Automatic detection of breast lesions in automated 3D breast ultrasound with cross-organ transfer learning

Background Deep convolutional neural networks have garnered considerable attention in numerous machine learning applications,particularly in visual recognition tasks such as image and video analyses.There is a growing interest in applying this technology to diverse applications in medical image analysis.Automated three dimensional Breast Ultrasound is a vital tool for detecting breast cancer,and computer-assisted diagnosis software,developed based on deep learning,can effectively assist radiologists in diagnosis.However,the network model is prone to overfitting during training,owing to challenges such as insufficient training data.This study attempts to solve the problem caused by small datasets and improve model detection performance.Methods We propose a breast cancer detection framework based on deep learning(a transfer learning method based on cross-organ cancer detection)and a contrastive learning method based on breast imaging reporting and data systems(BI-RADS).Results When using cross organ transfer learning and BIRADS based contrastive learning,the average sensitivity of the model increased by a maximum of 16.05%.Conclusion Our experiments have demonstrated that the parameters and experiences of cross-organ cancer detection can be mutually referenced,and contrastive learning method based on BI-RADS can improve the detection performance of the model.

Equivalent Hamiltonian Equations Modelling and Energy Function Construction for MMC-HVDC in Hybrid AC/DC Power Systems

This paper proposes an equivalent Hamiltonian equations model for the modular multilevel converter-based high-voltage direct-current(MMC-HVDC)transmission system,and constructs an energy function for multi-machine power systems with MMC-HVDC transmission lines.The equivalent Hamiltonian equations model is verified to be able to track the power output dynamics of the full model of an MMC-HVDC transmission system.Both theoretical and numerical studies have been undertaken to validate that the energy function proposed for hybrid AC/DC systems satisfies the conditions of an energy function.The work of this paper bridges the gap between the well-developed direct methods of transient stability analysis and power systems with MMC-HVDC transmission lines.

Fault Ride-through Hybrid Controller for MMC-HVDC Transmission System via Switching Control Units Based on Bang-bang Funnel Controller

This paper proposes a fault ride-through hybrid controller(FRTHC)for modular multi-level converter based high-voltage direct current(MMC-HVDC)transmission systems.The FRTHC comprises four loops of cascading switching control units(SCUs).Each SCU switches between a bang-bang funnel controller(BBFC)and proportional-integral(PI)control loop according to a state-dependent switching law.The BBFC can utilize the full control capability of each control loop using three-value control signals with the maximum available magnitude.A state-dependent switching law is designed for each SCU to guarantee its structural stability.Simulation studies are conducted to verify the superior fault ride-through capability of the MMC-HVDC transmission system controlled by FRTHC,in comparison to that controlled by a vector controller(VC)and a VC with DC voltage droop control(VDRC).

On the State-dependent Switched Energy Functions of DFIG-based Wind Power Generation Systems

This paper proposes a novel state-dependent switched energy function(SdSEF)for general nonlinear autonomous systems,and constructs an SdSEF for doubly-fed induction generator(DFIG)-based wind power generation systems(WPGSs).Different from the conventional energy function,SdSEF is a piece-wise continuous function,and it satisfies the conditions of conventional energy functions on each of its continuous segments.SdSEF is designed to bridge the gap between the well-developed energy function theory and the description of system energy of complex nonlinear systems,such as power electronics converter systems.The stability criterion of nonlinear autonomous systems is investigated with SdSEF,and mathematical proof is presented.The SdSEF of a typical DFIGbased WPGS is simulated in the whole processes of a grid fault and fault recovery.Simulation results verify the negativeness of the derivative of each continuous segment of the SdSEF.

Constructing an Energy Function for Power Systems with DFIGWT Generation Based on a Synchronous-generator-mimicking Model

In this paper we construct an energy function for multi-machine power systems with doubly-fed induction generator-based wind turbine(DFIGWT)according to a synchronous-generator-mimicking(SGM)model of the DFIGWT.An SGM model is proposed to approximate the dynamics of a DFIGWT.Similar to the modelling of a synchronous generator(SG),the internal dynamics of a DFIGWT are also described with differential equations of newly constructed virtual rotor angle and internal electromotive force(EMF)in the SGM model.Moreover,the power flow of a DFIGWT is expressed by nonlinear functions of its virtual rotor angle and internal EMF.The SGM model bridges the gap between the irregular and complex modelling of DFIGWTs and the well-developed energy function construction techniques for SG models.Based on the SGM model,a numerical energy function is constructed for power systems with DFIGWT generation.Both theoretical analysis and numerical studies were undertaken to validate that the proposed energy function satisfies the necessary conditions for an energy function of a power system.