Human Blastocyst's Zona Pellucida segmentation via boosting ensemble of complementary learning
Characteristics of Zona Pellucida (ZP), particularly its thickness, is a key indicator of human blastocyst (day-5 embryo) quality. Therefore, ZP segmentation is an important step towards achieving automatic embryo quality assessment. In this paper, a novel approach based on boosting ensemble of hybr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2018-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914818301679 |
| _version_ | 1818039346749505536 |
|---|---|
| author | Reza Moradi Rad Parvaneh Saeedi Jason Au Jon Havelock |
| author_facet | Reza Moradi Rad Parvaneh Saeedi Jason Au Jon Havelock |
| author_sort | Reza Moradi Rad |
| collection | DOAJ |
| description | Characteristics of Zona Pellucida (ZP), particularly its thickness, is a key indicator of human blastocyst (day-5 embryo) quality. Therefore, ZP segmentation is an important step towards achieving automatic embryo quality assessment. In this paper, a novel approach based on boosting ensemble of hybrid complementary learning is proposed to segment Zona Pellucida in human blastocyst images. First, an inner-ZP localization method is proposed to separate the ZP from the heavily textured area inside a blastocyst. Then, a deep Hierarchical Neural Network (HiNN) is proposed to segment ZP area. The hierarchical nature of the proposed network enables learning features with respect to their spatial location in the embryo. Finally, a Self-supervised Image-Specific Refinement (SISR) strategy is proposed as a complementary step to boost the performance. The proposed system is a hybrid approach in the sense that the HiNN learns the intra-correlation among images, while the SISR takes into account the inter-correlation within the query image. Experimental results confirm that the proposed method is capable of identifying ZP area with average Precision, Recall, Accuracy and Jaccard Index of 85.2%, 92.0%, 95.6% and 78.1%, respectively. The proposed HiNN system outperforms state of the art by 4.9% in Precision, 11.2% in Recall, 3.6% in Accuracy and 10.7% in Jaccard Index. Keywords: Zona pellucida, Human embryo, IVF, Medical image analysis, Deep neural network |
| first_indexed | 2024-12-10T07:57:11Z |
| format | Article |
| id | doaj.art-39efadcba9a54a018e4b16bcbb68ff91 |
| institution | Directory Open Access Journal |
| issn | 2352-9148 |
| language | English |
| last_indexed | 2024-12-10T07:57:11Z |
| publishDate | 2018-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj.art-39efadcba9a54a018e4b16bcbb68ff912022-12-22T01:56:53ZengElsevierInformatics in Medicine Unlocked2352-91482018-01-0113112121Human Blastocyst's Zona Pellucida segmentation via boosting ensemble of complementary learningReza Moradi Rad0Parvaneh Saeedi1Jason Au2Jon Havelock3School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada; Corresponding author.School of Engineering Science, Simon Fraser University, Burnaby, BC, CanadaPacific Centre for Reproductive Medicine, Burnaby, BC, CanadaReproductive Endocrinology and Infertility Special Interest Group, Canadian Fertility Andrology Society, Montreal, QC, CanadaCharacteristics of Zona Pellucida (ZP), particularly its thickness, is a key indicator of human blastocyst (day-5 embryo) quality. Therefore, ZP segmentation is an important step towards achieving automatic embryo quality assessment. In this paper, a novel approach based on boosting ensemble of hybrid complementary learning is proposed to segment Zona Pellucida in human blastocyst images. First, an inner-ZP localization method is proposed to separate the ZP from the heavily textured area inside a blastocyst. Then, a deep Hierarchical Neural Network (HiNN) is proposed to segment ZP area. The hierarchical nature of the proposed network enables learning features with respect to their spatial location in the embryo. Finally, a Self-supervised Image-Specific Refinement (SISR) strategy is proposed as a complementary step to boost the performance. The proposed system is a hybrid approach in the sense that the HiNN learns the intra-correlation among images, while the SISR takes into account the inter-correlation within the query image. Experimental results confirm that the proposed method is capable of identifying ZP area with average Precision, Recall, Accuracy and Jaccard Index of 85.2%, 92.0%, 95.6% and 78.1%, respectively. The proposed HiNN system outperforms state of the art by 4.9% in Precision, 11.2% in Recall, 3.6% in Accuracy and 10.7% in Jaccard Index. Keywords: Zona pellucida, Human embryo, IVF, Medical image analysis, Deep neural networkhttp://www.sciencedirect.com/science/article/pii/S2352914818301679 |
| spellingShingle | Reza Moradi Rad Parvaneh Saeedi Jason Au Jon Havelock Human Blastocyst's Zona Pellucida segmentation via boosting ensemble of complementary learning Informatics in Medicine Unlocked |
| title | Human Blastocyst's Zona Pellucida segmentation via boosting ensemble of complementary learning |
| title_full | Human Blastocyst's Zona Pellucida segmentation via boosting ensemble of complementary learning |
| title_fullStr | Human Blastocyst's Zona Pellucida segmentation via boosting ensemble of complementary learning |
| title_full_unstemmed | Human Blastocyst's Zona Pellucida segmentation via boosting ensemble of complementary learning |
| title_short | Human Blastocyst's Zona Pellucida segmentation via boosting ensemble of complementary learning |
| title_sort | human blastocyst s zona pellucida segmentation via boosting ensemble of complementary learning |
| url | http://www.sciencedirect.com/science/article/pii/S2352914818301679 |
| work_keys_str_mv | AT rezamoradirad humanblastocystszonapellucidasegmentationviaboostingensembleofcomplementarylearning AT parvanehsaeedi humanblastocystszonapellucidasegmentationviaboostingensembleofcomplementarylearning AT jasonau humanblastocystszonapellucidasegmentationviaboostingensembleofcomplementarylearning AT jonhavelock humanblastocystszonapellucidasegmentationviaboostingensembleofcomplementarylearning |