Delineating and sparing functional nephrons for radiotherapy in the case of lymphoma with polycystic kidney disease.

PURPOSE: It is imperative to spare functioning kidneys from high radiation doses when they are near enough to radiotherapy (RT) target volumes in patients with polycystic kidney disease (PKD). To achieve this intent, we designed the unique approach that we report here. METHODS AND MATERIALS: The patient who has PKD, presented with B-cell lymphoma involving paraaortic lymph nodes. After completing chemotherapy, RT was planned to the residual nodal disease. The diagnostic positron emission tomography computed tomography (PETCT) scan was fused with the RT planning CT scan. 18F-2-deoxy-2(F)-fluro-d-glucose (FDG) avid active kidneys were contoured separately, and the treatment plan was optimized to avoid these volumes. RESULTS: The functional volume was 17.52% of the right kidney whereas it was 7.44% of the left. The mean doses were 4.61 Gy and 4.2 Gy, respectively. The baseline estimated glomerular filtration rate (eGFR) was >60 mL/min; at 18 months follow-up, it was 62 mL/min. CONCLUSIONS: Delineation of functional nephrons was feasible while utilizing the staging FDG-PETCT scan for radiotherapy contouring in our patient, which aided to achieve the optimal dose-volume constraints. Further studies are warranted to analyze and quantify the benefit of this easily accessible method in the future.

Automatic segmentation of magnetic resonance images for high-dose-rate cervical cancer brachytherapy using deep learning.

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.

MRI Reduces Variation of Contouring for Boost Clinical Target Volume in Breast Cancer Patients Without Surgical Clips in the Tumour Bed.

BACKGROUND: Omitting 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 METHODS: CT- 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). RESULTS: Mean 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). CONCLUSIONS: When 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.

Off-line magnetic resonance imaging navigation of cervix cancer brachytherapy in patients with risk factors for uterine perforation.

PURPOSE: There are no reports on pre-insertion identification of cervix cancer patients at risk for uterine perforation during brachytherapy (BT). Our aim was to assess the incidence of risk factors in our patient cohort, and assess feasibility of a novel technique of magnetic resonance imaging (MRI)-guided navigation for applicator insertion (NAI) in high-risk cases. MATERIAL AND METHODS: All patients with locally advanced cervical cancer, treated with image guided adaptive BT at our department between October 2013 and June 2017 were considered for analysis. Tumor characteristics on initial MRI (MRIinitial), pre-BT MRI (MRIpre-BT), and BT MRI (MRIBT) were assessed. Frequency of risk factors (age above 60 years, retroverted/retroflected uterus, tumor necrosis, non-visible cervical orifice, distorted cervical canal) was recorded. Patients with two or more factors underwent MRI guided NAI. Time needed for NAI was estimated and procedure feasibility score assigned using a three-tiered scoring system. RESULTS: Twenty-seven patients (98 insertions) were included. Mean tumor volume was 70.2 (± 47.9), 17.8 (± 18.9), and 10.3 (± 9.1) cm3 on MRIinitial, MRIpre-BT, and MRIBT1, respectively (p < 0.05). In 16 (59%) cases, ≥ 1 perforation risk factor was found on MRIpre-BT: distorted canal in 12 (44%), necrosis in 9 (33%), retroverted/retroflected uterus in 8 (30%) cases. Nine (33%) patients had ≥ 2 risk factors and underwent MRI guided NAI. Additional time to perform NAI was estimated at 105 minutes, and feasibility score was 1 in all cases. There were no cases of uterine perforation. CONCLUSIONS: Using pre-insertion MRI, we found ≥ 2 risk factors for uterine perforation in 1/3 of patients. Off-line MRI navigation was feasible and enabled non-complicated insertion in all cases. Further studies with larger sample size are warranted to assess its clinical efficacy.