[68Ga]DOTATOC PET/CT Radiomics to Predict the Response in GEP-NETs Undergoing [177Lu]DOTATOC PRRT: The "Theragnomics" Concept

Riccardo Laudicella; Albert Comelli; Virginia Liberini; Antonio Vento; Alessandro Stefano; Alessandro Spataro; Ludovica Crocè; Sara Baldari; Michelangelo Bambaci; Desiree Deandreis; Demetrio Arico'; Massimo Ippolito; Michele Gaeta; Pierpaolo Alongi; Fabio Minutoli; Irene A Burger; Sergio Baldari

doi:10.3390/cancers14040984

[⁶⁸Ga]DOTATOC PET/CT Radiomics to Predict the Response in GEP-NETs Undergoing [¹⁷⁷Lu]DOTATOC PRRT: The "Theragnomics" Concept

Cancers (Basel). 2022 Feb 16;14(4):984. doi: 10.3390/cancers14040984.

Authors

Riccardo Laudicella^{1

2

3

4}, Albert Comelli², Virginia Liberini^{5

6}, Antonio Vento¹, Alessandro Stefano⁷, Alessandro Spataro¹, Ludovica Crocè¹, Sara Baldari⁸, Michelangelo Bambaci⁹, Desiree Deandreis⁵, Demetrio Arico'⁹, Massimo Ippolito⁸, Michele Gaeta¹⁰, Pierpaolo Alongi⁴, Fabio Minutoli¹, Irene A Burger^{3

11}, Sergio Baldari¹

Affiliations

¹ Nuclear Medicine Unit, Department of Biomedical and Dental Sciences and Morpho-Functional Imaging, University of Messina, 98125 Messina, Italy.
² Ri.MED Foundation, 90134 Palermo, Italy.
³ Department of Nuclear Medicine, University Hospital Zürich, University of Zürich, 8091 Zürich, Switzerland.
⁴ Nuclear Medicine Unit, Fondazione Istituto G.Giglio, 90015 Cefalù, Italy.
⁵ Nuclear Medicine Unit, Department of Medical Sciences, University of Turin, 10126 Turin, Italy.
⁶ Nuclear Medicine Department, S. Croce e Carle Hospital, 12100 Cuneo, Italy.
⁷ Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), 90015 Cefalù, Italy.
⁸ Nuclear Medicine Department, Cannizzaro Hospital, 95126 Catania, Italy.
⁹ Department of Nuclear Medicine, Humanitas Oncological Centre of Catania, 95125 Catania, Italy.
¹⁰ Section of Radiological Sciences, Department of Biomedical Sciences and Morphological and Functional Imaging, University of Messina, 98125 Messina, Italy.
¹¹ Department of Nuclear Medicine, Kantonsspital Baden, 5404 Baden, Switzerland.

Abstract

Despite impressive results, almost 30% of NET do not respond to PRRT and no well-established criteria are suitable to predict response. Therefore, we assessed the predictive value of radiomics [⁶⁸Ga]DOTATOC PET/CT images pre-PRRT in metastatic GEP NET. We retrospectively analyzed the predictive value of radiomics in 324 SSTR-2-positive lesions from 38 metastatic GEP-NET patients (nine G1, 27 G2, and two G3) who underwent restaging [⁶⁸Ga]DOTATOC PET/CT before complete PRRT with [¹⁷⁷Lu]DOTATOC. Clinical, laboratory, and radiological follow-up data were collected for at least six months after the last cycle. Through LifeX, we extracted 65 PET features for each lesion. Grading, PRRT number of cycles, and cumulative activity, pre- and post-PRRT CgA values were also considered as additional clinical features. [⁶⁸Ga]DOTATOC PET/CT follow-up with the same scanner for each patient determined the disease status (progression vs. response in terms of stability/reduction/disappearance) for each lesion. All features (PET and clinical) were also correlated with follow-up data in a per-site analysis (liver, lymph nodes, and bone), and for features significantly associated with response, the Δradiomics for each lesion was assessed on follow-up [⁶⁸Ga]DOTATOC PET/CT performed until nine months post-PRRT. A statistical system based on the point-biserial correlation and logistic regression analysis was used for the reduction and selection of the features. Discriminant analysis was used, instead, to obtain the predictive model using the k-fold strategy to split data into training and validation sets. From the reduction and selection process, HISTO_Skewness and HISTO_Kurtosis were able to predict response with an area under the receiver operating characteristics curve (AUC ROC), sensitivity, and specificity of 0.745, 80.6%, 67.2% and 0.722, 61.2%, 75.9%, respectively. Moreover, a combination of three features (HISTO_Skewness; HISTO_Kurtosis, and Grading) did not improve the AUC significantly with 0.744. SUV_max, however, could not predict the response to PRRT (p = 0.49, AUC 0.523). The presented preliminary "theragnomics" model proved to be superior to conventional quantitative parameters to predict the response of GEP-NET lesions in patients treated with complete [¹⁷⁷Lu]DOTATOC PRRT, regardless of the lesion site.

Keywords: 177Lu; GEP NET; PRRT; [68Ga]DOTATOC PET; artificial intelligence; delta radiomics; machine-learning.