The Knowledge Hub for Medical Imaging Professionals: Transforming Radiology with Structured Reporting, Data-Driven Approaches and Multicentric Research

Access breakthrough research, innovative case studies and collaborative projects advancing radiology worldwide. Dive into our activities and product updates, and learn who we are as a company and as a team.

Customized templates in mint Lesion 3.3

mint Lesion™ 3.3 features a novel data and knowledge modelling core that enables you to customize read procedures and reporting templates – or design them easily yourself.

Among the new oncologic screening and staging guidelines, we introduce comprehensive support for ACR BI-RADS®, a refined PI-RADSv2 template, lymphoma staging following the Ann Arbor schema, PCI (Peritoneal Cancer Index) scoring, as well as TACE / HCC templates and transplantation eligibility assessment and documentation.

We have extended the interactive anatomic location maps and provide support for a more detailed classification of anatomic sites supporting standards like the RadLex® classification.

Structured Reporting Standardized Reading Procedures Data Collection Data Analysis RADS HCC

Related Resources

Related Resources

Medical personnel looking at a technical device to discuss diagnostic guidelines

2,237 Patients, 11 Hospitals, four HCC Criteria: A Comparison Study

A recent study, conducted across 11 South Korean hospitals, compared the diagnostic performance of four hepatocellular carcinoma (HCC) diagnostic…

mint Lesion screenshot with HCC diagnosis according to APASL, AASLD, LI-RADS, KLCA-NCC, and EASL guidelines

Multicentric Study: Comparison of Diagnostic Guidelines for Hepatocellular Carcinoma

Recent advancements in MRI techniques and tumor biology have led to updated hepatocellular carcinoma (HCC) diagnostic guidelines from various liver…

Schematic visualization of the federated learning study and its data infrastructure

RACOON: A Guide to Bridging the Gap Between Simulated and Real-World Federated Learning Research

Deep learning (DL) has become an important part of radiological image analysis. To train these deep-learning models, access to large and diverse…