000			04147nas a2200433 a 4500
005			20260818134625.0
008			230202s2022 th m rtt 0| eng d
035			_a.b12398159
099		9	_aAIT Diss. no.ISE-22-01
100	0		_aAlisa Kunapinun
245	1	0	_aImproving GAN learning dynamics for thyroid nodule segmentation
260			_aPathum Thani, Thailand : _bAsian Institute of Technology, _c2022
300			_a83 leaves : _bill. +1 online resource
490	1		_aDissertation ; _vno. ISE-22-01
500			_aA dissertation submitted in partial fulfillment of the requirements for the degree of Doctoral of Engineering of Engineering in Mechatronics
502			_aThesis (Ph. D.) - Asian Institute of Technology, 2022
520			_aThe thyroid gland, which is responsible for secretion of critical hormones that regulate the body, is susceptible to a number of pathological conditions best diagnosed using ultrasound. A common diagnosis method involves identifying then characterizing the appearance of thyroid nodules: solid or fluid-filled lumps that could be benign or malignant. Physicians could be aided in this endeavor by an automated system to precisely identify nodules in a given ultrasound image. This thesis therefore presents a novel algorithm for segmenting thyroid nodules in ultrasound images named StableSeg GAN. The algorithm is based on the concept of image-to-image translation, which combines traditional supervised semantic segmentation with unsupervised learning using generative adversarial networks (GANs). GANs have been found to improve semantic segmentation models{u2019} performance in specific tasks. However, GAN learning dynamics are famously unstable, oftentimes leading to mode collapse. It is well known that controlling the discriminator in a GAN to not learn too quickly often improves generator learning, making the learning smoother and avoiding mode collapse. StableSeg GANs exploit the concept of closed-loop control of the gain on the loss output of the discriminator to stabilize training. We find that gain control leads to smoother generator training and avoids the mode collapse that typically occurs when the discriminator learns too quickly relative to the generator. We also find that the combination of the supervised and unsupervised learning styles encourages both low level accuracy and high-level consistency. As a test of the concept of controlled hybrid supervised and unsupervised semantic segmentation, StableSeg GANs use DeeplabV3+ as the generator, Resnet18 as the discriminator, and PID control to stabilize the GAN learning process. The new model is superior to the state-of-the-art DeeplabV3+ in terms of intersection over union (IoU), with a mean IoU of 81.26% over a challenging test set. The results of our thyroid nodule segmentation experiments show that StableSeg GANs have flexibility to segment nodules more accurately than supervised segmentation models or uncontrolled GANs.
650		0	_aThyroid Nodule
650		0	_aDeep learning
700	0		_aMongkol Ekpanyapong, _eChairperson
700	0		_aDittapong Songsaeng, _eCo-Chairperson
700	0		_aSiridech Boonsang, _eExamination committee
700	1		_aDailey, Mathew N., _eExamination Committee
700	0		_aManukid Parnichkun, _eExamination Committee
700	0		_aChadaporn Keatmanee, _eExamination committee
710	2		_aRoyal Thai Government, _eScholarship Donor
810	2		_aAsian Institute of Technology. _tDissertation ; _vno. ISE-22-01
856	4	0	_3Full-Text _uhttp://203.159.5.9/ait-thesis/detail.php?q=B18167
907			_a.b12398159 _bmnait _cm
902			_a250421
998			_b0 _c230202 _dm _ea _fm _g0
945			_lmnarc
945			_lmnait
942			_c67
942			_c20
909			_aBarcode : - _bCREATED : 2023-01-02 _cRECORD # : i13428846 _dLPATRON : 0 _eLCHKIN : - _f# RENEWALS : 0 _g# OVERDUE : 0 _hIUSE3 : 0 _iTOT CHKOUT : 0 _jTOT RENEW : 0
909			_aBarcode : 30050121076672 _bCREATED : 2023-09-02 _cRECORD # : i13431249 _dLPATRON : 0 _eLCHKIN : - _f# RENEWALS : 0 _g# OVERDUE : 0 _hIUSE3 : 0 _iTOT CHKOUT : 0 _jTOT RENEW : 0
999			_c58846 _d58846