Recurrence prognosis and prediction of added benefit of adjuvant chemotherapy in early stage non-small cell lung cancer with radiomic features on baseline computed tomography

An apparatus for predicting recurrence in early stage non-small cell lung cancer (NSCLC), comprising:

• a processor;
• a memory configured to store a radiological image of a region of tissue demonstrating NSCLC;
• an input/output (I/O) interface;
• a set of circuits;
• and
• an interface that connects the processor, the memory, the I/O interface, and the set of circuits, the set of circuits comprising:
• an image acquisition circuit configured to access a radiological image of a region of tissue demonstrating early stage NSCLC, where the region of tissue includes a tumor;
• a segmentation circuit configured to define a tumoral region by segmenting the tumor represented in the radiological image, where defining the tumoral region includes defining a tumoral boundary;
• a peritumoral region generation circuit configured to define a peritumoral region based on a morphological dilation of the tumoral boundary;
• a radiomic signature circuit configured to extract a radiomic signature from the radiological image, where the radiomic signature includes a set of tumoral radiomic features extracted from the tumoral region, and a set of peritumoral radiomic features extracted from the peritumoral region, where the set of tumoral radiomic features and the set of peritumoral radiomic features are selected based on a continuous time to event data;
• a radiomic score circuit configured to:
• compute a radiomic score based on the radiomic signature;
• an NSCLC prediction and prognosis circuit configured to:
• compute a probability of added benefit of adjuvant chemotherapy based, at least in part, on the radiomic score;
• and
• generate an NSCLC recurrence prognosis based, at least in part, on the radiomic score;
• and
• a display circuit configured to display the radiomic score, and at least one of the NSCLC recurrence prognosis, the probability of added benefit, or the radiological image.

A non-transitory computer-readable storage device storing computer-executable instructions that when executed control a computer to perform a method, the method comprising:

• accessing a radiological image of a region of tissue demonstrating cancerous pathology, where the radiological image includes a segmented tumor region and a peritumoral region;
• extracting a first set of radiomic features from the segmented tumor region;
• extracting a second, different set of radiomic features from the peritumoral region, where the first set of radiomic features and the second, different set of radiomic features are selected based on a continuous disease free survival (DFS) time data;
• computing a radiomic score based on a linear combination of a raw feature value of a member of the first set of radiomic features or a member of the second, different set of radiomic features, multiplied by a least absolute shrinkage and selection operator (LASSO) coefficient of the raw feature value of the member of the first set of radiomic features or the member of the second, different set of radiomic features, respectively;
• generating a prediction of added benefit of adjuvant chemotherapy based, at least in part, on the radiomic score;
• generating a disease recurrence prognosis based, at least in part, on the radiomic score;
• and
• displaying at least one of the prediction of added benefit, the disease recurrence prognosis, or the radiomic score.