Search: onr:"swepub:oai:lup.lub.lu.se:a3288c56-c33e-4260-9da8-52d75a795e12" >
Pelvic U-Net : mult...
Pelvic U-Net : multi-label semantic segmentation of pelvic organs at risk for radiation therapy anal cancer patients using a deeply supervised shuffle attention convolutional neural network
-
- Lempart, Michael (author)
- Lund University,Lunds universitet,Medicinsk strålningsfysik, Malmö,Forskargrupper vid Lunds universitet,LUCC: Lunds universitets cancercentrum,Övriga starka forskningsmiljöer,Medical Radiation Physics, Malmö,Lund University Research Groups,LUCC: Lund University Cancer Centre,Other Strong Research Environments,Skåne University Hospital
-
- Nilsson, Martin P. (author)
- Skåne University Hospital
-
- Scherman, Jonas (author)
- Skåne University Hospital
-
show more...
-
- Gustafsson, Christian Jamtheim (author)
- Lund University,Lunds universitet,Medicinsk strålningsfysik, Lund,Sektion V,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Radiotherapy Physics,Forskargrupper vid Lunds universitet,Medical Radiation Physics, Lund,Section V,Department of Clinical Sciences, Lund,Faculty of Medicine,Lund University Research Groups,Skåne University Hospital
-
- Nilsson, Mikael (author)
- Lund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,LTH profilområde: Teknik för hälsa,LTH profilområden,Lunds Tekniska Högskola,Lund University Research Groups,LTH Profile Area: Engineering Health,LTH Profile areas,Faculty of Engineering, LTH
-
- Alkner, Sara (author)
- Lund University,Lunds universitet,Individuell Bröstcancerbehandling,Forskargrupper vid Lunds universitet,LUCC: Lunds universitets cancercentrum,Övriga starka forskningsmiljöer,Strålterapi,Sektion I,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Personalized Breast Cancer Treatment,Lund University Research Groups,LUCC: Lund University Cancer Centre,Other Strong Research Environments,Radiation therapy,Section I,Department of Clinical Sciences, Lund,Faculty of Medicine,Skåne University Hospital
-
- Engleson, Jens (author)
- Lund University,Lunds universitet,Strålterapi,Sektion I,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Radiation therapy,Section I,Department of Clinical Sciences, Lund,Faculty of Medicine,Skåne University Hospital
-
- Adrian, Gabriel (author)
- Lund University,Lunds universitet,Strålterapi,Sektion I,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Radiation therapy,Section I,Department of Clinical Sciences, Lund,Faculty of Medicine,Skåne University Hospital
-
- Munck af Rosenschöld, Per (author)
- Skåne University Hospital
-
- Olsson, Lars E. (author)
- Lund University,Lunds universitet,Medicinsk strålningsfysik, Malmö,Forskargrupper vid Lunds universitet,Medical Radiation Physics, Malmö,Lund University Research Groups,Skåne University Hospital
-
show less...
-
(creator_code:org_t)
- 2022-06-28
- 2022
- English.
-
In: Radiation Oncology. - : Springer Science and Business Media LLC. - 1748-717X. ; 17:1
- 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
- Background: Delineation of organs at risk (OAR) for anal cancer radiation therapy treatment planning is a manual and time-consuming process. Deep learning-based methods can accelerate and partially automate this task. The aim of this study was to develop and evaluate a deep learning model for automated and improved segmentations of OAR in the pelvic region. Methods: A 3D, deeply supervised U-Net architecture with shuffle attention, referred to as Pelvic U-Net, was trained on 143 computed tomography (CT) volumes, to segment OAR in the pelvic region, such as total bone marrow, rectum, bladder, and bowel structures. Model predictions were evaluated on an independent test dataset (n = 15) using the Dice similarity coefficient (DSC), the 95th percentile of the Hausdorff distance (HD95), and the mean surface distance (MSD). In addition, three experienced radiation oncologists rated model predictions on a scale between 1–4 (excellent, good, acceptable, not acceptable). Model performance was also evaluated with respect to segmentation time, by comparing complete manual delineation time against model prediction time without and with manual correction of the predictions. Furthermore, dosimetric implications to treatment plans were evaluated using different dose-volume histogram (DVH) indices. Results: Without any manual corrections, mean DSC values of 97%, 87% and 94% were found for total bone marrow, rectum, and bladder. Mean DSC values for bowel cavity, all bowel, small bowel, and large bowel were 95%, 91%, 87% and 81%, respectively. Total bone marrow, bladder, and bowel cavity segmentations derived from our model were rated excellent (89%, 93%, 42%), good (9%, 5%, 42%), or acceptable (2%, 2%, 16%) on average. For almost all the evaluated DVH indices, no significant difference between model predictions and manual delineations was found. Delineation time per patient could be reduced from 40 to 12 min, including manual corrections of model predictions, and to 4 min without corrections. Conclusions: Our Pelvic U-Net led to credible and clinically applicable OAR segmentations and showed improved performance compared to previous studies. Even though manual adjustments were needed for some predicted structures, segmentation time could be reduced by 70% on average. This allows for an accelerated radiation therapy treatment planning workflow for anal cancer patients.
Subject headings
- 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)
Keyword
- Anal cancer
- Deep learning
- Organs at risk
- Radiation therapy
- Semantic segmentation
Publication and Content Type
- art (subject category)
- ref (subject category)
Find in a library
To the university's database