Skip to Main content Skip to Navigation
Journal articles

Prostate cancer detection using residual networks

Abstract : Purpose - To automatically identify regions where prostate cancer is suspected on multi-parametric magnetic resonance images (mp-MRI). Methods - A residual network was implemented based on segmentations from an expert radiologist on T2-weighted, apparent diffusion coefficient map, and high b-value diffusion-weighted images. Mp-MRIs from 346 patients were used in this study. Results - The residual network achieved a hit or miss accuracy of 93% for lesion detection, with an average Jaccard score of 71% that compared the agreement between network and radiologist segmentations. Conclusion - This paper demonstrated the ability for residual networks to learn features for prostate lesion segmentation.
Document type :
Journal articles
Complete list of metadatas

https://hal-univ-rennes1.archives-ouvertes.fr/hal-02378879
Contributor : Laurent Jonchère <>
Submitted on : Monday, November 25, 2019 - 2:05:51 PM
Last modification on : Friday, March 6, 2020 - 2:57:21 PM

Links full text

Identifiers

Collections

Citation

Helen Xu, John Baxter, Oguz Akin, Diego Cantor-Rivera. Prostate cancer detection using residual networks. International Journal of Computer Assisted Radiology and Surgery, Springer Verlag, 2019, 14 (10), pp.1647-1650. ⟨10.1007/s11548-019-01967-5⟩. ⟨hal-02378879⟩

Share

Metrics

Record views

31