BackgroundOmitting the placement of clips inside tumour bed during breast cancer surgery poses a challenge for delineation of lumpectomy cavity clinical target volume (CTVLC). We aimed to quantify inter-observer variation and accuracy for CT- and MRI-based segmentation of CTVLC in patients without clips.Patients and methodsCT- and MRI-simulator images of 12 breast cancer patients, treated by breast conserving surgery and radiotherapy, were included in this study. Five radiation oncologists recorded the cavity visualization score (CVS) and delineated CTVLC on both modalities. Expert-consensus (EC) contours were delineated by a senior radiation oncologist, respecting opinions of all observers. Inter-observer volumetric variation and generalized conformity index (CIgen) were calculated. Deviations from EC contour were quantified by the accuracy index (AI) and inter-delineation distances (IDD).ResultsMean CVS was 3.88 +/− 0.99 and 3.05 +/− 1.07 for MRI and CT, respectively (p = 0.001). Mean volumes of CTVLC were similar: 154 +/− 26 cm3 on CT and 152 +/− 19 cm3 on MRI. Mean CIgen and AI were superior for MRI when compared with CT (CIgen: 0.74 +/− 0.07 vs. 0.67 +/− 0.12, p = 0.007; AI: 0.81 +/− 0.04 vs. 0.76 +/− 0.07; p = 0.004). CIgen and AI increased with increasing CVS. Mean IDD was 3 mm +/− 1.5 mm and 3.6 mm +/− 2.3 mm for MRI and CT, respectively (p = 0.017).ConclusionsWhen compared with CT, MRI improved visualization of post-lumpectomy changes, reduced interobserver variation and improved the accuracy of CTVLC contouring in patients without clips in the tumour bed. Further studies with bigger sample sizes are needed to confirm our findings.
Purpose Magnetic resonance (MR) imaging is the gold standard in image‐guided brachytherapy (IGBT) due to its superior soft‐tissue contrast for target and organs‐at‐risk (OARs) delineation. Accurate and fast segmentation of MR images are very important for high‐quality IGBT treatment planning. The purpose of this work is to implement and evaluate deep learning (DL) models for the automatic segmentation of targets and OARs in MR image‐based high‐dose‐rate (HDR) brachytherapy for cervical cancer. Methods A 2D DL model using residual neural network architecture (ResNet50) was developed to contour the targets (gross tumor volume (GTV), high‐risk clinical target volume (HR CTV), and intermediate‐risk clinical target volume (IR CTV)) and OARs (bladder, rectum, sigmoid, and small intestine) automatically on axial MR slices of HDR brachytherapy patients. Furthermore, two additional 2D DL models using sagittal and coronal images were also developed. A 2.5D model was generated by combining the outputs from axial, sagittal, and coronal DL models. Similarly, a 2D and 2.5D DL models were also generated for the inception residual neural network (InceptionResNetv2 (InRN)) architecture. The geometric (Dice similarity coefficient (DSCs) and 95th percentile of Hausdorff distance (HD)) and dosimetric accuracy of 2D (axial only) and 2.5D (axial + sagittal + coronal) DL model generated contours were calculated and compared. Results The mean (range) DSCs of ResNet50 across all contours were 0.674 (0.05–0.96) and 0.715 (0.26–0.96) for the 2D and 2.5D models, respectively. For InRN, these were 0.676 (0.11–0.96) and 0.723 (0.35–0.97) for the 2D and 2.5D models, respectively. The mean HD of ResNet50 across all contours was 15.6 mm (1.8–69 mm) and 12.1 mm (1.7–44 mm) for the 2D and 2.5D models, respectively. The similar results for InRN were 15.4 mm (2–68 mm) and 10.3 mm (2.7–39 mm) for the 2D and 2.5D models, respectively. The dosimetric parameters (D90) of GTV and HR CTV for manually contoured plans matched better with the 2.5D model (p > 0.6) and the results from the 2D model were slightly lower (p < 0.08). On the other hand, the IR CTV doses (D90) for all of the models were slightly lower (2D: ‐1.3 to ‐1.5 Gy and 2.5D: ‐0.5 to ‐0.6 Gy) and the differences were statistically significant for the 2D model (2D: p < 0.000002 and 2.5D: p > 0.06). In case of OARs, the 2.5D model segmentations resulted in closer dosimetry than 2D models (2D: p = 0.07–0.91 and 2.5D: p = 0.16–1.0). Conclusions The 2.5D DL models outperformed their respective 2D models for the automatic contouring of targets and OARs in MR image‐based HDR brachytherapy for cervical cancer. The InceptionResNetv2 model performed slightly better than ResNet50.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.