2020
DOI: 10.1007/s00330-020-07108-w
|View full text |Cite
|
Sign up to set email alerts
|

A decade of radiomics research: are images really data or just patterns in the noise?

Abstract: Key Points• Although radiomics is potentially a promising approach to analyze medical image data, many pitfalls need to be considered to avoid a reproducibility crisis.• There is a translation gap in radiomics research, with many studies being published but so far little to no translation into clinical practice.• Going forward, more studies with higher levels of evidence are needed, ideally also focusing on prospective studies with relevant clinical impact.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

3
114
1
5

Year Published

2021
2021
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 123 publications
(123 citation statements)
references
References 17 publications
3
114
1
5
Order By: Relevance
“…In addition, ElKhamary et al suggested that median ADC was significantly different between benign and malignant OLPDs, and an ideal threshold of ADC values benefited the classification of diffuse orbital masses [ 14 ]. Notably, Lecler et al [ 15 ] and Maldonado et al [ 16 ] also reported similar results.…”
Section: Introductionsupporting
confidence: 53%
See 1 more Smart Citation
“…In addition, ElKhamary et al suggested that median ADC was significantly different between benign and malignant OLPDs, and an ideal threshold of ADC values benefited the classification of diffuse orbital masses [ 14 ]. Notably, Lecler et al [ 15 ] and Maldonado et al [ 16 ] also reported similar results.…”
Section: Introductionsupporting
confidence: 53%
“…Guo et al discovered that five features (4 from CE-T1WI and 1 from T2WI) achieved a larger AUC (> 0.70) [ 35 ]. Hou and his colleagues found bag-of-words features from CE-T1WI may significantly outperform the features from no-enhanced MR images [ 36 ]. In general, both studies indirectly provided support for our findings, suggesting that contrast-enhanced MR imaging may improve the differentiation between orbital lymphoma and IgG4-ROD.…”
Section: Discussionmentioning
confidence: 99%
“…The healthy volunteers study population was a small cohort of healthy volunteers of a younger age than typical patients with PCa. Although this may have introduced age-related heterogeneity, the reported high cross-system reproducibility of MRF is further complemented by its ability to differentiate normal PZ and TZ, which is considered less straightforward in younger adults [ 48 ]. Furthermore, the inclusion of older adults would limit our ability to sample healthy prostatic tissue due to high prevalence of benign conditions such as benign prostatic hyperplasia and prostatitis, or even undiagnosed PCa in otherwise healthy older men [ 49 , 50 ].…”
Section: Discussionmentioning
confidence: 99%
“…Schwerer, weil die Forschung auf dem Gebiet große Datenmengen zielorientiert filtert, also direkten Hypothesen folgt. Ohne vorherige Standardisierung der Datenarchive ist der Erfolg dieses Ablaufs jedoch limitiert [ 44 ]. Der klassische Ansatz von kleinen Forschungsgruppen, welche mit beschränkten lokalen Datenbanken Ergebnisse generieren und publizieren, ist bei Studien zur künstlichen Intelligenz gefährlich.…”
Section: Einsatzgebiete Der Künstlichen Intelligenzunclassified
“…Die Vielzahl der verfügbaren Daten, welche miteinander assoziiert werden, impliziert eine hohe Rate falsch-positiver Forschungsergebnisse. Insbesondere bei limitierter Studienqualität können die echten (richtig-positiven) Ergebnisse verschleiert werden [ 44 , 45 ]. Man kann Forschung auf dem Gebiet der KI mit industriellem Fischfang in trübem Wasser vergleichen.…”
Section: Einsatzgebiete Der Künstlichen Intelligenzunclassified