Portable Ultrasound Research System for Use in Automated Bladder Monitoring with Machine-Learning-Based Segmentation
We developed a new mobile ultrasound device for long-term and automated bladder monitoring without user interaction consisting of 32 transmit and receive electronics as well as a 32-element phased array 3 MHz transducer. The device architecture is based on data digitization and rapid transfer to a c...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/19/6481 |
| _version_ | 1797515709167697920 |
|---|---|
| author | Marc Fournelle Tobias Grün Daniel Speicher Steffen Weber Mehmet Yilmaz Dominik Schoeb Arkadiusz Miernik Gerd Reis Steffen Tretbar Holger Hewener |
| author_facet | Marc Fournelle Tobias Grün Daniel Speicher Steffen Weber Mehmet Yilmaz Dominik Schoeb Arkadiusz Miernik Gerd Reis Steffen Tretbar Holger Hewener |
| author_sort | Marc Fournelle |
| collection | DOAJ |
| description | We developed a new mobile ultrasound device for long-term and automated bladder monitoring without user interaction consisting of 32 transmit and receive electronics as well as a 32-element phased array 3 MHz transducer. The device architecture is based on data digitization and rapid transfer to a consumer electronics device (e.g., a tablet) for signal reconstruction (e.g., by means of plane wave compounding algorithms) and further image processing. All reconstruction algorithms are implemented in the GPU, allowing real-time reconstruction and imaging. The system and the beamforming algorithms were evaluated with respect to the imaging performance on standard sonographical phantoms (CIRS multipurpose ultrasound phantom) by analyzing the resolution, the SNR and the CNR. Furthermore, ML-based segmentation algorithms were developed and assessed with respect to their ability to reliably segment human bladders with different filling levels. A corresponding CNN was trained with 253 B-mode data sets and 20 B-mode images were evaluated. The quantitative and qualitative results of the bladder segmentation are presented and compared to the ground truth obtained by manual segmentation. |
| first_indexed | 2024-03-10T06:52:06Z |
| format | Article |
| id | doaj.art-614f394b9cfc45cfa80e4d30eb6fc55f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T06:52:06Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-614f394b9cfc45cfa80e4d30eb6fc55f2023-11-22T16:46:52ZengMDPI AGSensors1424-82202021-09-012119648110.3390/s21196481Portable Ultrasound Research System for Use in Automated Bladder Monitoring with Machine-Learning-Based SegmentationMarc Fournelle0Tobias Grün1Daniel Speicher2Steffen Weber3Mehmet Yilmaz4Dominik Schoeb5Arkadiusz Miernik6Gerd Reis7Steffen Tretbar8Holger Hewener9Department of Ultrasound, Fraunhofer Institute for Biomedical Engineering, 66280 Sulzbach, GermanyDepartment of Ultrasound, Fraunhofer Institute for Biomedical Engineering, 66280 Sulzbach, GermanyDepartment of Ultrasound, Fraunhofer Institute for Biomedical Engineering, 66280 Sulzbach, GermanyDepartment of Ultrasound, Fraunhofer Institute for Biomedical Engineering, 66280 Sulzbach, GermanyDepartment of Urology, Faculty of Medicine, Universitätsklinikum Freiburg University of Freiburg, Hugstetter Str. 55, 79106 Freiburg, GermanyDepartment of Urology, Faculty of Medicine, Universitätsklinikum Freiburg University of Freiburg, Hugstetter Str. 55, 79106 Freiburg, GermanyDepartment of Urology, Faculty of Medicine, Universitätsklinikum Freiburg University of Freiburg, Hugstetter Str. 55, 79106 Freiburg, GermanyDFKI—German Research Center for Artificial Intelligence, Trippstadter Straße 122, 67663 Kaiserslautern, GermanyDepartment of Ultrasound, Fraunhofer Institute for Biomedical Engineering, 66280 Sulzbach, GermanyDepartment of Ultrasound, Fraunhofer Institute for Biomedical Engineering, 66280 Sulzbach, GermanyWe developed a new mobile ultrasound device for long-term and automated bladder monitoring without user interaction consisting of 32 transmit and receive electronics as well as a 32-element phased array 3 MHz transducer. The device architecture is based on data digitization and rapid transfer to a consumer electronics device (e.g., a tablet) for signal reconstruction (e.g., by means of plane wave compounding algorithms) and further image processing. All reconstruction algorithms are implemented in the GPU, allowing real-time reconstruction and imaging. The system and the beamforming algorithms were evaluated with respect to the imaging performance on standard sonographical phantoms (CIRS multipurpose ultrasound phantom) by analyzing the resolution, the SNR and the CNR. Furthermore, ML-based segmentation algorithms were developed and assessed with respect to their ability to reliably segment human bladders with different filling levels. A corresponding CNN was trained with 253 B-mode data sets and 20 B-mode images were evaluated. The quantitative and qualitative results of the bladder segmentation are presented and compared to the ground truth obtained by manual segmentation.https://www.mdpi.com/1424-8220/21/19/6481POCUSmultichannel systemchannel databladder monitoringPOURmachine-learning |
| spellingShingle | Marc Fournelle Tobias Grün Daniel Speicher Steffen Weber Mehmet Yilmaz Dominik Schoeb Arkadiusz Miernik Gerd Reis Steffen Tretbar Holger Hewener Portable Ultrasound Research System for Use in Automated Bladder Monitoring with Machine-Learning-Based Segmentation Sensors POCUS multichannel system channel data bladder monitoring POUR machine-learning |
| title | Portable Ultrasound Research System for Use in Automated Bladder Monitoring with Machine-Learning-Based Segmentation |
| title_full | Portable Ultrasound Research System for Use in Automated Bladder Monitoring with Machine-Learning-Based Segmentation |
| title_fullStr | Portable Ultrasound Research System for Use in Automated Bladder Monitoring with Machine-Learning-Based Segmentation |
| title_full_unstemmed | Portable Ultrasound Research System for Use in Automated Bladder Monitoring with Machine-Learning-Based Segmentation |
| title_short | Portable Ultrasound Research System for Use in Automated Bladder Monitoring with Machine-Learning-Based Segmentation |
| title_sort | portable ultrasound research system for use in automated bladder monitoring with machine learning based segmentation |
| topic | POCUS multichannel system channel data bladder monitoring POUR machine-learning |
| url | https://www.mdpi.com/1424-8220/21/19/6481 |
| work_keys_str_mv | AT marcfournelle portableultrasoundresearchsystemforuseinautomatedbladdermonitoringwithmachinelearningbasedsegmentation AT tobiasgrun portableultrasoundresearchsystemforuseinautomatedbladdermonitoringwithmachinelearningbasedsegmentation AT danielspeicher portableultrasoundresearchsystemforuseinautomatedbladdermonitoringwithmachinelearningbasedsegmentation AT steffenweber portableultrasoundresearchsystemforuseinautomatedbladdermonitoringwithmachinelearningbasedsegmentation AT mehmetyilmaz portableultrasoundresearchsystemforuseinautomatedbladdermonitoringwithmachinelearningbasedsegmentation AT dominikschoeb portableultrasoundresearchsystemforuseinautomatedbladdermonitoringwithmachinelearningbasedsegmentation AT arkadiuszmiernik portableultrasoundresearchsystemforuseinautomatedbladdermonitoringwithmachinelearningbasedsegmentation AT gerdreis portableultrasoundresearchsystemforuseinautomatedbladdermonitoringwithmachinelearningbasedsegmentation AT steffentretbar portableultrasoundresearchsystemforuseinautomatedbladdermonitoringwithmachinelearningbasedsegmentation AT holgerhewener portableultrasoundresearchsystemforuseinautomatedbladdermonitoringwithmachinelearningbasedsegmentation |