Search: WFRF:(Thimansson Erik) >
Deep learning perfo...
Deep learning performance on MRI prostate gland segmentation : evaluation of two commercially available algorithms compared with an expert radiologist
-
- Thimansson, Erik (author)
- Lund University,Lunds universitet,Diagnostisk radiologi, Malmö,Forskargrupper vid Lunds universitet,LUCC: Lunds universitets cancercentrum,Övriga starka forskningsmiljöer,Radiology Diagnostics, Malmö,Lund University Research Groups,LUCC: Lund University Cancer Centre,Other Strong Research Environments,Helsingborg Hospital
-
- Baubeta, Erik (author)
- Lund University,Lunds universitet,Diagnostisk radiologi, Malmö,Forskargrupper vid Lunds universitet,LUCC: Lunds universitets cancercentrum,Övriga starka forskningsmiljöer,Radiology Diagnostics, Malmö,Lund University Research Groups,LUCC: Lund University Cancer Centre,Other Strong Research Environments,Skåne University Hospital
-
- Engman, Jonatan (author)
- Lund University,Lunds universitet,Diagnostisk radiologi, Malmö,Forskargrupper vid Lunds universitet,Radiology Diagnostics, Malmö,Lund University Research Groups,Skåne University Hospital
-
show more...
-
- Bjartell, Anders (author)
- Lund University,Lunds universitet,Urologisk cancerforskning, Malmö,Forskargrupper vid Lunds universitet,LUCC: Lunds universitets cancercentrum,Övriga starka forskningsmiljöer,Urological cancer, Malmö,Lund University Research Groups,LUCC: Lund University Cancer Centre,Other Strong Research Environments,Skåne University Hospital
-
- Zackrisson, Sophia (author)
- Lund University,Lunds universitet,Diagnostisk radiologi, Malmö,Forskargrupper vid Lunds universitet,LUCC: Lunds universitets cancercentrum,Övriga starka forskningsmiljöer,LTH profilområde: Avancerade ljuskällor,LTH profilområden,Lunds Tekniska Högskola,LU profilområde: Ljus och material,Lunds universitets profilområden,Radiology Diagnostics, Malmö,Lund University Research Groups,LUCC: Lund University Cancer Centre,Other Strong Research Environments,LTH Profile Area: Photon Science and Technology,LTH Profile areas,Faculty of Engineering, LTH,LU Profile Area: Light and Materials,Lund University Profile areas,Skåne University Hospital
-
show less...
-
(creator_code:org_t)
- 2024
- 2024
- English.
-
In: Journal of Medical Imaging. - 2329-4302. ; 11:1
- Related links:
-
http://dx.doi.org/10... (free)
-
show more...
-
https://lup.lub.lu.s...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- PURPOSE: Accurate whole-gland prostate segmentation is crucial for successful ultrasound-MRI fusion biopsy, focal cancer treatment, and radiation therapy techniques. Commercially available artificial intelligence (AI) models, using deep learning algorithms (DLAs) for prostate gland segmentation, are rapidly increasing in numbers. Typically, their performance in a true clinical context is scarcely examined or published. We used a heterogenous clinical MRI dataset in this study aiming to contribute to validation of AI-models.APPROACH: We included 123 patients in this retrospective multicenter (7 hospitals), multiscanner (8 scanners, 2 vendors, 1.5T and 3T) study comparing prostate contour assessment by 2 commercially available Food and Drug Association (FDA)-cleared and CE-marked algorithms (DLA1 and DLA2) using an expert radiologist's manual contours as a reference standard (RSexp) in this clinical heterogeneous MRI dataset. No in-house training of the DLAs was performed before testing. Several methods for comparing segmentation overlap were used, the Dice similarity coefficient (DSC) being the most important.RESULTS: The DSC mean and standard deviation for DLA1 versus the radiologist reference standard (RSexp) was 0.90±0.05 and for DLA2 versus RSexp it was 0.89±0.04. A paired t-test to compare the DSC for DLA1 and DLA2 showed no statistically significant difference (p=0.8).CONCLUSIONS: Two commercially available DL algorithms (FDA-cleared and CE-marked) can perform accurate whole-gland prostate segmentation on a par with expert radiologist manual planimetry on a real-world clinical dataset. Implementing AI models in the clinical routine may free up time that can be better invested in complex work tasks, adding more patient value.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Medicinteknik -- Medicinsk bildbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Medical Engineering -- Medical Image Processing (hsv//eng)
- MEDICIN OCH HÄLSOVETENSKAP -- Klinisk medicin -- Radiologi och bildbehandling (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Clinical Medicine -- Radiology, Nuclear Medicine and Medical Imaging (hsv//eng)
Publication and Content Type
- art (subject category)
- ref (subject category)
Find in a library
To the university's database