MRI with DWI for the Detection of Posttreatment Head and Neck Squamous Cell Carcinoma: Why Morphologic MRI Criteria Matter

Ailianou, Angeliki; Mundada, Pravin; Perrot, Thomas de; Pusztaszieri, M.; Poletti, Pierre A.; Becker, Minerva

doi:10.3174/ajnr.a5548

Cited by 35 publications

(32 citation statements)

References 24 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DW-MRI has shown promising results in staging nodal metastasis, the detection of recurrent disease and the assessment of tumor response and prognosis after chemo-radiotherapy for HNSCC. The sensitivity and specificity rates obtained are more or less similar to those obtained with [ 18 F]-FDG-PET [56][57][58][59][60][61][62][63][64][65][66] . unfortunately, the majority of these studies contain too few patients and included different sites.…”

Section: Discussionsupporting

confidence: 72%

C-11 methionine PET and 18-F FDG-PET for identifying recurrent laryngeal carcinoma

Wedman¹

View full text Add to dashboard Cite

Chapter 1 General Introduction Chapter 2 Effectiveness of an 18F FDG-PET based strategy to optimize the diagnostic trajectory of suspected recurrent laryngeal carcinoma after radiotherapy: The RELAPS multicenter randomized trial Chapter 3 Recurrent Laryngeal Carcinoma Pet Study (Relaps): Cost Analysis Of 18F FDG-PET In Patients With Suspected Recurrent Laryngeal Cancer Previously Treated With Radiotherapy Chapter 4 Alternative PET tracers in head and neck cancer. A review Chapter 5 Visualization of small glottic laryngeal cancer using methyl-labeled 11C-Methionine Positron emission tomography Chapter 6 Is C-11 Methionine PET an alternative to 18F FDG-PET for identifying recurrent laryngeal cancer after radiotherapy?

show abstract

Section: Discussionsupporting

confidence: 72%

C-11 methionine PET and 18-F FDG-PET for identifying recurrent laryngeal carcinoma

Wedman¹

View full text Add to dashboard Cite

show abstract

“…Feature selection algorithms are used for determination of relevant features to avoid over-fitting, resulted from more sample numbers compared with derived feature numbers, providing more accurate models. Quantitative texture analysis and data mining methods have been used as predictive and prognostic biomarkers in multiple cancers, including lung, breast, head and neck, and prostate cancer [14][15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Response to Neoadjuvant Chemoradiotherapy by MRI-Based Machine Learning Texture Analysis in Rectal Cancer Patients

Shayesteh

Alikhassi

Farhan

et al. 2019

J Gastrointest Canc

View full text Add to dashboard Cite

Introduction Neoadjuvant chemoradiotherapy (nCRT) followed by surgical resection is the standard treatment for locally advanced rectal cancer (LARC). Radiomics can be used as noninvasive biomarker for prediction of response to therapy. The main aim of this study was to evaluate the association of MRI texture features of LARC with nCRT response and the effect of Laplacian of Gaussian (LoG) filter and feature selection algorithm in prediction process improvement. Methods All patients underwent MRI with a 3T clinical scanner, 1 week before nCRT. For each patient, intensity, shape, and texture-based features were derived from MRI images with LoG filter using the IBEX software and without preprocessing. We identified responder from a non-responder group using 9 machine learning classifiers. Then, the effect of preprocessing LoG filters with 0.5, 1 and 1.5 value on these classification algorithms' performance was investigated. Eventually, classification algorithm's results were compared in different feature selection methods. Result Sixty-seven patients with LARC were included in the study. Patients' nCRT responses included 11 patients with Grade 0, 19 with Grade 1, 26 with Grade 2, and 11 with Grade 3 according to AJCC/CAP pathologic grading. In MR Images which were not preprocessed, the best performance was for Ada boost classifier (AUC = 74.8) with T2W MR Images. In T1W MR Images, the best performance was for aba boost classifier (AUC = 78.1) with a σ = 1 preprocessing LoG filter. In T2W MR Images, the best performance was for naive Bayesian network classifier (AUC = 85.1) with a σ = 0.5 preprocessing LoG filter. Also, performance of machine learning models with CfsSubsetEval (CF SUB E) feature selection algorithm was better than others. Conclusion Machine learning can be used as a response predictor model in LARC patients, but its performance should be improved. A preprocessing LoG filter can improve the machine learning methods performance and at the end, the effect of feature selection algorithm on model's performance is clear.

show abstract

“…18F-Fluorodeoxygluocose ( 18 F-FDG) positron emission tomography (PET) [7], quantitative diffusion-weighted (DW) MRI [8][9][10][11][12] and qualitative MRI descriptors have all been used to aid tumour detection in the post-treatment setting. MRI descriptors such as T2w and DWI signal, morphology and dimensions have been demonstrated to contribute to both the early post-treatment and later symptomatic assessment of recurrent disease [13][14][15][16][17][18][19][20][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

MRI in head and neck cancer following chemoradiotherapy: what is the optimal delay to demonstrate maximal response?

2021

View full text Add to dashboard Cite

Objectives To investigate the optimal timing for post-chemoradiotherapy (CRT) reference magnetic resonance imaging (MRI) in head and neck cancer, so as to demonstrate a maximal treatment response. To assess whether this differs in human papillomavirus–related oropharyngeal cancer (HPV-OPC) and whether the MRI timing impacts on the ability to predict treatment success. Methods Following ethical approval and informed consent, 45 patients (40 male, mean age 59.7 ± 7.9 years, 33 HPV-OPC) with stage 3 and 4 HNSCC underwent pre-treatment, 6- and 12-week post-CRT MRIs in this prospective cohort study. Primary tumour (n = 39) size, T2w morphology and diffusion weight imaging (DWI) scores, together with nodal (n = 42) size and necrotic/cystic change, were recorded. Interval imaging changes were analysed for all patients and according to HPV-OPC status. MRI descriptors and their interval changes were also compared with 2-year progression-free survival (PFS). Results All MRI descriptors significantly changed between pre-treatment and 6-week post-treatment MRI studies (p < .001). Primary tumour and nodal volume decreased between 6- and 12-week studies; however, interval changes in linear dimensions were only evident for HPV-OPC lymph nodes. Nodal necrosis scores also evolved after 6 weeks but other descriptors were stable. The 6-week nodal necrosis score and the 6- and 12-week nodal volume were predictive of 2-year PFS. Conclusion Apart from HPV-OPC patients with nodal disease, the 6-week post-CRT MRI demonstrates maximal reduction in the linear dimensions of head and neck cancer; however, a later reference study should be considered if volumetric analysis is applied. Key Points • This study provides guidance on when early post-treatment imaging should be performed in head and neck cancer following chemoradiotherapy, in order to aid subsequent detection of recurrent tumour. • Lymph nodes in HPV-related oropharyngeal cancer patients clearly reduced in size from 6 to 12 weeks post-treatment. However, other lymph node disease and all primary tumours showed only a minor reduction in size beyond 6 weeks, and this required a detailed volumetric analysis for demonstration. • Timing of the reference MRI following chemoradiotherapy for head and neck cancer depends on whether the patient has HPV-related oropharyngeal cancer and whether there is nodal disease. MRI as early as 6 weeks post-treatment may be performed unless volumetric analysis is routinely performed.

show abstract

MRI with DWI for the Detection of Posttreatment Head and Neck Squamous Cell Carcinoma: Why Morphologic MRI Criteria Matter

Abstract: Adding precise morphologic MRI criteria to quantitative DWI enables reproducible and accurate detection of recurrent head and neck squamous cell carcinoma/second primary head and neck squamous cell carcinoma occurring after treatment.

Cited by 35 publications

References 24 publications

C-11 methionine PET and 18-F FDG-PET for identifying recurrent laryngeal carcinoma

C-11 methionine PET and 18-F FDG-PET for identifying recurrent laryngeal carcinoma

Prediction of Response to Neoadjuvant Chemoradiotherapy by MRI-Based Machine Learning Texture Analysis in Rectal Cancer Patients

MRI in head and neck cancer following chemoradiotherapy: what is the optimal delay to demonstrate maximal response?

Contact Info

Product

Resources

About