Improving hypoxia map estimation by using model-free classification techniques in DCE-MRI images

Venianaki, Maria; Kontopodis, Eleftherios; Nikiforaki, Katerina; Bree, Eelco de; Maris, Thomas G.; Karantanas, Apostolos H.; Salvetti, Ovidio; Marias, Kostas

doi:10.1109/ist.2016.7738220

Cited by 1 publication

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These initialization methods relied on information extracted directly from the data and when tested on the same patient data, similar results were obtained, which were also repeatable [28]. In particular, the wash-in and the k trans maps were utilized for the initialization of the BU-NMF algorithm.…”

Section: Data-driven Initializationmentioning

confidence: 71%

“…Random initialization of the BU-NMF algorithm was proven not to be repeatable as it gave ambiguous results when running it for multiple times [28]. For Patient #1, we ran the BU-NMF algorithm with two different random initializations and the results were completely different.…”

Section: Bu-nmf Initializationmentioning

confidence: 99%

“…The algorithm detects the most representative patterns that comprise the data. In our previous studies [27,28] we have examined the efficiency and robustness of this algorithm on a single patient and investigated the most suitable initialization approach to use. In the present study, the BU-NMF algorithm is tested on three patients, which have different types of sarcomas.…”

mentioning

confidence: 99%

“…In the present study, the BU-NMF algorithm is tested on three patients, which have different types of sarcomas. Furthermore, in contrast to our previous reported works [27,28], where a single slice was used, in this work information from the entire tumor volume was given as input so that the maximum available information regarding the malignancy could be used. The proposed BU-NMF-based method was applied using three different initialization approaches and the structures of the patterns identified seemed to approximate the three most common shapes of the DCE main signal-time curves (Types 1, 2 and 3), which were described previously.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Pattern recognition and pharmacokinetic methods on DCE-MRI data for tumor hypoxia mapping in sarcoma

Venianaki

Salvetti

Bree

et al. 2017

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

The main purpose of this study is to analyze the intrinsic tumor physiologic characteristics in patients with sarcoma through model-free analysis of dynamic contrast enhanced MR imaging data (DCE-MRI). Clinical data were collected from three patients with two different types of histologically proven sarcomas who underwent conventional and advanced MRI examination prior to excision. An advanced matrix factorization algorithm has been applied to the data, resulting in the identification of the principal time-signal uptake Multimed Tools Appl (2018) curves of DCE-MRI data, which were used to characterize the physiology of the tumor area, described by three different perfusion patterns i.e. hypoxic, well-perfused and necrotic one. The performance of the algorithm was tested by applying different initialization approaches with subsequent comparison of their results. The algorithm was proven to be robust and led to the consistent segmentation of the tumor area in three regions of different perfusion, i.e. wellperfused, hypoxic and necrotic. Results from the model-free approach were compared with a widely used pharmacokinetic (PK) model revealing significant correlations.

show abstract

Section: Data-driven Initializationmentioning

confidence: 71%

Section: Bu-nmf Initializationmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations