Identification of Intracranial Germ Cell Tumors Based on Facial Photos: Exploratory Study on the Use of Deep Learning for Software Development

Abstract

Background: Primary intracranial germ cell tumors (iGCTs) are highly malignant brain tumors that predominantly occur in children and adolescents, with an incidence rate ranking third among primary brain tumors in East Asia (8%-15%). Due to their insidious onset and impact on critical functional areas of the brain, these tumors often result in irreversible abnormalities in growth and development, as well as cognitive and motor impairments in affected children. Therefore, early diagnosis through advanced screening techniques is vital for improving patient outcomes and quality of life.

Objective: This study aimed to investigate the application of facial recognition technology in the early detection of iGCTs in children and adolescents. Early diagnosis through advanced screening techniques is vital for improving patient outcomes and quality of life.

Methods: A multicenter, phased approach was adopted for the development and validation of a deep learning model, GVisageNet, dedicated to the screening of midline brain tumors from normal controls (NCs) and iGCTs from other midline brain tumors. The study comprised the collection and division of datasets into training (n=847, iGCTs=358, NCs=300, other midline brain tumors=189) and testing (n=212, iGCTs=79, NCs=70, other midline brain tumors=63), with an additional independent validation dataset (n=336, iGCTs=130, NCs=100, other midline brain tumors=106) sourced from 4 medical institutions. A regression model using clinically relevant, statistically significant data was developed and combined with GVisageNet outputs to create a hybrid model. This integration sought to assess the incremental value of clinical data. The model's predictive mechanisms were explored through correlation analyses with endocrine indicators and stratified evaluations based on the degree of hypothalamic-pituitary-target axis damage. Performance metrics included area under the curve (AUC), accuracy, sensitivity, and specificity.

Results: On the independent validation dataset, GVisageNet achieved an AUC of 0.938 (P<.01) in distinguishing midline brain tumors from NCs. Further, GVisageNet demonstrated significant diagnostic capability in distinguishing iGCTs from the other midline brain tumors, achieving an AUC of 0.739, which is superior to the regression model alone (AUC=0.632, P<.001) but less than the hybrid model (AUC=0.789, P=.04). Significant correlations were found between the GVisageNet's outputs and 7 endocrine indicators. Performance varied with hypothalamic-pituitary-target axis damage, indicating a further understanding of the working mechanism of GVisageNet.

Conclusions: GVisageNet, capable of high accuracy both independently and with clinical data, shows substantial potential for early iGCTs detection, highlighting the importance of combining deep learning with clinical insights for personalized health care.

Keywords: algorithms; artificial intelligence; cohort studies; deep learning; endocrine indicators; facial recognition; intracranial germ cell tumors; machine learning models; neural networks; software development; software engineering.

Figure 1

The study design and participant flow. DL: deep learning; iGCT: intracranial germ cell tumor; NC: normal control.

Figure 2

The figure depicts the GVisageNet model workflow for facial photo analysis, including preprocessing, configuration, training with loss function and optimizer selection, and evaluation using ROC and precision-recall curves on an independent external validation data set. iGCTs: intracranial germ cell tumors; NCs: normal controls.

Figure 3

(A) Tumor site distribution of iGCTs in different hospitals of different datasets. (B) Distribution of tumor types in all datasets in the other midline brain tumors group. (C) Comparison of performance of different algorithms (accuracy, sensitivity, specificity, and area under the curve). AUC: area under the curve; iGCTs: intracranial germ cell tumors.

Figure 4

(A) The receiver operator characteristic curve of GVisageNet in the initial stage of development in the testing and independent external validation datasets. (B) The receiver operator characteristic curve of GVisageNet in the second stage of development in the testing and independent external validation datasets. (C) The area under the curve, accuracy, sensitivity, and specificity of the GVisageNet in the testing dataset with 95 % CI. (D) The AUC, accuracy, sensitivity, and specificity of the GVisageNet in the independent external validation dataset with 95% CI. AUC: area under the curve.

Figure 5

(A) Correlation analysis between the output results of GVisageNet and endocrine indicators in the independent external validation dataset. (B) The area under the curve, accuracy, sensitivity, and specificity of the GVisageNet for the stratified analysis of the HPT axis damage degree in the independent external validation dataset. (C) The visual integration of GVisageNet into the facial photo collection system (independent validation dataset). ACTH: adrenocorticotrophic hormone; E2: estradiol; FT3: free triiodothyronine; FT4: free thyroxine; GH: growth hormone; iGCTs: intracranial germ cell tumors; IGF-1: insulin-like growth factor 1; IGFBP-3: insulin-like growth factor binding protein 3; LH: luteinizing hormone; P: progesterone; PRL: prolactin; T: testosterone; TSH: thyroid-stimulating hormone; TT3: total tri-iodothyronine; TT4: total thyroxine.