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

Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in Mammography

Background: Breast cancer is the second leading cause of cancer-related mortality among women, accounting for 12% of cases. Early diagnosis, based on the identification of radiological features, such as masses and microcalcifications in mammograms, is crucial for reducing mortality rates. However, manual interpretation by radiologists is complex and subject to variability, emphasizing the need for automated diagnostic tools to enhance accuracy and efficiency. This study compares a radiomics workflow based on machine learning (ML) with a deep learning (DL) approach for classifying breast lesions as benign or malignant. Methods: matRadiomics was used to extract radiomics features from mammographic images of 1219 patients from the CBIS-DDSM public database, including 581 cases of microcalcifications and 638 of masses. Among the ML models, a linear discriminant analysis (LDA) demonstrated the best performance for both lesion types. External validation was conducted on a private dataset of 222 images to evaluate generalizability to an independent cohort. Additionally, a deep learning approach based on the EfficientNetB6 model was employed for comparison. Results: The LDA model achieved a mean validation AUC of 68.28% for microcalcifications and 61.53% for masses. In the external validation, AUC values of 66.9% and 61.5% were obtained, respectively. In contrast, the EfficientNetB6 model demonstrated superior performance, achieving an AUC of 81.52% for microcalcifications and 76.24% for masses, highlighting the potential of DL for improved diagnostic accuracy. Conclusions: This study underscores the limitations of ML-based radiomics in breast cancer diagnosis. Deep learning proves to be a more effective approach, offering enhanced accuracy and supporting clinicians in improving patient management.

Prediction of lesion-based response to PRRT using baseline somatostatin receptor PET

Aim

The heterogeneous expression of somatostatin receptors in gastroenteropancreatic neuroendocrine tumors (GEP-NET) leads to significant intra-individual variability in tracer uptake during pre-therapeutic [68Ga]Ga-DOTATOC PET/CT for patients receiving peptide receptor radionuclide therapy (PRRT). This study aims to evaluate the lesion-based relationship between receptor-mediated tracer uptake and the functional response to PRRT.

Methods

A retrospective analysis was conducted on 32 patients with metastatic GEP-NET (12 pancreatic and 20 non-pancreatic), all treated with [177Lu]Lu-octreotate (4 cycles, with a mean of 7.9 GBq per cycle). [68Ga]Ga-DOTATOC PET/CT was performed at baseline and 3 months after the final PRRT cycle. Tumor uptake was quantified using the standardized uptake value (SUV). For each patient, 2 to 3 well-delineated tumor lesions were selected as target lesions. SUVmax, SUVmean (automated segmentation with a 50% SUVmax threshold), and corresponding tumor-to-liver ratios (SUVmaxT/L and SUVmeanT/L) were calculated. Functional tumor response was assessed based on the relative change in metabolic tumor volume (%ΔTVPET). The correlation between baseline SUV parameters and lesion-based functional response was analyzed using Spearman's rank correlation.

Results

A total of 71 lesions were included in the analysis. The mean baseline SUVmax and SUVmean were 28.1 ± 15.9 and 13.6 ± 5.1, respectively. Three months after PRRT completion, the mean %ΔTVPET was 39.6 ± 52.1%. Baseline SUVmax and SUVmean demonstrated a poor correlation with lesion-based response (p = 0.706 and p = 0.071, respectively). In contrast, SUVmaxT/L and SUVmeanT/L were significantly correlated with lesion-based response (SUVmeanT/L: p = 0.011, r = 0.412; SUVmaxT/L: p = 0.004, r = 0.434). Among patient characteristics-including primary tumor origin, baseline tumor volume, and metastatic sites-only pancreatic origin was significantly associated with functional tumor volume reduction (ΔTVPET%: 56.8 ± 39.8 in pancreatic vs. 28.4 ± 50.1 in non-pancreatic NET; p = 0.020).

Conclusion

The lesion-based molecular response to PRRT correlates with pretreatment somatostatin receptor PET uptake, particularly when expressed as tumor-to-liver SUV ratios (SUVmaxT/L and SUVmeanT/L).

Inter- and intra-tumoral heterogeneity on [68Ga]Ga-DOTA-TATE/[68Ga]Ga-DOTA-TOC PET/CT predicts response to [177Lu]Lu-DOTA-TATE PRRT in neuroendocrine tumor patients

BACKGROUND

Indices of tumor heterogeneity on somatostatin receptor PET/CT scans may potentially serve as predictive biomarkers of treatment efficacy in neuroendocrine tumor (NET) patients undergoing [177Lu]Lu-DOTA-TATE PRRT.

METHODS

NET patients who underwent [177Lu]Lu-DOTA-TATE therapy at the University of Iowa from August 2018 to February 2021 were retrospectively evaluated. Radiomic features on the pre-PRRT somatostatin receptor PET/CT were evaluated using a custom MIM Software® LesionID workflow. Conventional PET/CT metrics of tumor burden, such as somatostatin receptor expression and tumor volume, were calculated in addition to the indices of tumor heterogeneity for each lesion (intra-lesional) and then summarized across all lesions throughout the body (inter-lesional). Endpoints included post-PRRT 24-month time to progression (TTP) and overall survival (OS). Cox regression models were used to assess the predictive ability of the imaging factors on post-PRRT 24-month TTP and OS. LASSO-penalized Cox regression was used to build a multivariable model for each outcome.

RESULTS

Eighty patients with a mean age of 65.1 years were included, with most (71.3%) completing 4 cycles of PRRT. Median TTP was 19.1 months, and OS at 60 months was 50%. A large degree of variability between patients was evidenced for imaging features related to somatostatin receptor expression. On multivariable analysis, total receptor expression and mean liver-corrected SUVmean were selected for 24-month TTP. The model was not able to significantly predict progression (C-statistic = 0.58, 95% CI 0.50-0.62). Total receptor expression and mean skewness were selected for OS. The resulting model was able to significantly predict death (C-statistic = 0.62, 95% CI 0.53-0.67), but the predictive ability was limited, as evidenced by the low C-statistic.

CONCLUSIONS

Our exploratory analysis provides preliminary results showing that imaging indices of inter- and intra-tumor heterogeneity from pretreatment PET/CT images may potentially predict treatment efficacy in NET patients undergoing [177Lu]Lu-DOTA-TATE therapy. However, prospective evaluation in a larger cohort is needed to further assess whether a comprehensive characterization of tumor heterogeneity within a patient can help guide treatment decisions.

Radiolabeled Somatostatin Analogs for Cancer Imaging

Somatostatin receptors (SSTR) are expressed by many tumours especially those related to neuro-endocrine origin and molecular functional imaging of SSTR expression using radiolabelled somatostatin analogs have revolutionized imaging of patients with these group of malignancies. Coming a long way from the first radiolabelled somatostatin analog 123I-Tyr-3-octreotide, there has been significant developments in terms of radionuclides used, the ligands and somatostatin derivatives. 111In-Pentetreotide extensively employed for imaging NETs at the beginning has now been replaced by 68Ga-SSA based PET-CT. SSA-PET/CT performs superior to conventional imaging modalities and has evolved in the mainframe for NET imaging. The advantages were multiple: (i) superior spatial resolution of PET versus SPECT, (ii) quantitative capabilities of PET aiding in disease activity and treatment response monitoring with better precision, (iii) shorter scan time and (iv) less patient exposure to radiation. The modality is indicated for staging, detecting the primary in CUP-NETs, restaging, treatment planning (along with FDG: the concept of dual-tracer PET-CT) as well as treatment response evaluation and follow-up of NETs. SSA PET/CT has also been incorporated in the guidelines for imaging of Pheochromocytoma-Paraganglioma, Medullary carcinoma thyroid, Meningioma and Tumor induced osteomalacia. At present, there is rising interest on (a) 18F-labelled SSA, (b) 64Cu-labelled SSA, and (c) somatostatin antagonists. 18F offers excellent imaging properties, 64Cu makes delayed imaging feasible which has implications in dosimetry and SSTR antagonists bind with the SST receptors with high affinity and specificity, providing high contrast images with less background, which can be translated to theranostics effectively. SSTR have been demonstrated in non-neuroendocrine tumours as well in the peer-reviewed literature, with studies demonstrating the potential of SSA PET/CT in Neuroblastoma, Nasopharyngeal carcinoma, carcinoma prostate (neuroendocrine differentiation) and lymphoma. This review will focus on the currently available SSAs and their history, different SPECT/PET agents, SSTR antagonists, comparison between the various imaging tracers, and their utility in both neuroendocrine and non-neuroendocrine tumors.

Predicting the Response of Patients Treated with 177Lu-DOTATATE Using Single-photon Emission Computed Tomography-Computed Tomography Image-based Radiomics and Clinical Features

Background

In this study, we want to evaluate the response to Lutetium-177 (177Lu)-DOTATATE treatment in patients with neuroendocrine tumors (NETs) using single-photon emission computed tomography (SPECT) and computed tomography (CT), based on image-based radiomics and clinical features.

Methods

The total volume of tumor areas was segmented into 61 SPECT and 41 SPECT-CT images from 22 patients with NETs. A total of 871 radiomics and clinical features were extracted from the SPECT and SPECT-CT images. Subsequently, a feature reduction method called maximum relevance minimum redundancy (mRMR) was used to select the best combination of features. These selected features were modeled using a decision tree (DT), random forest (RF), K-nearest neighbor (KNN), and support vector machine (SVM) classifiers to predict the treatment response in patients. For the SPECT and SPECT-CT images, ten and eight features, respectively, were selected using the mRMR algorithm.

Results

The results revealed that the RF classifier with feature selection algorithms through mRMR had the highest classification accuracies of 64% and 83% for the SPECT and SPECT-CT images, respectively. The accuracy of the classifications of DT, KNN, and SVM for SPECT-CT images is 79%, 74%, and 67%, respectively. The poor accuracy obtained from different classifications in SPECT images (≈64%) showed that these images are not suitable for predicting treatment response.

Conclusions

Modeling the selected features of SPECT-CT images based on their anatomy and the presence of extensive gray levels makes it possible to predict responses to the treatment of 177Lu-DOTATATE for patients with NETs.

Diagnostic Performance of Radiomics and Deep Learning to Identify Benign and Malignant Soft Tissue Tumors: A Systematic Review and Meta-analysis

RATIONALE AND OBJECTIVES

To systematically evaluate the application value of radiomics and deep learning (DL) in the differential diagnosis of benign and malignant soft tissue tumors (STTs).

MATERIALS AND METHODS

A systematic review was conducted on studies published up to December 11, 2023, that utilized radiomics and DL methods for the diagnosis of STTs. The methodological quality and risk of bias were evaluated using the Radiomics Quality Score (RQS) 2.0 system and Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool, respectively. A bivariate random-effects model was used to calculate the summarized sensitivity and specificity. To identify factors contributing to heterogeneity, meta-regression and subgroup analyses were performed to assess the following covariates: diagnostic modality, region/volume of interest, imaging examination, study design, and pathology type. The asymmetry of Deeks' funnel plot was used to assess publication bias.

RESULTS

A total of 21 studies involving 3866 patients were included, with 13 studies using independent test/validation sets included in the quantitative statistical analysis. The average RQS was 21.31, with substantial or near-perfect inter-rater agreement. The combined sensitivity and specificity were 0.84 (95% CI: 0.76-0.89) and 0.88 (95% CI: 0.69-0.96), respectively. Meta-regression and subgroup analyses showed that study design and the region/volume of interest were significant factors affecting study heterogeneity (P < 0.05). No publication bias was observed.

CONCLUSION

Radiomics and DL can accurately distinguish between benign and malignant STTs. Future research should concentrate on enhancing the rigor of study designs, conducting multicenter prospective validations, amplifying the interpretability of DL models, and integrating multimodal data to elevate the diagnostic accuracy and clinical utility of soft tissue tumor assessments.

Theranostic Approaches for Gastric Cancer: An Overview of In Vitro and In Vivo Investigations

Gastric cancer (GC) is the second most common cause of cancer-related death worldwide and a serious public health concern. This high death rate is mostly caused by late-stage diagnoses, which lead to poor treatment outcomes. Radiation immunotherapy and targeted therapies are becoming increasingly popular in GC treatment, in addition to surgery and systemic chemotherapy. In this review, we have focused on both in vitro and in vivo research, which presents a summary of recent developments in targeted therapies for gastric cancer. We explore targeted therapy approaches, including integrin receptors, HER2, Claudin 18, and glutathione-responsive systems. For instance, therapies targeting the integrin receptors such as the αvβ3 and αvβ5 integrins have shown promise in enhancing diagnostic precision and treatment efficacy. Furthermore, nanotechnology provides novel approaches to targeted drug delivery and imaging. These include glutathione-responsive nanoplatforms and cyclic RGD peptide-conjugated nanoparticles. These novel strategies seek to reduce systemic toxicity while increasing specificity and efficacy. To sum up, the review addresses the significance of personalized medicine and advancements in gastric cancer-targeted therapies. It explores potential methods for enhancing gastric cancer prognosis and treatment in the future.

Challenges and limitations in applying radiomics to PET imaging: Possible opportunities and avenues for research

Radiomics, the high-throughput extraction of quantitative imaging features from medical images, holds immense potential for advancing precision medicine in oncology and beyond. While radiomics applied to positron emission tomography (PET) imaging offers unique insights into tumor biology and treatment response, it is imperative to elucidate the challenges and constraints inherent in this domain to facilitate their translation into clinical practice. This review examines the challenges and limitations of applying radiomics to PET imaging, synthesizing findings from the last five years (2019-2023) and highlights the significance of addressing these challenges to realize the full clinical potential of radiomics in oncology and molecular imaging. A comprehensive search was conducted across multiple electronic databases, including PubMed, Scopus, and Web of Science, using keywords relevant to radiomics issues in PET imaging. Only studies published in peer-reviewed journals were eligible for inclusion in this review. Although many studies have highlighted the potential of radiomics in predicting treatment response, assessing tumor heterogeneity, enabling risk stratification, and personalized therapy selection, various challenges regarding the practical implementation of the proposed models still need to be addressed. This review illustrates the challenges and limitations of radiomics in PET imaging across various cancer types, encompassing both phantom and clinical investigations. The analyzed studies highlight the importance of reproducible segmentation methods, standardized pre-processing and post-processing methodologies, and the need to create large multicenter studies registered in a centralized database to promote the continuous validation and clinical integration of radiomics into PET imaging.

Lutetium [177Lu]-DOTA-TATE in gastroenteropancreatic-neuroendocrine tumours: rationale, design and baseline characteristics of the Italian prospective observational (REAL-LU) study

PURPOSE

Gastroenteropancreatic -neuroendocrine tumours (GEP-NETs) are commonly treated with surgical resection or long-term therapies for tumour growth control. Lutetium [177Lu]-DOTA-TATE was approved for the treatment of GEP-NETs after the phase III NETTER 1trial demonstrated improved progression free survival, objective response rates and health-related quality of life (HRQoL) compared to high-dose somatostatin analogues. No real-world data exist on prescribing habits and clinically significant endpoints for [177Lu]Lu-DOTA-TATE treatment in Italy. REAL-LU is a multicentre, long-term observational study in patients with unresectable/metastatic GEP-NETs progressing on standard therapies in Italian clinical practice. A pre-specified interim analysis was performed at the end of the enrolment period, data from which are described herein.

METHODS

Overall duration of REAL-LU will be approximately 48 months, with 12- and 36-month recruitment and follow-up periods, respectively. The primary objective is to evaluate [177Lu]Lu-DOTA-TATE effectiveness in terms of progression-free survival. Secondary objectives include safety, impact on HRQoL, and identification of prognostic factors. This pre-specified interim analysis describes patient profiles, at the end of enrollment, of those prescribed [177Lu]Lu-DOTA-TATE for GEP-NETs in Italy.

RESULTS

Among 161 evaluable patients, mean age was 64.7 ± 10.3 years at study entry, 83.8% presented with no clinical signs of disease at physical examination, and most had minor disease symptoms. All patients had metastatic disease, most commonly in the liver (83.9%) with a median of two metastatic sites. In 90.7% of patients, the disease was stage IV, and 68.3% had ≥ 1 target lesion. [177Lu]Lu-DOTA-TATE was prescribed mainly as second-line therapy (61.6%) and following surgery (58.4%). HRQoL assessments revealed high levels of functioning and low levels of symptoms at baseline; 50.0% of patients were symptom-free at study entry.

CONCLUSION

The characteristics of patients who received [177Lu]Lu-DOTA-TATE in Italy are similar to those of the GEP-NET population of NETTER 1 with trial but with a higher proportion of patients with a grade 2 (71%). With regard to the tumor grade profile, our study cohort appears to be closer to that of NETTER-2 study population which included patients with G2 or G3 advanced GEP-NETs (i.e. Ki-67 ≥ 10% and ≤ 55%). Further analysis of effectiveness and safety can be anticipated as REAL-LU data mature.

STUDY REGISTRATION

ClinicalTrials.gov, NCT04727723; Study Registration Date: 25 January, 2021; https://clinicaltrials.gov/study/NCT04727723?cond=NCT04727723&rank=1.

Improvements and future perspective in diagnostic tools for neuroendocrine neoplasms

INTRODUCTION

Neuroendocrine neoplasms (NENs) represent a complex group of tumors arising from neuroendocrine cells, characterized by heterogeneous behavior and challenging diagnostics. Despite advancements in medical technology, NENs present a major challenge in early detection, often leading to delayed diagnosis and variable outcomes. This review aims to provide an in-depth analysis of current diagnostic methods as well as the evolving and future directions of diagnostic strategies for NENs.

AREA COVERED

The review extensively covers the evolution of diagnostic tools for NENs, from traditional imaging and biochemical tests to advanced genomic profiling and next-generation sequencing. The emerging role of technologies such as artificial intelligence, machine learning, and liquid biopsies could improve diagnostic precision, as could the integration of imaging modalities such as positron emission tomography (PET)/magnetic resonance imaging (MRI) hybrids and innovative radiotracers.

EXPERT OPINION

Despite progress, there is still a significant gap in the early diagnosis of NENs. Bridging this diagnostic gap and integrating advanced technologies and precision medicine are crucial to improving patient outcomes. However, challenges such as low clinical awareness, limited possibility of noninvasive diagnostic tools and funding limitations for rare diseases like NENs are acknowledged.

Peptide Receptor Radionuclide Therapy of Neuroendocrine Tumors: Agonist, Antagonist and Alternatives

Peptide receptor radionuclide therapy (PRRT) today is a well-established treatment strategy for patients with neuroendocrine tumors (NET). First performed already more than 30 years ago, PRRT was incorporated only in recent years into the major oncology guidelines, based on its proven efficacy and safety in clinical trials. Following the phase 3 NETTER-1 trial, which led to the final registration of the radiopharmaceutical Luthatera® for G1/G2 NET patients in 2017, the long-term results of the phase 3 NETTER-2 trial may pave the way for a new treatment option also for advanced G2/G3 patients as first-line therapy. The growing knowledge about the synergistic effect of combined therapies could also allow alternative (re)treatment options for NET patients, in order to create a tailored treatment strategy. The evolving thera(g)nostic concept could be applied for the identification of patients who might benefit from different image-guided treatment strategies. In this scenario, the use of dual tracer PET/CT in NET patients, using both [18F]F-FDG/[68Ga]Ga-DOTA-somatostatin analog (SSA) for diagnosis and follow-up, is under discussion and could also result in a powerful prognostic tool. In addition, alternative strategies based on different metabolic pathways, radioisotopes, or combinations of different medical approaches could be applied. A number of different promising "doors" could thus open in the near future for the treatment of NET patients - and the "key" will be thera(g)nostic!

Radiomics Analysis of Preprocedural CT Imaging for Outcome Prediction after Transjugular Intrahepatic Portosystemic Shunt Creation

PURPOSE

To evaluate the role of radiomics in preoperative outcome prediction in cirrhotic patients who underwent transjugular intrahepatic portosystemic shunt (TIPS) using "controlled expansion covered stents".

MATERIALS AND METHODS

This retrospective institutional review board-approved study included cirrhotic patients undergoing TIPS with controlled expansion covered stent placement. From preoperative CT images, the whole liver was segmented into Volumes of Interest (VOIs) at the unenhanced and portal venous phase. Radiomics features were extracted, collected, and analyzed. Subsequently, receiver operating characteristic (ROC) curves were drawn to assess which features could predict patients' outcomes. The endpoints studied were 6-month overall survival (OS), development of hepatic encephalopathy (HE), grade II or higher HE according to West Haven Criteria, and clinical response, defined as the absence of rebleeding or ascites. A radiomic model for outcome prediction was then designed.

RESULTS

A total of 76 consecutive cirrhotic patients undergoing TIPS creation were enrolled. The highest performances in terms of the area under the receiver operating characteristic curve (AUROC) were observed for the "clinical response" and "survival at 6 months" outcome with 0.755 and 0.767, at the unenhanced and portal venous phase, respectively. Specifically, on basal scans, accuracy, specificity, and sensitivity were 66.42%, 63.93%, and 73.75%, respectively. At the portal venous phase, an accuracy of 65.34%, a specificity of 62.38%, and a sensitivity of 74.00% were demonstrated.

CONCLUSIONS

A pre-interventional machine learning-based CT radiomics algorithm could be useful in predicting survival and clinical response after TIPS creation in cirrhotic patients.

Shearlet Transform Applied to a Prostate Cancer Radiomics Analysis on MR Images

For decades, wavelet theory has attracted interest in several fields in dealing with signals. Nowadays, it is acknowledged that it is not very suitable to face aspects of multidimensional data like singularities and this has led to the development of other mathematical tools. A recent application of wavelet theory is in radiomics, an emerging field aiming to improve diagnostic, prognostic and predictive analysis of various cancer types through the analysis of features extracted from medical images. In this paper, for a radiomics study of prostate cancer with magnetic resonance (MR) images, we apply a similar but more sophisticated tool, namely the shearlet transform which, in contrast to the wavelet transform, allows us to examine variations along more orientations. In particular, we conduct a parallel radiomics analysis based on the two different transformations and highlight a better performance (evaluated in terms of statistical measures) in the use of the shearlet transform (in absolute value). The results achieved suggest taking the shearlet transform into consideration for radiomics studies in other contexts.

Radiomics and Artificial Intelligence in Radiotheranostics: A Review of Applications for Radioligands Targeting Somatostatin Receptors and Prostate-Specific Membrane Antigens

Radiotheranostics refers to the pairing of radioactive imaging biomarkers with radioactive therapeutic compounds that deliver ionizing radiation. Given the introduction of very promising radiopharmaceuticals, the radiotheranostics approach is creating a novel paradigm in personalized, targeted radionuclide therapies (TRTs), also known as radiopharmaceuticals (RPTs). Radiotherapeutic pairs targeting somatostatin receptors (SSTR) and prostate-specific membrane antigens (PSMA) are increasingly being used to diagnose and treat patients with metastatic neuroendocrine tumors (NETs) and prostate cancer. In parallel, radiomics and artificial intelligence (AI), as important areas in quantitative image analysis, are paving the way for significantly enhanced workflows in diagnostic and theranostic fields, from data and image processing to clinical decision support, improving patient selection, personalized treatment strategies, response prediction, and prognostication. Furthermore, AI has the potential for tremendous effectiveness in patient dosimetry which copes with complex and time-consuming tasks in the RPT workflow. The present work provides a comprehensive overview of radiomics and AI application in radiotheranostics, focusing on pairs of SSTR- or PSMA-targeting radioligands, describing the fundamental concepts and specific imaging/treatment features. Our review includes ligands radiolabeled by 68Ga, 18F, 177Lu, 64Cu, 90Y, and 225Ac. Specifically, contributions via radiomics and AI towards improved image acquisition, reconstruction, treatment response, segmentation, restaging, lesion classification, dose prediction, and estimation as well as ongoing developments and future directions are discussed.

Application of Artificial Intelligence in Oncologic Molecular PET-Imaging: A Narrative Review on Beyond [18F]F-FDG Tracers - Part I. PSMA, Choline, and DOTA Radiotracers

Artificial intelligence (AI) has evolved significantly in the past few decades. This thriving trend has also been seen in medicine in recent years, particularly in the field of imaging. Machine learning (ML), deep learning (DL), and their methods (eg, SVM, CNN), as well as radiomics, are the terminologies that have been introduced to this field and, to some extent, become familiar to the expert clinicians. PET is one of the modalities that has been enhanced via these state-of-the-art algorithms. This robust imaging technique further merged with anatomical modalities, such as computed tomography (CT) and magnetic resonance imaging (MRI), to provide reliable hybrid modalities, PET/CT and PET/MRI. Applying AI-based algorithms on the different components (PET, CT, and MRI) has resulted in promising results, maximizing the value of PET imaging. However, [18F]F-FDG, the most commonly utilized tracer in molecular imaging, has been mainly in the spotlight. Thus, we aimed to look into the less discussed tracers in this review, moving beyond [18F]F-FDG. The novel non-[18F]F-FDG agents also showed to be valuable in various clinical tasks, including lesion detection and tumor characterization, accurate delineation, and prognostic impact. Regarding prostate patients, PSMA-based models were highly accurate in determining tumoral lesions' location and delineating them, particularly within the prostate gland. However, they also could assess whole-body images to detect extra-prostatic lesions in a patient automatically. Considering the prognostic value of prostate-specific membrane antigen (PSMA) PET using AI, it could predict response to treatment and patient survival, which are crucial in patient management. Choline imaging, another non-[18F]F-FDG tracer, similarly showed acceptable results that may be of benefit in the clinic, though the current evidence is significantly more limited than PSMA. Lastly, different subtypes of DOTA ligands were found to be valuable. They could diagnose tumoral lesions in challenging sites and even predict histopathology grade, being a highly advantageous noninvasive tool. In conclusion, the current limited investigations have shown promising results, leading us to a bright future for AI in molecular imaging beyond [18F]F-FDG.

Performance of 18F-DCFPyL PET/CT in Primary Prostate Cancer Diagnosis, Gleason Grading and D'Amico Classification: A Radiomics-Based Study

This study aimed to investigate the performance of 18F-DCFPyL positron emission tomography/computerized tomography (PET/CT) models for predicting benign-vs-malignancy, high pathological grade (Gleason score > 7), and clinical D'Amico classification with machine learning. The study included 138 patients with treatment-naïve prostate cancer presenting positive 18F-DCFPyL scans. The primary lesions were delineated on PET images, followed by the extraction of tumor-to-background-based general and higher-order textural features by applying five different binning approaches. Three layer-machine learning approaches were used to identify relevant in vivo features and patient characteristics and their relative weights for predicting high-risk malignant disease. The weighted features were integrated and implemented to establish individual predictive models for malignancy (Mm), high path-risk lesions (by Gleason score) (Mgs), and high clinical risk disease (by amico) (Mamico). The established models were validated in a Monte Carlo cross-validation scheme. In patients with all primary prostate cancer, the highest areas under the curve for our models were calculated. The performance of established models as revealed by the Monte Carlo cross-validation presenting as the area under the receiver operator characteristic curve (AUC): 0.97 for Mm, AUC: 0.73 for Mgs, AUC: 0.82 for Mamico. Our study demonstrated the clinical potential of 18F-DCFPyL PET/CT radiomics in distinguishing malignant from benign prostate tumors, and high-risk tumors, without biopsy sampling. And in vivo 18F-DCFPyL PET/CT can be considered a noninvasive tool for virtual biopsy for personalized treatment management.

Supplementary Information

The online version contains supplementary material available at 10.1007/s43657-023-00108-y.

Applications of Artificial Intelligence and Radiomics in Molecular Hybrid Imaging and Theragnostics for Neuro-Endocrine Neoplasms (NENs)

Nuclear medicine has acquired a crucial role in the management of patients with neuroendocrine neoplasms (NENs) by improving the accuracy of diagnosis and staging as well as their risk stratification and personalized therapies, including radioligand therapies (RLT). Artificial intelligence (AI) and radiomics can enable physicians to further improve the overall efficiency and accuracy of the use of these tools in both diagnostic and therapeutic settings by improving the prediction of the tumor grade, differential diagnosis from other malignancies, assessment of tumor behavior and aggressiveness, and prediction of treatment response. This systematic review aims to describe the state-of-the-art AI and radiomics applications in the molecular imaging of NENs.

PET Radiomics and Response to Immunotherapy in Lung Cancer: A Systematic Review of the Literature

The aim of this review is to provide a comprehensive overview of the existing literature concerning the applications of positron emission tomography (PET) radiomics in lung cancer patient candidates or those undergoing immunotherapy.

MATERIALS AND METHODS

A systematic review was conducted on databases and web sources. English-language original articles were considered. The title and abstract were independently reviewed to evaluate study inclusion. Duplicate, out-of-topic, and review papers, or editorials, articles, and letters to editors were excluded. For each study, the radiomics analysis was assessed based on the radiomics quality score (RQS 2.0). The review was registered on the PROSPERO database with the number CRD42023402302.

RESULTS

Fifteen papers were included, thirteen were qualified as using conventional radiomics approaches, and two used deep learning radiomics. The content of each study was different; indeed, seven papers investigated the potential ability of radiomics to predict PD-L1 expression and tumor microenvironment before starting immunotherapy. Moreover, two evaluated the prediction of response, and four investigated the utility of radiomics to predict the response to immunotherapy. Finally, two papers investigated the prediction of adverse events due to immunotherapy.

CONCLUSIONS

Radiomics is promising for the evaluation of TME and for the prediction of response to immunotherapy, but some limitations should be overcome.

Relationships between uptake of [68Ga]Ga-DOTA-TATE and absorbed dose in [177Lu]Lu-DOTA-TATE therapy

BACKGROUND

Somatostatin receptor ⁶⁸Ga PET imaging is standard for evaluation of a patient's suitability for ¹⁷⁷Lu peptide receptor radionuclide therapy of neuroendocrine tumours (NETs). The ⁶⁸Ga PET serves to ensure sufficient somatostatin receptor expression, commonly evaluated qualitatively. The aim of this study is to investigate the quantitative relationships between uptake in ⁶⁸Ga PET and absorbed doses in ¹⁷⁷Lu therapy.

METHOD

Eighteen patients underwent [⁶⁸Ga]Ga-DOTA-TATE PET imaging within 20 weeks prior to their first cycle of [¹⁷⁷Lu]Lu-DOTA-TATE. Absorbed doses for therapy were estimated for tumours, kidney, spleen, and normal liver parenchyma using a hybrid SPECT/CT-planar method. Gallium-68 activity concentrations were retrieved from PET images and also used to calculate SUVs and normalized SUVs, using blood and tissue for normalization. The ⁶⁸Ga activity concentrations per injected activity, SUVs, and normalized SUVs were compared with ¹⁷⁷Lu activity concentrations 1 d post-injection and ¹⁷⁷Lu absorbed doses. For tumours, for which there was a variable number per patient, both inter- and intra-patient correlations were analysed. Furthermore, the prediction of ¹⁷⁷Lu tumour absorbed doses based on a combination of tumour-specific ⁶⁸Ga activity concentrations and group-based estimates of the effective half-lives for grade 1 and 2 NETs was explored.

RESULTS

For normal organs, only spleen showed a significant correlation between the ⁶⁸Ga activity concentration and ¹⁷⁷Lu absorbed dose (r = 0.6). For tumours, significant, but moderate, correlations were obtained, with respect to both inter-patient (r = 0.7) and intra-patient (r = 0.45) analyses. The correlations to absorbed doses did not improve when using ⁶⁸Ga SUVs or normalized SUVs. The relationship between activity uptakes for ⁶⁸Ga PET and ¹⁷⁷Lu SPECT was stronger, with correlation coefficients r = 0.8 for both inter- and intra-patient analyses. The ¹⁷⁷Lu absorbed dose to tumour could be predicted from the ⁶⁸Ga activity concentrations with a 95% coverage interval of - 65% to 248%.

CONCLUSIONS

On a group level, a high uptake of [⁶⁸Ga]Ga-DOTA-TATE is associated with high absorbed doses at ¹⁷⁷Lu-DOTA-TATE therapy, but the relationship has a limited potential with respect to individual absorbed dose planning. Using SUV or SUV normalized to reference tissues do not improve correlations compared with using activity concentration per injected activity.

Nuclear Medicine and Radiological Imaging of Pancreatic Neuroendocrine Neoplasms: A Multidisciplinary Update

Pancreatic neuroendocrine neoplasms (panNENs) are part of a large family of tumors arising from the neuroendocrine system. PanNENs show low-intermediate tumor grade and generally high somatostatin receptor (SSTR) expression. Therefore, panNENs benefit from functional imaging with ⁶⁸Ga-somatostatin analogues (SSA) for diagnosis, staging, and treatment choice in parallel with morphological imaging. This narrative review aims to present conventional imaging techniques and new perspectives in the management of panNENs, providing the clinicians with useful insight for clinical practice. The ⁶⁸Ga-SSA PET/CT is the most widely used in panNENs, not only fr diagnosis and staging purpose but also to characterize the biology of the tumor and its responsiveness to SSAs. On the contrary, the ¹⁸F-Fluordeoxiglucose (FDG) PET/CT is not employed systematically in all panNEN patients, being generally preferred in G2-G3, to predict aggressiveness and progression rate. The combination of ⁶⁸Ga-SSA PET/CT and ¹⁸F-FDG PET/CT can finally suggest the best therapeutic strategy. Other radiopharmaceuticals are ⁶⁸Ga-exendin-4 in case of insulinomas and ¹⁸F-dopamine (DOPA), which can be helpful in SSTR-negative tumors. New promising but still-under-investigation radiopharmaceuticals include radiolabeled SSTR antagonists and ¹⁸F-SSAs. Conventional imaging includes contrast enhanced CT and multiparametric MRI. There are now enriched by radiomics, a new non-invasive imaging approach, very promising to early predict tumor response or progression.

matRadiomics: A Novel and Complete Radiomics Framework, from Image Visualization to Predictive Model

Radiomics aims to support clinical decisions through its workflow, which is divided into: (i) target identification and segmentation, (ii) feature extraction, (iii) feature selection, and (iv) model fitting. Many radiomics tools were developed to fulfill the steps mentioned above. However, to date, users must switch different software to complete the radiomics workflow. To address this issue, we developed a new free and user-friendly radiomics framework, namely matRadiomics, which allows the user: (i) to import and inspect biomedical images, (ii) to identify and segment the target, (iii) to extract the features, (iv) to reduce and select them, and (v) to build a predictive model using machine learning algorithms. As a result, biomedical images can be visualized and segmented and, through the integration of Pyradiomics into matRadiomics, radiomic features can be extracted. These features can be selected using a hybrid descriptive–inferential method, and, consequently, used to train three different classifiers: linear discriminant analysis, k-nearest neighbors, and support vector machines. Model validation is performed using k-fold cross-Validation and k-fold stratified cross-validation. Finally, the performance metrics of each model are shown in the graphical interface of matRadiomics. In this study, we discuss the workflow, architecture, application, future development of matRadiomics, and demonstrate its working principles in a real case study with the aim of establishing a reference standard for the whole radiomics analysis, starting from the image visualization up to the predictive model implementation.

A New Preclinical Decision Support System Based on PET Radiomics: A Preliminary Study on the Evaluation of an Innovative 64Cu-Labeled Chelator in Mouse Models

The 64Cu-labeled chelator was analyzed in vivo by positron emission tomography (PET) imaging to evaluate its biodistribution in a murine model at different acquisition times. For this purpose, nine 6-week-old female Balb/C nude strain mice underwent micro-PET imaging at three different time points after 64Cu-labeled chelator injection. Specifically, the mice were divided into group 1 (acquisition 1 h after [64Cu] chelator administration, n = 3 mice), group 2 (acquisition 4 h after [64Cu]chelator administration, n = 3 mice), and group 3 (acquisition 24 h after [64Cu] chelator administration, n = 3 mice). Successively, all PET studies were segmented by means of registration with a standard template space (3D whole-body Digimouse atlas), and 108 radiomics features were extracted from seven organs (namely, heart, bladder, stomach, liver, spleen, kidney, and lung) to investigate possible changes over time in [64Cu]chelator biodistribution. The one-way analysis of variance and post hoc Tukey Honestly Significant Difference test revealed that, while heart, stomach, spleen, kidney, and lung districts showed a very low percentage of radiomics features with significant variations (p-value < 0.05) among the three groups of mice, a large number of features (greater than 60% and 50%, respectively) that varied significantly between groups were observed in bladder and liver, indicating a different in vivo uptake of the 64Cu-labeled chelator over time. The proposed methodology may improve the method of calculating the [64Cu]chelator biodistribution and open the way towards a decision support system in the field of new radiopharmaceuticals used in preclinical imaging trials.