Early therapy response assessment of lesions

Abstract

For therapy response assessment, texture features are input for machine learning a classifier and for using a machine learnt classifier. Rather than or in addition to using formula-based texture features, data driven texture features are derived from training images. Such data driven texture features are independent analysis features, such as features from independent subspace analysis. The texture features may be used to predict the outcome of therapy based on a few number of or even one scan of the patient

Description

[0001] related application [0002] This patent document claims the benefit of the filing date under 35 U.S.C. Section 119(e) of U.S. Provisional Patent Application No. 61 / 882,143, filed September 25, 2013, the disclosure of which is incorporated by reference This article. Background technique [0003] This example relates to early treatment response assessment. In particular, computer-aided response assessment is provided. [0004] Tumor response to treatment is measured based on geometric measurements such as diameter (eg, RECIST or WHO criteria) or volume. Clinicians monitor geometric measurements with prolonged radiological scans (eg, CT or MRI) until a decision can be made about the results. Multiple rounds of treatment are performed before the clinician makes a decision based on geometric measures of whether the treatment will be successful. Long-term treatment can result in higher patient doses (eg, radiation therapy for geometric measurements and / or x-ray imaging) ...

AI Technical Summary

Problems solved by technology

However, such approaches are time consuming and / or difficult for physicians or others to perform

Images