Luigi vs IBTR Risk Estimation

This is the client app of Luigi web application which allows you to submit an image of your case easily without special equipment and view the retrieved results on the smartphone. ----------------- Luigi: Large Scale HistoPathological Image Retrieval System - https://luigi-pathology.com/ Luigi web application has the following features. - Use a deep texture representation to calculate relevance metrics between pathological images, which enables the proposed system to find relevant images that do not depend on spatial information, such as the location of cells. - Not require extra learning; thus, any tissues, cells, and even artifacts can be searched without training. ----------------- Users can search their own histopathology image in two different databases. Luigi-Genome This database contains more than 7,000 cases from 32 cancer types with genomic features and clinical information included in The Cancer Genome Atlas (TCGA) database. Additionally, registered users can use a function for somatic mutation prediction. - TCGA: The histopathological images of Luigi are in whole or part based upon data generated by the TCGA Research Network: http://cancergenome.nih.gov/. - cBioPortal: Cerami et al. The cBio Cancer Genomics Portal: An Open Platform for Exploring Multidimensional Cancer Genomics Data. Cancer Discovery. May 2012 2; 401. Gao et al. Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal. Sci. Signal. 6, pl1 (2013). Luigi-oral This database contains 605 cases across 85 oral tumor categories, including salivary gland, odontogenic, and maxillofacial bone tumors.

This application is a tool to estimate the risk of ipsilateral breast tumor recurrence (IBTR) after breast-conserving surgery. It provides 10-year IBTR risk estimates and treatment effects, based on clinicopathological factors (age, pathological T stage, grade, margin status, lymphovascular invasion, hormone receptor status, HER2 status) and treatment options (radiation therapy, chemotherapy, endocrine therapy, anti-HER2 therapy). The application is available for both iPhone and iPad. The tool was developed using a Cox proportional hazards model from a multicenter cohort of 8,938 patients and calibrated with treatment effects from the EBCTCG meta-analysis. It is designed for use in shared decision-making between patients and clinicians, as well as for educational purposes. The development methodology was presented at the 2025 ASCO Annual Meeting (Abstract No. 575) and published in JCO Clinical Cancer Informatics (Sagara et al., 2025). For further details, please refer to the publication. Disclaimer This application is intended for educational and informational purposes only and is not a substitute for professional medical advice, diagnosis, or treatment. Clinical decisions should always be made in consultation with the treating physician. The developers assume no legal responsibility for any outcomes resulting from the use of this application.