Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos
The application of segmentation methods to medical imaging has the potential to create novel diagnostic support models. With respect to fetal ultrasound, the thoracic wall is a key structure on the assessment of the chest region for examiners to recognize the relative orientation and size of structu...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/10/12/1691 |
| _version_ | 1827699862676701184 |
|---|---|
| author | Kanto Shozu Masaaki Komatsu Akira Sakai Reina Komatsu Ai Dozen Hidenori Machino Suguru Yasutomi Tatsuya Arakaki Ken Asada Syuzo Kaneko Ryu Matsuoka Akitoshi Nakashima Akihiko Sekizawa Ryuji Hamamoto |
| author_facet | Kanto Shozu Masaaki Komatsu Akira Sakai Reina Komatsu Ai Dozen Hidenori Machino Suguru Yasutomi Tatsuya Arakaki Ken Asada Syuzo Kaneko Ryu Matsuoka Akitoshi Nakashima Akihiko Sekizawa Ryuji Hamamoto |
| author_sort | Kanto Shozu |
| collection | DOAJ |
| description | The application of segmentation methods to medical imaging has the potential to create novel diagnostic support models. With respect to fetal ultrasound, the thoracic wall is a key structure on the assessment of the chest region for examiners to recognize the relative orientation and size of structures inside the thorax, which are critical components in neonatal prognosis. In this study, to improve the segmentation performance of the thoracic wall in fetal ultrasound videos, we proposed a novel model-agnostic method using deep learning techniques: the Multi-Frame + Cylinder method (MFCY). The Multi-frame method (MF) uses time-series information of ultrasound videos, and the Cylinder method (CY) utilizes the shape of the thoracic wall. To evaluate the achieved improvement, we performed segmentation using five-fold cross-validation on 538 ultrasound frames in the four-chamber view (4CV) of 256 normal cases using U-net and DeepLabv3+. MFCY increased the mean values of the intersection over union (IoU) of thoracic wall segmentation from 0.448 to 0.493 for U-net and from 0.417 to 0.470 for DeepLabv3+. These results demonstrated that MFCY improved the segmentation performance of the thoracic wall in fetal ultrasound videos without altering the network structure. MFCY is expected to facilitate the development of diagnostic support models in fetal ultrasound by providing further accurate segmentation of the thoracic wall. |
| first_indexed | 2024-03-10T13:59:29Z |
| format | Article |
| id | doaj.art-d2cf4e6dd7694e5ba3d7e351bccdd9ec |
| institution | Directory Open Access Journal |
| issn | 2218-273X |
| language | English |
| last_indexed | 2024-03-10T13:59:29Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj.art-d2cf4e6dd7694e5ba3d7e351bccdd9ec2023-11-21T01:21:39ZengMDPI AGBiomolecules2218-273X2020-12-011012169110.3390/biom10121691Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound VideosKanto Shozu0Masaaki Komatsu1Akira Sakai2Reina Komatsu3Ai Dozen4Hidenori Machino5Suguru Yasutomi6Tatsuya Arakaki7Ken Asada8Syuzo Kaneko9Ryu Matsuoka10Akitoshi Nakashima11Akihiko Sekizawa12Ryuji Hamamoto13Division of Molecular Modification and Cancer Biology, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanDivision of Molecular Modification and Cancer Biology, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanArtificial Intelligence Laboratory, Fujitsu Laboratories Ltd., 4-1-1 Kamikodanaka, Nakahara-Ku, Kawasaki, Kanagawa 211-8588, JapanRIKEN AIP-Fujitsu Collaboration Center, RIKEN Center for Advanced Intelligence Project, 1-4-1 Nihonbashi, Chuo-ku, Tokyo 103-0027, JapanDivision of Molecular Modification and Cancer Biology, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanDivision of Molecular Modification and Cancer Biology, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanArtificial Intelligence Laboratory, Fujitsu Laboratories Ltd., 4-1-1 Kamikodanaka, Nakahara-Ku, Kawasaki, Kanagawa 211-8588, JapanDepartment of Obstetrics and Gynecology, Showa University School of Medicine, 1-5-8 Hatanodai, Shinagawa-Ku, Tokyo 142-8666, JapanDivision of Molecular Modification and Cancer Biology, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanDivision of Molecular Modification and Cancer Biology, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanRIKEN AIP-Fujitsu Collaboration Center, RIKEN Center for Advanced Intelligence Project, 1-4-1 Nihonbashi, Chuo-ku, Tokyo 103-0027, JapanDepartment of Obstetrics and Gynecology, University of Toyama, 2630 Sugitani, Toyama 930-0194, JapanDepartment of Obstetrics and Gynecology, Showa University School of Medicine, 1-5-8 Hatanodai, Shinagawa-Ku, Tokyo 142-8666, JapanDivision of Molecular Modification and Cancer Biology, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, JapanThe application of segmentation methods to medical imaging has the potential to create novel diagnostic support models. With respect to fetal ultrasound, the thoracic wall is a key structure on the assessment of the chest region for examiners to recognize the relative orientation and size of structures inside the thorax, which are critical components in neonatal prognosis. In this study, to improve the segmentation performance of the thoracic wall in fetal ultrasound videos, we proposed a novel model-agnostic method using deep learning techniques: the Multi-Frame + Cylinder method (MFCY). The Multi-frame method (MF) uses time-series information of ultrasound videos, and the Cylinder method (CY) utilizes the shape of the thoracic wall. To evaluate the achieved improvement, we performed segmentation using five-fold cross-validation on 538 ultrasound frames in the four-chamber view (4CV) of 256 normal cases using U-net and DeepLabv3+. MFCY increased the mean values of the intersection over union (IoU) of thoracic wall segmentation from 0.448 to 0.493 for U-net and from 0.417 to 0.470 for DeepLabv3+. These results demonstrated that MFCY improved the segmentation performance of the thoracic wall in fetal ultrasound videos without altering the network structure. MFCY is expected to facilitate the development of diagnostic support models in fetal ultrasound by providing further accurate segmentation of the thoracic wall.https://www.mdpi.com/2218-273X/10/12/1691deep learningfetal ultrasoundprenatal diagnosisthoracic wall segmentationmodel-agnosticensemble learning |
| spellingShingle | Kanto Shozu Masaaki Komatsu Akira Sakai Reina Komatsu Ai Dozen Hidenori Machino Suguru Yasutomi Tatsuya Arakaki Ken Asada Syuzo Kaneko Ryu Matsuoka Akitoshi Nakashima Akihiko Sekizawa Ryuji Hamamoto Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos Biomolecules deep learning fetal ultrasound prenatal diagnosis thoracic wall segmentation model-agnostic ensemble learning |
| title | Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos |
| title_full | Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos |
| title_fullStr | Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos |
| title_full_unstemmed | Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos |
| title_short | Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos |
| title_sort | model agnostic method for thoracic wall segmentation in fetal ultrasound videos |
| topic | deep learning fetal ultrasound prenatal diagnosis thoracic wall segmentation model-agnostic ensemble learning |
| url | https://www.mdpi.com/2218-273X/10/12/1691 |
| work_keys_str_mv | AT kantoshozu modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT masaakikomatsu modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT akirasakai modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT reinakomatsu modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT aidozen modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT hidenorimachino modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT suguruyasutomi modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT tatsuyaarakaki modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT kenasada modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT syuzokaneko modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT ryumatsuoka modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT akitoshinakashima modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT akihikosekizawa modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos AT ryujihamamoto modelagnosticmethodforthoracicwallsegmentationinfetalultrasoundvideos |