Prediction of stent expansion for treatments

A non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations, comprising:

• accessing a pre-stent intravascular optical coherence tomography (IVOCT) image of a blood vessel of a patient;
• segmenting the pre-stent IVOCT image to identify a lumen and a calcification lesion;
• extracting a plurality of features from the lumen and the calcification lesion;
• identifying a plurality of predictive features from the plurality of features, wherein the plurality of predictive features comprise a first subset of the plurality of features different from a second subset of the plurality of features, wherein the first subset of the plurality of features are more determinative of a post-stent lumen area and/or a prediction of stent expansion than the second subset of the plurality of features;
• applying a regression model to the plurality of predictive features to determine a minimum stent expansion metric (mSEM), wherein the mSEM is predictive of how much a stent will expand after implantation into the blood vessel;
• and
• classifying the blood vessel as an under-expanded stent area or well-expanded stent area by comparing the mSEM to a predetermined threshold of expansion.

An apparatus for predicting stent expansion, comprising:

• a memory configured to store a pre-stent intravascular optical coherence tomography (IVOCT) image of a blood vessel of a patient;
• a segmentation stage configured to segment the pre-stent IVOCT image to identify a lumen and a calcification lesion;
• a feature extraction stage configured to extract a plurality of features from the lumen and the calcification lesion;
• a regression model configured to operate upon the plurality of features to determine a minimum stent expansion metric (mSEM), wherein the mSEM is determined across a plurality of frames of the pre-stent IVOCT image, the mSEM indicating how much a stent will expand within the blood vessel after implantation;
• and
• a classification tool configured to utilize the mSEM to generate a classification of the blood vessel as an under-expanded area or well-expanded area.