A Multi-centre, Multi-Device Validation of a Deep Learning System for the Automated Segmentation of Fetal Brain Structures from Two-Dimensional Ultrasound Images

31st World Congress on Ultrasound in Obstetrics and Gynecology
October 17, 2021
Authors
Adithya Narayan, Shivam Kaushik, Hari Shankar, Shefali Jain, Nivedita Hegde, Pooja Vyas, Jagruthi Atada, S.P. Manjushree, Jens Thang, Saw Shier Nee, Arunkumar Govindarajan, Roopa P.S., Muralidhar V. Pai, Akhila Vasudeva, Prathima Radhakrishnan, Sripad Krishna Devalla

Objective

To validate (multicentre, multi-device) the robustness of a single deep learning (DL) system for the simultaneous and automated segmentation of 10 key fetal brain structures from multiple planes (transventricular [TV] and transcerebellar [TC]).

Methods

We retrospectively obtained 4,190 two-dimensional (2D) ultrasonography (USG) images (1349 pregnancies; TV + TC images) from 3 centres (2 tertiary referral centre [TRC 1,2] + 1 routine imaging centre [RIC]) using 6 ultrasound (USG) devices (GE Voluson: P8,P6,E8,E10,S10; Samsung: HERA W10). A custom U-Net was trained (2744 images from TRC 1 [E8, S10]) on 2D fetal brain images (TV + TC images) and their corresponding manual segmentations to segment 10 key fetal structures (TV + TC planes). We assessed the robustness (operator & centre variability) and generalisability (across devices) of the proposed approach across 4 independent (unseen) test sets. Test set 1 (TRC 1, trained devices): 718 images (E8, S10); test 2 (TRC 1, unseen devices): 192 images (HERA W10, P6, E10); test set 3 (TRC 2, trained device): 378 images (E8), and test set 4 (RIC, unseen device): 158 images (P8). The segmentation performance was qualitatively and quantitatively (Dice coefficient [DC]) assessed.

Results

Irrespective of the USG device/centre, the DL segmentations were qualitatively comparable to their manual segmentations. The mean (10 structures; test sets 1/2/3/4) DC were: 0.83 ± 0.09/0.80 ± 0.08/0.75 ± 0.09/0.80 ± 0.07.

Conclusion

The proposed DL system offered a promising and generalisable performance (multi centres, multi-device). Its clinical translation can assist a wide range of users across settings to deliver standardized and quality prenatal examinations.

Figure 1: Methodology of ultrasound imaging and dataset preparation
Figure 2: Results obtained from the study