Abstract: Methods and systems for generating a predictive HER2 score using machine learning models are disclosed. An example method generally includes identifying a plurality of nuclei and membrane segments in regions of interest in an input image using a first machine learning model. For the plurality of nuclei and membrane segments identified in the input image, a plurality of features are extracted and classified into one of a plurality of feature categories. Using a second machine learning model, a predictive HER2 score indicating the likelihood of whether a stained tissue sample captured in the input image is HER2 positive or HER2 negative is generated based on the classification assigned to the plurality of extracted features associated with the plurality of segments.

Abstract: Disclosed is a signal generator that includes a memory to store tuning voltage values and offset voltage values. An adder/subtractor circuit is coupled to the memory to produce a sum and a difference of the tuning and offset voltages. A comparator circuit is coupled to the adder/subtractor circuit to receive a digitized voltage controlled oscillator tuning voltage and to compare the digitized voltage controlled oscillator tuning voltage to the sum and difference of the tuning and offset voltages to produce a window bounded by the sum and difference of the tuning and offset voltages. The comparator circuit is further configured to generate control signals. A steering current circuit is coupled to the comparator circuit to receive the control signals from the comparator circuit and to control a steering current based on the control signals.

Abstract: A signal generator is disclosed that in one form employs an indirect digital-to-analog converter (DAC) assisted frequency synthesizer for switching a steering current into or out of a phase locked loop (PLL) filter capacitor. The signal generator provides fast switching performance and loop bandwidth adjustment to reduce phase noise and improve phase jitter performance. The signal generator comprises a channel signal selector, a digital-to-analog converter, a window generator circuit, a window comparator, a steering current circuit, a PLL circuit with voltage controlled oscillator (VCO), programmable divider, and a reference oscillator.