Radiomics analysis of pre-treatment F-18 FDG PET/CT for predicting response to transarterial radioembolization in liver tumors

Nazım COŞKUN; Alptuğ Özer YÜKSEL; Murat CANYİĞİT; Elif ÖZDEMİR

doi:https://doi.org/10.32322/jhsm.1118649

Makale detayları

Radiomics analysis of pre-treatment F-18 FDG PET/CT for predicting response to transarterial radioembolization in liver tumors

Yazarlar:

Nazım COŞKUN | Alptuğ Özer YÜKSEL | Murat CANYİĞİT | Elif ÖZDEMİR

Yayıncı:

MediHealth Academy Yayıncılık

Ana Başlıklar:

Sağlık teşvikleri

Dergi:

Journal of Health Sciences and Medicine 2022 Vol.5 Issue 4, pp.1156-1161

Belge Tipi:

Makale

Yayın Tarihi:

7/2022

Belge Dili:

İngilizce

Document ID (Org No.):

2000481369

Sıklık:

İki Aylık

eISSN:

2636-8579

DOI:

https://doi.org/10.32322/jhsm.1118649

Özet:

 

Aim: To investigate the relationship between the textural features extracted from pre-treatment fluorine-18 fluorodeoxyglucose positron emission with computed tomography (F-18 FDG PET/CT) and the response to treatment in patients undergoing transarterial radioembolization (TARE) due to primary or metastatic liver tumors.
Material and Method: A total of 25 liver lesions from the pre-treatment F-18 PET/CT images of 14 patients were segmented manually. Standard uptake value (SUV) metrics and radiomics features were extracted for each lesion. Metabolic treatment response was determined according to PERCIST criteria in 18F-FDG PET/CT imaging performed 2 months after the treatment. Feature selection was done with recursive feature elimination (RFE). The association between selected features and treatment response was evaluated with logistic regression analysis.
Results: Eventually, 13 lesions responded to TARE, while 12 lesions remain stable or progressed. All standard uptake values and 27 out of 30 textural heterogeneity indicators were significantly higher in lesions that responded to treatment. SUVmax, kurtosis and dissimilarity features were selected by the RFE algorithm for the prediction of response to TARE. Logistic regression analysis revealed that all three parameters were significantly associated with treatment outcome.
Conclusion: Textural features extracted from pre-treatment F-18 FDG PET/CT in patients undergoing TARE due to liver tumors are promising biomarkers that can be potentially used to predict metabolic treatment response.

Makale detayları

Radiomics analysis of pre-treatment F-18 FDG PET/CT for predicting response to transarterial radioembolization in liver tumors

Yazarlar: Nazım COŞKUN | Alptuğ Özer YÜKSEL | Murat CANYİĞİT | Elif ÖZDEMİR

Yayıncı: MediHealth Academy Yayıncılık

Ana Başlıklar: Sağlık teşvikleri

Dergi: Journal of Health Sciences and Medicine 2022 Vol.5 Issue 4, pp.1156-1161

Belge Tipi: Makale

Yayın Tarihi: 7/2022

Belge Dili: İngilizce

Document ID (Org No.): 2000481369

Sıklık: İki Aylık

eISSN: 2636-8579

DOI: https://doi.org/10.32322/jhsm.1118649

Sayı

Yazarlar:

Nazım COŞKUN | Alptuğ Özer YÜKSEL | Murat CANYİĞİT | Elif ÖZDEMİR

Yayıncı:

MediHealth Academy Yayıncılık

Ana Başlıklar:

Sağlık teşvikleri

Dergi:

Journal of Health Sciences and Medicine 2022 Vol.5 Issue 4, pp.1156-1161

Belge Tipi:

Makale

Yayın Tarihi:

7/2022

Belge Dili:

İngilizce

Document ID (Org No.):

2000481369

Sıklık:

İki Aylık

eISSN:

2636-8579

DOI:

https://doi.org/10.32322/jhsm.1118649