REC-ResNet： Feature enhancement model for COVID-19 aided diagnosis

Tao ZHOU; Yuncan LIU; Senbao HOU; Xinyu YE; Huiling LU

doi:10.37188/OPE.20233114.2093

Journals >Optics and Precision Engineering >Volume 31 >Issue 14 >Page 2093 > Article

Optics and Precision Engineering
Vol. 31, Issue 14, 2093 (2023)

REC-ResNet： Feature enhancement model for COVID-19 aided diagnosis

Tao ZHOU^1,2, Yuncan LIU^1,*, Senbao HOU¹, Xinyu YE¹, and Huiling LU³

Author Affiliations

¹School of Computer Science and Engineering， North Minzu University， Yinchuan75002， China

²Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission， North Minzu University， Yinchuan75001， China

³School of Science， Ningxia Medical University， Yinchuan750004， China

show less

DOI: 10.37188/OPE.20233114.2093 Cite this Article

Tao ZHOU, Yuncan LIU, Senbao HOU, Xinyu YE, Huiling LU. REC-ResNet： Feature enhancement model for COVID-19 aided diagnosis[J]. Optics and Precision Engineering, 2023, 31(14): 2093 Copy Citation Text

EndNote(RIS)

BibTex

Plain Text

show less

Abstract

Keywords

attention mechanism chest X-Ray image COVID-19 feature enhancement residual neural network

U = U_{1}^{s} + \dots + U_{m}^{s} + \dots + U_{M}^{s}

(1)

View in Article

s_{c} = F_{g p} (u_{c}) = \frac{1}{H \times W} \sum_{i = 1}^{H} \sum_{j = 1}^{W} u_{c} (i, j)

(2)

View in Article

Z = F_{f c} (S) = δ (B N (W S))

(3)

View in Article

B_{m, c} = \frac{e^{A_{m, c} Z}}{\sum_{m = 1}^{M} e^{A_{m, c} Z}}

(4)

View in Article

v_{c} = \sum_{m = 1}^{M} B_{m, c} ∙ U_{m, c}^{s}, s . t . \sum_{m = 1}^{M} B_{m, c} = 1

(5)

View in Article

R_{o u t} = C o n v_{1 \times 1}^{1} (V) + I_{s}

(6)

View in Article

\hat{x} = x + F E_M S A (L N (x))

(7)

View in Article

y = \hat{x} + F F N (L N (\hat{x}))

(8)

View in Article

A t t e n t i o n (Q, K, V) =

(9)

View in Article

I N (S o f t m a x (C o n v_{1 \times 1} (S E (\frac{Q K^{T}}{\sqrt[]{d_{k}}})))) V

(9)

View in Article

F F N (\hat{x}) = σ (\hat{x} W_{1} + b_{1}) W_{2} + b_{2}

(10)

View in Article

Q = F_{L} W^{Q}, K = F_{H} W^{K}, V = F_{H} W^{V}

(11)

View in Article

F_{M} = F_{H} + S o f t m a x (\frac{Q K^{T}}{\sqrt[]{d_{k}}}) V

(12)

View in Article

W_{S A} = C o n v_{1 \times 1} ([F_{G M P}; F_{G V P}; F_{Φ}])

(13)

View in Article

F_{Φ} = C o n v_{1 \times 1} (δ (C o n v_{3 \times 3} (F_{L}^{'})))

(14)

View in Article

F_{L}^{''} = F_{L}^{'} \otimes W_{S A}

(15)

View in Article

F_{S} = C o n v_{3 \times 3} (F_{H}^{'})

(16)

View in Article

W_{C A} = W_{G} + W_{R}

(17)

View in Article

F_{H} = F_{H}^{'} \otimes W_{C A}

(18)

View in Article

A c c = \frac{T P + T N}{T P + F P + F N + T N}

(19)

View in Article

P r e = \frac{1}{C} \sum_{i = 1}^{C} \frac{T P_{i}}{T P_{i} + F P_{i}}

(20)

View in Article

R e c = \frac{1}{C} \sum_{i = 1}^{C} \frac{T P_{i}}{T P_{i} + F N_{i}}

(21)

View in Article

S p e = \frac{1}{C} \sum_{i = 1}^{C} \frac{T N_{i}}{T N_{i} + F P_{i}}

(22)

View in Article

F 1 S c o r e = \frac{2 \times P r e \times R e c}{P r e + R e c}

(23)

View in Article

F P R = \frac{F P}{T N + F P}

(24)

View in Article

Tao ZHOU, Yuncan LIU, Senbao HOU, Xinyu YE, Huiling LU. REC-ResNet： Feature enhancement model for COVID-19 aided diagnosis[J]. Optics and Precision Engineering, 2023, 31(14): 2093

Download Citation

Save the article for my favorites

Paper Information

微信扫一扫：分享

微信扫一扫：分享