Systems and methods for improved diagnostics for nuclear medicine imaging

A method comprising:

• defining an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system;
• acquiring image data of a patient from the medical imaging system;
• calculating an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model;
• applying a classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values;
• and
• calculating an uncertainty metric based on the realizations, wherein a range of the uncertainty metric is used in the calculating operation of the confidence values.

A method comprising:

• defining an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system;
• acquiring image data of a patient from the medical imaging system;
• calculating an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model;
• applying a classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values;
• and
• overlaying the confidence values on an image volume based on the image data, wherein the confidence values are based on at least one of the realizations.

A medical imaging system, comprising:

• a plurality of detector units disposed about a gantry configured to acquire image data of a patient;
• a memory that includes a classification or ranking algorithm;
• and
• at least one processor operably coupled to the detector units, the at least one processor configured to:
• define an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system;
• acquire image data of a patient from the medical imaging system;
• calculate an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model;
• and
• apply the classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values,
• wherein the realizations are based on simulations of selections from the uncertainty model, the simulations automatically randomize parameters of the medical imaging system to select different image voxel values.

A medical imaging system, comprising:

• a plurality of detector units disposed about a gantry configured to acquire image data of a patient;
• a memory that includes a classification or ranking algorithm;
• and
• at least one processor operably coupled to the detector units, the at least one processor configured to:
• define an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system;
• acquire image data of a patient from the medical imaging system;
• calculate an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model;
• calculate an uncertainty metric based on the realizations;
• and
• and
• apply the classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values, wherein a range of the uncertainty metric is used to calculate the confidence values.

A medical imaging system, comprising:

• a plurality of detector units disposed about a gantry configured to acquire image data of a patient;
• a memory that includes a classification or ranking algorithm;
• and
• at least one processor operably coupled to the detector units, the at least one processor configured to:
• define an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system;
• acquire image data of a patient from the medical imaging system;
• calculate an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model;
• apply the classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values;
• and
• overlay the confidence values on an image volume based on the image data, wherein the confidence values are based on at least one of the realizations.

A tangible and non-transitory computer readable medium comprising one or more programmed instructions configured to direct one or more processors to:

• define an uncertainty model of a medical imaging system, wherein the uncertainty model is based on a natural-statistics distribution of the medical imaging system;
• acquire image data of a patient from the medical imaging system;
• calculate an uncertainty map of the patient based on the uncertainty model and the image data, wherein the uncertainty map represents a collection of realizations that are generated based on the image data and the uncertainty model;
• and
• applying a classification or ranking algorithm to the image data and the uncertainty map to calculate image data classification or ranking of the patient including confidence values,
• wherein the realizations are based on simulations from the uncertainty model, the simulations automatically randomize parameters of the medical imaging system to select different image voxel values.