scholarly journals Evaluation of auto-segmentation accuracy of cloud-based artificial intelligence and atlas-based models

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Yuka Urago ◽  
Hiroyuki Okamoto ◽  
Tomoya Kaneda ◽  
Naoya Murakami ◽  
Tairo Kashihara ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Head And Neck Cancer ◽  
Head And Neck ◽  
Neck Cancer ◽  
Organs At Risk ◽  
Observer Variation ◽  
Dice Similarity Coefficient ◽  
Visual Evaluation ◽  
Significant Difference

Abstract Background Contour delineation, a crucial process in radiation oncology, is time-consuming and inaccurate due to inter-observer variation has been a critical issue in this process. An atlas-based automatic segmentation was developed to improve the delineation efficiency and reduce inter-observer variation. Additionally, automated segmentation using artificial intelligence (AI) has recently become available. In this study, auto-segmentations by atlas- and AI-based models for Organs at Risk (OAR) in patients with prostate and head and neck cancer were performed and delineation accuracies were evaluated. Methods Twenty-one patients with prostate cancer and 30 patients with head and neck cancer were evaluated. MIM Maestro was used to apply the atlas-based segmentation. MIM Contour ProtégéAI was used to apply the AI-based segmentation. Three similarity indices, the Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean distance to agreement (MDA), were evaluated and compared with manual delineations. In addition, radiation oncologists visually evaluated the delineation accuracies. Results Among patients with prostate cancer, the AI-based model demonstrated higher accuracy than the atlas-based on DSC, HD, and MDA for the bladder and rectum. Upon visual evaluation, some errors were observed in the atlas-based delineations when the boundary between the small bowel or the seminal vesicle and the bladder was unclear. For patients with head and neck cancer, no significant differences were observed between the two models for almost all OARs, except small delineations such as the optic chiasm and optic nerve. The DSC tended to be lower when the HD and the MDA were smaller in small volume delineations. Conclusions In terms of efficiency, the processing time for head and neck cancers was much shorter than manual delineation. While quantitative evaluation with AI-based segmentation was significantly more accurate than atlas-based for prostate cancer, there was no significant difference for head and neck cancer. According to the results of visual evaluation, less necessity of manual correction in AI-based segmentation indicates that the segmentation efficiency of AI-based model is higher than that of atlas-based model. The effectiveness of the AI-based model can be expected to improve the segmentation efficiency and to significantly shorten the delineation time.

scholarly journals Clinical Enhancement in AI-Based Post-processed Fast-Scan Low-Dose CBCT for Head and Neck Adaptive Radiotherapy

2021 ◽  
Vol 3 ◽  
Author(s):  
Wen Chen ◽  
Yimin Li ◽  
Nimu Yuan ◽  
Jinyi Qi ◽  
Brandon A. Dyer ◽  
...  
Keyword(s):  
At Risk ◽  
Head And Neck Cancer ◽  
Head And Neck ◽  
Neck Cancer ◽  
Low Dose ◽  
Organs At Risk ◽  
Similarity Index ◽  
Adaptive Radiotherapy ◽  
Qualitative Assessment ◽  
Dice Similarity Coefficient

Purpose: To assess image quality and uncertainty in organ-at-risk segmentation on cone beam computed tomography (CBCT) enhanced by deep-learning convolutional neural network (DCNN) for head and neck cancer.Methods: An in-house DCNN was trained using forty post-operative head and neck cancer patients with their planning CT and first-fraction CBCT images. Additional fifteen patients with repeat simulation CT (rCT) and CBCT scan taken on the same day (oCBCT) were used for validation and clinical utility assessment. Enhanced CBCT (eCBCT) images were generated from the oCBCT using the in-house DCNN. Quantitative imaging quality improvement was evaluated using HU accuracy, signal-to-noise-ratio (SNR), and structural similarity index measure (SSIM). Organs-at-risk (OARs) were delineated on o/eCBCT and compared with manual structures on the same day rCT. Contour accuracy was assessed using dice similarity coefficient (DSC), Hausdorff distance (HD), and center of mass (COM) displacement. Qualitative assessment of users’ confidence in manual segmenting OARs was performed on both eCBCT and oCBCT by visual scoring.Results: eCBCT organs-at-risk had significant improvement on mean pixel values, SNR (p < 0.05), and SSIM (p < 0.05) compared to oCBCT images. Mean DSC of eCBCT-to-rCT (0.83 ± 0.06) was higher than oCBCT-to-rCT (0.70 ± 0.13). Improvement was observed for mean HD of eCBCT-to-rCT (0.42 ± 0.13 cm) vs. oCBCT-to-rCT (0.72 ± 0.25 cm). Mean COM was less for eCBCT-to-rCT (0.28 ± 0.19 cm) comparing to oCBCT-to-rCT (0.44 ± 0.22 cm). Visual scores showed OAR segmentation was more accessible on eCBCT than oCBCT images.Conclusion: DCNN improved fast-scan low-dose CBCT in terms of the HU accuracy, image contrast, and OAR delineation accuracy, presenting potential of eCBCT for adaptive radiotherapy.

scholarly journals Evaluation of the prevalence and severity of xerophthalmia in head and neck cancers patients undergoing curative radiotherapy

2016 ◽  
Vol 14 (4) ◽  
Author(s):  
Sowmya V ◽  
Dipika Jayachander ◽  
Vijna Kamath ◽  
Mithun SK Rao ◽  
Mohammed Raees Tonse ◽  
...  
Keyword(s):  
Head And Neck Cancer ◽  
Head And Neck ◽  
Cancer Patients ◽  
Neck Cancer ◽  
Keratoconjunctivitis Sicca ◽  
Study Objective ◽  
Cancer Group ◽  
Curative Radiotherapy ◽  
Significant Difference ◽  
Rectal Cancers

  Background: The study objective was to assess the development of xerophthalmia [dry eye syndrome (DES) or keratoconjunctivitis sicca] in head and neck cancer patients undergoing radiotherapy.Methods: Twenty two head and neck cancer patients requiring more than 60 Gy of curative radiotherapy/chemoradiotherapy and ten patients requiring radiotherapy/ chemoradiotherapy for treating cancers in the non head and neck regions (like breast, oesophagus, prostate, cervix and rectal cancers) were also enrolled in the study. The development of DES was studied at the beginning (day 0, before the start of radiotherapy) at day 21 (after completion of 30 Gy) and on completion of the treatment (> 60 Gy). As a comparative cohort, people with non head and neck cancer needing curative radiotherapy were also evaluated for comparison.Results: There was no difference in degree of DES between the Head and Neck cancer cohorts and non head and neck group at the beginning of treatment. However there was a statistically significant difference (p < 0.001) between the two groups at both mid and end of RT time point. Inter comparison between the various time points in the head and neck cancer group showed that the incidence of DES increased with the radiation exposure and was significant (pre to mid p < 0.001; and mid to end p < 0.005). A negative (r = -0.262) correlation was seen between DES and distance.Conclusions: The study showed that lesser the distance from the epicenter of the radiation to the orbital rim more was the severity of DES.

scholarly journals Investigation of Autosegmentation Techniques on T2-Weighted MRI for Off-line Dose Reconstruction in MR-Linac Adapt to Position Workflow for Head and Neck Cancers

2021 ◽  
Author(s):  
Brigid A McDonald ◽  
Carlos Cardenas ◽  
Nicolette O'Connell ◽  
Sara Ahmed ◽  
Mohamed A. Naser ◽  
...  
Keyword(s):  
Head And Neck ◽  
Execution Time ◽  
Organs At Risk ◽  
Ground Truth ◽  
Dice Similarity Coefficient ◽  
Observer Variability ◽  
Dose Reconstruction ◽  
Inter Observer Variability ◽  
Significant Difference ◽  
Delivered Dose

Purpose: In order to accurately accumulate delivered dose for head and neck cancer patients treated with the Adapt to Position workflow on the 1.5T magnetic resonance imaging (MRI)-linear accelerator (MR-linac), the low-resolution T2-weighted MRIs used for daily setup must be segmented to enable reconstruction of the delivered dose at each fraction. In this study, our goal is to evaluate various autosegmentation methods for head and neck organs at risk (OARs) on on-board setup MRIs from the MR-linac for off-line reconstruction of delivered dose. Methods: Seven OARs (parotid glands, submandibular glands, mandible, spinal cord, and brainstem) were contoured on 43 images by seven observers each. Ground truth contours were generated using a simultaneous truth and performance level estimation (STAPLE) algorithm. 20 autosegmentation methods were evaluated in ADMIRE: 1-9) atlas-based autosegmentation using a population atlas library (PAL) of 5/10/15 patients with STAPLE, patch fusion (PF), random forest (RF) for label fusion; 10-19) autosegmentation using images from a patient's 1-4 prior fractions (individualized patient prior (IPP)) using STAPLE/PF/RF; 20) deep learning (DL) (3D ResUNet trained on 43 ground truth structure sets plus 45 contoured by one observer). Execution time was measured for each method. Autosegmented structures were compared to ground truth structures using the Dice similarity coefficient, mean surface distance, Hausdorff distance, and Jaccard index. For each metric and OAR, performance was compared to the inter-observer variability using Dunn's test with control. Methods were compared pairwise using the Steel-Dwass test for each metric pooled across all OARs. Further dosimetric analysis was performed on three high-performing autosegmentation methods (DL, IPP with RF and 4 fractions (IPP_RF_4), IPP with 1 fraction (IPP_1)), and one low-performing (PAL with STAPLE and 5 atlases (PAL_ST_5)). For five patients, delivered doses from clinical plans were recalculated on setup images with ground truth and autosegmented structure sets. Differences in maximum and mean dose to each structure between the ground truth and autosegmented structures were calculated and correlated with geometric metrics. Results: DL and IPP methods performed best overall, all significantly outperforming inter-observer variability and with no significant difference between methods in pairwise comparison. PAL methods performed worst overall; most were not significantly different from the inter-observer variability or from each other. DL was the fastest method (33 seconds per case) and PAL methods the slowest (3.7 - 13.8 minutes per case). Execution time increased with number of prior fractions/atlases for IPP and PAL. For DL, IPP_1, and IPP_RF_4, the majority (95%) of dose differences were within 250 cGy from ground truth, but outlier differences up to 785 cGy occurred. Dose differences were much higher for PAL_ST_5, with outlier differences up to 1920 cGy. Dose differences showed weak but significant correlations with all geometric metrics (R2 between 0.030 and 0.314). Conclusions: The autosegmentation methods offering the best combination of performance and execution time are DL and IPP_1. Dose reconstruction on on-board T2-weighted MRIs is feasible with autosegmented structures with minimal dosimetric variation from ground truth, but contours should be visually inspected prior to dose reconstruction in an end-to-end dose accumulation workflow.

Importance of Treatment Institution in Head and Neck Cancer Radiotherapy

2009 ◽  
Vol 141 (2) ◽  
pp. 172-176 ◽  
Author(s):  
Gregory J. Kubicek ◽  
Fen Wang ◽  
Eashwar Reddy ◽  
Yelizaveta Shnayder ◽  
Cristina E. Cabrera ◽  
...  
Keyword(s):  
Head And Neck Cancer ◽  
Treatment Outcome ◽  
Head And Neck ◽  
Neck Cancer ◽  
Time Course ◽  
Medical Center ◽  
Recurrence Rates ◽  
Historical Cohort ◽  
Initial Surgery ◽  
Significant Difference

OBJECTIVE: The treatment for head and neck cancer (HNC) often involves radiotherapy. Many HNC patients are treated at the academic center (AC) where the initial surgery or diagnosis was made. Because of the lengthy time course for radiotherapy, some patients are treated at community radiation facilities (non-AC) rather than the AC despite potential AC advantages in terms of experience and technology. Our goal is to determine if these potential AC advantages correspond to a difference in treatment outcome. STUDY DESIGN: Historical cohort study. SETTING: University of Kansas Medical Center, Kansas City, Kansas. SUBJECTS AND METHODS: Review of records of patients with HNC cancers evaluated at the otolaryngology (ENT) department of an AC. Each patient's information and treatment characteristics were recorded, including radiotherapy treatment venue and treatment outcome. RESULTS: Three hundred seventy-four patients were analyzed, 263 were treated at an AC and 101 at a non-AC. Patients treated at a non-AC were more likely to present with earlier stage tumors, be treated with radiation alone rather than chemoradiotherapy, and be treated with adjuvant rather than primary radiotherapy. There was no difference in overall survival or recurrence rates between AC and non-AC. CONCLUSION: Patients treated at an AC are more likely to have advanced stage tumors and receive chemoradiotherapy as their primary treatment. In analyses of matching patient subsets, there was no significant difference in patient outcomes. Patients can be treated at a non-AC without affecting outcome compared with treatment at an AC.

scholarly journals Benefits of deep learning for delineation of organs at risk in head and neck cancer

2019 ◽  
Vol 138 ◽  
pp. 68-74 ◽  
Author(s):  
J. van der Veen ◽  
S. Willems ◽  
S. Deschuymer ◽  
D. Robben ◽  
W. Crijns ◽  
...  
Keyword(s):  
At Risk ◽  
Head And Neck Cancer ◽  
Deep Learning ◽  
Head And Neck ◽  
Neck Cancer ◽  
Organs At Risk

scholarly journals TO COMPARE THE TOXICITY PROFILE OF ACCELERATED RADIOTHERAPY (SIX FRACTIONS PER WEEK) WITH CONCOMITANT CHEMO-RADIOTHERAPY IN LOCALLY ADVANCED HEAD AND NECK CANCER

2019 ◽  
Vol 3 (11) ◽  
Author(s):  
Vikrant Kaushal ◽  
Amit Rana ◽  
Manoj Gupta ◽  
Rajeev Seam ◽  
Manish Gupta
Keyword(s):  
Head And Neck Cancer ◽  
Head And Neck ◽  
Neck Cancer ◽  
Randomized Study ◽  
Locally Advanced ◽  
Medical Science ◽  
Hematological Toxicity ◽  
P Value ◽  
Significant Difference ◽  
The Difference

Background: Head and neck malignancies are common among males in India. The age adjusted incidence rate of head and neck cancer in India in males is 16.4/100,000 and in females it is 8.8/100,000.In All India Institute of Medical Science head and neck cancer represents 25% of all malignancies registered Methods: This prospective randomized study was conducted in the Department of Radiation Therapy & Oncology, Regional Cancer Centre, IGMC, Shimla and patients were enrolled for a period of one year, from July 2012 to July 2013.It included all the eligible, previously untreated patients of squamous cell carcinoma of Head and Neck with histologically confirmed diagnosis and no evidence of distant metastasis. The sites included were oro-pharynx, hypo-pharynx and larynx with stages III, IV A and IV B. Results: Grade 3 and grade 4 skin toxicities were higher in CRT arm but without statistically significant difference from that in ART arm. G3 & G4 mucositis was higher in the Concomitant CRT arm however the difference was not statistically significant. G2 and G3 Laryngeal Toxicities were higher in Concomitant CRT arm as compared to Accelerated arm but the difference was not statistically significant. G2 & G3 haematological toxicities were significantly (combined p value = 0.002) higher in the concomitant CRT arm (32.4%) as compared to Accelerated RT arm (2.9%). Only one patient in accelerated arm had any hematological toxicity. Conclusion: Higher peak incidence of toxicities was seen in concomitant CRT arm as compared to accelerated arm. Keywords: Toxocity, six fraction, chemoradiation, Local control

Sign in / Sign up

Export Citation Format

Share Document