Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight Prediction
Ultrasound is one of the most commonly used imaging methodologies in obstetrics to monitor the growth of a fetus during the gestation period. Specifically, ultrasound images are routinely utilized to gather fetal information, including body measurements, anatomy structure, fetal movements, and pregn...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/9/2229 |
| _version_ | 1797489385999958016 |
|---|---|
| author | Mahmood Alzubaidi Marco Agus Uzair Shah Michel Makhlouf Khalid Alyafei Mowafa Househ |
| author_facet | Mahmood Alzubaidi Marco Agus Uzair Shah Michel Makhlouf Khalid Alyafei Mowafa Househ |
| author_sort | Mahmood Alzubaidi |
| collection | DOAJ |
| description | Ultrasound is one of the most commonly used imaging methodologies in obstetrics to monitor the growth of a fetus during the gestation period. Specifically, ultrasound images are routinely utilized to gather fetal information, including body measurements, anatomy structure, fetal movements, and pregnancy complications. Recent developments in artificial intelligence and computer vision provide new methods for the automated analysis of medical images in many domains, including ultrasound images. We present a full end-to-end framework for segmenting, measuring, and estimating fetal gestational age and weight based on two-dimensional ultrasound images of the fetal head. Our segmentation framework is based on the following components: (i) eight segmentation architectures (UNet, UNet Plus, Attention UNet, UNet 3+, TransUNet, FPN, LinkNet, and Deeplabv3) were fine-tuned using lightweight network EffientNetB0, and (ii) a weighted voting method for building an optimized ensemble transfer learning model (ETLM). On top of that, ETLM was used to segment the fetal head and to perform analytic and accurate measurements of circumference and seven other values of the fetal head, which we incorporated into a multiple regression model for predicting the week of gestational age and the estimated fetal weight (EFW). We finally validated the regression model by comparing our result with expert physician and longitudinal references. We evaluated the performance of our framework on the public domain dataset HC18: we obtained 98.53% mean intersection over union (mIoU) as the segmentation accuracy, overcoming the state-of-the-art methods; as measurement accuracy, we obtained a 1.87 mm mean absolute difference (MAD). Finally we obtained a 0.03% mean square error (MSE) in predicting the week of gestational age and 0.05% MSE in predicting EFW. |
| first_indexed | 2024-03-10T00:15:47Z |
| format | Article |
| id | doaj.art-42eb841eb2ff4baba7fd7cca3ca9d3a4 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T00:15:47Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-42eb841eb2ff4baba7fd7cca3ca9d3a42023-11-23T15:50:47ZengMDPI AGDiagnostics2075-44182022-09-01129222910.3390/diagnostics12092229Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight PredictionMahmood Alzubaidi0Marco Agus1Uzair Shah2Michel Makhlouf3Khalid Alyafei4Mowafa Househ5College of Science and Engineering, Hamad Bin Khalifa University, Doha P.O. Box 34110 , QatarCollege of Science and Engineering, Hamad Bin Khalifa University, Doha P.O. Box 34110 , QatarCollege of Science and Engineering, Hamad Bin Khalifa University, Doha P.O. Box 34110 , QatarSidra Medical and Research Center, Sidra Medicine, Doha P.O. Box 26999, QatarSidra Medical and Research Center, Sidra Medicine, Doha P.O. Box 26999, QatarCollege of Science and Engineering, Hamad Bin Khalifa University, Doha P.O. Box 34110 , QatarUltrasound is one of the most commonly used imaging methodologies in obstetrics to monitor the growth of a fetus during the gestation period. Specifically, ultrasound images are routinely utilized to gather fetal information, including body measurements, anatomy structure, fetal movements, and pregnancy complications. Recent developments in artificial intelligence and computer vision provide new methods for the automated analysis of medical images in many domains, including ultrasound images. We present a full end-to-end framework for segmenting, measuring, and estimating fetal gestational age and weight based on two-dimensional ultrasound images of the fetal head. Our segmentation framework is based on the following components: (i) eight segmentation architectures (UNet, UNet Plus, Attention UNet, UNet 3+, TransUNet, FPN, LinkNet, and Deeplabv3) were fine-tuned using lightweight network EffientNetB0, and (ii) a weighted voting method for building an optimized ensemble transfer learning model (ETLM). On top of that, ETLM was used to segment the fetal head and to perform analytic and accurate measurements of circumference and seven other values of the fetal head, which we incorporated into a multiple regression model for predicting the week of gestational age and the estimated fetal weight (EFW). We finally validated the regression model by comparing our result with expert physician and longitudinal references. We evaluated the performance of our framework on the public domain dataset HC18: we obtained 98.53% mean intersection over union (mIoU) as the segmentation accuracy, overcoming the state-of-the-art methods; as measurement accuracy, we obtained a 1.87 mm mean absolute difference (MAD). Finally we obtained a 0.03% mean square error (MSE) in predicting the week of gestational age and 0.05% MSE in predicting EFW.https://www.mdpi.com/2075-4418/12/9/2229image segmentationensemble transfer learningfetal headgestational ageestimated fetal weightultrasound |
| spellingShingle | Mahmood Alzubaidi Marco Agus Uzair Shah Michel Makhlouf Khalid Alyafei Mowafa Househ Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight Prediction Diagnostics image segmentation ensemble transfer learning fetal head gestational age estimated fetal weight ultrasound |
| title | Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight Prediction |
| title_full | Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight Prediction |
| title_fullStr | Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight Prediction |
| title_full_unstemmed | Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight Prediction |
| title_short | Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight Prediction |
| title_sort | ensemble transfer learning for fetal head analysis from segmentation to gestational age and weight prediction |
| topic | image segmentation ensemble transfer learning fetal head gestational age estimated fetal weight ultrasound |
| url | https://www.mdpi.com/2075-4418/12/9/2229 |
| work_keys_str_mv | AT mahmoodalzubaidi ensembletransferlearningforfetalheadanalysisfromsegmentationtogestationalageandweightprediction AT marcoagus ensembletransferlearningforfetalheadanalysisfromsegmentationtogestationalageandweightprediction AT uzairshah ensembletransferlearningforfetalheadanalysisfromsegmentationtogestationalageandweightprediction AT michelmakhlouf ensembletransferlearningforfetalheadanalysisfromsegmentationtogestationalageandweightprediction AT khalidalyafei ensembletransferlearningforfetalheadanalysisfromsegmentationtogestationalageandweightprediction AT mowafahouseh ensembletransferlearningforfetalheadanalysisfromsegmentationtogestationalageandweightprediction |