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

Fujima, Noriyuki; Arasa, Vanessa Carlota Andreu; Meibom, Sara K.; Mercier, Gustavo; Truong, Minh Tam; Sakai, Osamu

doi:10.1016/j.ejrad.2020.108936

Cited by 16 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One possible solution to this problem is given by transfer learning, an approach making use of large non-medical data sets in order to inject information into the network before the actual learning task is started. Fujima et al [22] trained a 2D convolutional neuronal network (CNN) on FDG-PET images to classify HPV status in OPC patients and achieved an AUC of 83%, using a transfer learning approach based on natural images from the ImageNet database [23]. However, they did not test their data on an external cohort and excluded images containing severe motion artifacts and tumors with diameters below 1.5 cm.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based HPV Status Prediction for Oropharyngeal Cancer Patients

Lang

Peeken

Combs

et al. 2021

Cancers

View full text Add to dashboard Cite

Infection with the human papillomavirus (HPV) has been identified as a major risk factor for oropharyngeal cancer (OPC). HPV-related OPCs have been shown to be more radiosensitive and to have a reduced risk for cancer related death. Hence, the histological determination of HPV status of cancer patients depicts an essential diagnostic factor. We investigated the ability of deep learning models for imaging based HPV status detection. To overcome the problem of small medical datasets, we used a transfer learning approach. A 3D convolutional network pre-trained on sports video clips was fine-tuned, such that full 3D information in the CT images could be exploited. The video pre-trained model was able to differentiate HPV-positive from HPV-negative cases, with an area under the receiver operating characteristic curve (AUC) of 0.81 for an external test set. In comparison to a 3D convolutional neural network (CNN) trained from scratch and a 2D architecture pre-trained on ImageNet, the video pre-trained model performed best. Deep learning models are capable of CT image-based HPV status determination. Video based pre-training has the ability to improve training for 3D medical data, but further studies are needed for verification.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning Based HPV Status Prediction for Oropharyngeal Cancer Patients

Lang

Peeken

Combs

et al. 2021

Cancers

View full text Add to dashboard Cite

show abstract

“…In all slices with the tumor FDG uptake, a specific slice that included the largest tumor area (i.e., the largest number of pixels) was selected in axial and coronal planes and further analyzed. All selected images were converted from the DICOM to Joint Photographic Experts Group (JPEG) picture data; the grayscale level was set so that the pixel with non-FDG uptake (i.e., SUV = 0) becomes black (lower limit) and the pixel with its SUV of 30 becomes white (upper limit) [ 16 ]. These processes are illustrated in Fig.…”

Section: Methodsmentioning

confidence: 99%

Prediction of the local treatment outcome in patients with oropharyngeal squamous cell carcinoma using deep learning analysis of pretreatment FDG-PET images

et al. 2021

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…The HPV+ cases were, however, significantly more likely to exhibit cystic nodal metastases than HPV− tumors [ 75 ], which can be translated to SCCUP since cystic morphology is a common trait in both SCCUP and OPSCC [ 59 ]. Recently, in a hypothesis-generating study, a deep learning algorithm of PET-images was able to successfully distinguish between HPV+ and HPV− OPSCC disease with an AUC of 0.83 [ 76 ]. Future radiological imaging in SCCUP will most likely benefit from possible deep learning algorithms.…”

Section: Identification Of the Primary Tumor Site Addressing Hpvmentioning

confidence: 99%

Human Papillomavirus and Squamous Cell Carcinoma of Unknown Primary in the Head and Neck Region: A Comprehensive Review on Clinical Implications

Larsen

Channir

Buchwald

2021

Viruses

View full text Add to dashboard Cite

Squamous cell carcinoma of unknown primary (SCCUP) is a challenging diagnostic subgroup of oropharyngeal squamous cell carcinoma (OPSCC). The incidence of SCCUP is increasing in parallel with the well-documented increase in OPSCC and is likewise driven by the increase in human papillomavirus (HPV). The SCCUP patient often presents with a cystic lymph node metastasis and undergoes an aggressive diagnostic and treatment program. Detection of HPV in cytologic specimens indicates an oropharyngeal primary tumor origin and can guide the further diagnostic strategy. Advances in diagnostic modalities, e.g., transoral robotic surgery and transoral laser microsurgery, have increased the successful identification of the primary tumor site in HPV-induced SCCUP, and this harbors a potential for de-escalation treatment and increased survival. This review provides an overview of HPV-induced SCCUP, diagnostic modalities, and treatment options.

show abstract

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

Cited by 16 publications

References 27 publications

Deep Learning Based HPV Status Prediction for Oropharyngeal Cancer Patients

Deep Learning Based HPV Status Prediction for Oropharyngeal Cancer Patients

Prediction of the local treatment outcome in patients with oropharyngeal squamous cell carcinoma using deep learning analysis of pretreatment FDG-PET images

Human Papillomavirus and Squamous Cell Carcinoma of Unknown Primary in the Head and Neck Region: A Comprehensive Review on Clinical Implications

Contact Info

Product

Resources

About