Image registration based automated lesion correspondence pipeline for longitudinal CT data

Patients diagnosed with metastatic breast cancer (mBC) typically undergo several radiographic assessments during their treatment. Accurately detecting and monitoring individual lesions over time, is crucial for making informed clinical decisions. mBC often involves multiple metastatic lesions in different organs, therefore it is imperative to accurately track and assess these lesions to gain a comprehensive understanding of the disease's response to treatment. Computerized analysis methods that rely on lesion-level tracking have often used manual matching of corresponding lesions, a time-consuming process that is prone to errors. This paper introduces an automated lesion correspondence algorithm designed to precisely track both targets' lesions (mBC lesions that are actively monitored and tracked) and non-targets' lesions (abnormalities that are not currently of primary focus) in longitudinal data. As part of a collaboration between U. S. Food and Drug Administration and Novartis Pharmaceuticals, we demonstrate the applicability of our algorithm on the anonymized data from two Phase III trials, MONALEESA-3 and MONALEESA-7. The dataset contains imaging data of patients for different followup timepoints and the radiologist annotations for the patients enrolled in the trials. Target and non-target lesions are annotated by either one or two groups of radiologists. To facilitate accurate tracking, we have developed a registration-assisted lesion correspondence algorithm. The algorithm employs a sequential two-step pipeline: (a) Firstly, an adaptive Hungarian algorithm is used to establish correspondence among lesions within a single volumetric image series which have been annotated by multiple radiologists at a specific timepoint. (b) Secondly, after establishing correspondence and assigning unique names to the lesions, three-dimensional (3D) rigid registration is applied to various image series at the same timepoint. Registration is followed by ongoing lesion correspondence based on the adaptive Hungarian algorithm and updating lesion names for accurate tracking. This iterative algorithm is then applied to all timestamps and extended across multiple timepoints for a given patient to ensure precise temporal tracking of targets and nontargets. Validation of our automated lesion correspondence algorithm is performed through triaxial plots based on axial, sagittal, and coronal views, confirming its efficacy in matching lesions.