Noriyuki Fujima1,2, V Carlota Andreu-Arasa1, Sara K Meibom1, Gustavo A Mercier1, Minh Tam Truong3, Kenji Hirata4, Koichi Yasuda5, Satoshi Kano6, Akihiro Homma6, Kohsuke Kudo4,7, Osamu Sakai8,9. 1. Departments of Radiology, Boston University School of Medicine, One Boston Medical Center Place, 3rd Floor, 820 Harrison Avenue, Boston, MA, 02118, USA. 2. Research Center for Cooperative Projects, Hokkaido University Graduate School of Medicine, kita 15, nishi 7, kita-ku, Sapporo, Hokkaido, 060-8638, Japan. 3. Departments of Radiation Oncology, Boston Medical Center, Boston University School of Medicine, One Boston Medical Center Place, Boston, MA, 02118, USA. 4. Departments of Diagnostic Imaging, Hokkaido University Graduate School of Medicine, kita 15, nishi 7, kita-ku, Sapporo, Hokkaido, 060-8638, Japan. 5. Departments of Radiation Medicine, Hokkaido University Graduate School of Medicine, kita 15, nishi 7, kita-ku, Sapporo, Hokkaido, 060-8638, Japan. 6. Otolaryngology-Head and Neck Surgery, Hokkaido University Graduate School of Medicine, kita 15, nishi 7, kita-ku, Sapporo, Hokkaido, 060-8638, Japan. 7. The Global Station for Quantum Medical Science and Engineering, Global Institution for collaborative research and education, Sapporo, Hokkaido, 060-0808, Japan. 8. Departments of Radiology, Boston University School of Medicine, One Boston Medical Center Place, 3rd Floor, 820 Harrison Avenue, Boston, MA, 02118, USA. Osamu.Sakai@bmc.org. 9. Departments of Radiation Oncology, Boston Medical Center, Boston University School of Medicine, One Boston Medical Center Place, Boston, MA, 02118, USA. Osamu.Sakai@bmc.org.
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.
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.
Authors: Kristin A Higgins; Jenny K Hoang; Michael C Roach; Junzo Chino; David S Yoo; Timothy G Turkington; David M Brizel Journal: Int J Radiat Oncol Biol Phys Date: 2011-01-27 Impact factor: 7.038
Authors: Stuart J Wong; Paul M Harari; Adam S Garden; Marc Schwartz; Lisa Bellm; Amy Chen; Walter J Curran; Barbara A Murphy; K Kian Ang Journal: Cancer Date: 2010-11-08 Impact factor: 6.860
Authors: Mehdi Taghipour; Sara Sheikhbahaei; Wael Marashdeh; Lilja Solnes; Anna Kiess; Rathan M Subramaniam Journal: JAMA Otolaryngol Head Neck Surg Date: 2016-01 Impact factor: 6.223