdaDelta, AdaGrad, Adam, NAdam, RMSprop, and stochastic gradient descent(SGD), were investigated. To assess the agreement between the predicted volume and the ground truth, several metrics including Dice similarity coefficient (DSC), Jaccard index, sensitivity, precision, Hausdorff distance (HD), 95th percentile Hausdorff distance (HD95), and average symmetric surface distance (ASSD) were utilized. Results: The DSC values for AdaDelta, AdaGrad, Adam, NAdam, RMSprop, and SGD were 0.75, 0.84, 0.85, 0.84, 0.83, and 0.81, respectively, for the TCIA test data. However, when the model trained on TCIA datasets was applied to the clinical datasets, the DSC, HD, HD95, and ASSD metrics showed a statistically significant decrease in performance compared to the TCIA test datasets, indicating the presence of image and/or mask heterogeneity between the data sources. Conclusion: The choice of optimizer in deep learning is a critical factor that can significantly impact the performance of autosegmentation models. However, it is worth noting that the behavior of optimizers may vary when applied to new clinical datasets, which can lead to changes in models’ performance. Therefore, selecting the appropriate optimizer for a specific task is essential to ensure optimal performance and generalizability of the model to different datasets. [ABSTRACT FROM AUTHOR]

Aim: Current radiotherapy treatment techniques require a large amount of imaging data for treatment planning which demand significant clinician’s time to segment target volume and organs at risk (OARs). In this study, we propose to use U‑net‑based architecture to segment OARs commonly encountered in lung cancer radiotherapy. Materials and Methods: Four U‑Net OAR models were generated and trained on 20 lung cancer patients’ computed tomography(CT) datasets, with each trained for 100 epochs. The model was tested for each OAR, including the right lung, left lung, heart, and spinal cord. Dice similarity coefficient (DSC) and Hausdorff distance (HD) were used to assess the agreement between the predicted contour and ground truth. Results: The highest of the average DSC among the test patients for the left lung and the right lung was 0.96 ± 0.03 and 0.94 ± 0.06, respectively, and 0.88 ± 0.04 for heart, and 0.76 ± 0.07 for the spinal cord. The HD for these corresponding DSCs was 3.51 ± 0.85, 4.06 ± 1.12, 4.09 ± 0.85, and 2.76 ± 0.52 mm for left lung, right lung, heart, and spinal cord, respectively. Conclusion: The autosegmented regions predicted by right and left lung models matched well with the manual contours. However, in a few cases, the heart model struggled to outline the boundary precisely. The spinal cord model had the lowest DSC, which may be due to its small size. This is an ongoing study aimed to assist radiation oncologists in segmenting the OARs with minimal effort. [ABSTRACT FROM AUTHOR]

Aim: The aim of this study is to determine the variation in Hounsfield values with single and multi-slice methods using in-house software on fan-beam computed tomography (FCT), linear accelerator (linac) cone-beam computed tomography (CBCT), and Icon-CBCT datasets acquired using Gammex and advanced electron density (AED) phantoms. Materials and Methods: The AED phantom was scanned on a Toshiba computed tomography (CT) scanner, five linac-based CBCT X-ray volumetric imaging systems, and Leksell Gamma Knife Icon. The variation between single and multi-slice methods was assessed by comparing scans acquired using Gammex and AED phantoms. The variation in Hounsfield units (HUs) between seven different clinical protocols was assessed using the AED phantom. A CIRS Model 605 Radiosurgery Head Phantom (TED) phantom was scanned on all three imaging systems to assess the target dosimetric changes due to HU variation. An in-house software was developed in MATLAB to assess the HU statistics and the trend along the longitudinal axis. Results: The FCT dataset showed a minimal variation (central slice ± 3 HU) in HU values along the long axis. A similar trend was also observed between the studied clinical protocols acquired on FCT. Variation among multiple linac CBCTs was insignificant. In the case of the water insert, a maximum HU variation of -7.23 ± 68.67 was observed for Linac 1 towards the inferior end of the phantom. All five linacs appeared to have a similar trend in terms of HU variation from the proximal to the distal end of the phantom, with a few outliers for Linac 5. Among three imaging modalities, the maximum variation was observed in gamma knife CBCTs, whereas FCT showed no appreciable deviation from the central value. In terms of dosimetric comparison, the mean dose in CT and Linac CBCT scans differed by <0.5 Gy, whereas at least a 1 Gy difference was observed between CT and gamma knife CBCT. Conclusion: This study shows a minimal variation with FCT between single, volume-based, and multislice methods, and hence the current approach of determining the CT-electron density curve based on a single-slice method would be sufficient for producing a HU calibrations curve for treatment planning. However, CBCTs acquired on linac, and in particular, gamma knife systems, show noticeable variations along the long axis, which is likely to affect the dose calculations performed on CBCTs. It is highly recommended to assess the Hounsfield values on multiple slices before using the HU curve for dose calculations. [ABSTRACT FROM AUTHOR]