Imperial College London
Portrait Picture

Professor Hashim Ahmed

Faculty of Medicine, Department of Surgery & Cancer

Chair in Urology (Clinical)
 
 
 
//

Contact

 

hashim.ahmed

 
 
//

Location

 

5L28Lab BlockCharing Cross Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Antonelli:2019:10.1007/s00330-019-06244-2,
author = {Antonelli, M and Johnston, EW and Dikaios, N and Cheung, KK and Sidhu, HS and Appayya, MB and Giganti, F and Simmons, LAM and Freeman, A and Allen, C and Ahmed, HU and Atkinson, D and Ourselin, S and Punwani, S},
doi = {10.1007/s00330-019-06244-2},
journal = {European Radiology},
pages = {4754--4764},
title = {Machine learning classifiers can predict Gleason pattern 4 prostate cancer with greater accuracy than experienced radiologists},
url = {http://dx.doi.org/10.1007/s00330-019-06244-2},
volume = {29},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - OBJECTIVE: The purpose of this study was: To test whether machine learning classifiers for transition zone (TZ) and peripheral zone (PZ) can correctly classify prostate tumors into those with/without a Gleason 4 component, and to compare the performance of the best performing classifiers against the opinion of three board-certified radiologists. METHODS: A retrospective analysis of prospectively acquired data was performed at a single center between 2012 and 2015. Inclusion criteria were (i) 3-T mp-MRI compliant with international guidelines, (ii) Likert ≥ 3/5 lesion, (iii) transperineal template ± targeted index lesion biopsy confirming cancer ≥ Gleason 3 + 3. Index lesions from 164 men were analyzed (119 PZ, 45 TZ). Quantitative MRI and clinical features were used and zone-specific machine learning classifiers were constructed. Models were validated using a fivefold cross-validation and a temporally separated patient cohort. Classifier performance was compared against the opinion of three board-certified radiologists. RESULTS: The best PZ classifier trained with prostate-specific antigen density, apparent diffusion coefficient (ADC), and maximum enhancement (ME) on DCE-MRI obtained a ROC area under the curve (AUC) of 0.83 following fivefold cross-validation. Diagnostic sensitivity at 50% threshold of specificity was higher for the best PZ model (0.93) when compared with the mean sensitivity of the three radiologists (0.72). The best TZ model used ADC and ME to obtain an AUC of 0.75 following fivefold cross-validation. This achieved higher diagnostic sensitivity at 50% threshold of specificity (0.88) than the mean sensitivity of the three radiologists (0.82). CONCLUSIONS: Machine learning classifiers predict Gleason pattern 4 in prostate tumors better than radiologists. KEY POINTS: • Predictive models developed from quantitative multiparametric magnetic resonance imaging regarding the characterization of prostate cancer grade
AU  - Antonelli,M
AU  - Johnston,EW
AU  - Dikaios,N
AU  - Cheung,KK
AU  - Sidhu,HS
AU  - Appayya,MB
AU  - Giganti,F
AU  - Simmons,LAM
AU  - Freeman,A
AU  - Allen,C
AU  - Ahmed,HU
AU  - Atkinson,D
AU  - Ourselin,S
AU  - Punwani,S
DO  - 10.1007/s00330-019-06244-2
EP  - 4764
PY  - 2019///
SN  - 0938-7994
SP  - 4754
TI  - Machine learning classifiers can predict Gleason pattern 4 prostate cancer with greater accuracy than experienced radiologists
T2  - European Radiology
UR  - http://dx.doi.org/10.1007/s00330-019-06244-2
UR  - https://www.ncbi.nlm.nih.gov/pubmed/31187216
UR  - https://link.springer.com/article/10.1007%2Fs00330-019-06244-2
UR  - http://hdl.handle.net/10044/1/71084
VL  - 29
ER  -
Download