Creating a Random Forest model to predict the progression of bladder cancer

Executable of trained model presented in Boll&Vázquez Montes de Oca et al. (unpublished).

R code used for the master thesis entitled "Germline variants associated with prognosis of patients with non muscle invasive bladder cancer".

Image analysis pipelines for double stained urothelial carcinoma samples featuring the watershed-based algorithm and template matching techniques.

Using biological constraints to improve the performance of transcriptomic gene signatures

Analyses and figures related to Mossanen and Carvalho et al Eur Urol 2021 manuscript entitled "Genomic Features of Muscle-Invasive Bladder Cancer Arising After Prostate Radiotherapy"

A new tool to predict early-stage bladder cancer recurrence and progression. The application uses advanced artificial intelligence to combine state-of-the-art scales, outperforms them, and is freely available online.

Performing Automatic Identification and Staging of Urothelial Carcinoma in Bladder Cancer Patients Using a Hybrid Deep-Machine Learning Approach, Sarkar et al, MDPI Cancers, 2023.

Code, models, and pipeline for CHIMERA Challenge Task 3: predicting patient survival risk from whole-slide histopathology images, RNA expression data, and clinical features.

Transcriptomic bladder cancer biomarker discovery analysis

This is a group project

Using Keras to build a deep neural network for bladder cancer progression

Genetic alterations and expression of genes coding for FGF ligands and FGF reseptors in urothelial cancer

ML-PETIL: A machine learning tool to stratify individual patients into Yes-TIL vs. No-TIL classes that define TIL expansion potential.

Code, models, and pipeline for CHIMERA Challenge Task 2: predicting BCG response subtypes from whole-slide histopathology images and clinical data.