Joint Image Quality Assessment and Brain Extraction of Fetal MRI Using Deep Learning

Liao, Lufan; Zhang, Xin; Zhao, Fenqiang; Zhong, Tao; Pei, Yuchen; Xu, Xiangmin; Wang, Li; Zhang, He; Shen, Dinggang; Li, Gang

doi:10.1007/978-3-030-59725-2_40

Cited by 11 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic image quality assessment methods for fetal brain MRIs have been proposed in a limited number of studies. 22,23 Xu et al 22 used a mean teacher method to assess the image quality of fetal brain MRI slices. They reported accuracy and AUC of 0.85 and 0.89, respectively.…”

Section: Discussionmentioning

confidence: 99%

“…They reported accuracy and AUC of 0.85 and 0.89, respectively. Liao et al 23 used a 2D U‐Net to jointly assess image quality and segment fetal brain MRI slices. They reported an accuracy, recall, F‐score of 0.99, 0.99, and 0.99, respectively.…”

Section: Discussionmentioning

confidence: 99%

“…Although fetal brain MRIs are subject to more artifacts than adult and pediatric brain MRIs, automatic image quality assessment methods for fetal brain MRIs have been proposed in a limited number of studies. 22,23 Xu et al 22 proposed a mean teacher method to assess the image quality of fetal brain MRIs. Liao et al 23 used a 2D U-Net to jointly assess image quality and segment fetal brain MRIs.…”

mentioning

confidence: 99%

“…22,23 Xu et al 22 proposed a mean teacher method to assess the image quality of fetal brain MRIs. Liao et al 23 used a 2D U-Net to jointly assess image quality and segment fetal brain MRIs. Unfortunately, these methods considered only 2D slices and not whole 3D MRI volumes.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Image Quality Assessment of Fetal Brain MRI Using Multi‐Instance Deep Learning Methods

Largent

Kapse

Barnett

et al. 2021

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Due to random motion of fetuses and maternal respirations, image quality of fetal brain MRIs varies considerably. To address this issue, visual inspection of the images is performed during acquisition phase and after 3D‐reconstruction, and the images are re‐acquired if they are deemed to be of insufficient quality. However, this process is time‐consuming and subjective. Multi‐instance (MI) deep learning methods (DLMs) may perform this task automatically. Purpose To propose an MI count‐based DLM (MI‐CB‐DLM), an MI vote‐based DLM (MI‐VB‐DLM), and an MI feature‐embedding DLM (MI‐FE‐DLM) for automatic assessment of 3D fetal‐brain MR image quality. To quantify influence of fetal gestational age (GA) on DLM performance. Study type Retrospective. Subjects Two hundred and seventy‐one MR exams from 211 fetuses (mean GA ± SD = 30.9 ± 5.5 weeks). Field Strength/Sequence T2‐weighted single‐shot fast spin‐echo acquired at 1.5 T. Assessment The T2‐weighted images were reconstructed in 3D. Then, two fetal neuroradiologists, a clinical neuroscientist, and a fetal MRI technician independently labeled the reconstructed images as 1 or 0 based on image quality (1 = high; 0 = low). These labels were fused and served as ground truth. The proposed DLMs were trained and evaluated using three repeated 10‐fold cross‐validations (training and validation sets of 244 and 27 scans). To quantify GA influence, this variable was included as an input of the DLMs. Statistical Tests DLM performance was evaluated using precision, recall, F‐score, accuracy, and AUC values. Results Precision, recall, F‐score, accuracy, and AUC averaged over the three cross validations were 0.85 ± 0.01, 0.85 ± 0.01, 0.85 ± 0.01, 0.85 ± 0.01, 0.93 ± 0.01, for MI‐CB‐DLM (without GA); 0.75 ± 0.03, 0.75 ± 0.03, 0.75 ± 0.03, 0.75 ± 0.03, 0.81 ± 0.03, for MI‐VB‐DLM (without GA); 0.81 ± 0.01, 0.81 ± 0.01, 0.81 ± 0.01, 0.81 ± 0.01, 0.89 ± 0.01, for MI‐FE‐DLM (without GA); and 0.86 ± 0.01, 0.86 ± 0.01, 0.86 ± 0.01, 0.86 ± 0.01, 0.93 ± 0.01, for MI‐CB‐DLM with GA. Data Conclusion MI‐CB‐DLM performed better than other DLMs. Including GA as an input of MI‐CB‐DLM improved its performance. MI‐CB‐DLM may potentially be used to objectively and rapidly assess fetal MR image quality. Evidence Level 4 Technical Efficacy Stage 3

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Image Quality Assessment of Fetal Brain MRI Using Multi‐Instance Deep Learning Methods

Largent

Kapse

Barnett

et al. 2021

Magnetic Resonance Imaging

View full text Add to dashboard Cite

show abstract

“…QA for fetal MRI is thus particularly critical when considering potential translation in clinical routine, where the variations in image quality might impact the measurement of interest for diagnostics at the individual level. Some works have thus introduced automated QA methods for either the clinical acquisition of 2D stacks [9][10][11][12][13][14] or the output SRR volume [15,16]. Most of them rely on a binary include/exclude criterion, and train a supervised model to identify and exclude poor quality data.…”

Section: Introductionmentioning

confidence: 99%

Assessing data quality on fetal brain MRI reconstruction: a multi-site and multi-rater study

Sanchez,

Mihailov,

Gomez

et al. 2024

Preprint

View full text Add to dashboard Cite

Quality assessment (QA) has long been considered essential to guarantee the reliability of neuroimaging studies. It is particularly important for fetal brain MRI, where unpredictable fetal motion can lead to substantial artifacts in the acquired images. Multiple images are then combined into a single volume through super-resolution reconstruction (SRR) pipelines, a step that can also introduce additional artifacts. While multiple studies designed automated quality control pipelines, no work evaluated the reproducibility of the manual quality ratings used to train these pipelines. In this work, our objective is twofold. First, we assess the inter- and intra-rater variability of the quality scoring performed by three experts on over 100 SRR images reconstructed using three different SRR pipelines. The raters were asked to assess the quality of images following 8 specific criteria like blurring or tissue contrast, providing a multi-dimensional view on image quality. We show that, using a protocol and training sessions, artifacts like bias field and blur level still have a low agreement (ICC below 0.5), while global quality scores show very high agreement (ICC = 0.9) across raters. We also observe that the SRR methods are influenced differently by factors like gestational age, input data quality and number of stacks used by reconstruction. Finally, our quality scores allow us to unveil systematic weaknesses of the different pipelines, indicating how further development could lead to more robust, well rounded SRR methods.

show abstract

Learning Spatiotemporal Probabilistic Atlas of Fetal Brains with Anatomically Constrained Registration Network

Pei¹,

Chen²,

Zhao³

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Joint Image Quality Assessment and Brain Extraction of Fetal MRI Using Deep Learning

Cited by 11 publications

References 21 publications

Image Quality Assessment of Fetal Brain MRI Using Multi‐Instance Deep Learning Methods

Image Quality Assessment of Fetal Brain MRI Using Multi‐Instance Deep Learning Methods

Assessing data quality on fetal brain MRI reconstruction: a multi-site and multi-rater study

Learning Spatiotemporal Probabilistic Atlas of Fetal Brains with Anatomically Constrained Registration Network

Contact Info

Product

Resources

About