Primjena strojnog učenja u određivanju dobi djece na temelju rendgenskih snimki šake

undergraduate thesis

• Title (english): Application of machine learning for predicting the age of a child from X-ray hand images
• Author: Antea Ribarić
• Mentor: Mirjana Domazet-Lošo (mentor)
• Committee member: Mirjana Domazet-Lošo (predsjednik povjerenstva)
• Committee member: Nikica Hlupić (član povjerenstva)
• Committee member: Marina Bagić Babac (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Za određivanje koštane dobi iz snimki zapešća, danas se u medicinskoj struci koristi Greulich-Pyleova metoda. Ova metoda temelji se na vizualnoj usporedbi snimke s referentnim snimkama iz atlasa, stoga je idealni kandidat za programsku implementaciju pomoću strojnog učenja.
U radu sam obradila temu predviđanja koštane dobi na temelju rendgenskih snimki zapšća. Opisala sam trenutno postojeća rješenja s natjecanja Radiološkog društva Sjeverne Amerike i predložila rješenje za dani problem. Rješenje je napisano u programskom jeziku Python pomoću biblioteka Keras i TensorFlow, a temelji se na konvolucijskoj neuronskoj mreži.

Abstract (english)

Greulich-Pyle method is a standard for predicting bone age from X-ray hand images in medicine. This method is based on visual comparison of X-ray hand images with the references from the atlas, which means it is a great candidate for machine learning implementation. In this thesis, I have discussed predicting bone age from X-ray hand images. I have proposed my own solution and compared it to the existing solutions from the competition held by Radiological Society of North America. The solution, based on convolutional neural network, was written in Python using Keras and TensorFlow libraries.

• Keywords: strojno učenje; konvolucijske neuronske mreže; umjetne neuronske mreže; umjetna inteligencija; Keras; TensorFlow; InceptionV3; MobileNetV2; radiologija; koštana dob
• Keywords (english): machine learning; convolutional neural network; artificial neural network; artificial intelligence; Keras; TensorFlow; InceptionV3; MobileNetV2; radiology; bone age
• Language: croatian
• URN:NBN: urn:nbn:hr:168:158652
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 21:33:16