Outcome Prediction at Patient Level Derived from Pre-Treatment 18F-FDG PET Due to Machine Learning in Metastatic Melanoma Treated with Anti-PD1 Treatment

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.

Can Delta Radiomics Improve the Prediction of Best Overall Response, Progression-Free Survival, and Overall Survival of Melanoma Patients Treated with Immune Checkpoint Inhibitors?

BACKGROUND

The prevalence of metastatic melanoma is increasing, necessitating the identification of patients who do not benefit from immunotherapy. This study aimed to develop a radiomic biomarker based on the segmentation of all metastases at baseline and the first follow-up CT for the endpoints best overall response (BOR), progression-free survival (PFS), and overall survival (OS), encompassing various immunotherapies. Additionally, this study investigated whether reducing the number of segmented metastases per patient affects predictive capacity.

METHODS

The total tumour load, excluding cerebral metastases, from 146 baseline and 146 first follow-up CTs of melanoma patients treated with first-line immunotherapy was volumetrically segmented. Twenty-one random forest models were trained and compared for the endpoints BOR; PFS at 6, 9, and 12 months; and OS at 6, 9, and 12 months, using as input either only clinical parameters, whole-tumour-load delta radiomics plus clinical parameters, or delta radiomics from the largest ten metastases plus clinical parameters.

RESULTS

The whole-tumour-load delta radiomics model performed best for BOR (AUC 0.81); PFS at 6, 9, and 12 months (AUC 0.82, 0.80, and 0.77); and OS at 6 months (AUC 0.74). The model using delta radiomics from the largest ten metastases performed best for OS at 9 and 12 months (AUC 0.71 and 0.75). Although the radiomic models were numerically superior to the clinical model, statistical significance was not reached.

CONCLUSIONS

The findings indicate that delta radiomics may offer additional value for predicting BOR, PFS, and OS in metastatic melanoma patients undergoing first-line immunotherapy. Despite its complexity, volumetric whole-tumour-load segmentation could be advantageous.

Machine learning in the prediction of immunotherapy response and prognosis of melanoma: a systematic review and meta-analysis

Background

The emergence of immunotherapy has changed the treatment modality for melanoma and prolonged the survival of many patients. However, a handful of patients remain unresponsive to immunotherapy and effective tools for early identification of this patient population are still lacking. Researchers have developed machine learning algorithms for predicting immunotherapy response in melanoma, but their predictive accuracy has been inconsistent. Therefore, the present systematic review and meta-analysis was performed to comprehensively evaluate the predictive accuracy of machine learning in melanoma response to immunotherapy.

Methods

Relevant studies were searched in PubMed, Web of Sciences, Cochrane Library, and Embase from their inception to July 30, 2022. The risk of bias and applicability of the included studies were assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Meta-analysis was performed on R4.2.0.

Results

A total of 36 studies consisting of 30 cohort studies and 6 case-control studies were included. These studies were mainly published between 2019 and 2022 and encompassed 75 models. The outcome measures of this study were progression-free survival (PFS), overall survival (OS), and treatment response. The pooled c-index was 0.728 (95%CI: 0.629-0.828) for PFS in the training set, 0.760 (95%CI: 0.728-0.792) and 0.819 (95%CI: 0.757-0.880) for treatment response in the training and validation sets, respectively, and 0.746 (95%CI: 0.721-0.771) and 0.700 (95%CI: 0.677-0.724) for OS in the training and validation sets, respectively.

Conclusion

Machine learning has considerable predictive accuracy in melanoma immunotherapy response and prognosis, especially in the former. However, due to the lack of external validation and the scarcity of certain types of models, further studies are warranted.

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.

Methodological evaluation of original articles on radiomics and machine learning for outcome prediction based on positron emission tomography (PET)

AIM

Despite a vast number of articles on radiomics and machine learning in positron emission tomography (PET) imaging, clinical applicability remains limited, partly owing to poor methodological quality. We therefore systematically investigated the methodology described in publications on radiomics and machine learning for PET-based outcome prediction.

METHODS

A systematic search for original articles was run on PubMed. All articles were rated according to 17 criteria proposed by the authors. Criteria with >2 rating categories were binarized into "adequate" or "inadequate". The association between the number of "adequate" criteria per article and the date of publication was examined.

RESULTS

One hundred articles were identified (published between 07/2017 and 09/2023). The median proportion of articles per criterion that were rated "adequate" was 65% (range: 23-98%). Nineteen articles (19%) mentioned neither a test cohort nor cross-validation to separate training from testing. The median number of criteria with an "adequate" rating per article was 12.5 out of 17 (range, 4-17), and this did not increase with later dates of publication (Spearman's rho, 0.094; p = 0.35). In 22 articles (22%), less than half of the items were rated "adequate". Only 8% of articles published the source code, and 10% made the dataset openly available.

CONCLUSION

Among the articles investigated, methodological weaknesses have been identified, and the degree of compliance with recommendations on methodological quality and reporting shows potential for improvement. Better adherence to established guidelines could increase the clinical significance of radiomics and machine learning for PET-based outcome prediction and finally lead to the widespread use in routine clinical practice.

Artificial Intelligence and Radiomics: Clinical Applications for Patients with Advanced Melanoma Treated with Immunotherapy

Immunotherapy has greatly improved the outcomes of patients with metastatic melanoma. However, it has also led to new patterns of response and progression, creating an unmet need for better biomarkers to identify patients likely to achieve a lasting clinical benefit or experience immune-related adverse events. In this study, we performed a focused literature survey covering the application of artificial intelligence (AI; in the form of radiomics, machine learning, and deep learning) to patients diagnosed with melanoma and treated with immunotherapy, reviewing 12 studies relevant to the topic published up to early 2022. The most commonly investigated imaging modality was CT imaging in isolation (n = 9, 75.0%), while patient cohorts were most frequently recruited retrospectively and from single institutions (n = 7, 58.3%). Most studies concerned the development of AI tools to assist in prognostication (n = 5, 41.7%) or the prediction of treatment response (n = 6, 50.0%). Validation methods were disparate, with two studies (16.7%) performing no validation and equal numbers using cross-validation (n = 3, 25%), a validation set (n = 3, 25%), or a test set (n = 3, 25%). Only one study used both validation and test sets (n = 1, 8.3%). Overall, promising results have been observed for the application of AI to immunotherapy-treated melanoma. Further improvement and eventual integration into clinical practice may be achieved through the implementation of rigorous validation using heterogeneous, prospective patient cohorts.

Cancer immunotherapy response prediction from multi-modal clinical and image data using semi-supervised deep learning

BACKGROUND AND PURPOSE

Immunotherapy is a standard treatment for many tumor types. However, only a small proportion of patients derive clinical benefit and reliable predictive biomarkers of immunotherapy response are lacking. Although deep learning has made substantial progress in improving cancer detection and diagnosis, there is limited success on the prediction of treatment response. Here, we aim to predict immunotherapy response of gastric cancer patients using routinely available clinical and image data.

MATERIALS AND METHODS

We present a multi-modal deep learning radiomics approach to predict immunotherapy response using both clinical data and computed tomography images. The model was trained using 168 advanced gastric cancer patients treated with immunotherapy. To overcome limitations of small training data, we leverage an additional dataset of 2,029 patients who did not receive immunotherapy in a semi-supervised framework to learn intrinsic imaging phenotypes of the disease. We evaluated model performance in two independent cohorts of 81 patients treated with immunotherapy.

RESULTS

The deep learning model achieved area under receiver operating characteristics curve (AUC) of 0.791 (95% CI 0.633-0.950) and 0.812 (95% CI 0.669-0.956) for predicting immunotherapy response in the internal and external validation cohorts. When combined with PD-L1 expression, the integrative model further improved the AUC by 4-7% in absolute terms.

CONCLUSION

The deep learning model achieved promising performance for predicting immunotherapy response from routine clinical and image data. The proposed multi-modal approach is general and can incorporate other relevant information to further improve prediction of immunotherapy response.

Development and Validation of a Predictive Model for Metastatic Melanoma Patients Treated with Pembrolizumab Based on Automated Analysis of Whole-Body [18F]FDG PET/CT Imaging and Clinical Features

BACKGROUND

Antibodies that inhibit the programmed cell death protein 1 (PD-1) receptor offer a significant survival benefit, potentially cure (i.e., durable disease-free survival following treatment discontinuation), a substantial proportion of patients with advanced melanoma. Most patients however fail to respond to such treatment or acquire resistance. Previously, we reported that baseline total metabolic tumour volume (TMTV) determined by whole-body [18F]FDG PET/CT was independently correlated with survival and able to predict the futility of treatment. Manual delineation of [18F]FDG-avid lesions is however labour intensive and not suitable for routine use. A predictive survival model is proposed based on automated analysis of baseline, whole-body [18F]FDG images.

METHODS

Lesions were segmented on [18F]FDG PET/CT using a deep-learning approach and derived features were investigated through Kaplan-Meier survival estimates with univariate logrank test and Cox regression analyses. Selected parameters were evaluated in multivariate Cox survival regressors.

RESULTS

In the development set of 69 patients, overall survival prediction based on TMTV, lactate dehydrogenase levels and presence of brain metastases achieved an area under the curve of 0.78 at one year, 0.70 at two years. No statistically significant difference was observed with respect to using manually segmented lesions. Internal validation on 31 patients yielded scores of 0.76 for one year and 0.74 for two years.

CONCLUSIONS

Automatically extracted TMTV based on whole-body [18F]FDG PET/CT can aid in building predictive models that can support therapeutic decisions in patients treated with immune-checkpoint blockade.

Artificial intelligence and radiomics: fundamentals, applications, and challenges in immunotherapy

Immunotherapy offers the potential for durable clinical benefit but calls into question the association between tumor size and outcome that currently forms the basis for imaging-guided treatment. Artificial intelligence (AI) and radiomics allow for discovery of novel patterns in medical images that can increase radiology’s role in management of patients with cancer, although methodological issues in the literature limit its clinical application. Using keywords related to immunotherapy and radiomics, we performed a literature review of MEDLINE, CENTRAL, and Embase from database inception through February 2022. We removed all duplicates, non-English language reports, abstracts, reviews, editorials, perspectives, case reports, book chapters, and non-relevant studies. From the remaining articles, the following information was extracted: publication information, sample size, primary tumor site, imaging modality, primary and secondary study objectives, data collection strategy (retrospective vs prospective, single center vs multicenter), radiomic signature validation strategy, signature performance, and metrics for calculation of a Radiomics Quality Score (RQS). We identified 351 studies, of which 87 were unique reports relevant to our research question. The median (IQR) of cohort sizes was 101 (57–180). Primary stated goals for radiomics model development were prognostication (n=29, 33.3%), treatment response prediction (n=24, 27.6%), and characterization of tumor phenotype (n=14, 16.1%) or immune environment (n=13, 14.9%). Most studies were retrospective (n=75, 86.2%) and recruited patients from a single center (n=57, 65.5%). For studies with available information on model testing, most (n=54, 65.9%) used a validation set or better. Performance metrics were generally highest for radiomics signatures predicting treatment response or tumor phenotype, as opposed to immune environment and overall prognosis. Out of a possible maximum of 36 points, the median (IQR) of RQS was 12 (10–16). While a rapidly increasing number of promising results offer proof of concept that AI and radiomics could drive precision medicine approaches for a wide range of indications, standardizing the data collection as well as optimizing the methodological quality and rigor are necessary before these results can be translated into clinical practice.

Imaging More than Skin-Deep: Radiologic and Dermatologic Presentations of Systemic Disorders

Background: Cutaneous manifestations of systemic diseases are diverse and sometimes precede more serious diseases and symptomatology. Similarly, radiologic imaging plays a key role in early diagnosis and determination of the extent of systemic involvement. Simultaneous awareness of skin and imaging manifestations can help the radiologist to narrow down differential diagnosis even if imaging findings are nonspecific. Aims: To improve diagnostic accuracy and patient care, it is important that clinicians and radiologists be familiar with both cutaneous and radiologic features of various systemic disorders. This article reviews cutaneous manifestations and imaging findings of commonly encountered systemic diseases. Conclusions: Familiarity with the most disease-specific skin lesions help the radiologist pinpoint a specific diagnosis and consequently, in preventing unnecessary invasive workups and contributing to improved patient care.

The Role and Potential of 18F-FDG PET/CT in Malignant Melanoma: Prognostication, Monitoring Response to Targeted and Immunotherapy, and Radiomics

Novel therapeutic approaches, consisting of immune check-point inhibitors (ICIs) and molecularly targeted therapy, have thoroughly changed the clinical management of malignant melanoma (MM), the most frequent and deadly skin cancer. Since only 30-40% of MM patients respond to ICIs, imaging biomarkers suitable for the pre-therapeutic stratification and response assessment are warmly welcome. In this scenario, positron emission computed tomography (PET/CT) with 18F-fluorodeoxyglucose (18F-FDG) has been successfully utilized for advanced MM staging and therapy response evaluation. Furthermore, several PET-derived parameters (SUVmax, MTV, TLG) were particularly impactful for the prognostic evaluation of patients submitted to targeted and immunotherapy. In this review, we performed a web-based and desktop research on the clinical applications of 18F-FDG PET/CT in MM, with a particular emphasis on the various metabolic criteria developed for interpreting PET/CT scan in patients undergoing immunotherapy or targeted therapy or a combination of both. Furthermore, the emerging role of radiomics, a quantitative approach to medical imaging applying analysis methodology derived by the field of artificial intelligence, was examined in the peculiar context, putting a particular emphasis on the potential of this discipline to support clinicians in the delicate process of building patient-tailored pathways of care.