Artificial Intelligence System (AIS) to Automatically Obtain Multiple Key Sonographic Measurements of the Fetal Brain in the Axial Views: A Validation Study

Aim ‍

To develop and validate an artificial intelligence system (AIS) to automatically obtain 9 key fetal brain measurements. 

Methods

​​A total of 2435 2D- ultrasound images of transventricular (TV) and transcerebellar (TC) planes were retrospectively obtained from 582 subjects (targeted mid trimester assessment; 3 centres) using 3 ultrasound devices (GE Voluson E8/P8/S10) to train and test a (dataset split = 80:20) a custom AI model (U - Net) to segment 10 fetal brain structures. On an independent test set (144  images;  1  per  subject),  using  the  segmentation  masks,  9  measurements  (biparietal diameter  [BPD],  occipitofrontal  diameter  [OFD],  cephalic  index  [CI],  head  circumference [HC],  atrial  width  [AW],  cavum  septum  pellucidum  [CSP]  ratio,  transcerebellar  diameter [TCD],  cisterna  magna  size  [CMS], Nuchal Fold Thickness  [NFT])  were  computed  and Benchmarked (intraclass  correlation  coefficients  [ICC],  mean  error)  against  the  manual measurements of 4 fetal medicine specialists [FMS].

Results

The  AIS offered  a  good  segmentation  performance  (mean  Dice  coefficient:  0.83). When compared to the  4  FMS,  the  automated  measurements  were  in  excellent  (BPD:  0.99,  OFD:0.95, HC: 0.98),good (CI: 0.72,TCD: 0.89), and moderate agreements (CSP ratio: 0.51, AW:0.57, CMS: 0.65, NFT: 0.68). The mean intra-rater differences for each FMS were comparable to the absolute error between the AIS and FMS panel.
Conclusions: The  proposed  AI  system  can  assist  novice  users  in  delivering  standardized  quality  prenatal examinations in high volume settings.