Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: multiclass

Sortuj według:

Ogranicz wyniki do:

Leveraging network using controlled weight learning approach for thyroid cancer lymph node detection

Kavitha Muthu Subash, Yudistira Novanto, Ahn Byeong-Cheol, Kurita Takio

Biocybernetics and Biomedical Engineering

2021

Vol. 41, no. 4

1589--1600

Identification of cervical metastatic lymph nodes (LN) on I-131 post-ablation whole-body planar scans (WBS) for cancer staging is crucial for patients with papillary thyroid cancer (PTC). The existing deep network is plagued by instability in finding the under-represented LN classes on highly complex WBS, where end-to-end tuned models that can account for this uncertainty region for multi-class locations are needed. Hence, as a key contribution of this study, we designed a novel leveraging segmentation network with input guidance (LSIG) end-to-end training model without pre and post-processing features that can learn ideal parameter settings depending on the quantity of multiple-object instances. To improve the co-occurrence of classes and control the false positive regions, we proposed a re-weighting negative control (RNC) mechanism that combines two key components, namely the re-weighting (Rw) term and the negative control function (NcF). This unified approximation of weighted training would leverage the network to control and learn the desired weights of true positives towards the LN region. As an end-to-end network training, we utilize a Unet-like convolution neural network (CNN) model. The performance of the LSIG is compared with the CNN-based networks, based on the ground truth (GT) mask developed using post-ablation single-photon emission computed tomography (SPECT/CT). Furthermore, the effectiveness of the two components used in the LSIG framework is evaluated on WBS datasets. Our proposed LSIG with a fully guided (Fg) LS-FgCNN model yielded a superior performance with high AUC value of 94.9%, which is 14.6% higher than the previous network for PTC.

Multiusers, Multimode, Multicriteria traffic network model for ITS systems

Adamski A.

Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie

2003

T. 7, z. 1-2

43-49

In this paper, we develop a traffic network model 3M (Multiclass, Multimode, Multicriteria) for ITS applications. The model explicitly treats many user classes, many traffic modes corresponding to different traffic situations in the network and many travel disutility optimization criteria e.g. travel time, travel costs (safety, environment, comfort, payment) on the links and paths levels. Moreover, unlike the existing multicriteria approaches with scalarizing functions the model offers strictly multicriteria approach with whole N-set as a solution. This makes it possible to use robust measures as additional criterion in the network equilibrium evaluations. The numerical examples illustrate analytical solutions for simple networks.

W pracy rozwinięto sieciowy model 3M (Multiclass, Multimode, Multicriteria) ruchu drogowego dla zastosowań optymalizacyjnych w ITS systemach. W modelu tym wiele klas użytkowników sieci, wiele modów ruchowych odpowiadających różnym sytuacjom ruchowym i wiele kryteriów optymalizacji, np. czas podróży, koszty podróży (bezpieczeństwo, środowisko, komfort, opłaty) może być reprezentowanych na poziomie łuków i ścieżek sieci. W odróżnieniu od istniejących modeli wielokryterialnych wykorzystujących funkcje skalaryzujące, rozwiązaniem jest cały zbiór kompromisów, który dostarcza bardzo istotnej informacji (dodatkowego kryterium) o wrażliwości wyznaczanych punktów równowagi na zmiany parametrów sieci. Podano przykłady analitycznych rozwiązań dla prostych sieci.