Fully automatic fossa ovalis segmentation from computed tomography images using deep neural network with atlas-based localization
Background and objective: Information on the location of the fossa ovalis (FO) is necessary for planning interventional procedures that require an inter-atrial septal (IAS) puncture. At present, this information is obtained manually from pre-procedural medical images, which is time consuming with li...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914825000012 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841545895510802432 |
|---|---|
| author | Gakuto Aoyama Toru Tanaka Yukiteru Masuda Naoki Matsuki Ryo Ishikawa Masahiko Asami Kiyohide Satoh Takuya Sakaguchi |
| author_facet | Gakuto Aoyama Toru Tanaka Yukiteru Masuda Naoki Matsuki Ryo Ishikawa Masahiko Asami Kiyohide Satoh Takuya Sakaguchi |
| author_sort | Gakuto Aoyama |
| collection | DOAJ |
| description | Background and objective: Information on the location of the fossa ovalis (FO) is necessary for planning interventional procedures that require an inter-atrial septal (IAS) puncture. At present, this information is obtained manually from pre-procedural medical images, which is time consuming with limited reproducibility. In this paper, we propose a method to automatically segment the FO region from computed tomography (CT) images. Methods: Our proposed method roughly crops CT images based on atlas information of the FO and heart chambers, and inputs the cropped CT images to a U-Net-based deep neural network (DNN) to segment the FO region. This method was evaluated by five-fold cross validation using 215 CT images with manually annotated FO regions, and its segmentation accuracy was compared to two previously reported methods based on thinness of the IAS wall and on simple DNN. Results: The segmentation process was successful in all cases for the IAS-based method, but failed in 4 cases for the proposed method and in 30 cases for the DNN method due to irregular heart structure. For the segmentation accuracies of our proposed method, the IAS wall thinness-based method and DNN based-method, mean chamfer distances were 2.16 ± 1.43, 3.30 ± 1.37 and 2.66 ± 1.32 respectively, with the difference being statistically significant. Conclusions: These results suggest that our proposed method can automatically segment the FO region more accurately with fewer failures. |
| format | Article |
| id | doaj-art-401a4744f62c46f3ac7bd666940c2ee2 |
| institution | Kabale University |
| issn | 2352-9148 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj-art-401a4744f62c46f3ac7bd666940c2ee22025-01-11T06:41:38ZengElsevierInformatics in Medicine Unlocked2352-91482025-01-0152101613Fully automatic fossa ovalis segmentation from computed tomography images using deep neural network with atlas-based localizationGakuto Aoyama0Toru Tanaka1Yukiteru Masuda2Naoki Matsuki3Ryo Ishikawa4Masahiko Asami5Kiyohide Satoh6Takuya Sakaguchi7Research and Development Center, Canon Medical Systems Corporation, 1385 Shimoishigami, Otawara, 324-8550, Japan; Corresponding author.Canon Inc., 30-2, Shimomaruko 3-chome, Ohta-ku, Tokyo, 146-8501, JapanCanon Inc., 30-2, Shimomaruko 3-chome, Ohta-ku, Tokyo, 146-8501, JapanCanon Inc., 30-2, Shimomaruko 3-chome, Ohta-ku, Tokyo, 146-8501, JapanCanon Inc., 30-2, Shimomaruko 3-chome, Ohta-ku, Tokyo, 146-8501, JapanDivision of Cardiology, Mitsui Memorial Hospital, Kanda-Izumicho 1, Chiyoda-ku, Tokyo, 101-8643, JapanCanon Inc., 30-2, Shimomaruko 3-chome, Ohta-ku, Tokyo, 146-8501, JapanResearch and Development Center, Canon Medical Systems Corporation, 1385 Shimoishigami, Otawara, 324-8550, JapanBackground and objective: Information on the location of the fossa ovalis (FO) is necessary for planning interventional procedures that require an inter-atrial septal (IAS) puncture. At present, this information is obtained manually from pre-procedural medical images, which is time consuming with limited reproducibility. In this paper, we propose a method to automatically segment the FO region from computed tomography (CT) images. Methods: Our proposed method roughly crops CT images based on atlas information of the FO and heart chambers, and inputs the cropped CT images to a U-Net-based deep neural network (DNN) to segment the FO region. This method was evaluated by five-fold cross validation using 215 CT images with manually annotated FO regions, and its segmentation accuracy was compared to two previously reported methods based on thinness of the IAS wall and on simple DNN. Results: The segmentation process was successful in all cases for the IAS-based method, but failed in 4 cases for the proposed method and in 30 cases for the DNN method due to irregular heart structure. For the segmentation accuracies of our proposed method, the IAS wall thinness-based method and DNN based-method, mean chamfer distances were 2.16 ± 1.43, 3.30 ± 1.37 and 2.66 ± 1.32 respectively, with the difference being statistically significant. Conclusions: These results suggest that our proposed method can automatically segment the FO region more accurately with fewer failures.http://www.sciencedirect.com/science/article/pii/S2352914825000012Fossa ovalisSegmentationDeep learningComputed tomography |
| spellingShingle | Gakuto Aoyama Toru Tanaka Yukiteru Masuda Naoki Matsuki Ryo Ishikawa Masahiko Asami Kiyohide Satoh Takuya Sakaguchi Fully automatic fossa ovalis segmentation from computed tomography images using deep neural network with atlas-based localization Informatics in Medicine Unlocked Fossa ovalis Segmentation Deep learning Computed tomography |
| title | Fully automatic fossa ovalis segmentation from computed tomography images using deep neural network with atlas-based localization |
| title_full | Fully automatic fossa ovalis segmentation from computed tomography images using deep neural network with atlas-based localization |
| title_fullStr | Fully automatic fossa ovalis segmentation from computed tomography images using deep neural network with atlas-based localization |
| title_full_unstemmed | Fully automatic fossa ovalis segmentation from computed tomography images using deep neural network with atlas-based localization |
| title_short | Fully automatic fossa ovalis segmentation from computed tomography images using deep neural network with atlas-based localization |
| title_sort | fully automatic fossa ovalis segmentation from computed tomography images using deep neural network with atlas based localization |
| topic | Fossa ovalis Segmentation Deep learning Computed tomography |
| url | http://www.sciencedirect.com/science/article/pii/S2352914825000012 |
| work_keys_str_mv | AT gakutoaoyama fullyautomaticfossaovalissegmentationfromcomputedtomographyimagesusingdeepneuralnetworkwithatlasbasedlocalization AT torutanaka fullyautomaticfossaovalissegmentationfromcomputedtomographyimagesusingdeepneuralnetworkwithatlasbasedlocalization AT yukiterumasuda fullyautomaticfossaovalissegmentationfromcomputedtomographyimagesusingdeepneuralnetworkwithatlasbasedlocalization AT naokimatsuki fullyautomaticfossaovalissegmentationfromcomputedtomographyimagesusingdeepneuralnetworkwithatlasbasedlocalization AT ryoishikawa fullyautomaticfossaovalissegmentationfromcomputedtomographyimagesusingdeepneuralnetworkwithatlasbasedlocalization AT masahikoasami fullyautomaticfossaovalissegmentationfromcomputedtomographyimagesusingdeepneuralnetworkwithatlasbasedlocalization AT kiyohidesatoh fullyautomaticfossaovalissegmentationfromcomputedtomographyimagesusingdeepneuralnetworkwithatlasbasedlocalization AT takuyasakaguchi fullyautomaticfossaovalissegmentationfromcomputedtomographyimagesusingdeepneuralnetworkwithatlasbasedlocalization |