Abstract: A power management integrated circuit (PMIC) soldered onto a printed circuit board, includes: a first output stage circuit and a second output stage circuit. In a separate power supply configuration, first and second current inflow pins of the first and second output stage circuits are soldered to first and second current inflow printed lines, respectively, wherein the first and second current inflow printed lines are not directly electrically connected to each other; and, first and second current outflow pins of the first and second output stage circuits are soldered to first and second current outflow printed lines respectively, wherein the first and second current outflow printed lines are not directly electrically connected to each other. In a cooperation power supply configuration, the first and second current inflow pins are both soldered to a common current inflow printed line of the PCB, to be electrically connected with each other.

Abstract: The disclosure provides a power management method. The power management method is applicable to an electronic device. The electronic device is electrically coupled to an adapter, and includes a system and a battery. The adapter has a feed power. The battery has a discharge power. The power management method of the disclosure includes: reading a power value of the battery; determining a state of the system; and discharging power to the system, when the system is in a power-on state and the power value is greater than a charging stopping value, by using the battery, and controlling, according to the discharge power and the feed power, the adapter to selectively supply power to the system. The disclosure further provides an electronic device using the power management method.

Abstract: The present invention disclose a medical image-based system for predicting lesion classification and a method thereof. The system comprises a feature data extracting module for providing a raw feature data based on a medical image, and a predicting module for outputting a predicted class and a risk index according to the raw feature data. The predicting module comprises a classification unit for generating the predicted class and a prediction score corresponding thereto according to the raw feature data, and a risk evaluation unit for generating the risk index according to the prediction score. The system provides medical personnels a reference score and a risk index to determine progression of a certain disease.