Machine learning defined diagnostic criteria for differentiating pituitary metastasis from autoimmune hypophysitis in patients undergoing immune checkpoint blockade therapy

Neuroimaging features of immune-related adverse events due to immune checkpoint inhibitor therapy

Immune checkpoint inhibitors, a type of intravenous immunotherapy targeting T cells, are being increasingly used in cancer treatment. They work by increasing the immune system's response to tumour cells, through blockade of inhibitory "checkpoint" receptors. Immune checkpoint inhibitors commonly induce immune-related adverse events (irAEs) affecting multiple organ systems. Hypophysitis is strictly an endocrine irAE, but is the most common irAE identified on neuroimaging. True neurologic irAEs are rare and widely varied. Examples include meningitis, encephalitis, vasculitis, demyelinating syndromes and neuritis. Some neurologic irAEs are not associated with neuroimaging findings (for example, neuromuscular junction disorders), while in others, imaging findings are present in only a proportion of patients (for example, encephalitis). Diagnosing, or at least considering, a neurologic irAE is important for instigating the appropriate management and optimising patient outcomes. This educational review illustrates irAEs that may be identified on neuroimaging and provides practical tips for optimising diagnosis, including relevant clinical considerations. CRITICAL RELEVANCE STATEMENT: Immune checkpoint inhibitors, which are being increasingly used in cancer treatment, commonly induce immune-related adverse events. This educational review illustrates the range of immune-related adverse events for which neuroimaging plays a key role in diagnosis. KEY POINTS: Immune checkpoint inhibitors commonly result in immune-related adverse events (irAEs) affecting multiple organ systems. Hypophysitis, the most common irAE identified on neuroimaging, is characterised by transient pituitary enlargement. True neurologic irAEs are rare and include meningitis, encephalitis, vasculitis, demyelination and neuritis. An understanding of the overall clinical picture is important for supporting the diagnosis.

18 F-FDG PET/CT for Detection of Immunotherapy-Induced Hypophysitis-A Case-Control Study

PURPOSE

Hypophysitis occurs in up to 10% of patients treated with immune-checkpoint inhibitors (ICIs). MRI shows no abnormalities of the pituitary gland in one third of patients. A delayed diagnosis increases the risk for life-threatening adrenal crisis, underscoring the need for early detection. This study evaluates the diagnostic accuracy FDG PET/CT in detecting ICI-induced hypophysitis in a cohort of melanoma patients.

MATERIALS AND METHODS

Patients with metastatic melanoma and ICI-induced hypophysitis, who underwent FDG PET/CT 90 days before to 10 days after diagnosis, were compared with an age- and sex-matched control group of patients undergoing ICI treatment without signs of hypophysitis. The ratio of SUV max of the pituitary gland to the SUV mean of the blood pool (target-to-background ratio [TBR]) was calculated. Diagnostic accuracy of the TBR was assessed using area under the receiver operating characteristics curve analysis.

RESULTS

A total of 28 patients was included. The majority of patients with hypophysitis received ipilimumab/nivolumab (64.3%, 9/14). Visual assessment of the TBR distribution demonstrated a positive correlation with decreasing time to diagnosis. To evaluate diagnostic performance, only patients with FDG PET/CT 50 days before to 8 days after diagnosis (11/14) were included. TBR was significantly higher in these compared with the control group (median [interquartile range], 2.78 [2.41] vs 1.59 [0.70], respectively; P = 0.034). A sensitivity of 72.7% and a specificity of 90.9% were achieved at a TBR threshold of 2.41 (area under the receiver operating characteristics curve = 0.769).

CONCLUSIONS

Our findings suggest that, in patients undergoing ICI treatment for metastatic melanoma, a pituitary TBR of approximately 2.4 may indicate impending ICI-induced hypophysitis.

Differences in checkpoint-inhibitor-induced hypophysitis: mono- versus combination therapy induced hypophysitis

Objective

Immune checkpoint inhibitors (ICIs) are revolutionary in oncology but may cause immune-related (IR) side effects, such as hypophysitis. Treatment with anti-PD-(L)1, anti-CTLA-4 or anti-CLTA-4/PD-1 may induce hypophysitis, but little is known about the differences in clinical presentation or need for different treatment. We analyzed the differences of anti-PD-(L)1, anti-CTLA-4 and anti-CTLA-4/PD-1 induced hypophysitis.

Methods

retrospective analysis of 67 patients (27 anti-PD-(L)1, 6 anti-CLTA-4 and 34 anti-CTLA-4/PD-1 induced hypophysitis).

Results

The median time between starting ICIs and IR-hypophysitis was longer after anti-PD(L)-1) therapy (22 weeks versus 11 and 14 weeks after anti-CTLA-4 and anti-CTLA-4/PD-1 therapy, respectively). The majority of patients (>90%), presented with atypical complaints such as fatigue, nausea, and muscle complaints. Headache, TSH or LH/FSH deficiency were more common in anti-CTLA-4 and anti-CLTA-4/PD-1 versus anti-PD-(L)1 induced hypophysitis (83% and 58% versus 8%, 67% and 41% versus 11%, and 83% and 48% versus 7%, respectively). Pituitary abnormalities on MRI (hypophysitis or secondary empty sella syndrome) were only seen in patients receiving anti-CTLA-4 or anti-CTLA-4/PD-1 therapy. Recovery from TSH, LH/FSH and ACTH deficiency was described in 92%, 70% and 0% of patients after a mean period of 14 and 104 days, respectively, and did not differ between patients who did or did not receive high-dose steroids.

Conclusion

The clinical presentation of IR-hypophysitis varies depending on the type of ICIs. MRI abnormalities were only seen in anti-CTLA-4 or anti-CTLA-4/PD-1 induced hypophysitis. Endocrine recovery is seen for LH/FSH and TSH deficiency but not for ACTH deficiency, irrespective of the corticosteroid dose.

Immune-Related Adverse Events Induced by Immune Checkpoint Inhibitors and CAR-T Cell Therapy: A Comprehensive Imaging-Based Review

Immunotherapy has revolutionized oncology care, improving patient outcomes in several cancers. However, these therapies are also associated with typical immune-related adverse events due to the enhanced inflammatory and immune response. These toxicities can arise at any time during treatment but are more frequent within the first few months. Any organ and tissue can be affected, ranging from mild to life-threatening. While some manifestations are common and more often mild, such as dermatitis and colitis, others are rarer and more severe, such as myocarditis. Management depends on the severity, with treatment being held for >grade 2 toxicities. Steroids are used in more severe cases, and immunosuppressive treatment may be considered for non-responsive toxicities, along with specific organ support. A multidisciplinary approach is mandatory for prompt identification and management. The diagnosis is primarily of exclusion. It often relies on imaging features, and, when possible, cytologic and/or pathological analyses are performed for confirmation. In case of clinical suspicion, imaging is required to assess the presence, extent, and features of abnormalities and to evoke and rule out differential diagnoses. This imaging-based review illustrates the diverse system-specific toxicities associated with immune checkpoint inhibitors and chimeric antigen receptor T-cells with a multidisciplinary perspective. Clinical characteristics, imaging features, cytological and histological patterns, as well as the management approach, are presented with insights into radiological tips to distinguish these toxicities from the most important differential diagnoses and mimickers-including tumor progression, pseudoprogression, inflammation, and infection-to guide imaging and clinical specialists in the pathway of diagnosing immune-related adverse events.

Immunotherapy-Induced Hypophysitis Following Treatment With Tislelizumab in an Elderly Patient With Bladder Cancer and Prostate Cancer: A Case Report

Immune checkpoint inhibitors represent a hopeful and emerging group of medications employed in the regulation of the immune response against cancer, displaying tremendous potential in cancer treatment. However, the administration of these drugs has been linked to the occurrence of adverse events, among which hypophysitis appears to be a prevailing complication affecting a substantial number of patients. Given the potential gravity of this condition, it is strongly recommended to actively monitor hormone levels throughout the treatment process, allowing for the prompt detection and provision of appropriate therapeutic measures. The present study showcases a case involving a 72-year-old individual afflicted with both bladder cancer and prostate cancer, who subsequently developed autoimmune hypophysitis and secondary adrenocortical insufficiency following the administration of programmed death protein 1 (PD-1) inhibitors.

Pituitary metastasis of salivary gland carcinoma mimicking hypophysitis: A case report and literature review

INTRODUCTION

Pituitary metastases from salivary gland carcinomas are rare. Moreover, pituitary metastasis and hypophysitis exhibit neuroimaging similarities that complicate the diagnosis in patients receiving immune checkpoint drugs.

PRESENTATION OF CASE

We present a case of pituitary metastasis derived from a sublingual gland carcinoma; this case posed a challenge in the differential diagnosis of hypophysitis. A 52-year-old male patient presented with anorexia and visual disturbances. The patient was previously diagnosed with sublingual gland carcinoma that necessitated surgical intervention consisting of tumor resection and residual lymph node dissection. Subsequently, the patient underwent immune checkpoint blockade therapy following platinum-based chemotherapy. Magnetic resonance imaging revealed the presence of an intrasellar tumor infiltrating the dura mater, cavernous sinus, and pituitary stalk with isointensity on T1 and T2 weighted images and homogeneous gadolinium enhancement. Despite the initial suspicion of hypophysitis, diagnostic treatment with systemic corticosteroids failed to induce significant tumor reduction. Diagnostic clarification was achieved via an endoscopic transsphenoidal biopsy, which confirmed the histological diagnosis of pituitary metastasis from the prior sublingual gland adenocarcinoma. Radiotherapy was administered as a therapeutic intervention.

DISCUSSION

The case report highlighted the rarity of metastases from salivary gland carcinoma to the pituitary gland and emphasized the challenges in distinguishing between pituitary metastasis and hypophysitis based on imaging studies alone, particularly in patients receiving immune checkpoint inhibitors.

CONCLUSION

Given the rarity of this condition and its neuroimaging similarities with hypophysitis, pathological confirmation is imperative for a definitive diagnosis.

Radiomics and machine learning for predicting the consistency of benign tumors of the central nervous system: A systematic review

PURPOSE

Predicting the consistency of benign central nervous system (CNS) tumors prior to surgery helps to improve surgical outcomes. This review summarizes and analyzes the literature on using radiomics and/or machine learning (ML) for consistency prediction.

METHOD

The Medical Literature Analysis and Retrieval System Online (MEDLINE) database was screened for studies published in English from January 1st 2000. Data was extracted according to the PRISMA guidelines and quality of the studies was assessed in compliance with the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2).

RESULTS

Eight publications were included focusing on pituitary macroadenomas (n = 5), pituitary adenomas (n = 1), and meningiomas (n = 2) using a retrospective (n = 6), prospective (n = 1), and unknown (n = 1) study design with a total of 763 patients for the consistency prediction. The studies reported an area under the curve (AUC) of 0.71-0.99 for their respective best performing model regarding the consistency prediction. Of all studies, four articles validated their models internally whereas none validated their models externally. Two articles stated making data available on request with the remaining publications lacking information with regard to data availability.

CONCLUSIONS

The research on consistency prediction of CNS tumors is still at an early stage regarding the use of radiomics and different ML techniques. Best-practice procedures regarding radiomics and ML need to be followed more rigorously to facilitate the comparison between publications and, accordingly, the possible implementation into clinical practice in the future.

Imaging assessment of toxicity related to immune checkpoint inhibitors

In recent years, a wide range of cancer immunotherapies have been developed and have become increasingly important in cancer treatment across multiple oncologic diseases. In particular, immune checkpoint inhibitors (ICIs) offer promising options to improve patient outcomes. However, a major limitation of these treatments consists in the development of immune-related adverse events (irAEs) occurring in potentially any organ system and affecting up to 76% of the patients. The most frequent toxicities involve the skin, gastrointestinal tract, and endocrine system. Although mostly manageable, potentially life-threatening events, particularly due to neuro-, cardiac, and pulmonary toxicity, occur in up to 30% and 55% of the patients treated with ICI-monotherapy or -combination therapy, respectively. Imaging, in particular computed tomography (CT), magnetic resonance imaging (MRI), and 2-deoxy-2-[¹⁸F]fluoro-D-glucose positron emission tomography/computed tomography (¹⁸F-FDG-PET/CT), plays an important role in the detection and characterization of these irAEs. In some patients, irAEs can even be detected on imaging before the onset of clinical symptoms. In this context, it is particularly important to distinguish irAEs from true disease progression and specific immunotherapy related response patterns, such as pseudoprogression. In addition, there are irAEs which might be easily confused with other pathologies such as infection or metastasis. However, many imaging findings, such as in immune-related pneumonitis, are nonspecific. Thus, accurate diagnosis may be delayed underling the importance for adequate imaging features characterization in the appropriate clinical setting in order to provide timely and efficient patient management. ¹⁸F-FDG-PET/CT and radiomics have demonstrated to reliably detect these toxicities and potentially have predictive value for identifying patients at risk of developing irAEs. The purpose of this article is to provide a review of the main immunotherapy-related toxicities and discuss their characteristics on imaging.

Emerging and Evolving Concepts in Cancer Immunotherapy Imaging

Criteria based on measurements of lesion diameter at CT have guided treatment with historical therapies due to the strong association between tumor size and survival. Clinical experience with immune checkpoint modulators shows that editing immune system function can be effective in various solid tumors. Equally, novel immune-related phenomena accompany this novel therapeutic paradigm. These effects of immunotherapy challenge the association of tumor size with response or progression and include risks and adverse events that present new demands for imaging to guide treatment decisions. Emerging and evolving approaches to immunotherapy highlight further key issues for imaging evaluation, such as dissociated response following local administration of immune checkpoint modulators, pseudoprogression due to immune infiltration in the tumor environment, and premature death due to hyperprogression. Research that may offer tools for radiologists to meet these challenges is reviewed. Different modalities are discussed, including immuno-PET, as well as new applications of CT, MRI, and fluorodeoxyglucose PET, such as radiomics and imaging of hematopoietic tissues or anthropometric characteristics. Multilevel integration of imaging and other biomarkers may improve clinical guidance for immunotherapies and provide theranostic opportunities.

Artificial intelligence for prediction of response to cancer immunotherapy

Artificial intelligence (AI) indicates the application of machines to imitate intelligent behaviors for solving complex tasks with minimal human intervention, including machine learning and deep learning. The use of AI in medicine improves health-care systems in multiple areas such as diagnostic confirmation, risk stratification, analysis, prognosis prediction, treatment surveillance, and virtual health support, which has considerable potential to revolutionize and reshape medicine. In terms of immunotherapy, AI has been applied to unlock underlying immune signatures to associate with responses to immunotherapy indirectly as well as predict responses to immunotherapy responses directly. The AI-based analysis of high-throughput sequences and medical images can provide useful information for management of cancer immunotherapy considering the excellent abilities in selecting appropriate subjects, improving therapeutic regimens, and predicting individualized prognosis. In present review, we aim to evaluate a broad framework about AI-based computational approaches for prediction of response to cancer immunotherapy on both indirect and direct manners. Furthermore, we summarize our perspectives about challenges and opportunities of further AI applications on cancer immunotherapy relating to clinical practicability.

Endocrine-related adverse conditions in patients receiving immune checkpoint inhibition: an ESE clinical practice guideline

Immune checkpoint inhibitors (ICI) have revolutionized cancer treatment but are associated with significant autoimmune endocrinopathies that pose both diagnostic and treatment challenges. The aim of this guideline is to provide clinicians with the best possible evidence-based recommendations for treatment and follow-up of patients with ICI-induced endocrine side-effects based on the Grading of Recommendations Assessment, Development, and Evaluation system. As these drugs have been used for a relatively short time, large systematic investigations are scarce. A systematic approach to diagnosis, treatment, and follow-up is needed, including baseline tests of endocrine function before each treatment cycle. We conclude that there is no clear evidence for the benefit of high-dose glucocorticoids to treat endocrine toxicities with the possible exceptions of severe thyroid eye disease and hypophysitis affecting the visual apparatus. With the exception of thyroiditis, most endocrine dysfunctions appear to be permanent regardless of ICI discontinuation. Thus, the development of endocrinopathies does not dictate a need to stop ICI treatment.

Tumor response assessment on imaging following immunotherapy

In recent years, various systemic immunotherapies have been developed for cancer treatment, such as monoclonal antibodies (mABs) directed against immune checkpoints (immune checkpoint inhibitors, ICIs), oncolytic viruses, cytokines, cancer vaccines, and adoptive cell transfer. While being estimated to be eligible in 38.5% of patients with metastatic solid or hematological tumors, ICIs, in particular, demonstrate durable disease control across many oncologic diseases (e.g., in melanoma, lung, bladder, renal, head, and neck cancers) and overall survival benefits. Due to their unique mechanisms of action based on T-cell activation, response to immunotherapies is characterized by different patterns, such as progression prior to treatment response (pseudoprogression), hyperprogression, and dissociated responses following treatment. Because these features are not encountered in the Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST 1.1), which is the standard for response assessment in oncology, new criteria were defined for immunotherapies. The most important changes in these new morphologic criteria are, firstly, the requirement for confirmatory imaging examinations in case of progression, and secondly, the appearance of new lesions is not necessarily considered a progressive disease. Until today, five morphologic (immune-related response criteria (irRC), immune-related RECIST (irRECIST), immune RECIST (iRECIST), immune-modified RECIST (imRECIST), and intra-tumoral RECIST (itRECIST)) criteria have been developed to accurately assess changes in target lesion sizes, taking into account the specific response patterns after immunotherapy. In addition to morphologic response criteria, 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography/computed tomography (18F-FDG-PET/CT) is a promising option for metabolic response assessment and four metabolic criteria are used (PET/CT Criteria for Early Prediction of Response to Immune Checkpoint Inhibitor Therapy (PECRIT), PET Response Evaluation Criteria for Immunotherapy (PERCIMT), immunotherapy-modified PET Response Criteria in Solid Tumors (imPERCIST5), and immune PERCIST (iPERCIST)). Besides, there is evidence that parameters on 18F-FDG-PET/CT, such as the standardized uptake value (SUV)max and several radiotracers, e.g., directed against PD-L1, may be potential imaging biomarkers of response. Moreover, the emerge of human intratumoral immunotherapy (HIT-IT), characterized by the direct injection of immunostimulatory agents into a tumor lesion, has given new importance to imaging assessment. This article reviews the specific imaging patterns of tumor response and progression and available imaging response criteria following immunotherapy.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

BACKGROUND

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people's health. It is necessary to assess the current status on the application of AI towards the improvement of people's health in the domains defined by WHO's Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people's health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

METHODS

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO's PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

RESULTS

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

CONCLUSION

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

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.

Exploring a New Entity of Single-Agent Pembrolizumab-Associated Hypophysitis

Hypophysitis is the inflammation of the pituitary gland primary or secondary to local or systemic disease. It tends to occur more with cytotoxic T-lymphocyte-associated protein 4 inhibitors (10-15% of cases), which is a different entity compared to that associated with anti-program death 1 (anti-PD1) inhibitors. We describe a case of pembrolizumab-associated hypophysitis and conduct a systematic review of the literature. A 55-year-old woman with stage pT3aN1a (TNM stadium IIIb) melanoma presented with headache, nausea and fatigue three and a half months after starting pembrolizumab. Blood analyses revealed secondary adrenal failure, thyrotropic insufficiency and defective gonadotrophin secretion. An imaging study showed an enlarged pituitary gland with a homogeneous enhancement of the gland and pituitary stalk. Interruption of anti-PD1 therapy and administration of hormonal supplementation lead to clinical, biological and radiologic improvement after eight months. We identified 17 studies (20 patients) on single-agent pembrolizumab-associated hypophysitis. Patients were treated for melanoma (n=7; 33.3%), urogenital (n=5 ; 23.8%), lung (n=4 ; 19.0%), larynx (n=1 ; 4.8%), pharynx (n=1, 4.8%), breast (n=1, 4.8%) and colon (n=1, 4.8%) neoplasia. The time to onset of pituitary insufficiency was most frequently six months (range 1.5-39.0 months) after treatment initiation. The most prevalent hormonal defect was isolated adrenocorticotropic hormone (ACTH) deficiency. Four cases were reported with multiple central hormonal defects. In those patients, an enlarged pituitary gland was also observed. Our case has distinct features, including early disease onset after single-agent pembrolizumab initiation, panhypopituitarism and increased pituitary mass. These findings are in contrast with the majority of other cases of pembrolizumab-induced hypophysitis, as most patients present an isolated ACTH deficiency. Whether or not this is a new clinical entity warrants further investigation.

Machine Learning for the Detection and Segmentation of Benign Tumors of the Central Nervous System: A Systematic Review

Simple Summary

Machine learning in radiology of the central nervous system has seen many interesting publications in the past few years. Since the focus has largely been on malignant tumors such as brain metastases and high-grade gliomas, we conducted a systematic review on benign tumors to summarize what has been published and where there might be gaps in the research. We found several studies that report good results, but the descriptions of methodologies could be improved to enable better comparisons and assessment of biases.

Abstract

Objectives: To summarize the available literature on using machine learning (ML) for the detection and segmentation of benign tumors of the central nervous system (CNS) and to assess the adherence of published ML/diagnostic accuracy studies to best practice. Methods: The MEDLINE database was searched for the use of ML in patients with any benign tumor of the CNS, and the records were screened according to PRISMA guidelines. Results: Eleven retrospective studies focusing on meningioma (n = 4), vestibular schwannoma (n = 4), pituitary adenoma (n = 2) and spinal schwannoma (n = 1) were included. The majority of studies attempted segmentation. Links to repositories containing code were provided in two manuscripts, and no manuscripts shared imaging data. Only one study used an external test set, which raises the question as to whether some of the good performances that have been reported were caused by overfitting and may not generalize to data from other institutions. Conclusions: Using ML for detecting and segmenting benign brain tumors is still in its infancy. Stronger adherence to ML best practices could facilitate easier comparisons between studies and contribute to the development of models that are more likely to one day be used in clinical practice.

Machine Learning in Pituitary Surgery

Machine learning applications in neurosurgery are increasingly reported for diverse tasks such as faster and more accurate preoperative diagnosis, enhanced lesion characterization, as well as surgical outcome, complications and healthcare cost prediction. Even though the pertinent literature in pituitary surgery is less extensive with respect to other neurosurgical diseases, past research attempted to answer clinically relevant questions to better assist surgeons and clinicians. In the present chapter we review reported ML applications in pituitary surgery including differential diagnosis, preoperative lesion characterization (immunohistochemistry, cavernous sinus invasion, tumor consistency), surgical outcome and complication predictions (gross total resection, tumor recurrence, and endocrinological remission, cerebrospinal fluid leak, postoperative hyponatremia). Moreover, we briefly discuss from a practical standpoint the current barriers to clinical translation of machine learning research. On the topic of pituitary surgery, published reports can be considered mostly preliminary, requiring larger training populations and strong external validation. Thoughtful selection of clinically relevant outcomes of interest and transversal application of model development pipeline-together with accurate methodological planning and multicenter collaborations-have the potential to overcome current limitations and ultimately provide additional tools for more informed patient management.

A Study of the Recent Trends of Immunology: Key Challenges, Domains, Applications, Datasets, and Future Directions

The human immune system is very complex. Understanding it traditionally required specialized knowledge and expertise along with years of study. However, in recent times, the introduction of technologies such as AIoMT (Artificial Intelligence of Medical Things), genetic intelligence algorithms, smart immunological methodologies, etc., has made this process easier. These technologies can observe relations and patterns that humans do and recognize patterns that are unobservable by humans. Furthermore, these technologies have also enabled us to understand better the different types of cells in the immune system, their structures, their importance, and their impact on our immunity, particularly in the case of debilitating diseases such as cancer. The undertaken study explores the AI methodologies currently in the field of immunology. The initial part of this study explains the integration of AI in healthcare and how it has changed the face of the medical industry. It also details the current applications of AI in the different healthcare domains and the key challenges faced when trying to integrate AI with healthcare, along with the recent developments and contributions in this field by other researchers. The core part of this study is focused on exploring the most common classifications of health diseases, immunology, and its key subdomains. The later part of the study presents a statistical analysis of the contributions in AI in the different domains of immunology and an in-depth review of the machine learning and deep learning methodologies and algorithms that can and have been applied in the field of immunology. We have also analyzed a list of machine learning and deep learning datasets about the different subdomains of immunology. Finally, in the end, the presented study discusses the future research directions in the field of AI in immunology and provides some possible solutions for the same.

Applying artificial intelligence for cancer immunotherapy

Artificial intelligence (AI) is a general term that refers to the use of a machine to imitate intelligent behavior for performing complex tasks with minimal human intervention, such as machine learning; this technology is revolutionizing and reshaping medicine. AI has considerable potential to perfect health-care systems in areas such as diagnostics, risk analysis, health information administration, lifestyle supervision, and virtual health assistance. In terms of immunotherapy, AI has been applied to the prediction of immunotherapy responses based on immune signatures, medical imaging and histological analysis. These features could also be highly useful in the management of cancer immunotherapy given their ever-increasing performance in improving diagnostic accuracy, optimizing treatment planning, predicting outcomes of care and reducing human resource costs. In this review, we present the details of AI and the current progression and state of the art in employing AI for cancer immunotherapy. Furthermore, we discuss the challenges, opportunities and corresponding strategies in applying the technology for widespread clinical deployment. Finally, we summarize the impact of AI on cancer immunotherapy and provide our perspectives about underlying applications of AI in the future.

Current and Future Role of Medical Imaging in Guiding the Management of Patients With Relapsed and Refractory Non-Hodgkin Lymphoma Treated With CAR T-Cell Therapy

Chimeric antigen receptor (CAR) T-cells are a novel immunotherapy available for patients with refractory/relapsed non-Hodgkin lymphoma. In this indication, clinical trials have demonstrated that CAR T-cells achieve high rates of response, complete response, and long-term response (up to 80%, 60%, and 40%, respectively). Nonetheless, the majority of patients ultimately relapsed. This review provides an overview about the current and future role of medical imaging in guiding the management of non-Hodgkin lymphoma patients treated with CAR T-cells. It discusses the value of predictive and prognostic biomarkers to better stratify the risk of relapse, and provide a patient-tailored therapeutic strategy. At baseline, high tumor volume (assessed on CT-scan or on [18F]-FDG PET/CT) is a prognostic factor associated with treatment failure. Response assessment has not been studied extensively yet. Available data suggests that current response assessment developed on CT-scan or on [18F]-FDG PET/CT for cytotoxic systemic therapies remains relevant to estimate lymphoma response to CAR T-cell therapy. Nonetheless, atypical patterns of response and progression have been observed and should be further analyzed. The potential advantages as well as limitations of artificial intelligence and radiomics as tools providing high throughput quantitative imaging features is described.

The imaging of immunotherapy-related hypophysitis and other pituitary lesions in oncology patients

Immunotherapy has revolutionised the treatment of metastatic disease from a variety of different primaries, but is frequently associated with immune-related adverse events. This review illustrates the imaging features of immunotherapy-related hypophysitis (IH) and some of the important differential diagnoses in oncology patients. The key radiological characteristic of IH is diffuse, modest enlargement of the pituitary gland with temporal evolution attributable to immunotherapy. Pituitary enlargement is transient, and the gland size returns to baseline size or smaller within months. IH is usually associated with homogeneous enhancement of the pituitary gland, and the pituitary stalk may be thickened. Larger pituitary size, deviation of the pituitary stalk, the presence of a discrete lesion surrounding by normal pituitary tissue, sellar expansion, and clival invasion are not typical of IH and suggest alternate diagnoses. On integrated 2-[¹⁸F]-fluoro-2-deoxy-d-glucose positron-emission tomography (PET)/computed tomography (CT), a transient increase in the metabolic activity of the pituitary gland with subsequent decline to background activity is also suggestive of IH. We suggest that the sella is assessed routinely on imaging performed in the first 6 months after commencing immunotherapy to detect subtle changes. Radiologists should also be aware of features that either support a diagnosis of IH or suggest alternate diagnoses.

Assessing immune organs on 18F-FDG PET/CT imaging for therapy monitoring of immune checkpoint inhibitors: inter-observer variability, prognostic value and evolution during the treatment course of melanoma patients

BACKGROUND

Immune checkpoint inhibitors (ICIs) have significantly improved survival in advanced melanoma. There is a need for robust biomarkers to identify patients who do not respond. We analysed 14 baseline ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) metrics and their evolution to assess their correlation with patient outcome, compared with 7 established biological markers and 7 clinical variables.

METHODS

We conducted a retrospective monocentric observational study of 29 patients with advanced melanoma who underwent baseline ¹⁸F-FDG PET/CT, followed by an early monitoring PET/CT (iPET) scan after 1 month of treatment and follow-up studies at 3rd (M3PET) and 6th month (M6PET). ¹⁸F-FDG uptake in immune organs (spleen, bone marrow, ileocecal valve) and derived spleen-to-liver (SLR) and bone-to-liver (BLR) ratios were reviewed by two PET readers for reproducibility analysis purposes including 14 PET variables. The most reproducible indexes were used for evaluation as predictors of overall survival (OS) in comparison with PET response using imPERCIST5, whole-body metabolic active tumour volume (WB-MATV) and biological parameters (lactate dehydrogenases (LDH), reactive protein c (CRP), white blood count (WBC), absolute lymphocyte count (ALC), neutrophil to lymphocyte ratio (NLR) and derived neutrophils to lymphocyte ratio).

RESULTS

Strong reproducibility's (intraclass coefficients of correlation (ICC) > 0.90) were observed for spleen anterior SUV_peak, spleen MV, spleen TLG, spleen length and BLR_mean. ICC for SLR_mean and ileocecal SUV_mean were 0.86 and 0.65, respectively. In the 1-year OS 1 group, SLR_mean tended to increase at each time point to reach a significant difference at M6-PET (p = 0.019). The same trends were observed with spleen SUV_peak anterior and spleen length. In the 1-year OS 0 group, a significative increase of spleen length was found at iPET, as compared with baseline PET (p = 0.014) and M3-PET (p = 0.0239). Univariable Kaplan-Meier survival analysis found that i%var spleen length, M3%var SLR_mean, baseline LDH, i%var NLR and response at M6PET were all predictors of 1-year OS.

CONCLUSIONS

SLR_mean is recommended as a prognosticator in melanoma patients under immunotherapy: its increase greater than 25% at 3 months, compared with baseline, was associated with poor outcome after ICIs.

Pituitary Tumors in the Computational Era, Exploring Novel Approaches to Diagnosis, and Outcome Prediction with Machine Learning

BACKGROUND

Machine learning has emerged as a viable asset in the setting of pituitary surgery. In the past decade, the number of machine learning models developed to aid in the diagnosis of pituitary lesions and predict intraoperative and postoperative complications following transsphenoidal surgery has increased exponentially. As computational processing power continues to increase, big data sets continue to expand, and learning algorithms continue to surpass gold standard predictive tools, machine learning will serve to become an important component in improving patient care and outcomes.

METHODS

Relevant studies were identified based on a literature search in PubMed and MEDLINE databases, as well as from other sources including reference lists of published articles.

RESULTS

Radiomics and artificial neural networks comprise the majority of machine learning-based applications in pituitary surgery. Radiomics serves to quantify specific imaging features, which can then be used to noninvasively identify tumor characteristics and make definitive diagnoses, circumventing presurgical biopsy altogether. Neural networks can be adapted to predict intraoperative changes in visual evoked potentials or cerebral spinal fluid leak. In addition, these algorithms may be combined with others to predict tumor aggressiveness, gross total resection, recurrence and remission, and even total cost burden.

CONCLUSIONS

The field of machine learning is broad, with radiomics and artificial neural networks comprising 2 commonly used supervised learning methods in pituitary surgery. Given the large heterogeneity of pituitary and sellar lesions, the promise of machine learning lies in its ability to identify relationships and patterns that are otherwise hidden from standard statistical methods. While machine learning has great potential as a clinical adjunct during the surgical preplanning process and in predicting complications and outcomes, challenges moving forward include standardization and validation of these paradigms.

Immune-related adverse events of checkpoint inhibitors

Cancer immunotherapies have changed the landscape of cancer treatment during the past few decades. Among them, immune checkpoint inhibitors, which target PD-1, PD-L1 and CTLA-4, are increasingly used for certain cancers; however, this increased use has resulted in increased reports of immune-related adverse events (irAEs). These irAEs are unique and are different to those of traditional cancer therapies, and typically have a delayed onset and prolonged duration. IrAEs can involve any organ or system. These effects are frequently low grade and are treatable and reversible; however, some adverse effects can be severe and lead to permanent disorders. Management is primarily based on corticosteroids and other immunomodulatory agents, which should be prescribed carefully to reduce the potential of short-term and long-term complications. Thoughtful management of irAEs is important in optimizing quality of life and long-term outcomes.

Hypophysitis induced by immune checkpoint inhibitors: a 10-year assessment

Introduction: Hypophysitis caused by immune checkpoint inhibitors (ICIs) has risen to the medical attention during the past decade. ICIs are monoclonal antibodies that block the interaction between molecules that normally inhibit the function of effector T cells, ultimately increasing their ability to destroy cancer cells but also causing immune-related adverse events, such as hypophysitis. Ipilimumab, a CTLA-4 blocker, was the first ICI approved from the Food and Drug Administration for advanced melanoma patients in 2011. Several additional ICIs targeting CTLA-4, PD-1, or PD-L1 are now used in many clinical trials, making it important for physicians to recognize and treat hypophysitis adequately.Areas covered: This review will provide insights into the mechanisms of pituitary toxicity, highlight the complexity of clinical phenotypes of ICI hypophysitis, and offer practical recommendations.Expert opinion: ICI hypophysitis differs in many respects from primary hypophysitis, and also according to the type of ICI that caused it. Its pathogenesis remains unknown, although the expression of CTLA-4 and PD-1 on pituitary cells could play a role. The diagnosis is mainly clinical since there are no specific serological markers and MRI findings are subtle. The treatment is based on long-term hormone replacement and does not typically require discontinuation of immunotherapy.