Žagar, Martin
4D medical data compression architecture = Arhitektura sustava za kompresiju četverodimenzionalnih medicinskih podataka : doctoral thesis = doktorska disertacija / Martin Žagar ; [mentor Mario Kovač] - Zagreb : M. Žagar ; Fakultet elektrotehnike i računarstva, 2008. - viii, 202 str. : graf. prikazi ; 30 cm + CD
Bibliografija str. 184-193
U ovom doktorskom radu prezentirane su osnovne znaèajke arhitekture za èetvero-dimenzionalnu kompresiju medicinskih podataka koja se temelji na razlièitim procedurama i algoritmima za analizu vremenske i prostorne zalihosti MR zapisa u NIfTI podatkovnom formatu.
Za analizu i procjenu pokreta, a u cilju uklanjanja vremenske zalihosti koja postoji u slijedu 3D prostornih podataka koriste se neuronske mreže. Da bi se ostvarila kompresija takvih podataka, koristi se ekspertno znanje u razlièitim algoritmima segmentacije podataka, procjene oblika, predviðanja i definiranja polja pokreta. Frekvencijska analiza je ostvarena proširenjem transformacije temeljene na teoriji valiæa u tri dimenzije. Za statièke 3D prostorne podatke koriste se razlièite baze i paketi valiæa koji pružaju širok raspon frekvencijske analize. Uklanjanjem vremenske i prostorne zalihosti postiže se visok stupanj kompresije.
Predložena arhitektura kompresije služi u podizanju razine kvalitete usluga u telemedicini. Svaki dio ove arhitekture predstavlja zasebnu cjelinu te se može primijeniti nezavisno i u druge svrhe, kao što su aplikacije namijenjene zabavi i druge aplikacije koje koriste èetverodimenzionalne podatke. This thesis presents a novel framework for four-dimensional medical data compression architecture. This framework is based on different procedures and algorithms that detect time and spatial redundancy in recorded MRI volumes.
Motion in time is analyzed through motion estimation based on neural networks. Motion estimation is used to eliminate a large amount of temporal and frequency redundancies that exists in sequences of 3D data. Combination of segmentation, block matching and motion field prediction along with expert knowledge are incorporated to achieve better performance. Frequency analysis is done through an extension of wavelet transformations to three dimensions. For still volume objects different wavelet packets with different filter banks can be constructed, providing a wide range of frequency analysis. With combination of removing temporal and spatial redundancies, very high compression ratio is achived.
The suggested data compression architecture can be implemented in telemedicine to improve the quality of service. It incorporates operations for frequency and time analysis of datasets, creating kernel shapes and models, and fitting of medical 4D datasets. Each part of the system architecture is implemented independently and can be used for other approaches such as entertainment applications and other new applications that use 4D data.
Keywords:
4D medical datasets, time and frequency redundancy, 3D wavelet transform, motion field, motion estimation based on neural networks, medical data segmentation, shape estimation, medical data compression
004.627
4D medical data compression architecture = Arhitektura sustava za kompresiju četverodimenzionalnih medicinskih podataka : doctoral thesis = doktorska disertacija / Martin Žagar ; [mentor Mario Kovač] - Zagreb : M. Žagar ; Fakultet elektrotehnike i računarstva, 2008. - viii, 202 str. : graf. prikazi ; 30 cm + CD
Bibliografija str. 184-193
U ovom doktorskom radu prezentirane su osnovne znaèajke arhitekture za èetvero-dimenzionalnu kompresiju medicinskih podataka koja se temelji na razlièitim procedurama i algoritmima za analizu vremenske i prostorne zalihosti MR zapisa u NIfTI podatkovnom formatu.
Za analizu i procjenu pokreta, a u cilju uklanjanja vremenske zalihosti koja postoji u slijedu 3D prostornih podataka koriste se neuronske mreže. Da bi se ostvarila kompresija takvih podataka, koristi se ekspertno znanje u razlièitim algoritmima segmentacije podataka, procjene oblika, predviðanja i definiranja polja pokreta. Frekvencijska analiza je ostvarena proširenjem transformacije temeljene na teoriji valiæa u tri dimenzije. Za statièke 3D prostorne podatke koriste se razlièite baze i paketi valiæa koji pružaju širok raspon frekvencijske analize. Uklanjanjem vremenske i prostorne zalihosti postiže se visok stupanj kompresije.
Predložena arhitektura kompresije služi u podizanju razine kvalitete usluga u telemedicini. Svaki dio ove arhitekture predstavlja zasebnu cjelinu te se može primijeniti nezavisno i u druge svrhe, kao što su aplikacije namijenjene zabavi i druge aplikacije koje koriste èetverodimenzionalne podatke. This thesis presents a novel framework for four-dimensional medical data compression architecture. This framework is based on different procedures and algorithms that detect time and spatial redundancy in recorded MRI volumes.
Motion in time is analyzed through motion estimation based on neural networks. Motion estimation is used to eliminate a large amount of temporal and frequency redundancies that exists in sequences of 3D data. Combination of segmentation, block matching and motion field prediction along with expert knowledge are incorporated to achieve better performance. Frequency analysis is done through an extension of wavelet transformations to three dimensions. For still volume objects different wavelet packets with different filter banks can be constructed, providing a wide range of frequency analysis. With combination of removing temporal and spatial redundancies, very high compression ratio is achived.
The suggested data compression architecture can be implemented in telemedicine to improve the quality of service. It incorporates operations for frequency and time analysis of datasets, creating kernel shapes and models, and fitting of medical 4D datasets. Each part of the system architecture is implemented independently and can be used for other approaches such as entertainment applications and other new applications that use 4D data.
Keywords:
4D medical datasets, time and frequency redundancy, 3D wavelet transform, motion field, motion estimation based on neural networks, medical data segmentation, shape estimation, medical data compression
004.627