Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
The widening gap between radiomics research and clinical translation: rethinking current practices and shared responsibilities
11
Zitationen
3
Autoren
2025
Jahr
Abstract
Despite exponential growth in radiomics literature, a substantial gap remains between published findings and integration into clinical practice. Building on the authors’ previous works and editorial experience across various journals, this paper critically examines factors contributing to this widening gap from their perspectives. Key issues include proliferation of studies prioritizing superficial novelty over foundational understanding, inherent methodological complexity that often evades rigorous scrutiny during peer review, significant publication bias, limited external testing or validation, and insufficient adherence to open science principles. The authors call for a paradigm shift, emphasizing the need to investigate dependencies and interdependencies within radiomics workflows to support standardization, encourage true independent testing by external teams, and promote adoption of methodological quality assessment and transparent reporting tools. Additionally, development of ready-to-use open science resources is highlighted as a critical step forward. Bridging this gap will require coordinated effort among researchers, reviewers, editors, and funders to ensure radiomics achieves its transformative promise in clinical practice. • Two pathways to radiomics research were discussed: superficial novelty vs deep scientific inquiry. • In radiomics, superficial novelty is prioritized over deep scientific inquiry. • Complex methods in radiomics hinder rigorous peer review. • Radiomics' credibility needs independent external testing by other teams. • Open science in radiomics must go beyond data, code, and model sharing.
Ähnliche Arbeiten
New response evaluation criteria in solid tumours: Revised RECIST guideline (version 1.1)
2008 · 28.830 Zit.
TNM Classification of Malignant Tumours
1987 · 16.123 Zit.
A survey on deep learning in medical image analysis
2017 · 13.526 Zit.
Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening
2011 · 10.749 Zit.
The American Joint Committee on Cancer: the 7th Edition of the AJCC Cancer Staging Manual and the Future of TNM
2010 · 9.104 Zit.