The product mint Lesion helps qualified radiologists with the image-based diagnosis and treatment response assessment of oncological diseases. Fields of application are radiological diagnosis and follow-up examinations in oncology, as well as clinical or pharmaceutical drug trials across a defined group of patients. mint Lesion implements various radiological guidelines and response evaluation criteria, such as RECIST (Response Evaluation Criteria In Solid Tumors). This also includes the assessment of the stage of oncological disease (staging) and the objective response to therapy (e.g. timepoint response / overall response). The timepoint response is an empirical measure to evaluate therapy success according to the response criteria in use. It is mainly used to assess patient cohorts in the course of clinical trials of novel therapy agents. The timepoint response may differ from a radiological assessment of response to therapy and must not be used as a surrogate. mint Lesion allows for the documentation of size and assessment of changes in size of solid tumors described by the respective criteria that are monitored by means of radiological imaging (computed tomography (CT), magnetic resonance imaging (MRI), nuclear medicine (PET, NM), digital radiography (XR, CR)). mint Lesion follows the typical workflow of follow-up examinations, from assessment to reporting, and enables the integration of a clinical-radiological software environment (PACS, Picture Archiving and Communication System). Assessment results can be exported into different electronical formats and processed further by other applications.
A software program dedicated for installation on a central server as part of a picture archiving and communication system (PACS) to allow storage, retrieval, analysis, and management of a broad range of radiological images throughout the healthcare system. As a PACS-dedicated software, it is not primarily intended for diagnosis support, triage, or treatment planning. It does not incorporate adaptive/dynamic machine learning (ML) models.
mint-medical.de