Wentao Cui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wentao Cui has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Enqing Dong
School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China
11 shared publications - Peng Xue
School of Airspace Science and Engineering, Shandong University, Weihai, China
7 shared publications Yu Fu
School of Mechanical, Electrical & Information Engineering Shandong University Weihai China
4 shared publications- Zhili Zhang
School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China
4 shared publications Huizhong Ji
School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264209, China
3 shared publicationsPeng Xue
School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264209, China
3 shared publications
Latest Publications
- 14 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. PP (15513203) , 1-11
Obstacle-Resilient Topology Optimization for Industrial IoT via DRL-Driven Potential Field
In industrial Internet of Things (IIoT), the nonline-of-sightconstraints caused by ubiquitous obstacles pose severe challenges to wireless communication. Existing clustering strategies suffer from problems of relying on idealized geometric prior information, leading to obstacle-ignorant structures, and easily causing topological discontinuities. These problems result in a severe mismatch between network topology and convergent traffic, thereby compromising both network connectivity and energy balance. To address these problems, a topology-adaptive clustering (TAC) framework based on deep reinforcement learning (DRL)-driven potential field is proposed. TAC reformulates the clustering problem as a generalized Voronoi tessellation constrained by physical potential fields. By utilizing a DRL agent to dynamically tune potential parameters within a nonconvex solution space, the framework achieves a posteriori topological awareness and adaptive obstacle avoidance. Furthermore, a generic mechanism is introduced to derive a theoretical closed-form solution for traffic load via graph theory. This graph-theoretic mechanism constructs a deterministic reward function decoupled from specific routing protocols, ensuring precise alignment between the clustering topology and intrinsic traffic demands to guarantee energy balance across various downstream protocols. Simulation results demonstrate that TAC adaptively generates obstacle-resilient topological structures, outperforming existing baseline protocols in terms of network connectivity and lifespan, offering a general, obstacle-resilient, and energy-efficient topology optimization framework for IIoTs.
- 14 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. PP (15513203) , 1-11
Obstacle-Resilient Topology Optimization for Industrial IoT via DRL-Driven Potential Field
In industrial Internet of Things (IIoT), the nonline-of-sightconstraints caused by ubiquitous obstacles pose severe challenges to wireless communication. Existing clustering strategies suffer from problems of relying on idealized geometric prior information, leading to obstacle-ignorant structures, and easily causing topological discontinuities. These problems result in a severe mismatch between network topology and convergent traffic, thereby compromising both network connectivity and energy balance. To address these problems, a topology-adaptive clustering (TAC) framework based on deep reinforcement learning (DRL)-driven potential field is proposed. TAC reformulates the clustering problem as a generalized Voronoi tessellation constrained by physical potential fields. By utilizing a DRL agent to dynamically tune potential parameters within a nonconvex solution space, the framework achieves a posteriori topological awareness and adaptive obstacle avoidance. Furthermore, a generic mechanism is introduced to derive a theoretical closed-form solution for traffic load via graph theory. This graph-theoretic mechanism constructs a deterministic reward function decoupled from specific routing protocols, ensuring precise alignment between the clustering topology and intrinsic traffic demands to guarantee energy balance across various downstream protocols. Simulation results demonstrate that TAC adaptively generates obstacle-resilient topological structures, outperforming existing baseline protocols in terms of network connectivity and lifespan, offering a general, obstacle-resilient, and energy-efficient topology optimization framework for IIoTs.
- 13 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (24) , 45050-45060
An Energy Efficiency Optimization Scheme for Uniform Line-Distributed Wireless Geophone Networks
This article focuses on energy efficiency (EE) optimization for large-scale uniform line-distributed wireless geophone networks (WGNs). To address the issues of unbalanced subnetwork load and excessive energy consumption in traditional WGNs, we propose an EE optimization scheme—Markov-chain-based clustering and farthest vector forwarding (MCBC–FVF). For intracluster energy optimization, a state transition probability model based on Markov chain (MC) is constructed for cluster head (CH) election. An energy-aware objective function with a spatial bias term is designed to reduce and balance energy consumption. For intercluster energy optimization, a farthest vector forwarding (FVF) mechanism is introduced to mitigate communication failure and low packet delivery ratio (PDR) caused by excessive distances between CHs. It also helps reduce redundant traffic and suppresses path inflation. Compared with MH-LEACH, LEACH-C, and MMRP, simulation results based on IEEE 802.15.4 demonstrate that the proposed MCBC–FVF scheme improves the first node death (FND) time by 38.68%, 22.62%, and 17.20%, respectively, while reducing intercluster average energy consumption by 32.73%, 18.41%, and 43.38%, respectively. These results indicate that MCBC–FVF not only significantly prolongs network lifetime but also provides a novel integration of probabilistic modeling and topologyaware forwarding, offering a practical and effective solution for energy-constrained WGNs.
- 13 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (24) , 45050-45060
An Energy Efficiency Optimization Scheme for Uniform Line-Distributed Wireless Geophone Networks
This article focuses on energy efficiency (EE) optimization for large-scale uniform line-distributed wireless geophone networks (WGNs). To address the issues of unbalanced subnetwork load and excessive energy consumption in traditional WGNs, we propose an EE optimization scheme—Markov-chain-based clustering and farthest vector forwarding (MCBC–FVF). For intracluster energy optimization, a state transition probability model based on Markov chain (MC) is constructed for cluster head (CH) election. An energy-aware objective function with a spatial bias term is designed to reduce and balance energy consumption. For intercluster energy optimization, a farthest vector forwarding (FVF) mechanism is introduced to mitigate communication failure and low packet delivery ratio (PDR) caused by excessive distances between CHs. It also helps reduce redundant traffic and suppresses path inflation. Compared with MH-LEACH, LEACH-C, and MMRP, simulation results based on IEEE 802.15.4 demonstrate that the proposed MCBC–FVF scheme improves the first node death (FND) time by 38.68%, 22.62%, and 17.20%, respectively, while reducing intercluster average energy consumption by 32.73%, 18.41%, and 43.38%, respectively. These results indicate that MCBC–FVF not only significantly prolongs network lifetime but also provides a novel integration of probabilistic modeling and topologyaware forwarding, offering a practical and effective solution for energy-constrained WGNs.
- 1 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Chinese Journal of Electronics
- Vol. 34 (6) , 1678-1688
A Low-Frequency Extension Method for Geophone Based on Force Balance and Approximate Integrator
To address the issue of receiving extremely low-frequency weak signals in ultra-deep oil and gas seismic exploration, a low-frequency extension method for geophone based on force balance and approximate integrator is proposed in this paper. Based on electromagnetic dynamics principles for moving-coil geophone, the force balance closed-loop model is established. After analyzing the closed-loop damping and frequency response characteristics of this model's transfer function, a highly stable and gain-compensated negative resistance conversion circuit is designed. Thereafter, a low-frequency extended accelerometer with high consistency is developed. For designing a high-sensitivity low-frequency velocity sensor, an approximate integrator suitable for this extended accelerometer is constructed based on the least squares algorithm. The problem of inconsistent sensitivity caused by component tolerance is solved by independent adjustment of gain resistors. A cost-effective, compact, and alloy waterproof housing is designed to meet the requirements of large-scale field applications. Laboratory tests show a sensitivity of $200 \mathrm{V}/(\mathrm{m}\cdot \mathrm{s}^{-2}$) with an operational bandwidth of 0.25-100 Hz, while field validation confirms the system fully meets the requirements for low-frequency signal detection.
- 1 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Chinese Journal of Electronics
- Vol. 34 (6) , 1678-1688
A Low-Frequency Extension Method for Geophone Based on Force Balance and Approximate Integrator
To address the issue of receiving extremely low-frequency weak signals in ultra-deep oil and gas seismic exploration, a low-frequency extension method for geophone based on force balance and approximate integrator is proposed in this paper. Based on electromagnetic dynamics principles for moving-coil geophone, the force balance closed-loop model is established. After analyzing the closed-loop damping and frequency response characteristics of this model's transfer function, a highly stable and gain-compensated negative resistance conversion circuit is designed. Thereafter, a low-frequency extended accelerometer with high consistency is developed. For designing a high-sensitivity low-frequency velocity sensor, an approximate integrator suitable for this extended accelerometer is constructed based on the least squares algorithm. The problem of inconsistent sensitivity caused by component tolerance is solved by independent adjustment of gain resistors. A cost-effective, compact, and alloy waterproof housing is designed to meet the requirements of large-scale field applications. Laboratory tests show a sensitivity of $200 \mathrm{V}/(\mathrm{m}\cdot \mathrm{s}^{-2}$) with an operational bandwidth of 0.25-100 Hz, while field validation confirms the system fully meets the requirements for low-frequency signal detection.
- 23 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. PP (00189456) , 1
A Low Frequency Response Extension Method with Low Noise Floor, High Sensitivity and High Temperature Stability for Geophone
In the fields of microseismic monitoring and deep earth exploration, low-frequency signal detection faces problems such as weak vibration signals, large ambient temperature changes, and complex ambient noise. A novel comprehensive low-frequency response extension method for a moving coil geophone is proposed to implement a high-sensitivity low-frequency vibration sensor with low noise floor for measuring seismic wave velocity. Based on exploring the principle of increasing the damping ratio of geophone to expand the linear variation range of acceleration with frequency, a model in which both damping and gain vary with temperature is established by introducing the temperature-dependent coil resistance parameter. Developed on the typical negative impedance conversion method, a damping adjustment circuit with temperature compensation, gain adjustment and differential noise suppression is designed comprehensively, thereby a new scheme of low-frequency response extension based on the force balance principle is proposed. To further suppress the inherent 1/f noise of the operational amplifier in the low frequency band, an acceleration-velocity conversion scheme based on a dual operational amplifier narrowband filter is designed to flatten the velocity-frequency curve while suppressing low-frequency noise. Through standard vibration table and field comparative tests, the proposed comprehensive low-frequency extension method not only extends the natural frequency of the conventional moving coil detector from 5Hz to 0.25Hz, but also has low noise, high gain (sensitivity of 420V/(m·s⁻¹)) and high-temperature stability.
- 23 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. PP (00189456) , 1
A Low Frequency Response Extension Method with Low Noise Floor, High Sensitivity and High Temperature Stability for Geophone
In the fields of microseismic monitoring and deep earth exploration, low-frequency signal detection faces problems such as weak vibration signals, large ambient temperature changes, and complex ambient noise. A novel comprehensive low-frequency response extension method for a moving coil geophone is proposed to implement a high-sensitivity low-frequency vibration sensor with low noise floor for measuring seismic wave velocity. Based on exploring the principle of increasing the damping ratio of geophone to expand the linear variation range of acceleration with frequency, a model in which both damping and gain vary with temperature is established by introducing the temperature-dependent coil resistance parameter. Developed on the typical negative impedance conversion method, a damping adjustment circuit with temperature compensation, gain adjustment and differential noise suppression is designed comprehensively, thereby a new scheme of low-frequency response extension based on the force balance principle is proposed. To further suppress the inherent 1/f noise of the operational amplifier in the low frequency band, an acceleration-velocity conversion scheme based on a dual operational amplifier narrowband filter is designed to flatten the velocity-frequency curve while suppressing low-frequency noise. Through standard vibration table and field comparative tests, the proposed comprehensive low-frequency extension method not only extends the natural frequency of the conventional moving coil detector from 5Hz to 0.25Hz, but also has low noise, high gain (sensitivity of 420V/(m·s⁻¹)) and high-temperature stability.
- 30 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
A Novel Inverse Filtering-Negative Feedback Low-Frequency Extension Method for Seismic Geophone
To address the challenge of low-frequency seismic signal measurement in ultra-deep oil and gas exploration, an inverse filtering-negative feedback low-frequency extension (IF-NF-LFE) method is proposed based on the negative feedback closed-loop (NFCL) model. An adjustable negative feedback circuit (ANFC) is firstly designed by incorporating tunable resistors. For the NFCL model comprising the ANFC and geophone electromagnetic dynamics model, the system transfer function is derived through the force-balance principle, followed by analysis of system consistency performance and frequency response characteristics. Theoretically cascading an ideal inverse filter can ensure voltage-velocity linearity but exhibit complex circuit and notable low-frequency inherent noise. Consequently, an approximate transfer function is constructed via the least-squares algorithm to asymptotically approach the ideal inverse filter, and the stability of the IF-NF-LFE system is analyzed. Finally, we implement the extension circuit, and propose a dual-frequency calibration strategy to optimize the consistency of sensitivity and cutoff frequency. Using the proposed method, a low-frequency extension circuit is designed for a 5 Hz moving-coil geophone, and its performance (sensitivity of 200 V/(m·s⁻¹) ±5%, corner frequency extended to 0.2 Hz ±5%, consistency and noise floor) is validated through standard vibration table testing. Furthermore, a small batch of compact and rugged integrated low-frequency geophones are manufactured, with multiple comparative verification tests performed under field conditions.
- 30 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
A Novel Inverse Filtering-Negative Feedback Low-Frequency Extension Method for Seismic Geophone
To address the challenge of low-frequency seismic signal measurement in ultra-deep oil and gas exploration, an inverse filtering-negative feedback low-frequency extension (IF-NF-LFE) method is proposed based on the negative feedback closed-loop (NFCL) model. An adjustable negative feedback circuit (ANFC) is firstly designed by incorporating tunable resistors. For the NFCL model comprising the ANFC and geophone electromagnetic dynamics model, the system transfer function is derived through the force-balance principle, followed by analysis of system consistency performance and frequency response characteristics. Theoretically cascading an ideal inverse filter can ensure voltage-velocity linearity but exhibit complex circuit and notable low-frequency inherent noise. Consequently, an approximate transfer function is constructed via the least-squares algorithm to asymptotically approach the ideal inverse filter, and the stability of the IF-NF-LFE system is analyzed. Finally, we implement the extension circuit, and propose a dual-frequency calibration strategy to optimize the consistency of sensitivity and cutoff frequency. Using the proposed method, a low-frequency extension circuit is designed for a 5 Hz moving-coil geophone, and its performance (sensitivity of 200 V/(m·s⁻¹) ±5%, corner frequency extended to 0.2 Hz ±5%, consistency and noise floor) is validated through standard vibration table testing. Furthermore, a small batch of compact and rugged integrated low-frequency geophones are manufactured, with multiple comparative verification tests performed under field conditions.
- Open Access
- 4 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 149456-149467
Enhancing Real-Time Simulation of the Complexity Natural Gas Pipeline Network Through MLP-Newton Algorithm for High Precision and Reliability
Aiming at the challenge of high-precision and high-reliability simulation of urban medium- and high-pressure natural gas pipeline networks, the model establishment is analyzed in detail, solution algorithm and optimization process in gas pipeline network simulation, and designs a modeling and solution method that is easy to analyze and implement to solve the complexity problem of existing natural gas pipeline network simulation algorithms. First, a steady-state simulation model was established, and the nonlinear equations were converted to linear equations using Newton’s iterative method. Then, Kirchhoff’s law and the nodal pipe segment correlation matrix are applied to establish the system of equations. Finally, by combining the iterative process of Newton’s method with the "numerical table" method, a simple calculation method based on the contribution value is established. To solve the sensitivity problem of Newton’s iterative method, the advantages of Multilayer Perceptron (MLP) in data prediction are utilized in this work. A new initial value prediction algorithm of Newton’s iterative method is proposed based on the multilayer perceptron in the real-time simulation system of gas pipeline network. In the simulation of a complex natural gas network with 134 nodes and a total length of 35.843 kilometers, the results show that the average number of iterations of the Newton’s iterative method after inputting the predicted values is reduced by 87.51% and the computation time of the simulation system is reduced by 47.32%. In addition, the absolute error between the pressure values calculated by our proposed algorithm and the pressure values calculated by the commercial software TGNET software is within 1.3% for a single point, and the average absolute error for multiple points is within 0.9%. The experimental results demonstrate the advantages of the proposed algorithm in terms of real-time, effectiveness and stability.
- 4 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 149456-149467
Open AccessEnhancing Real-Time Simulation of the Complexity Natural Gas Pipeline Network Through MLP-Newton Algorithm for High Precision and Reliability
Aiming at the challenge of high-precision and high-reliability simulation of urban medium- and high-pressure natural gas pipeline networks, the model establishment is analyzed in detail, solution algorithm and optimization process in gas pipeline network simulation, and designs a modeling and solution method that is easy to analyze and implement to solve the complexity problem of existing natural gas pipeline network simulation algorithms. First, a steady-state simulation model was established, and the nonlinear equations were converted to linear equations using Newton’s iterative method. Then, Kirchhoff’s law and the nodal pipe segment correlation matrix are applied to establish the system of equations. Finally, by combining the iterative process of Newton’s method with the "numerical table" method, a simple calculation method based on the contribution value is established. To solve the sensitivity problem of Newton’s iterative method, the advantages of Multilayer Perceptron (MLP) in data prediction are utilized in this work. A new initial value prediction algorithm of Newton’s iterative method is proposed based on the multilayer perceptron in the real-time simulation system of gas pipeline network. In the simulation of a complex natural gas network with 134 nodes and a total length of 35.843 kilometers, the results show that the average number of iterations of the Newton’s iterative method after inputting the predicted values is reduced by 87.51% and the computation time of the simulation system is reduced by 47.32%. In addition, the absolute error between the pressure values calculated by our proposed algorithm and the pressure values calculated by the commercial software TGNET software is within 1.3% for a single point, and the average absolute error for multiple points is within 0.9%. The experimental results demonstrate the advantages of the proposed algorithm in terms of real-time, effectiveness and stability.
- Open Access
A Precise Pulmonary Airway Tree Segmentation Method Using Quasi-Spherical Region Constraint and Tracheal Wall Gap Sealing
Accurate segmentation of the pulmonary airway tree is crucial for diagnosing lung diseases. To tackle the issues of low segmentation accuracy and frequent leaks in existing methods, this paper proposes a precise segmentation method using quasi-spherical region-constrained wavefront propagation with tracheal wall gap sealing. Based on the characteristic that the surface formed by seed points approximates the airway cross-section, the width of the unsegmented airway is calculated, determining the initial quasi-spherical constraint region. Using the wavefront propagation method, seed points are continuously propagated and segmented along the tracheal wall within the quasi-spherical constraint region, thus overcoming the need to determine complex segmentation directions. To seal tracheal wall gaps, a morphological closing operation is utilized to extract the characteristics of small holes and locate low-brightness tracheal wall gaps. By filling the CT values at these gaps, the method seals the tracheal wall gaps. Extensive experiments on the EXACT09 dataset demonstrate that our algorithm ranks third in segmentation completeness. Moreover, its performance in preventing airway leaks is significantly better than the top-two algorithms, effectively preventing large-scale leak-induced spread.
Open AccessA Precise Pulmonary Airway Tree Segmentation Method Using Quasi-Spherical Region Constraint and Tracheal Wall Gap Sealing
Accurate segmentation of the pulmonary airway tree is crucial for diagnosing lung diseases. To tackle the issues of low segmentation accuracy and frequent leaks in existing methods, this paper proposes a precise segmentation method using quasi-spherical region-constrained wavefront propagation with tracheal wall gap sealing. Based on the characteristic that the surface formed by seed points approximates the airway cross-section, the width of the unsegmented airway is calculated, determining the initial quasi-spherical constraint region. Using the wavefront propagation method, seed points are continuously propagated and segmented along the tracheal wall within the quasi-spherical constraint region, thus overcoming the need to determine complex segmentation directions. To seal tracheal wall gaps, a morphological closing operation is utilized to extract the characteristics of small holes and locate low-brightness tracheal wall gaps. By filling the CT values at these gaps, the method seals the tracheal wall gaps. Extensive experiments on the EXACT09 dataset demonstrate that our algorithm ranks third in segmentation completeness. Moreover, its performance in preventing airway leaks is significantly better than the top-two algorithms, effectively preventing large-scale leak-induced spread.
- 15 March 2022
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 32 (5) , 1727-1742
3D multi‐resolution attention capsule network for diagnosing multi‐pathological types of pulmonary nodules
To achieve effective diagnosis of multi‐pathological types on pulmonary nodules, a three‐dimensional (3D) multi‐resolution attention (MRA) capsule network (3D MRA‐CapsNet‐DL) was proposed by using a self‐constructed lung CT image dataset. In the construction of 3D MRA‐CapsNet‐DL, an improved dynamic routing algorithm (DRA) with limiting the update increment (called DL) was first designed to solve the inactivation problem of a large number of vector neurons. Then, MRA was used to build three kinds of multi‐path 3D MRA‐CapsNet‐DL for multi‐pathological classification. Besides, we also investigated whether the interpolation perturbation introduced by multi‐resolution methods will affect the classification performance. Experiments showed that the proposed 3D MRA‐CapsNet‐DL can achieve a better classification (79.27% ACC and 0.9056 AUC) effect than classical convolutional neural networks (CNNs), and the interpolation disturbance has favorable and unfavorable effects on the classification performance of multi‐path and single‐path models, respectively.
- 15 March 2022
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 32 (5) , 1727-1742
3D multi‐resolution attention capsule network for diagnosing multi‐pathological types of pulmonary nodules
To achieve effective diagnosis of multi‐pathological types on pulmonary nodules, a three‐dimensional (3D) multi‐resolution attention (MRA) capsule network (3D MRA‐CapsNet‐DL) was proposed by using a self‐constructed lung CT image dataset. In the construction of 3D MRA‐CapsNet‐DL, an improved dynamic routing algorithm (DRA) with limiting the update increment (called DL) was first designed to solve the inactivation problem of a large number of vector neurons. Then, MRA was used to build three kinds of multi‐path 3D MRA‐CapsNet‐DL for multi‐pathological classification. Besides, we also investigated whether the interpolation perturbation introduced by multi‐resolution methods will affect the classification performance. Experiments showed that the proposed 3D MRA‐CapsNet‐DL can achieve a better classification (79.27% ACC and 0.9056 AUC) effect than classical convolutional neural networks (CNNs), and the interpolation disturbance has favorable and unfavorable effects on the classification performance of multi‐path and single‐path models, respectively.
- 1 October 2021
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 210, 106381
Fusion of 3D lung CT and serum biomarkers for diagnosis of multiple pathological types on pulmonary nodules
- 1 October 2021
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 210, 106381
Fusion of 3D lung CT and serum biomarkers for diagnosis of multiple pathological types on pulmonary nodules
- 6 August 2021
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 32 (1) , 74-87
3D multi‐resolution deep learning model for diagnosis of multiple pathological types on pulmonary nodules
- 6 August 2021
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 32 (1) , 74-87
3D multi‐resolution deep learning model for diagnosis of multiple pathological types on pulmonary nodules