Feasibility of No-Code Deep Learning for Diagnosing Bone Metastasis in Bone Scans: A Comparative Study of Teachable Machine and ResNet.
Authors
Affiliations (5)
Affiliations (5)
- Department of Medicine, Hallym University College of Medicine, Chuncheon, Gangwon, Republic of Korea.
- Department of Radiology, Hallym University Kangnam Sacred Heart Hospital, Hallym University College of Medicine, 1 Singil-ro, Yeongdeungpo-gu, Seoul, 07441, Republic of Korea.
- Department of Nuclear Medicine, Chung-Ang University Hospital, Chung-Ang University School of Medicine, Seoul, Republic of Korea.
- Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA.
- Department of Radiology, Hallym University Kangnam Sacred Heart Hospital, Hallym University College of Medicine, 1 Singil-ro, Yeongdeungpo-gu, Seoul, 07441, Republic of Korea. [email protected].
Abstract
This study explored the feasibility of developing a model that can diagnose positive and negative bone metastasis from bone scan images using Teachable Machine by Google, a no-code AI platform that does not require programming skills or a GPU environment. A fourth-year medical student trained deep learning models using a Teachable Machine on a dataset of 4626 bone scan images from patients with cancer (mean age 65.1 ± 11.3 years; 50.5% female). Because of severe class imbalance (bone metastasis positive:negative = 400:4226), we compared the diagnostic performance of two strategies (original set and augmented dataset with tenfold data augmentation applied to positive images). We investigated the diagnostic performance using various hyperparameters (epochs 50-1000, batch sizes 16-32) with a learning rate of 0.001. The final model generated by Teachable Machine was compared with a conventional deep learning model based on ResNet50. The combination of epoch = 150 and batch size = 16 showed the optimal diagnostic performance. The overall sensitivity, specificity, and positive and negative predictive values were 57.1%, 93.9%, 90.4%, and 68.7%, respectively. Both Teachable Machine and ResNet50 showed good diagnostic performance (area under the curve = 0.812 and 0.869, respectively), although the diagnostic performance of Teachable Machine was inferior to that of the conventional ResNet50 model (p < 0.001). Given its convenience, Teachable Machine represents a valuable and accessible tool for medical education and preliminary model development. It allows researchers without programming skills or GPU resources to construct feasibility models for medical image classification.