Deep learning analysis using FDG-PET to predict treatment outcome in patients with oral cavity squamous cell carcinoma

Abstract Background This study aimed to assess the utility of deep learning analysis using pretreatment FDG-PET images to predict local treatment outcome in oropharyngeal squamous cell carcinoma (OPSCC) patients. Methods One hundred fifty-four OPSCC patients who received pretreatment FDG-PET were included and divided into training (n = 102) and test (n = 52) sets. The diagnosis of local failure and local progression-free survival (PFS) rates were obtained from patient medical records. In deep learning analyses, axial and coronal images were assessed by three different architectures (AlexNet, GoogLeNET, and ResNet). In the training set, FDG-PET images were analyzed after the data augmentation process for the diagnostic model creation. A multivariate clinical model was also created using a binomial logistic regression model from a patient’s clinical characteristics. The test data set was subsequently analyzed for confirmation of diagnostic accuracy. Assessment of local PFS rates was also performed. Results Training sessions were successfully performed with an accuracy of 74–89%. ROC curve analyses revealed an AUC of 0.61–0.85 by the deep learning model in the test set, whereas it was 0.62 by T-stage, 0.59 by clinical stage, and 0.74 by a multivariate clinical model. The highest AUC (0.85) was obtained with deep learning analysis of ResNet architecture. Cox proportional hazards regression analysis revealed deep learning-based classification by a multivariate clinical model (P < .05), and ResNet (P < .001) was a significant predictor of the treatment outcome. In the Kaplan-Meier analysis, the deep learning-based classification divided the patient’s local PFS rate better than the T-stage, clinical stage, and a multivariate clinical model. Conclusions Deep learning-based diagnostic model with FDG-PET images indicated its possibility to predict local treatment outcomes in OPSCCs.

Download Full-text

Prediction of the human papillomavirus status in patients with oropharyngeal squamous cell carcinoma by FDG-PET imaging dataset using deep learning analysis: A hypothesis-generating study

European Journal of Radiology ◽

10.1016/j.ejrad.2020.108936 ◽

2020 ◽

Vol 126 ◽

pp. 108936

Author(s):

Noriyuki Fujima ◽

V Carlota Andreu-Arasa ◽

Sara K Meibom ◽

Gustavo A Mercier ◽

Minh Tam Truong ◽

...

Keyword(s):

Squamous Cell Carcinoma ◽

Deep Learning ◽

Human Papillomavirus ◽

Cell Carcinoma ◽

Squamous Cell ◽

Pet Imaging ◽

Fdg Pet ◽

Oropharyngeal Squamous Cell Carcinoma ◽

Learning Analysis

Download Full-text

Evaluation of Lymphatic and Vascular Invasion in Relation to Clinicopathological Factors and Treatment Outcome in Oral Cavity Squamous Cell Carcinoma

Medicine ◽

10.1097/md.0000000000001510 ◽

2015 ◽

Vol 94 (43) ◽

pp. e1510 ◽

Cited By ~ 28

Author(s):

Mohamad Adel ◽

Huang-Kai Kao ◽

Cheng-Lung Hsu ◽

Jung-Ju Huang ◽

Li-Yu Lee ◽

...

Keyword(s):

Squamous Cell Carcinoma ◽

Treatment Outcome ◽

Oral Cavity ◽

Cell Carcinoma ◽

Squamous Cell ◽

Vascular Invasion ◽

Clinicopathological Factors

Download Full-text

Is There a Need for Positron Emission Tomography Imaging to Stage the N0 Neck in T1-T2 Squamous Cell Carcinoma of the Oral Cavity or Oropharynx?

Annals of Otology Rhinology & Laryngology ◽

10.1177/000348940811701111 ◽

2008 ◽

Vol 117 (11) ◽

pp. 854-863 ◽

Cited By ~ 28

Author(s):

Ursula Schroeder ◽

Markus Dietlein ◽

Claus Wittekindt ◽

Monika Ortmann ◽

Hartmut Stuetzer ◽

...

Keyword(s):

Positron Emission Tomography ◽

Squamous Cell Carcinoma ◽

Oral Cavity ◽

Cell Carcinoma ◽

Squamous Cell ◽

Fdg Pet ◽

Emission Tomography ◽

Elective Neck Dissection ◽

Cross Sectional ◽

Positron Emission

Objectives: We assess whether negative findings on computed tomography (CT), magnetic resonance imaging (MRI), and/or 18F-fluorodeoxyglucose positron emission tomography (18FDG-PET) may contribute to the decision-making process of elective neck dissection (eND) in patients with squamous cell carcinoma of the oral cavity or the oropharynx (oSCC) staged cT1-T2 cN0 cM0. Methods: We interpreted CT, MRI, and 18FDG-PET images separately, after combining the data of CT with those of 18FDG-PET and the data of MRI with those of 18FDG-PET. Each set of results was then compared with the histopathologic results of ipsilateral or bilateral eND in a prospective, blinded study. Results: The histopathologic examination of 594 lymph nodes revealed 4 metastases less than 4 mm in diameter and 3 micrometastases (less than 2 mm) in 6 of 17 patients. On CT, MRI, and 18FDG-PET, respectively, 5, 5, and 0 cases were true-malignant (true positives) and 4, 10, and 1 cases were false-malignant (false positives). The accuracy was not enhanced by fusing CT with 18FDG-PET or MRI with 18FDG-PET. Conclusions: The detectability threshold of occult metastases appears to be below the spatial and contrast resolution of CT, MRI, and 18FDG-PET. The decision for eND in patients with cT1-T2 cN0 cM0 oSCC cannot be based upon cross-sectional imaging at the resolutions currently available.

Download Full-text