Urinary bladder cancer is one of the most common cancers of the urinary tract. This cancer is characterized by its high metastatic potential and recurrence rate. Due to the high metastatic potential and recurrence rate, correct and timely diagnosis is crucial for successful treatment and care. With the aim of increasing diagnosis accuracy, artificial intelligence algorithms are introduced to clinical decision making and diagnostics. One of the standard procedures for bladder cancer diagnosis is computer tomography (CT) scanning. In this research, a transfer learning approach to the semantic segmentation of urinary bladder cancer masses from CT images is presented. The initial data set is divided into three sub-sets according to image planes: frontal (4413 images), axial (4993 images), and sagittal (996 images). First, AlexNet is utilized for the design of a plane recognition system, and it achieved high classification and generalization performances with an AUCmicro¯ of 0.9999 and σ(AUCmicro) of 0.0006. Furthermore, by applying the transfer learning approach, significant improvements in both semantic segmentation and generalization performances were achieved. For the case of the frontal plane, the highest performances were achieved if pre-trained ResNet101 architecture was used as a backbone for U-net with DSC¯ up to 0.9587 and σ(DSC) of 0.0059. When U-net was used for the semantic segmentation of urinary bladder cancer masses from images in the axial plane, the best results were achieved if pre-trained ResNet50 was used as a backbone, with a DSC¯ up to 0.9372 and σ(DSC) of 0.0147. Finally, in the case of images in the sagittal plane, the highest results were achieved with VGG-16 as a backbone. In this case, DSC¯ values up to 0.9660 with a σ(DSC) of 0.0486 were achieved. From the listed results, the proposed semantic segmentation system worked with high performance both from the semantic segmentation and generalization standpoints. The presented results indicate that there is the possibility for the utilization of the semantic segmentation system in clinical practice.

Sažetak. Izvantjelesno mrvljenje kamenaca (ESWL) je novija terapijska metoda u liječenju urolitijaze. Temelji se na uporabi šok-valova koji se stvaraju u generatoru, fokusiraju i usmjeruju na kamenac u tijelu pacijenta. Razbijanje kamenca je posljedica nekoliko različitih efekata tih valova na sam konkrement. Razbijanjem nastaju manji fragmenti koji se moraju izmokriti. ESWL se koristi u liječenju bubrežnih kao i kamenaca u mokraćovodu. Metoda je izbora za liječenje bubrežnih kamenaca manjih od 2 cm te onih u proksimalnom dijelu mokraćovoda veličine do 1 cm. Komplikacije su rijetke i najčešće klinički beznačajne. Efikasnost ove metode ovisi o veličini kamenca, njegovom sastavu, kanalnom sustavu bubrega te o iskustvu i vještini urologa. Velika prednost ove metode je da nije potrebna anestezija, za razliku od drugih minimalno invazivnih metoda. Tretman ESWL-a može se ponavljati više puta. Do sada nije dokazan štetan učinak na bubrežnu funkciju, a može se koristiti i u dječjoj populaciji.Ključne riječi: izvantjelesno mrvljenje kamenaca; nefrolitijaza; ureterolitijaza Abstract. Extracorporeal shock wave lithotripsy (ESWL) is a novel method for the treatment of urolithiasis. It is based on the use of shock waves that are generated in the generator, focused and directed to the stone in the body of the patient. Cracking of the stone is the result of several different effects of these waves. It results with stone fragmentation and spontaneous elimination of fragments. ESWL is used in the treatment of kidney stones and stones in the ureter. These method is the method of choice for treating kidney stones smaller than 2 cm, and those in the proximal part of the ureter up to 1 cm. Complications are rare and usually clinically insignificant. The effectiveness of this method depends on the stone size, its composition, the renal system morphology and the experience and skill of the urologist. The great advantage of this method is that anesthesia is not needed, unlike other minimally-invasive treatements. Also, the ESWL treatment can be repeated several times. There is no proven damaging effect on the renal function and can be used for treatment of stones in the children.

Cilj: Prikazati učestalost uroloških komplikacija nakon transplantacije bubrega u našem transplantacijskom centru. Ispitanici i metode: Retrospektivnim istraživanjem bili su obuhvaćeni svi pacijenti u Kliničkom bolničkom centru Rijeka u kojih je između 30. siječnja 1971. godine i 31. prosinca 2018. godine učinjena transplantacija bubrega. Rezultati: U promatranom razdoblju u našem transplantacijskom centru učinjeno je 1160 transplantacija bubrega. Urološke komplikacije imala su ukupno 154 pacijenta (13,3 %). Najčešće komplikacije su bile stenoza uretera u 52 pacijenta (4,5 %), urinarna fistula u 50 pacijenata (4,3 %), retencija urina u 23 pacijenta (1,9 %) te urolitijaza u 8 pacijenata (0,7 %). U većine pacijenata je provedeno kirurško liječenje. U posljednje vrijeme značajno se povećalo rješavanje uroloških komplikacija korištenjem minimalno-invazivnih metoda. U dvoje pacijenata (0,17 %) je zbog uroloških komplikacija došlo do gubitka grafta, a u troje pacijenata (0,25 %) su one dovele do smrtnog ishoda. Zaključak: Urološke komplikacije u našoj transplantacijskoj populaciji nisu česte. U pacijenata u kojih je potrebno kirurško liječenje endourološke metode predstavljaju danas inicijalnu metodu liječenja.

Bladder cancer is one of the most common malignancies of the urinary tract. It is characterized by high metastatic potential and a high recurrence rate, which significantly complicates diagnosis and treatment. In order to increase the accuracy of the diagnostic procedure, algorithms based on artificial intelligence are introduced. This paper presents the principle of selection of convolutional neural network (CNN) models based on a multi-objective approach that maximizes classification and generalization performance. Model selection is performed on two standard CNN architectures, AlexNet and VGG-16. Classification performances are measured by using ROC analysis and the resulting AUC value. On the other hand, generalization performances are evaluated by using a 5-fold cross-validation procedure. By using these two metrics, a multi-objective fitness function, used in meta-heuristic algorithms, is designed. The multi-objective search was performed using a Genetic algorithm (GA) and a Discrete Particle Swarm (D-PS) algorithm. From obtained results, it can be noticed that such an approach has resulted in CNN models that are defined with high classification and generalization performances. When a GA-based approach is used, fitness values up to 0.97 are achieved. On the other hand, by using the D-PS approach, fitness values up to 0.99 are achieved pointing towards the conclusion that such an approach has provided models with higher classification and generalization performances.

No abstract