Artificial intelligence in bone metastasis analysis: Current advancements, opportunities and challenges.
Authors
Affiliations (5)
Affiliations (5)
- Laboratory of IEMN, CNRS, Centrale Lille, UMR 8520, Univ. Polytechnique Hauts-de-France, F-59313, Valenciennes, France; CES-laboratory, National Engineering School of Sfax, University of Sfax, 3038, Sfax, Tunisia. Electronic address: [email protected].
- Junia, UMR 8520, CNRS, Centrale Lille, 59000, Lille, France. Electronic address: [email protected].
- CES-laboratory, National Engineering School of Sfax, University of Sfax, 3038, Sfax, Tunisia. Electronic address: [email protected].
- University of the Basque Country UPV/EHU, San Sebastian, Spain; IKERBASQUE, Basque Foundation for Science, Bilbao, Spain. Electronic address: [email protected].
- Laboratory of IEMN, CNRS, Centrale Lille, UMR 8520, Univ. Polytechnique Hauts-de-France, F-59313, Valenciennes, France. Electronic address: [email protected].
Abstract
Artificial Intelligence is transforming medical imaging, particularly in the analysis of bone metastases (BM), a serious complication of advanced cancers. Machine learning and deep learning techniques offer new opportunities to improve detection, recognition, and segmentation of bone metastasis. Yet, challenges such as limited data, interpretability, and clinical validation remain. Following PRISMA guidelines, we reviewed artificial intelligence methods and applications for bone metastasis analysis across major imaging modalities including CT, MRI, PET, SPECT, and bone scintigraphy. The survey includes traditional machine learning models and modern deep learning architectures such as CNNs and transformers. We also examined available datasets and their effect in developing artificial intelligence in this field. Artificial intelligence models have achieved strong performance across tasks and modalities, with Convolutional Neural Network (CNN) and Transformer architectures showing particularly efficient performance across different tasks. However, limitations persist, including data imbalance, overfitting risks, and the need for greater transparency. Clinical translation is also challenged by regulatory and validation hurdles. Artificial intelligence holds strong potential to improve BM diagnosis and streamline radiology workflows. To reach clinical maturity, future work must address data diversity, model explainability, and large-scale validation, which are critical steps for being trusted to be integrated into the oncology care routines.