Parathyroid Gland Detection in Nuclear Medecine (2024)

Available

Dataset

Licence : CC BY-NC-SA doi:10.25666/DATAUBFC-2024-12-17

Data creator : Ouassim Boukhennoufa ^[1]

Related person : Jean-Marc Nicod ^[1], Noureddine Zerhouni ^[1], Hatem Boulahdour ^[2], Laurent Comas ^[3]

[1] : Franche-Comté Electronique Mécanique Thermique et Optique - Sciences et Technologies (UMR 6174) (École Nationale Supérieure de Mécanique et des Microtechniques)

[2] : Nanomedicine lab, imagery and therapeutics (Université de Franche-Comté)

[3] : Centre Hospitalier Régional Universitaire de Besançon

Description :

This repository contains different codes of a generative model NM-USNet that is a combination of a Siamese Network and a U-Net model for parathyroid glands detection through automatic image subtraction using 123-I and 99m-Tc images. The combination of the two components is monitored with an optimized loss function that includes reconstruction error (MSE of the U-NET) and similarity computed by the SN, with dynamic weighting adjustment methodology.

Disciplines :

computer science, artificial intelligence (engineering science), computer science, interdisciplinary applications (engineering science), computer science, software engineering (engineering science), radiology, nuclear medicine & medical imaging (medical research)

Keywords :

generative artificial intelligence, nuclear medicine, parathyroid glands, siamese neural network, U-net

General metadata

Data acquisition date : Oct 2024

Data acquisition methods :

Simulation or computational data :
Python code using mainly the tensorflow package. This code aims at using synthetic 123-I and 99m-TC images to train siamese and U-net networks to generate subtracted images and exhibit the parathyroid glands of the studied patient.

Update periodicity : as needed

Language : English (eng)

Formats : image/png, text/x-python

Audience : Research

Coverages

Taxonomic coverage :

Parathyroid gland detection

Species
Homo sapiens (Human)

Collection :

Publisher : GitHub

Labels : Graduate School Engineering, Physics and Sciences for Innovation and Research, Mésocentre(s) UBFC

Project and funder :

Thèse de doctorat en informatique - Ouassim Boukhennoufa
- Contrat doctoral Ministère de l'Enseignement Supérieur, de la Recherche (Ministry)

Additional information :

Source code designed and implemented during the PhD thesis of Ouassim Boukhennoufa and in collaboration with CHU of Besançon (Professor Hatem Boulahdour (UFC) and Dr. Laurent Comas (CHU)) supervised by Professor Noureddine Zerhouni and Professor Jean-Marc Nicod from SUPMICROTECH both researchers at FEMTO-ST Institute.