Modeling lung cancer survival probability after or side-effects from therapy
View Patent ↗Modeling of prognosis of survivability, side-effect, or both is provided. For example, RILI is predicted using bullae information. The amount, volume or ratio of Bullae, even alone, may indicate the likelihood of complication, such as the likelihood of significant (e.g., stage 3) pneumonitis. As another example, RILI is predicted using uptake values of an imaging agent. Standardized uptake from a functional image (e.g., FDG uptake from a positron emission image), alone or in combination with other features, may indicate the likelihood of side-effect. In another example, survivability, such as two-year survivability, is predicted using blood biomarkers. The characteristics of a patient's blood may be measured and, alone or in combination with other features, may indicate the likelihood of survival. The modeling may be for survivability, side-effect, or both and may use one or more of the blood biomarker, uptake value, and bullae features.
1. A system for modeling side effects for lung cancer patients, the system comprising:
an input configured to receive lung cancer patient information representing at least lung bullae information of the lung cancer patient;
a processor configured to apply a model to the lung cancer patient information, to generate at least a side-effects prediction for the lung cancer patient as a response to radiation therapy, wherein the processor is configured to determine a ratio of the lung bullae to a lung volume, and wherein the model is applied with only said ratio to the side-effects prediction, the side-effects prediction comprising pneumonitis; and
a display configured to output the side-effects prediction generated from the model for the lung cancer patient.
2. The system of claim 1 wherein the input is configured to receive the lung bullae as the lung cancer patient information, wherein the processor is configured to determine a ratio of the lung bullae to a lung volume, and wherein the model is applied with only the ratio to generate the side-effects prediction, the side-effects prediction comprising pneumonitis.
3. The system of claim 1 wherein the model comprises a model for non-small cell lung cancer for the radiation therapy.
4. The system of claim 1 wherein the model is a machine-learned model.
5. The system of claim 1 wherein the output of the model represents a probability.
6. The system of claim 1 wherein the side-effects prediction comprises a radiation-induced lung injury prediction.
7. The system of claim 6 wherein the side-effects prediction comprises a grade of the radiation-induced lung injury prediction.
8. The system of claim 7 wherein the side-effects prediction comprises a prediction of grade 3 radiation-induced lung injury occurrence as a function of the bullae information.
9. The system of claim 1 wherein the model generates the side-effects prediction as a function of a feature vector including only the bullae information.
10. The system of claim 1 wherein the model generates the side-effects prediction by segmenting bullae from a medical image of a lung of the patient, determining a bullae volume, and determining a percentage of the bullae volume to a total lung volume, the percentage being the received bullae information.
11. The system of claim 1 wherein the model generates the side-effects prediction by applying a threshold to the bullae information.