yimis-source/prostaaireal

How yimis-source/prostaaireal works

Prosta-AI is an academic prostate-MRI segmentation project, but the implemented runtime in this checkout is primarily dataset acquisition, quality control, preprocessing, patient-level splitting, and leakage checks. The README describes a planned 3D U-Net/MONAI inference and visualization experience; those components are represented as designed capabilities, not as sampled implementation. Edges reflect the README or excerpted callers; unsampled design details are not inferred.

Main entry points: preprocesar.py Preprocessing runner · verificar_fuga.py Leakage verification · ejecucion 3D U-Net inference · division.py Patient split

Components 17

Dataset preparation

Dataset download scripts/descargar_datos.py
Anonymity checks scripts/verificar_anonimizacion.py
Geometry analysis scripts/analizar_geometria.py

Preprocessing

Case adapters preprocesamiento/fuentes.py
Quality control preprocesamiento/control_calidad.py
Image transforms preprocesamiento/transformaciones.py
Preprocessing runner preprocesamiento/preprocesar.py
Prepared NIfTI cases

Training data

Patient split entrenamiento/division.py
Split manifest entrenamiento/division_task05.json
Leakage verification scripts/verificar_fuga.py

Segmentation experience

3D U-Net inference docs/ejecucion
Dice and IoU docs/ejecucion
ROI overlay docs/ejecucion

Other components

Research user
Public datasets
Application user

Connections 19

Research user → Dataset download: selects dataset README.md
Dataset download → Public datasets: downloads and extracts scripts/descargar_datos.py
Research user → Anonymity checks: runs checks README.md
Research user → Geometry analysis: runs analysis README.md
Research user → Preprocessing runner: starts preprocessing README.md
Preprocessing runner → Case adapters: lists cases preprocesamiento/preprocesar.py
Preprocessing runner → Quality control: checks cases preprocesamiento/preprocesar.py
Preprocessing runner → Image transforms: transforms accepted cases preprocesamiento/preprocesar.py
Preprocessing runner → Prepared NIfTI cases: writes images and masks preprocesamiento/preprocesar.py
Research user → Patient split: creates patient split README.md
Patient split → Split manifest: writes verified split entrenamiento/division.py
Research user → Leakage verification: checks leakage README.md
Leakage verification → Patient split: validates split scripts/verificar_fuga.py
Leakage verification → Case adapters: loads cases scripts/verificar_fuga.py
Leakage verification → Quality control: reads T2 cases scripts/verificar_fuga.py
Application user → 3D U-Net inference: submits MRI README.md
3D U-Net inference → Dice and IoU: computes overlap metrics README.md
3D U-Net inference → ROI overlay: provides segmentation README.md
ROI overlay → Application user: shows ROI overlay README.md

Drawn by GitDiagram on November 10, 2026 from the repository's file tree, README and source files. Read as Markdown ·