Toxoplasmosis versus lymphoma: Cerebral lesion characterization using DSC-MRI revisited

FDA-approved machine learning algorithms in neuroradiology: A systematic review of the current evidence for approval

Over the past decade, machine learning (ML) and artificial intelligence (AI) have become increasingly prevalent in the medical field. In the United States, the Food and Drug Administration (FDA) is responsible for regulating AI algorithms as "medical devices" to ensure patient safety. However, recent work has shown that the FDA approval process may be deficient. In this study, we evaluate the evidence supporting FDA-approved neuroalgorithms, the subset of machine learning algorithms with applications in the central nervous system (CNS), through a systematic review of the primary literature. Articles covering the 53 FDA-approved algorithms with applications in the CNS published in PubMed, EMBASE, Google Scholar and Scopus between database inception and January 25, 2022 were queried. Initial searches identified 1505 studies, of which 92 articles met the criteria for extraction and inclusion. Studies were identified for 26 of the 53 neuroalgorithms, of which 10 algorithms had only a single peer-reviewed publication. Performance metrics were available for 15 algorithms, external validation studies were available for 24 algorithms, and studies exploring the use of algorithms in clinical practice were available for 7 algorithms. Papers studying the clinical utility of these algorithms focused on three domains: workflow efficiency, cost savings, and clinical outcomes. Our analysis suggests that there is a meaningful gap between the FDA approval of machine learning algorithms and their clinical utilization. There appears to be room for process improvement by implementation of the following recommendations: the provision of compelling evidence that algorithms perform as intended, mandating minimum sample sizes, reporting of a predefined set of performance metrics for all algorithms and clinical application of algorithms prior to widespread use. This work will serve as a baseline for future research into the ideal regulatory framework for AI applications worldwide.

Role of Positron Emission Tomography in Primary Central Nervous System Lymphoma

Simple Summary

Primary central nervous system lymphoma (PCNSL) is a rare but highly aggressive lymphoma with increasing incidence in immunocompetent patients. To date, the only established biomarkers for survival are age and functional status. Currently, the magnetic resonance imaging (MRI) criteria of the International Collaborative Group on Primary Central Nervous System Lymphoma are the only ones recommended for follow-up. However, early occurrence of recurrence after treatment in patients with a complete response on MRI raises the question of its performance in assessing residual disease. While the use of ¹⁸F-fluorodeoxyglucose body positron emission tomography for identification of systemic disease has been established and can be pivotal in patient treatment decisions, the role of brain PET scan is less clear. Here we review the potential role of PET in the management of patients with PCNSL, both at diagnosis and for follow-up under treatment.

Abstract

The incidence of primary central nervous system lymphoma has increased over the past two decades in immunocompetent patients and the prognosis remains poor. A diagnosis and complete evaluation of the patient is needed without delay, but histologic evaluation is not always available and PCNSL can mimic a variety of brain lesions on MRI. In this article, we review the potential role of ¹⁸F-FDG PET for the diagnosis of PCNSL in immunocompetent and immunocompromised patients. Its contribution to systemic assessment at the time of diagnosis has been well established by expert societies over the past decade. In addition, ¹⁸F-FDG provides valuable information for differential diagnosis and outcome prediction. The literature also shows the potential role of ¹⁸F-FDG as a therapeutic evaluation tool during the treatment and the end of the treatment. Finally, we present several new radiotracers that may have a potential role in the management of PCNSL in the future.

The landscape of brain tumor mimics in neuro-oncology practice

BACKGROUND AND OBJECTIVE

Differentiating neoplastic and non-neoplastic brain lesions is essential to make management recommendations and convey prognosis, but the distinction between brain tumors and their mimics in practice may prove challenging. The aim of this study is to provide the incidence of brain tumor mimics in the neuro-oncology setting and describe this patient subset.

METHODS

Retrospective study of adult patients referred to the Division of Neuro-oncology for a presumed diagnosis of brain tumor from January 1, 2005 through December 31, 2017, who later satisfied the diagnosis of a non-neoplastic entity based on neuroimaging, clinical course, and/or histopathology evaluation. We classified tumor mimic entities according to clinical, radiologic, and laboratory characteristics that correlated with the diagnosis.

RESULTS

The incidence of brain tumor mimics was 3.4% (132/3897). The etiologies of the non-neoplastic entities were vascular (35%), inflammatory non-demyelinating (26%), demyelinating (15%), cysts (10%), infectious (9%), and miscellaneous (5%). In our study, 38% of patients underwent biopsy to determine diagnosis, but in 26%, the biopsy was inconclusive.

DISCUSSION

Brain tumor mimics represent a small but important subset of the neuro-oncology referrals. Vascular, inflammatory, and demyelinating etiologies represent two-thirds of cases. Recognizing the clinical, radiologic and laboratory characteristics of such entities may improve resource utilization and prevent unnecessary as well as potentially harmful diagnostic and therapeutic interventions.

Differentiation of Acquired Immune Deficiency Syndrome Related Primary Central Nervous System Lymphoma from Cerebral toxoplasmosis with Use of Susceptibility-Weighted Imaging and Contrast Enhanced 3D-T1WI

BACKGROUND

We aimed to investigate whether susceptibility-weighted imaging (SWI) and contrast-enhanced 3D-T1WI can differentiate Acquired Immune Deficiency Syndrome-Related Primary Central Nervous System Lymphoma (AR-PCNSL) from cerebral toxoplasmosis.

METHODS

This was a prospective cohort study. 20 AIDS patients were divided into AR-PCNSL group (13 cases) and cerebral toxoplasmosis group (7 cases) based on pathology results. We analyzed the appearance of lesions on SWI and enhanced 3D T1WI and ROC curves in the diagnosis of AR-PCNSL and cerebral toxoplasmosis.

RESULTS

Cerebral toxoplasmosis was more likely to show annular enhancement (p = 0.002) and complete smooth ring enhancement (p = 0.002). It was also more likely to present a complete, smooth low signal intensity rim (LSIR) (p = 0.002) and an incomplete, smooth LSIR (p = 0.019) on SWI. AR-PCNSL was more likely to present an incomplete, irregular LSIR (p < 0.001) and irregular central low signal intensity (CLSI) (p<0.001) on SWI. The areas under the ROC curve of the SWI-ILSS grade and enhanced volume on 3D-T1WI were 0.872 and 0.862, respectively.

CONCLUSION

A higher SWI-ILSS grade and larger 3D-T1WI volume enhancement were diagnostic for AR-PCNSL. SWI and CE 3D-T1WI were useful in the differential diagnosis of AR-PCNSL and cerebral toxoplasmosis.

MRI imaging features of HIV-related central nervous system diseases: diagnosis by pattern recognition in daily practice

With the advent of antiretroviral therapy (ART), the prognosis of people infected with human immunodeficiency virus (HIV) has improved, and the frequency of HIV-related central nervous system (CNS) diseases has decreased. Nevertheless, mortality from HIV-related CNS diseases, including those associated with ART (e.g., immune reconstitution inflammatory syndrome) remains significant. Magnetic resonance imaging (MRI) can improve the outlook for people with HIV through early diagnosis and prompt treatment. For example, HIV encephalopathy shows a diffuse bilateral pattern, whereas progressive multifocal leukoencephalopathy, HIV-related primary CNS lymphoma, and CNS toxoplasmosis show focal patterns on MRI. Among the other diseases caused by opportunistic infections, CNS cryptococcosis and CNS tuberculosis have extremely poor prognoses unless diagnosed early. Immune reconstitution inflammatory syndrome shows distinct MRI findings from the offending opportunistic infections. Although distinguishing between HIV-related CNS diseases based on imaging alone is difficult, in this review, we discuss how pattern recognition approaches can contribute to their early differentiation.

Imaging Mimics of Brain Tumors

Nonneoplastic entities may closely resemble the imaging findings of primary or metastatic intracranial neoplasia, posing diagnostic challenges for the referring provider and radiologist. Prospective identification of brain tumor mimics is an opportunity for the radiologist to add value to patient care by decreasing time to diagnosis and avoiding unnecessary surgical procedures and medical therapies, but requires familiarity with mimic entities and a high degree of suspicion on the part of the interpreting radiologist. This article provides a framework for the radiologist to identify "brain tumor mimics," highlighting imaging and laboratory pearls and pitfalls, and illustrating unique and frequently encountered lesions.

A comparative study of multimodal magnetic resonance in the differential diagnosis of acquired immune deficiency syndrome related primary central nervous system lymphoma and infection

Background

Patients with acquired immune deficiency syndrome (AIDS) often suffer from opportunistic infections and related primary central nervous system lymphoma (AR-PCNSL). Both diseases showed multiple ring enhancement lesions in conventional magnetic resonance (MR). It is very difficult to make the differential diagnosis. We aimed to investigate whether multimodal MR (diffusion weighted imaging (DWI)/ apparent diffusion coefficient (ADC), 3D pseudo-continuous arterial spin labeling (3D-pCASL) and susceptibility-weighted imaging (SWI)) combined with conventional MR can differentiate AR-PCNSL from infections.

Methods

This was a prospective study. We recruited 19 AIDS patients who were divided into AR-PCNSL group (9 cases) and infection group (10 cases) by pathological results. We analyzed whether there was statistical (Fisher’s method) difference in multimodal MR between the two groups. We analyzed whether multimodal MR combined with conventional MR could improve the diagnosis of AR-PCNSL.

Results

The lesions were more likely involved the paraventricular (0.020) and corpus callosum (0.033) in AR-PCNSL group in conventional MR. In multimodal MR, AR-PCNSL group showed low ADC value, with p values of 0.001. Infection group more inclined to high ADC value, with p was 0.003. In multimodal MR, AR-PCNSL group had more low signal intensity (grade 2–3) in the degree of intratumoral susceptibility signal intensity in SWI (SWI-ITSS), with p values of 0.001. The sensitivity, specificity of conventional MR in the diagnosis of AR-PCNSL was 88.9 and 70.0%. The conventional MR sequence combined with DWI/ADC sequence in the diagnosis of AR-PCNSL had a sensitivity of 100.0%, and a specificity of 60.0%. The sensitivity and specificity of the conventional MR sequence combined with the SWI-ITSS sequence in the diagnosis of AR-PCNSL were 100 and 70.0%. The conventional MR combined with ADC or SWI-ITSS improved the diagnosis of AR-PCNSL.

Conclusion

Multimodal MR could distinguish AR-PCNSL from infectious lesions. The multimodal MR (DWI/ADC or SWI-ITSS) combined with conventional MR could improve the diagnosis of AR-PCNSL. The ADC value should be attached importance in clinical work. When distinguishing AR-PCNSL from toxoplasmosis or tuberculoma, SWI should be used to obtain a correct diagnosis.

Imaging in Differentiating Cerebral Toxoplasmosis and Primary CNS Lymphoma With Special Focus on FDG PET/CT

OBJECTIVE. The purpose of this article is to present a brief review of literature evaluating different imaging modalities with special focus on ¹⁸F-FDG PET/CT in differentiating cerebral toxoplasmosis and primary CNS lymphoma. CONCLUSION. Differentiating cerebral toxoplasmosis and primary CNS lymphoma is crucial in the care of patients with HIV infection. Delayed diagnosis can lead to considerable morbidity and mortality. The reference standard for diagnosis is biopsy and histopathologic examination. Biopsy has disadvantages due to its invasive nature and associated complications. Noninvasive imaging can be an alternative to biopsy for differentiation of toxoplasmosis and primary CNS lymphoma. Despite advances in MRI techniques, prophylaxis of opportunistic infection, and treatment of HIV infection, clinical situations continue to arise in which the diagnosis is not clear. In these instances, molecular imaging can be helpful.

The value of whole lesion ADC histogram profiling to differentiate between morphologically indistinguishable ring enhancing lesions-comparison of glioblastomas and brain abscesses

Background

Morphologically similar appearing ring enhancing lesions in the brain parenchyma can be caused by a number of distinct pathologies, however, they consistently represent life-threatening conditions. The two most frequently encountered diseases manifesting as such are glioblastoma multiforme (GBM) and brain abscess (BA), each requiring disparate therapeutical approaches. As a result of their morphological resemblance, essential treatment might be significantly delayed or even ommited, in case results of conventional imaging remain inconclusive. Therefore, our study aimed to investigate, whether ADC histogram profiling reliably can distinguish between both entities, thus enhancing the differential diagnostic process and preventing treatment failure in this highly critical context.

Methods

103 patients (51 BA, 52 GBM) with histopathologically confirmed diagnosis were enrolled. Pretreatment diffusion weighted imaging (DWI) was obtained in a 1.5T system using b values of 0, 500, and 1000 s/mm². Whole lesion ADC volumes were analyzed using a histogram-based approach. Statistical analysis was performed using SPSS version 23.

Results

All investigated parameters were statistically different in comparison of both groups. Most importantly, ADCp10 was able to differentiate reliably between BA and GBM with excellent accuracy (0.948) using a cutpoint value of 70 × 10⁻⁵ mm² × s⁻¹.

Conclusions

ADC whole lesion histogram profiling provides a valuable tool to differentiate between morphologically indistinguishable mass lesions. Among the investigated parameters, the 10th percentile of the ADC volume distinguished best between GBM and BA.