Sökning: WFRF:(Strand A)
> (2020-2024) >
Patient-specific fi...
Patient-specific fine-tuning of convolutional neural networks for follow-up lesion quantification
-
- Jansen, Marielle J. A. (författare)
- Univ Med Ctr Utrecht, Utrecht, Netherlands.;Univ Utrecht, Image Sci Inst, Utrecht, Netherlands.
-
- Kuijf, Hugo J. (författare)
- Univ Med Ctr Utrecht, Utrecht, Netherlands.;Univ Utrecht, Image Sci Inst, Utrecht, Netherlands.
-
- Dhara, Ashis Kumar (författare)
- Uppsala universitet,Avdelningen för visuell information och interaktion
-
visa fler...
-
- Weaver, Nick A. (författare)
- Univ Med Ctr Utrecht, Brain Ctr Rudolf Magnus, Dept Neurol, Utrecht, Netherlands.
-
- Biessels, Geert Jan (författare)
- Univ Med Ctr Utrecht, Brain Ctr Rudolf Magnus, Dept Neurol, Utrecht, Netherlands.
-
- Strand, Robin, 1978- (författare)
- Uppsala universitet,Avdelningen för visuell information och interaktion
-
- Pluim, Josien P. W. (författare)
- Univ Med Ctr Utrecht, Utrecht, Netherlands.;Univ Utrecht, Image Sci Inst, Utrecht, Netherlands.
-
visa färre...
-
Univ Med Ctr Utrecht, Utrecht, Netherlands;Univ Utrecht, Image Sci Inst, Utrecht, Netherlands. Avdelningen för visuell information och interaktion (creator_code:org_t)
- SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS, 2020
- 2020
- Engelska.
-
Ingår i: Journal of Medical Imaging. - : SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS. - 2329-4302 .- 2329-4310. ; 7:6
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://uu.diva-port... (primary) (Raw object)
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Purpose: Convolutional neural network (CNN) methods have been proposed to quantify lesions in medical imaging. Commonly, more than one imaging examination is available for a patient, but the serial information in these images often remains unused. CNN-based methods have the potential to extract valuable information from previously acquired imaging to better quantify lesions on current imaging of the same patient.Approach: A pretrained CNN can be updated with a patient's previously acquired imaging: patient-specific fine-tuning (FT). In this work, we studied the improvement in performance of lesion quantification methods on magnetic resonance images after FT compared to a pretrained base CNN. We applied the method to two different approaches: the detection of liver metastases and the segmentation of brain white matter hyperintensities (WMH).Results: The patient-specific fine-tuned CNN has a better performance than the base CNN. For the liver metastases, the median true positive rate increases from 0.67 to 0.85. For the WMH segmentation, the mean Dice similarity coefficient increases from 0.82 to 0.87.Conclusions: We showed that patient-specific FT has the potential to improve the lesion quantification performance of general CNNs by exploiting a patient's previously acquired imaging.
Ämnesord
- MEDICIN OCH HÄLSOVETENSKAP -- Klinisk medicin -- Radiologi och bildbehandling (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Clinical Medicine -- Radiology, Nuclear Medicine and Medical Imaging (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Medicinteknik -- Medicinsk bildbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Medical Engineering -- Medical Image Processing (hsv//eng)
Nyckelord
- convolutional neural network
- magnetic resonance imaging
- patient-specific
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas