Skip to main content
. Author manuscript; available in PMC: 2022 Jun 1.
Published in final edited form as: IEEE Trans Ultrason Ferroelectr Freq Control. 2021 May 25;68(6):2038–2047. doi: 10.1109/TUFFC.2021.3052143

Fig. 1.

Fig. 1.

Convolutional neural network architecture of the models: (a) placental segmentation (PS) model; (b) the dual pathway (T - top; B - bottom pathway) hybrid (HB) model, where T encodes the PS model. The architectures of the multi-class (MC) and multi-class transfer learning (MCTL) models are not shown as they are identical to Fig 1a except for having four channels instead of two in the layer before softmax.