Sökning: WFRF:(Wang Chunliang 1980 ) >
Benign-malignant pu...
-
Astaraki, Mehdi,PhD Student,1984-KTH,Medicinsk avbildning,Karolinska Institutet, Department of Oncology-Pathology, Karolinska Universitetssjukhuset, Solna, SE-17176 Stockholm, Sweden
(författare)
Benign-malignant pulmonary nodule classification in low-dose CT with convolutional features
- Artikel/kapitelEngelska2021
Förlag, utgivningsår, omfång ...
-
Elsevier BV,2021
-
printrdacarrier
Nummerbeteckningar
-
LIBRIS-ID:oai:DiVA.org:kth-296814
-
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-296814URI
-
https://doi.org/10.1016/j.ejmp.2021.03.013DOI
-
http://kipublications.ki.se/Default.aspx?queryparsed=id:146843585URI
-
https://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-191608URI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:ref swepub-contenttype
-
Ämneskategori:art swepub-publicationtype
Anmärkningar
-
QC 20210720
-
Purpose: Low-Dose Computed Tomography (LDCT) is the most common imaging modality for lung cancer diagnosis. The presence of nodules in the scans does not necessarily portend lung cancer, as there is an intricate relationship between nodule characteristics and lung cancer. Therefore, benign-malignant pulmonary nodule classification at early detection is a crucial step to improve diagnosis and prolong patient survival. The aim of this study is to propose a method for predicting nodule malignancy based on deep abstract features.Methods: To efficiently capture both intra-nodule heterogeneities and contextual information of the pulmonary nodules, a dual pathway model was developed to integrate the intra-nodule characteristics with contextual attributes. The proposed approach was implemented with both supervised and unsupervised learning schemes. A random forest model was added as a second component on top of the networks to generate the classification results. The discrimination power of the model was evaluated by calculating the Area Under the Receiver Operating Characteristic Curve (AUROC) metric. Results: Experiments on 1297 manually segmented nodules show that the integration of context and target supervised deep features have a great potential for accurate prediction, resulting in a discrimination power of 0.936 in terms of AUROC, which outperformed the classification performance of the Kaggle 2017 challenge winner.Conclusion: Empirical results demonstrate that integrating nodule target and context images into a unified network improves the discrimination power, outperforming the conventional single pathway convolutional neural networks.
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Zakko, YousufKarolinska University Hospital, Imaging and Function, Radiology Department, Solna, SE-17176 Stockholm, Sweden
(författare)
-
Toma-Dasu, IulianaStockholms universitet,Fysikum,Karolinska Institutet, Sweden(Swepub:su)iuda0736
(författare)
-
Smedby, Örjan,Professor,1956-KTH,Medicinsk avbildning(Swepub:kth)u1vc2uzb
(författare)
-
Wang, Chunliang,1980-KTH,Medicinsk avbildning(Swepub:kth)u1tbkeej
(författare)
-
KTHMedicinsk avbildning
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:Physica medica (Testo stampato): Elsevier BV83, s. 146-1531120-17971724-191X
Internetlänk
Hitta via bibliotek
Till lärosätets databas