Early thrombus detection in ECMO with optimized impedance measurements: A simulative study

Figure 1:

Figure 2:

Figure 3:

Figure 4:

Figure 5:

Figure 6:

Figure 7:

Figure 8:

Figure 9:

Figure 10:

Figure 11:

Figures of merit chosen for position optimization NN training_

Feature	Explanation
median Jmin J \[\frac{medianJ}{\min J}\]	J homogeneity
maxσkminσk \frac{\text{max} \sigma_{k}}{\text{min} \sigma_{k}}	J condition number
medianΔVminΔV \frac{\text{median} \Delta \text{V}}{min \Delta \text{V}}	∆Vr measurement homogeneity

Overview of the FEM model component properties_

Part	Conductivity	Characteristics
BG	6.62 × 10−1 S·m−1	9 × 9 × 5 cm
Clot	6.62 × 10−2 S·m−1	Spherical targets
SG	1 ×10−6 S·m−1	Rod diameter 0.4 cm

Overview of measurement-selection methods and counts_

Maximization	Number of measurements
Parallelotope volume	144
L1-norm	32
L2-norm	32

Overview of layers for an electrode position optimization NN_

#	Layer type	Layer information
1	input layer	3-element vector
2	FC layer	254 neurons
3	ReLU layer	activation layer
4	FC layer	203 neurons
5	ReLU layer	activation layer
6	FC layer	48 neurons
7	regression layer	determine positions

Overview of layers for a thrombus detection NN_

#	Layer type	Layer information
1	input layer	208-element vector
2	FC layer	200 neurons
3	ReLU layer	activation layer
4	FC layer	100 neurons
5	ReLU layer	activation layer
6	FC layer	2 neurons
7	softmax layer	to probabilities
8	classification layer	more probable class