scholarly journals Automatic Segmentation of Clinical Target Volume and Organs-At-Risk for Breast Conservative Radiotherapy Using a Convolutional Neural Network

2021 ◽  
Author(s):  
Zhikai Liu ◽  
Fangjie Liu ◽  
Wanqi Chen ◽  
Yinjie Tao ◽  
Xia Liu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Spinal Cord ◽  
At Risk ◽  
Clinical Target Volume ◽  
Organs At Risk ◽  
Target Volume ◽  
Contralateral Breast ◽  
Dice Similarity Coefficient ◽  
Proposed Model ◽  
The Mean

Abstract Background and Objective: Delineation of the clinical target volume (CTV) and organs at risk (OARs) is very important for radiotherapy but is time-consuming and prone to inter- and intra-observer variation. We trained and evaluated a U-Net-based model to provide fast and consistent auto-segmentation for breast cancer radiotherapy. Methods: We collected 160 patients’ computed tomography (CT) scans with early-stage breast cancer who underwent breast-conserving surgery (BCS) and were treated with radiotherapy in our center. CTV and OARs (contralateral breast, heart, lungs and spinal cord) were delineated manually by two experienced radiation oncologists. The data were used for model training and testing. The dice similarity coefficient (DSC) and 95th Hausdorff distance (95HD) were used to assess the performance of our model. CTV and OARs were randomly selected as ground truth (GT) masks, and artificial intelligence (AI) masks were generated by the proposed model. The contours were randomly distributed to two clinicians to compare CTV score differences. The consistency between two clinicians was tested. We also evaluated time cost for auto-delineation. Results: The mean DSC values of the proposed method were 0.94, 0.95, 0.94, 0.96, 0.96 and 0.93 for breast CTV, contralateral breast, heart, right lung, left lung and spinal cord, respectively. The mean 95HD values were 4.31 mm, 3.59 mm, 4.86 mm, 3.18 mm, 2.79 mm and 4.37 mm for the above structures respectively. The average CTV scores for AI and GT were 2.92 versus 2.89 when evaluated by oncologist A (P=.612), and 2.75 versus 2.83 by oncologist B (P=.213), with no statistically significant differences. The consistency between two clinicians was poor (Kappa=0.282). The times for auto-segmentation of CTV and OARs were 3.88 s and 6.15 s. Conclusions: Our proposed model can improve the speed and accuracy of delineation compared with U-Net, while it performed equally well with the segmentation generated by oncologists.

Comparative dosimetry of brachytherapy treatment planning between a volume-based plan by CT and a point-based plan by TAUS in CT datasets for brachytherapy

2021 ◽  
pp. 1-8
Author(s):  
Chaiyaporn Pintakham ◽  
Ekkasit Tharavichitkul ◽  
Somsak Wanwilairat ◽  
Wannapha Nobnop
Keyword(s):  
At Risk ◽  
Treatment Planning ◽  
Sigmoid Colon ◽  
Clinical Target Volume ◽  
Organs At Risk ◽  
Target Volume ◽  
Reference Points ◽  
Uterine Perforation ◽  
Target Dose ◽  
The Mean

Abstract Aim: To evaluate comparative dosimetry of brachytherapy treatment planning between a volume-based plan by computed tomography (CT) and a point-based plan by transabdominal ultrasound (TAUS) in CT datasets for brachytherapy. Materials and methods: From 2019 to 2021, 59 different datasets of CT images were collected from 38 patients treated by intracavitary brachytherapy with tandem ovoid or tandem ring applicators. At that time, TAUS was performed to prevent uterine perforation and to evaluate topography of the cervix during application. In volume-based planning by CT, the target dose was used to keep the dose at 90% of high-risk clinical target volume (HR-CTV), to give a dose of at least 7Gy, while in the point-based plan by TAUS, the target dose was used to keep the minimum dose to eight cervix reference points (measured by TAUS), to give a dose of at least 7Gy. The doses to targets and organs at risk were evaluated and compared between volume-based planning by CT and the point-based plan by TAUS. Results: Of 59 fractions, a tandem ovoid applicator was used in 48 fractions (81·3%). In the volume-based plan by CT, the mean doses to HR-CTV(D90), intermediate-risk clinical target volume (IR-CTV)(D90), bladder(D2cc), rectum(D2cc) and sigmoid colon(D2cc) were 7·0, 3·9, 4·9, 2·9 and 3·3 Gy, respectively, while in the point-based plan by TAUS, the mean doses to HR-CTV(D90), IR-CTV(D90), bladder(D2cc), rectum(D2cc) and sigmoid colon(D2cc) were 8·2, 4·6, 5·9, 3·4 and 3·9 Gy, respectively. The percentages of mean dose differences between TAUS and CT of HR-CTV(D90), IR-CTV(D90), bladder(D2cc), rectum(D2cc) and sigmoid colon(D2cc) were 17·7, 19·5, 20·5, 19·5, 21·3 and 19·8%, respectively. With the target dose to the point-based plan by TAUS (7 Gy to the cervix reference points), this was close to D98 of HR-CTV with a mean percentage of difference of 0·6%. Findings: The point-based plan by TAUS showed higher values to targets and organs at risk than the volume-based plan by CT. With the point-based plan by TAUS, it was close to D98 of HR-CTV.

scholarly journals Clinical Validation and Treatment Plan Evaluation Based on Auto-Delineation of the Clinical Target Volume for Prostate Cancer Radiotherapy

2022 ◽  
Author(s):  
Jing Shen ◽  
Yinjie TAO ◽  
Hui GUAN ◽  
Hongnan ZHEN ◽  
Lei HE ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
At Risk ◽  
Organs At Risk ◽  
Treatment Plan ◽  
Statistical Significance ◽  
Locally Advanced ◽  
Target Volume ◽  
Ct Scans ◽  
Dice Similarity Coefficient ◽  
Treatment Plans

Abstract Purpose Clinical target volumes (CTV) and organs at risk (OAR) could be auto-contoured to save workload. The goal of this study was to assess a convolutional neural network (CNN) for totally automatic and accurate CTV and OAR in prostate cancer, while also comparing anticipated treatment plans based on auto-contouring CTV to clinical plans. Methods From January 2013 to January 2019, 217 computed tomography (CT) scans of patients with locally advanced prostate cancer treated at our hospital were collected and analyzed. CTV and OAR were delineated with a deep learning based method, which named CUNet. The performance of this strategy was evaluated using the mean Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (95HD), and subjective evaluation. Treatment plans were graded using predetermined evaluation criteria, and % errors for clinical doses to the planned target volume (PTV) and organs at risk(OARs) were calculated. Results The defined CTVs had mean DSC and 95HD values of 0.84 and 5.04 mm, respectively. For one patient's CT scans, the average delineation time was less than 15 seconds. When CTV outlines from CUNetwere blindly chosen and compared to GT, the overall positive rate in clinicians A and B was 53.15% vs 46.85%, and 54.05% vs 45.95%, respectively (P>0.05), demonstrating that our deep machine learning model performed as good as or better than human demarcation Furthermore, 8 testing patients were chosen at random to design the predicted plan based on the auto-courtoring CTV and OAR, demonstrating acceptable agreement with the clinical plan: average absolute dose differences of D2, D50, D98, Dmean for PTV are within 0.74%, and average absolute volume differences of V45, V50 for OARs are within 3.4%. Without statistical significance (p>0.05), the projected findings are comparable to clinical truth. Conclusion The experimental results show that the CTV and OARs defined by CUNet for prostate cancer were quite close to the ground reality.CUNet has the potential to cut radiation oncologists' contouring time in half. When compared to clinical plans, the differences between estimated doses to CTV and OAR based on auto-courtoring were small, with no statistical significance, indicating that treatment planning for prostate cancer based on auto-courtoring has potential.

Geometric contour variation in clinical target volume of axillary lymph nodes in breast cancer radiotherapy: an AIRO multi-institutional study

2021 ◽  
pp. 20201177
Author(s):  
Maria Cristina Leonardi ◽  
Matteo Pepa ◽  
Simone Giovanni Gugliandolo ◽  
Rosa Luraschi ◽  
Sabrina Vigorito ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Lymph Nodes ◽  
Clinical Target Volume ◽  
Target Volume ◽  
Radiotherapy Planning ◽  
Axillary Lymph Nodes ◽  
Dice Similarity Coefficient ◽  
Axillary Lymph ◽  
Computed Tomography Images ◽  
Breast Cancer Radiotherapy

Objectives: To determine interobserver variability in axillary nodal contouring in breast cancer (BC) radiotherapy (RT) by comparing the clinical target volume of participating single centres (SC-CTV) with a gold-standard CTV (GS-CTV). Methods: The GS-CTV of 3 patients (P1, P2, P3) with increasing complexity was created in DICOM format from the median contour of axillary CTVs drawn by BC experts, validated using the simultaneous truth and performance level estimation and peer-reviewed. GS-CTVs were compared with the correspondent SC-CTVs drawn by radiation oncologists, using validated metrics and a total score (TS) integrating all of them. Results: Eighteen RT centres participated in the study. Comparative analyses revealed that, on average, the SC-CTVs were smaller than GS-CTV for P1 and P2 (by −29.25% and −27.83%, respectively) and larger for P3 (by +12.53%). The mean Jaccard index was greater for P1 and P2 compared to P3, but the overlap extent value was around 0.50 or less. Regarding nodal levels, L4 showed the highest concordance with the GS. In the intra patient comparison, L2 and L3 achieved lower TS than L4. Nodal levels showed discrepancy with GS which was not statistically significant for P1, and negligible for P2, while P3 had the worst agreement. DICE Similarity Coefficient did not exceed the minimum threshold for agreement of 0.70 in all the measurements. Conclusions: Substantial differences were observed between SC- and GS-CTV, especially for P3 with altered arm set-up. L2 and L3 were the most critical levels. The study highlighted these key points to address. Advances in knowledge The present study compares, by means of validated geometric indexes, manual segmentationsof axillary lymph nodes in breast cancer from different observers and different institutionsmade on radiotherapy planning computed tomography images. Assessing such variability is ofparamount importance, as geometric uncertainties might lead to incorrect dosimetry andcompromise oncological outcome.

scholarly journals Impact of cervicothoracic region stereotactic spine radiosurgery on adjacent organs at risk

2017 ◽  
Vol 42 (1) ◽  
pp. E14 ◽  
Author(s):  
Mayur Sharma ◽  
Elizabeth E. Bennett ◽  
Gazanfar Rahmathulla ◽  
Samuel T. Chao ◽  
Hilary K. Koech ◽  
...  
Keyword(s):  
Spinal Cord ◽  
At Risk ◽  
Radiation Dose ◽  
Brachial Plexus ◽  
Organs At Risk ◽  
Cleveland Clinic ◽  
Compression Fracture ◽  
Target Volume ◽  
Tumor Control ◽  
Radiation Toxicity

OBJECTIVE Stereotactic radiosurgery (SRS) of the spine is a conformal method of delivering a high radiation dose to a target in a single or few (usually ≤ 5) fractions with a sharp fall-off outside the target volume. Although efforts have been focused on evaluating spinal cord tolerance when treating spinal column metastases, no study has formally evaluated toxicity to the surrounding organs at risk (OAR), such as the brachial plexus or the oropharynx, when performing SRS in the cervicothoracic region. The aim of this study was to evaluate the radiation dosimetry and the acute and delayed toxicities of SRS on OAR in such patients. METHODS Fifty-six consecutive patients (60 procedures) with a cervicothoracic spine tumor involving segments within C5–T1 who were treated using single-fraction SRS between February 2006 and July 2014 were included in the study. Each patient underwent CT simulation and high-definition MRI before treatment. The clinical target volume and OAR were contoured on BrainScan and iPlan software after image fusion. Radiation toxicity was evaluated using the common toxicity criteria for adverse events and correlated to the radiation doses delivered to these regions. The incidence of vertebral body compression fracture (VCF) before and after SRS was evaluated also. RESULTS Metastatic lesions constituted the majority (n = 52 [93%]) of tumors treated with SRS. Each patient was treated with a median single prescription dose of 16 Gy to the target. The median percentage of tumor covered by SRS was 93% (maximum target dose 18.21 Gy). The brachial plexus received the highest mean maximum dose of 17 Gy, followed by the esophagus (13.8 Gy) and spinal cord (13 Gy). A total of 14 toxicities were encountered in 56 patients (25%) during the study period. Overall, 14% (n = 8) of the patients had Grade 1 toxicity, 9% (n = 5) had Grade 2 toxicity, 2% (n = 1) had Grade 3 toxicity, and none of the patients had Grade 4 or 5 toxicity. The most common (12%) toxicity was dysphagia/odynophagia, followed by axial spine pain flare or painful radiculopathy (9%). The maximum radiation dose to the brachial plexus showed a trend toward significance (p = 0.066) in patients with worsening post-SRS pain. De novo and progressive VCFs after SRS were noted in 3% (3 of 98) and 4% (4 of 98) of vertebral segments, respectively. CONCLUSIONS From the analysis, the current SRS doses used at the Cleveland Clinic seem safe and well tolerated at the cervicothoracic junction. These preliminary data provide tolerance benchmarks for OAR in this region. Because the effect of dose-escalation SRS strategies aimed at improving local tumor control needs to be balanced carefully with associated treatment-related toxicity on adjacent OAR, larger prospective studies using such approaches are needed.

Sign in / Sign up

Export Citation Format

Share Document