Artificial intelligence in immunotherapy PET/SPECT imaging

OBJECTIVE

Immunotherapy has dramatically altered the therapeutic landscape for oncology, but more research is needed to identify patients who are likely to achieve durable clinical benefit and those who may develop unacceptable side effects. We investigated the role of artificial intelligence in PET/SPECT-guided approaches for immunotherapy-treated patients.

METHODS

We performed a scoping review of MEDLINE, CENTRAL, and Embase databases using key terms related to immunotherapy, PET/SPECT imaging, and AI/radiomics through October 12, 2022.

RESULTS

Of the 217 studies identified in our literature search, 24 relevant articles were selected. The median (interquartile range) sample size of included patient cohorts was 63 (157). Primary tumors of interest were lung (n = 14/24, 58.3%), lymphoma (n = 4/24, 16.7%), or melanoma (n = 4/24, 16.7%). A total of 28 treatment regimens were employed, including anti-PD-(L)1 (n = 13/28, 46.4%) and anti-CTLA-4 (n = 4/28, 14.3%) monoclonal antibodies. Predictive models were built from imaging features using univariate radiomics (n = 7/24, 29.2%), radiomics (n = 12/24, 50.0%), or deep learning (n = 5/24, 20.8%) and were most often used to prognosticate (n = 6/24, 25.0%) or describe tumor phenotype (n = 5/24, 20.8%). Eighteen studies (75.0%) performed AI model validation.

CONCLUSION

Preliminary results suggest broad potential for the application of AI-guided immunotherapy management after further validation of models on large, prospective, multicenter cohorts.

CLINICAL RELEVANCE STATEMENT

This scoping review describes how artificial intelligence models are built to make predictions based on medical imaging and explores their application specifically in the PET and SPECT examination of immunotherapy-treated cancers.

KEY POINTS

• Immunotherapy has drastically altered the cancer treatment landscape but is known to precipitate response patterns that are not accurately accounted for by traditional imaging methods. • There is an unmet need for better tools to not only facilitate in-treatment evaluation but also to predict, a priori, which patients are likely to achieve a good response with a certain treatment as well as those who are likely to develop side effects. • Artificial intelligence applied to PET/SPECT imaging of immunotherapy-treated patients is mainly used to make predictions about prognosis or tumor phenotype and is built from baseline, pre-treatment images. Further testing is required before a true transition to clinical application can be realized.

Integrating Artificial Intelligence and PET Imaging for Drug Discovery: A Paradigm Shift in Immunotherapy

The integration of artificial intelligence (AI) and positron emission tomography (PET) imaging has the potential to become a powerful tool in drug discovery. This review aims to provide an overview of the current state of research and highlight the potential for this alliance to advance pharmaceutical innovation by accelerating the development and deployment of novel therapeutics. We previously performed a scoping review of three databases (Embase, MEDLINE, and CENTRAL), identifying 87 studies published between 2018 and 2022 relevant to medical imaging (e.g., CT, PET, MRI), immunotherapy, artificial intelligence, and radiomics. Herein, we reexamine the previously identified studies, performing a subgroup analysis on articles specifically utilizing AI and PET imaging for drug discovery purposes in immunotherapy-treated oncology patients. Of the 87 original studies identified, 15 met our updated search criteria. In these studies, radiomics features were primarily extracted from PET/CT images in combination (n = 9, 60.0%) rather than PET imaging alone (n = 6, 40.0%), and patient cohorts were mostly recruited retrospectively and from single institutions (n = 10, 66.7%). AI models were used primarily for prognostication (n = 6, 40.0%) or for assisting in tumor phenotyping (n = 4, 26.7%). About half of the studies stress-tested their models using validation sets (n = 4, 26.7%) or both validation sets and test sets (n = 4, 26.7%), while the remaining six studies (40.0%) either performed no validation at all or used less stringent methods such as cross-validation on the training set. Overall, the integration of AI and PET imaging represents a paradigm shift in drug discovery, offering new avenues for more efficient development of therapeutics. By leveraging AI algorithms and PET imaging analysis, researchers could gain deeper insights into disease mechanisms, identify new drug targets, or optimize treatment regimens. However, further research is needed to validate these findings and address challenges such as data standardization and algorithm robustness.

Proton-Coupled Electron-Transfer Reactivity Controls Iron versus Sulfur Oxidation in Nonheme Iron-Thiolate Complexes

Reaction of the five-coordinate Fe^II(N₄S) complexes, [Fe^II(iPr₃TACN)(abt^X)](OTf) (abt = aminobenzenethiolate, X = H, CF₃), with a one-electron oxidant and an appropriate base leads to net H atom loss, generating new Fe^III(iminobenzenethiolate) complexes that were characterized by single-crystal X-ray diffraction (XRD), as well as UV-vis, EPR, and Mössbauer spectroscopies. The spectroscopic data indicate that the iminobenzenethiolate complexes have S = 3/2 ground states. In the absence of a base, oxidation of the Fe^II(abt) complexes leads to disulfide formation instead of oxidation at the metal center. Bracketing studies with separated proton-coupled electron-transfer (PCET) reagents show that the Fe^II(aminobenzenethiolate) and Fe^III(iminobenzenethiolate) forms are readily interconvertible by H⁺/e^- transfer and provide a measure of the bond dissociation free energy (BDFE) for the coordinated N-H bond between 64 and 69 kcal mol^-1. This work shows that coordination to the iron center causes a dramatic weakening of the N-H bond and that Fe- versus S-oxidation in a nonheme iron complex can be controlled by the protonation state of an ancillary amino donor.

Structures, Spectroscopic Properties, and Dioxygen Reactivity of 5- and 6-Coordinate Nonheme Iron(II) Complexes: A Combined Enzyme/Model Study of Thiol Dioxygenases

The synthesis of four new FeII(N4S(thiolate)) complexes as models of the thiol dioxygenases are described. They are composed of derivatives of the neutral, tridentate ligand triazacyclononane (R3TACN; R = Me, iPr) and 2-aminobenzenethiolate (abtx; X = H, CF3), a non-native substrate for thiol dioxygenases. The coordination number of these complexes depends on the identity of the TACN derivative, giving 6-coordinate (6-coord) complexes for FeII(Me3TACN)(abtx)(OTf) (1: X = H; 2: X = CF3) and 5-coordinate (5-coord) complexes for [FeII(iPr3TACN)(abtx)](OTf) (3: X = H; 4: X = CF3). Complexes 1-4 were examined by UV-vis, 1H/19F NMR, and Mössbauer spectroscopies, and density functional theory (DFT) calculations were employed to support the data. Mössbauer spectroscopy reveals that the 6-coord 1-2 and 5-coord 3- 4 exhibit distinct spectra, and these data are compared with that for cysteine-bound CDO, helping to clarify the coordination environment of the cys-bound FeII active site. Reaction of 1 or 2 with O2 at -95 °C leads to S-oxygenation of the abt ligand, and in the case of 2, a rare di(sulfinato)-bridged complex, [Fe2III(μ-O)((2-NH2) p-CF3C6H3SO2)2](OTf)2 ( 5), was obtained. Parallel enzymatic studies on the CDO variant C93G were carried out with the abt substrate and show that reaction with O2 leads to disulfide formation, as opposed to S-oxygenation. The combined model and enzyme studies show that the thiol dioxygenases can operate via a 6-coord FeII center, in contrast to the accepted mechanism for nonheme iron dioxygenases, and that proper substrate chelation to Fe appears to be critical for S-oxygenation.