Data di Pubblicazione:
2023
Citazione:
High-performance prediction models for prostate cancer radiomics / L.J. Isaksson, M. Repetto, P.E. Summers, M. Pepa, M. Zaffaroni, M.G. Vincini, G. Corrao, G.C. Mazzola, M. Rotondi, F. Bellerba, S. Raimondi, Z. Haron, S. Alessi, P. Pricolo, F.A. Mistretta, S. Luzzago, F. Cattani, G. Musi, O. De Cobelli, M. Cremonesi, R. Orecchia, D. La Torre, G. Marvaso, G. Petralia, B.A. Jereczek-Fossa. - In: INFORMATICS IN MEDICINE UNLOCKED. - ISSN 2352-9148. - 37:(2023), pp. 101161.1-101161.9. [10.1016/j.imu.2023.101161]
Abstract:
When researchers are faced with building machine learning (ML) radiomic models, the first choice they have
to make is what model to use. Naturally, the goal is to use the model with the best performance. But what is
the best model? It is well known in ML that modern techniques such as gradient boosting and deep learning
have better capacity than traditional models to solve complex problems in high dimensions. Despite this, most
radiomics researchers still do not focus on these models in their research. As access to high-quality and large
data sets increase, these high-capacity ML models may become even more relevant. In this article, we use
a large dataset of 949 prostate cancer patients to compare the performance of a few of the most promising
ML models for tabular data: gradient-boosted decision trees (GBDTs), multilayer perceptions, convolutional
neural networks, and transformers. To this end, we predict nine different prostate cancer pathology outcomes
of clinical interest. Our goal is to give a rough overview of how these models compare against one another in
a typical radiomics setting. We also investigate if multitask learning improves the performance of these models
when multiple targets are available. Our results suggest that GBDTs perform well across all targets, and that
multitask learning does not provide a consistent improvement.
Tipologia IRIS:
01 - Articolo su periodico
Keywords:
Radiomics; Prostate cancer; Deep learning; Gradient boost
Elenco autori:
L.J. Isaksson, M. Repetto, P.E. Summers, M. Pepa, M. Zaffaroni, M.G. Vincini, G. Corrao, G.C. Mazzola, M. Rotondi, F. Bellerba, S. Raimondi, Z. Haron, S. Alessi, P. Pricolo, F.A. Mistretta, S. Luzzago, F. Cattani, G. Musi, O. De Cobelli, M. Cremonesi, R. Orecchia, D. La Torre, G. Marvaso, G. Petralia, B.A. Jereczek-Fossa
Link alla scheda completa: