Head and neck target delineation using a novel PET automatic segmentation algorithm

Berthon, Béatrice; Evans, Mererid; Marshall, Christopher; Palaniappan, Nachi; Cole, Naomi; Jayaprakasam, Vetri Sudar; Rackley, T.; Spezi, Emiliano

doi:10.1016/j.radonc.2016.12.008

Cited by 43 publications

(39 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The methods of Stefano et al [ 14 ] and Song et al [ 17 ] were all semiautomatic. Berthon et al [ 15 ] reported a higher accuracy of 0.77; however, their gold standard for performance evaluation incorporated the information of automatic segmentation results. Compared to these studies [ 13 – 17 ] with the data from one center only, our proposed method shows stable performance on dual-center data.…”

Section: Discussionmentioning

confidence: 99%

“…Positron emission tomography-computed tomography (PET-CT) has played an important role in the diagnosis and treatment of HNC, providing both anatomical and metabolic information about the tumor. The automatic or semiautomatic segmentation of tumor lesions on PET-CT or PET images of HNC has been reported, using machine-learning (ML) methods such as k-nearest neighbor (KNN) [ 11 , 12 ], Markov random fields (EM-MRFs) [ 13 ], adaptive random walker with k-means (AK-RW) [ 14 ], decision tree algorithm [ 15 ], and active surface modeling [ 16 ]. The segmentation of tumor lesions on the coregistered PET and CT images has shown better results than those on solely PET or CT images [ 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fully Automated Delineation of Gross Tumor Volume for Head and Neck Cancer on PET-CT Using Deep Learning: A Dual-Center Study

Huang

Chen

et al. 2018

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

Purpose In this study, we proposed an automated deep learning (DL) method for head and neck cancer (HNC) gross tumor volume (GTV) contouring on positron emission tomography-computed tomography (PET-CT) images. Materials and Methods PET-CT images were collected from 22 newly diagnosed HNC patients, of whom 17 (Database 1) and 5 (Database 2) were from two centers, respectively. An oncologist and a radiologist decided the gold standard of GTV manually by consensus. We developed a deep convolutional neural network (DCNN) and trained the network based on the two-dimensional PET-CT images and the gold standard of GTV in the training dataset. We did two experiments: Experiment 1, with Database 1 only, and Experiment 2, with both Databases 1 and 2. In both Experiment 1 and Experiment 2, we evaluated the proposed method using a leave-one-out cross-validation strategy. We compared the median results in Experiment 2 (GTVa) with the performance of other methods in the literature and with the gold standard (GTVm). Results A tumor segmentation task for a patient on coregistered PET-CT images took less than one minute. The dice similarity coefficient (DSC) of the proposed method in Experiment 1 and Experiment 2 was 0.481∼0.872 and 0.482∼0.868, respectively. The DSC of GTVa was better than that in previous studies. A high correlation was found between GTVa and GTVm (R = 0.99, P < 0.001). The median volume difference (%) between GTVm and GTVa was 10.9%. The median values of DSC, sensitivity, and precision of GTVa were 0.785, 0.764, and 0.789, respectively. Conclusion A fully automatic GTV contouring method for HNC based on DCNN and PET-CT from dual centers has been successfully proposed with high accuracy and efficiency. Our proposed method is of help to the clinicians in HNC management.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fully Automated Delineation of Gross Tumor Volume for Head and Neck Cancer on PET-CT Using Deep Learning: A Dual-Center Study

Huang

Chen

et al. 2018

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

show abstract

“…However, machine-learned segmentation methods have showed promise for accurate MTV delineation [ 9 ]. Machine-learned-based and consensus-based segmentation methodologies have been proposed for the standardisation of the delineation of the MTV [ 20 , 40 , 41 ]. In Additional file 3 , radiomic features derived from each segmentation method were correlated with MTV.…”

Section: Discussionmentioning

confidence: 99%

Evaluation of prognostic models developed using standardised image features from different PET automated segmentation methods

Parkinson

Foley²,

Whybra

et al. 2018

EJNMMI Res

View full text Add to dashboard Cite

BackgroundPrognosis in oesophageal cancer (OC) is poor. The 5-year overall survival (OS) rate is approximately 15%. Personalised medicine is hoped to increase the 5- and 10-year OS rates. Quantitative analysis of PET is gaining substantial interest in prognostic research but requires the accurate definition of the metabolic tumour volume. This study compares prognostic models developed in the same patient cohort using individual PET segmentation algorithms and assesses the impact on patient risk stratification.Consecutive patients (n = 427) with biopsy-proven OC were included in final analysis. All patients were staged with PET/CT between September 2010 and July 2016. Nine automatic PET segmentation methods were studied. All tumour contours were subjectively analysed for accuracy, and segmentation methods with < 90% accuracy were excluded. Standardised image features were calculated, and a series of prognostic models were developed using identical clinical data. The proportion of patients changing risk classification group were calculated.ResultsOut of nine PET segmentation methods studied, clustering means (KM2), general clustering means (GCM3), adaptive thresholding (AT) and watershed thresholding (WT) methods were included for analysis. Known clinical prognostic factors (age, treatment and staging) were significant in all of the developed prognostic models. AT and KM2 segmentation methods developed identical prognostic models. Patient risk stratification was dependent on the segmentation method used to develop the prognostic model with up to 73 patients (17.1%) changing risk stratification group.ConclusionPrognostic models incorporating quantitative image features are dependent on the method used to delineate the primary tumour. This has a subsequent effect on risk stratification, with patients changing groups depending on the image segmentation method used.Electronic supplementary materialThe online version of this article (10.1186/s13550-018-0379-3) contains supplementary material, which is available to authorized users.

show abstract

“…Several recent studies have shown the potential of using CT, MRI and PET imaging for improving target volume delineation for radiotherapy treatment planning [7,8]. Multi-parametric imaging information from PET/CT or PET/ MRI contains different layers of information which can be combined using novel machine learning methods to automatically generate target volumes in a robust manner [9,10]. Furthermore, plan adaptation according to daily position of target volume and organs at risk (OAR) can be effectively performed using cone beam CT (CBCT) or MRI available at the treatment machine [11].…”

Section: Imagingmentioning

confidence: 99%

Adapting training for medical physicists to match future trends in radiation oncology

Clark

Gagliardi

Heijmen

et al. 2019

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

Head and neck target delineation using a novel PET automatic segmentation algorithm

Abstract: 1Purpose: To evaluate the feasibility and impact of using a novel advanced PET 2 auto-segmentation method in Head and Neck (H&N) radiotherapy treatment (RT) 3 planning. 4

Cited by 43 publications

References 26 publications

Fully Automated Delineation of Gross Tumor Volume for Head and Neck Cancer on PET-CT Using Deep Learning: A Dual-Center Study

Fully Automated Delineation of Gross Tumor Volume for Head and Neck Cancer on PET-CT Using Deep Learning: A Dual-Center Study

Evaluation of prognostic models developed using standardised image features from different PET automated segmentation methods

Adapting training for medical physicists to match future trends in radiation oncology

Contact Info

Product

Resources

About