Skin layer classification by feedforward neural network in bioelectrical impedance spectroscopy

Ibrahim, Kiagus Aufa; Baidillah, Marlin Ramadhan; Wicaksono, Ridwan; Takei, Masahiro

doi:10.2478/joeb-2023-0004

Figures & Tables

Schematic flow of skin layer classification of conductivity change

Electrical properties of skin, fat, and muscle.

Nyquist plot based on numerical simulation of φs in the Δσ and D/H < 1 in all frequency range.

DRT results based on simulation of φs in the case of D/H < 1 in all frequency range.

The comparison of FNN results related to feature extraction of αξ effect on bipolar and tetrapolar.

Fig. 6:

The comparison of FNN results related to feature extraction of αξ effect on bipolar and tetrapolar using four matrices profile.

Experimental setup conditions with porcine skin.

DRT results based on experiment with φs = Bipolar in all frequencies.

DRT results based on experiment with φs = Tetrapolar in all frequencies.

The confusion matrix shows the highest validation accuracy of experiments of porcine skin with FNN and four impedance inputs αξ.

Comparison of sensitivity map distribution: bipolar and tetrapolar.

Experimental conditions

Configuration parameter

Measurement parameter

Injection pattern φ_s

Electrode length ratio to skin thicknessδ_b

Conductivity-changed layery_p

ConcentrationC_Nacl [mM]

Frequency pair frlh

$f_{r}^{lh}$

[kHz]

I. Bipolar

II. Tetrapolar

D/H < 1, D/H = 1, D/H > 1

Dermis (D) only

c₁ = 15

c₂ = 20;

c₃ = 25;

c₄ = 30;

c₅ = 35;

f1lh=2&10;f2lh=2&35;f3lh=2&100;f4lh=2&225;f5lh=10&35;f6lh=10&100;f7lh=10&225;f8lh=35&100;f9lh=35&225;f10lh=100&225

$\begin{array}{*{35}{l}} f_{1}^{lh}=2\And 10; \\ f_{2}^{lh}=2\And 35; \\ f_{3}^{lh}=2\And 100; \\ f_{4}^{lh}=2\And 225; \\ f_{5}^{lh}=10\And 35; \\ f_{6}^{lh}=10\And 100; \\ f_{7}^{lh}=10\And 225; \\ f_{8}^{lh}=35\And 100; \\ f_{9}^{lh}=35\And 225; \\ f_{10}^{lh}=100\And 225 \\ \end{array}$

Comparison studies of skin condition detection using only BIS or combined with machine learning algorithm_

No	Author	Skin Condition	Machine Learning Algorithm & Data Features	Frequency Pair Selection & Reason	Injection Patterns
1	Stig Ollmar [18]	Oral mucosa	NA & Ź, Θ´${\Theta }'$, Ŕ, and X′ ${X}'$	20 [kHz] & 50 [kHz]: NA	Bipolar
2	Nicander et al. [7]	Irritant dermatitis	NA & Ź	20 [kHz] & 1 [MHz]: NA	Bipolar
3	Ramos & Bertemes-Filho [36]	Skin cancer	NA & Electrical equivalent circuit	100 [Hz] – 1 [MHz]:To analyze the tetrapolar probe’s sensitivities’ frequency response. It was discovered that frequency has little effect on sensitivity.	Tetrapolar
4	Ferreira et al. [37]	Skin irritation	NA & Resistance ratio from two depth locations	20 [kHz] & 50 [kHz]:The ratio of total skin impedance obtained at low (20 [kHz]) and high frequencies (500 [kHz]) is the basis of the irritation indices.	Bipolar
5	Gessert et al. [12]	Skin melanoma	CNN and SVM & Ź and Images	1 [kHz] − 2.5 [MHz]:Following the device’s frequency range.	Bipolar
6	Luo et al. [38]	Skin cancer	NA & Transversal and longitudinal of relative permittivity and conductivity	8 – 256 [kHz]:For measurements of lesional and normal skin, intraclass correlation coefficient (ICC) conductivity values were low at 8 and 16 [kHz]. In contrast, relative permittivity ICC results displayed excellent repeatability at 16 [kHz].	Tetrapolar
7	Sarac et al. [39]	Skin cancer	NA & EIS Score	1 [kHz] – 2.5 [MHz]:The extracellular environment affects resistance to low frequencies, whereas both the intracellular and extracellular environments influence readings at higher frequencies.	Bipolar
8	This study	Skin layer classification	FNN & α_\|Z\|, α_θ, α_R, and α_X	frlh$f_{r}^{lh}$ are selected based on DRT results.	Bipolar, Tetrapolar

Comparison of FNN accuracy Acc in terms of variation of frequency pair selection from experiment results_

Frequency pair frlh$f_{r}^{lh}$ [kHz]	Bipolar Acc [%]	Tetrapolar Acc [%]
f1lh=2&10$f_{1}^{lh}=2\And 10$	44.1	1.2
f2lh=2&35$f_{2}^{lh}=2\And 35$	80.6	17.6
f3lh=2&100$f_{3}^{lh}=2\And 100$	56.5	16.5
f4lh=2&225$f_{4}^{lh}=2\And 225$	40.6	10.0
f5lh=10&35$f_{5}^{lh}=10\And 35$	88.8	90.0
f6lh=10&100$f_{6}^{lh}=10\And 100$	90.6	84.1
f7lh=10&225$f_{7}^{lh}=10\And 225$	61.2	32.4
f8lh=35&100$f_{8}^{lh}=35\And 100$	60.6	90.6
f9lh=35&225$f_{9}^{lh}=35\And 225$	55.3	25.3
f10lh=100&225$f_{10}^{lh}=100\And 225$	68.2	23.5

Parameters for training data set

Configuration parameter

Measurement parameter

Injection pattern φ_s

Electrode-length-to-skin-thickness ratio δ_b

Conductivity-changed layer ψ_p

Conductivity change Δσ_q [%]

Frequency pair frlh

$f_{r}^{lh}$

[kHz]

I. Bipolar

II. Tetrapolar

D/H < 1, D/H = 1, D/H > 1

Fixed electrode gap:

d_g = 1 [mm]

Variable electrode diameter:

d_e = {1, 2, 3}[mm]

Electrode length:

D = d_g + d_e

Fixed each layer thickness:

h^S = 50 [μm], h^E = 0.45 [mm],

h^D = 2.5 [mm], h^F = 5 [mm]

Fixed skin thickness:

H = h^S + h^E + h^D + h^F

ψ₁ = Stratum Corneum only (S)

ψ₂ = Epidermis (E) only

ψ₃ = Dermis (D) only

ψ₄ = Fat (F) only

ψ₅ = S + E

ψ₆ = E + D

ψ₇ = D + F

ψ₈ = S + E + D

ψ₉ = E + D + F

ψ₁₀ = S + E + D + F

Δσ₁ = −20

Δσ₂ = −17.5

Δσ₃ = −15

Δσ₄ = −12.5

Δσ₅ = −10

Δσ₆ = −7.5

Δσ₇ = −5

Δσ₈ = −2.5

Δσ₉ = 0

Δσ₁₀ = 2.5

Δσ₁₁ = 5

Δσ₁₂ = 7.5

Δσ₁₃ = 10

Δσ₁₄ = 12.5

Δσ₁₅ = 15

Δσ₁₆ = 17.5

Δσ₁₇ = 20

f1lh=2&10f2lh=2&35f3lh=2&100f4lh=2&225f5lh=10&35f6lh=10&100f7lh=10&225f8lh=35&100f9lh=35&225f10lh=100&225

$\begin{array}{*{35}{l}} f_{1}^{lh}=2\And 10 \\ f_{2}^{lh}=2\And 35 \\ f_{3}^{lh}=2\And 100 \\ f_{4}^{lh}=2\And 225 \\ f_{5}^{lh}=10\And 35 \\ f_{6}^{lh}=10\And 100 \\ f_{7}^{lh}=10\And 225 \\ f_{8}^{lh}=35\And 100 \\ f_{9}^{lh}=35\And 225 \\ f_{10}^{lh}=100\And 225 \\ \end{array}$

Matrix profile of αξ

Matrix Profile	Number of input features α_ξ	Details
One matrix	4	Z´,θ´,R´,X´${Z}',{\theta }',{R}',{X}'$
Two matrices	6	Z´+θ´,Z´+R´,Z´+X´,θ´+R´,θ´+X´,R´+X´${Z}'+{\theta }',{Z}'+{R}',{Z}'+{X}',{\theta }'+{R}',{\theta }'+{X}',{R}'+{X}'$
Three matrices	3	Z´+θ´+R´,Z´+θ´+X´,θ´+R´+X´${Z}'+{\theta }'+{R}',{Z}'+{\theta }'+{X}',{\theta }'+{R}'+{X}'$
Four matrices	1	Z´+θ´+R´+X´${Z}'+{\theta }'+{R}'+{X}'$

Skin layer classification by feedforward neural network in bioelectrical impedance spectroscopy

Figures & Tables

Fig.1:

Fig. 2:

Fig. 3:

Fig. 4:

Fig. 5:

Fig. 6:

Fig. 7:

Fig. 8:

Fig. 9:

Fig. 10:

Fig. 11:

Experimental conditions

Comparison studies of skin condition detection using only BIS or combined with machine learning algorithm_

Comparison of FNN accuracy Acc in terms of variation of frequency pair selection from experiment results_

Parameters for training data set

Matrix profile of αξ

Paradigm

My account