PMID- 34242884
OWN - NLM
STAT- MEDLINE
DCOM- 20210831
LR  - 20210831
IS  - 1724-191X (Electronic)
IS  - 1120-1797 (Linking)
VI  - 88
DP  - 2021 Aug
TI  - Automatic fetal biometry prediction using a novel deep convolutional network 
      architecture.
PG  - 127-137
LID - S1120-1797(21)00243-X [pii]
LID - 10.1016/j.ejmp.2021.06.020 [doi]
AB  - PURPOSE: Fetal biometric measurements face a number of challenges, including the 
      presence of speckle, limited soft-tissue contrast and difficulties in the 
      presence of low amniotic fluid. This work proposes a convolutional neural network 
      for automatic segmentation and measurement of fetal biometric parameters, 
      including biparietal diameter (BPD), head circumference (HC), abdominal 
      circumference (AC), and femur length (FL) from ultrasound images that relies on 
      the attention gates incorporated into the multi-feature pyramid Unet (MFP-Unet) 
      network. METHODS: The proposed approach, referred to as Attention MFP-Unet, 
      learns to extract/detect salient regions automatically to be treated as the 
      object of interest via the attention gates. After determining the type of 
      anatomical structure in the image using a convolutional neural network, Niblack's 
      thresholding technique was applied as pre-processing algorithm for head and 
      abdomen identification, whereas a novel algorithm was used for femur extraction. 
      A publicly-available dataset (HC18 grand-challenge) and clinical data of 1334 
      subjects were utilized for training and evaluation of the Attention MFP-Unet 
      algorithm. RESULTS: Dice similarity coefficient (DSC), hausdorff distance (HD), 
      percentage of good contours, the conformity coefficient, and average 
      perpendicular distance (APD) were employed for quantitative evaluation of fetal 
      anatomy segmentation. In addition, correlation analysis, good contours, and 
      conformity were employed to evaluate the accuracy of the biometry predictions. 
      Attention MFP-Unet achieved 0.98, 1.14 mm, 100%, 0.95, and 0.2 mm for DSC, HD, 
      good contours, conformity, and APD, respectively. CONCLUSIONS: Quantitative 
      evaluation demonstrated the superior performance of the Attention MFP-Unet 
      compared to state-of-the-art approaches commonly employed for automatic 
      measurement of fetal biometric parameters.
CI  - Copyright (c) 2021 Associazione Italiana di Fisica Medica. Published by Elsevier 
      Ltd. All rights reserved.
FAU - Ghelich Oghli, Mostafa
AU  - Ghelich Oghli M
AD  - Research and Development Department, Med Fanavarn Plus Co., Karaj, Iran; 
      Department of Cardiovascular Sciences, KU Leuven, Leuven, Belgium. Electronic 
      address: m.g31_mesu@yahoo.com.
FAU - Shabanzadeh, Ali
AU  - Shabanzadeh A
AD  - Research and Development Department, Med Fanavarn Plus Co., Karaj, Iran. 
      Electronic address: shabanzadeh.ali@gmail.com.
FAU - Moradi, Shakiba
AU  - Moradi S
AD  - Research and Development Department, Med Fanavarn Plus Co., Karaj, Iran.
FAU - Sirjani, Nasim
AU  - Sirjani N
AD  - Research and Development Department, Med Fanavarn Plus Co., Karaj, Iran.
FAU - Gerami, Reza
AU  - Gerami R
AD  - Radiation Sciences Research Center (RSRC), Aja University of Medical Sciences, 
      Tehran, Iran.
FAU - Ghaderi, Payam
AU  - Ghaderi P
AD  - Research and Development Department, Med Fanavarn Plus Co., Karaj, Iran.
FAU - Sanei Taheri, Morteza
AU  - Sanei Taheri M
AD  - R Department of Radiology, Shohada-e-Tajrish Hospital, Shahid Beheshti University 
      of Medical Sciences, Tehran, Iran.
FAU - Shiri, Isaac
AU  - Shiri I
AD  - Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, 
      CH-1211 Geneva 4, Switzerland.
FAU - Arabi, Hossein
AU  - Arabi H
AD  - Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, 
      CH-1211 Geneva 4, Switzerland.
FAU - Zaidi, Habib
AU  - Zaidi H
AD  - Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, 
      CH-1211 Geneva 4, Switzerland; Geneva University Neurocenter, Geneva University, 
      CH-1205 Geneva, Switzerland; Department of Nuclear Medicine and Molecular 
      Imaging, University of Groningen, University Medical Center Groningen, Groningen, 
      Netherlands; Department of Nuclear Medicine, University of Southern Denmark, 
      Odense, Denmark.
LA  - eng
PT  - Journal Article
DEP - 20210706
PL  - Italy
TA  - Phys Med
JT  - Physica medica : PM : an international journal devoted to the applications of 
      physics to medicine and biology : official journal of the Italian Association of 
      Biomedical Physics (AIFB)
JID - 9302888
SB  - IM
MH  - Algorithms
MH  - *Biometry
MH  - Head/diagnostic imaging
MH  - Humans
MH  - Image Processing, Computer-Assisted
MH  - *Neural Networks, Computer
MH  - Ultrasonography
OTO - NOTNLM
OT  - Convolutional neural network
OT  - Deep learning
OT  - Fetal biometry
OT  - Image classification
OT  - Ultrasound imaging
EDAT- 2021/07/10 06:00
MHDA- 2021/09/01 06:00
CRDT- 2021/07/09 20:20
PHST- 2021/02/06 00:00 [received]
PHST- 2021/06/23 00:00 [revised]
PHST- 2021/06/27 00:00 [accepted]
PHST- 2021/07/10 06:00 [pubmed]
PHST- 2021/09/01 06:00 [medline]
PHST- 2021/07/09 20:20 [entrez]
AID - S1120-1797(21)00243-X [pii]
AID - 10.1016/j.ejmp.2021.06.020 [doi]
PST - ppublish
SO  - Phys Med. 2021 Aug;88:127-137. doi: 10.1016/j.ejmp.2021.06.020. Epub 2021 Jul 6.