Natural language processing deep learning models for the differential between high-grade gliomas and metastasis: what if the key is how we report them?

OBJECTIVES: The differential between high-grade glioma (HGG) and metastasis remains challenging in common radiological practice. We compare different natural language processing (NLP)-based deep learning models to assist radiologists based on data contained in radiology reports. METHODS: This retrospective study included 185 MRI reports between 2010 and 2022 from two different institutions. A total of 117 reports were used for the training and 21 were reserved for the validation set, while the rest were used as a test set. A comparison of the performance of different deep learning models for HGG and metastasis classification has been carried out. Specifically, Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), a hybrid version of BiLSTM and CNN, and a radiology-specific Bidirectional Encoder Representations from Transformers (RadBERT) model were used. RESULTS: For the classification of MRI reports, the CNN network provided the best results among all tested, showing a macro-avg precision of 87.32%, a sensitivity of 87.45%, and an F1 score of 87.23%. In addition, our NLP algorithm detected keywords such as tumor, temporal, and lobe to positively classify a radiological report as HGG or metastasis group. CONCLUSIONS: A deep learning model based on CNN enables radiologists to discriminate between HGG and metastasis based on MRI reports with high-precision values. This approach should be considered an additional tool in diagnosing these central nervous system lesions. CLINICAL RELEVANCE STATEMENT: The use of our NLP model enables radiologists to differentiate between patients with high-grade glioma and metastasis based on their MRI reports and can be used as an additional tool to the conventional image-based approach for this challenging task. KEY POINTS: • Differential between high-grade glioma and metastasis is still challenging in common radiological practice. • Natural language processing (NLP)-based deep learning models can assist radiologists based on data contained in radiology reports. • We have developed and tested a natural language processing model for discriminating between high-grade glioma and metastasis based on MRI reports that show high precision for this task.

An update on susceptibility-weighted imaging in brain gliomas.

Susceptibility-weighted imaging (SWI) has become a standard component of most brain MRI protocols. While traditionally used for detecting and characterising brain hemorrhages typically associated with stroke or trauma, SWI has also shown promising results in glioma assessment. Numerous studies have highlighted SWI's role in differentiating gliomas from other brain lesions, such as primary central nervous system lymphomas or metastases. Additionally, SWI aids radiologists in non-invasively grading gliomas and predicting their phenotypic profiles. Various researchers have suggested incorporating SWI as an adjunct sequence for predicting treatment response and for post-treatment monitoring. A significant focus of these studies is on the detection of intratumoural susceptibility signals (ITSSs) in gliomas, which are indicative of microhemorrhages and vessels within the tumour. The quantity, distribution, and characteristics of these ITSSs can provide radiologists with more precise information for evaluating and characterising gliomas. Furthermore, the potential benefits and added value of performing SWI after the administration of gadolinium-based contrast agents (GBCAs) have been explored. This review offers a comprehensive, educational, and practical overview of the potential applications and future directions of SWI in the context of glioma assessment. CLINICAL RELEVANCE STATEMENT: SWI has proven effective in evaluating gliomas, especially through assessing intratumoural susceptibility signal changes, and is becoming a promising, easily integrated tool in MRI protocols for both pre- and post-treatment assessments. KEY POINTS: • Susceptibility-weighted imaging is the most sensitive sequence for detecting blood and calcium inside brain lesions. • This sequence, acquired with and without gadolinium, helps with glioma diagnosis, characterisation, and grading through the detection of intratumoural susceptibility signals. • There are ongoing challenges that must be faced to clarify the role of susceptibility-weighted imaging for glioma assessment.

Understanding Visual Disorders through Correlation of Clinical and Radiologic Findings.

Patients presenting with visual disturbances often require a neuroimaging approach. The spectrum of visual disturbances includes three main categories: vision impairment, ocular motility dysfunction, and abnormal pupillary response. Decreased vision is usually due to an eye abnormality. However, it can also be related to other disorders affecting the visual pathway, from the retina to the occipital lobe. Ocular motility dysfunction may follow disorders of the cranial nerves responsible for eye movements (ie, oculomotor, trochlear, and abducens nerves); may be due to any abnormality that directly affects the extraocular muscles, such as tumor or inflammation; or may result from any orbital disease that can alter the anatomy or function of these muscles, leading to diplopia and strabismus. Given that pupillary response depends on the normal function of the sympathetic and parasympathetic pathways, an abnormality affecting these neuronal systems manifests, respectively, as pupillary miosis or mydriasis, with other related symptoms. In some cases, neuroimaging studies must complement the clinical ophthalmologic examination to better assess the anatomic and pathologic conditions that could explain the symptoms. US has a major role in the assessment of diseases of the eye and anterior orbit. CT is usually the first-line imaging modality because of its attainability, especially in trauma settings. MRI offers further information for inflammatory and tumoral cases. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

Automatic generation of conclusions from neuroradiology MRI reports through natural language processing.

PURPOSE: The conclusion section of a radiology report is crucial for summarizing the primary radiological findings in natural language and essential for communicating results to clinicians. However, creating these summaries is time-consuming, repetitive, and prone to variability and errors among different radiologists. To address these issues, we evaluated a fine-tuned Text-To-Text Transfer Transformer (T5) model for abstractive summarization to automatically generate conclusions for neuroradiology MRI reports in a low-resource language. METHODS: We retrospectively applied our method to a dataset of 232,425 neuroradiology MRI reports in Spanish. We compared various pre-trained T5 models, including multilingual T5 and those newly adapted for Spanish. For precise evaluation, we employed BLEU, METEOR, ROUGE-L, CIDEr, and cosine similarity metrics alongside expert radiologist assessments. RESULTS: The findings are promising, with the models specifically fine-tuned for neuroradiology MRI achieving scores of 0.46, 0.28, 0.52, 2.45, and 0.87 in the BLEU-1, METEOR, ROUGE-L, CIDEr, and cosine similarity metrics, respectively. In the radiological experts' evaluation, they found that in 75% of the cases evaluated, the conclusions generated by the system were as good as or even better than the manually generated conclusions. CONCLUSION: The methods demonstrate the potential and effectiveness of customizing state-of-the-art pre-trained models for neuroradiology, yielding automatic MRI report conclusions that nearly match expert quality. Furthermore, these results underscore the importance of designing and pre-training a dedicated language model for radiology report summarization.

Natural Language Processing in Pathology: Current Trends and Future Insights.

Natural language processing (NLP) plays a key role in advancing health care, being key to extracting structured information from electronic health reports. In the last decade, several advances in the field of pathology have been derived from the application of NLP to pathology reports. Herein, a comprehensive review of the most used NLP methods for extracting, coding, and organizing information from pathology reports is presented, including how the development of tools is used to improve workflow. In addition, this article discusses, from a practical point of view, the steps necessary to extract data and encode natural language information for its analytical processing, ranging from preprocessing of text to its inclusion in complex algorithms. Finally, the potential of NLP-based automatic solutions for improving workflow in pathology and their further applications in the near future is highlighted.

Past, present, and future in sports imaging: how to drive in a three-lane freeway.

KEY POINTS: • Morphological evaluation of SRIs is still nowadays the clinical standard in daily practice.• New functional imaging modalities show potential to add valuable physiopathological information about the insights of SRIs in specific clinical scenarios.• In the era of personalized medicine, AI algorithms may help athletes and all professionals involved in their care to improve the evaluation of SRIs through a definitive quantitative metric approach.

MR dynamic-susceptibility-contrast perfusion metrics in the presurgical discrimination of adult solitary intra-axial cerebellar tumors.

OBJECTIVES: Adult solitary intra-axial cerebellar tumors are uncommon. Their presurgical differentiation based on neuroimaging is crucial, since management differs substantially. Comprehensive full assessment of MR dynamic-susceptibility-contrast perfusion-weighted imaging (DSC-PWI) may reveal key differences between entities. This study aims to provide new insights on perfusion patterns of these tumors and to explore the potential of DSC-PWI in their presurgical discrimination. METHODS: Adult patients with a solitary cerebellar tumor on presurgical MR and confirmed histological diagnosis of metastasis, medulloblastoma, hemangioblastoma, or pilocytic astrocytoma were retrospectively retrieved (2008-2023). Volumetric segmentation of tumors and normal-appearing white matter (for normalization) was semi-automatically performed on CE-T1WI and coregistered with DSC-PWI. Mean normalized values per patient tumor-mask of relative cerebral blood volume (rCBV), percentage of signal recovery (PSR), peak height (PH), and normalized time-intensity curves (nTIC) were extracted. Statistical comparisons were done. Then, the dataset was split into training (75%) and test (25%) cohorts and a classifier was created considering nTIC, rCBV, PSR, and PH in the model. RESULTS: Sixty-eight patients (31 metastases, 13 medulloblastomas, 13 hemangioblastomas, and 11 pilocytic astrocytomas) were included. Relevant differences between tumor types' nTICs were demonstrated. Hemangioblastoma showed the highest rCBV and PH, pilocytic astrocytoma the highest PSR. All parameters showed significant differences on the Kruskal-Wallis tests (p < 0.001). The classifier yielded an accuracy of 98% (47/48) in the training and 85% (17/20) in the test sets. CONCLUSIONS: Intra-axial cerebellar tumors in adults have singular and significantly different DSC-PWI signatures. The combination of perfusion metrics through data-analysis rendered excellent accuracies in discriminating these entities. CLINICAL RELEVANCE STATEMENT: In this study, the authors constructed a classifier for the non-invasive imaging presurgical diagnosis of adult intra-axial cerebellar tumors. The resultant tool can be a support for decision-making in the clinical practice and enables optimal personalized patient management. KEY POINTS: • Adult intra-axial cerebellar tumors exhibit specific, singular, and statistically significant different MR dynamic-susceptibility-contrast perfusion-weighted imaging (DSC-PWI) signatures. • Data-analysis, applied to MR DSC-PWI, could provide added value in the presurgical diagnosis of solitary cerebellar metastasis, medulloblastoma, hemangioblastoma, and pilocytic astrocytoma. • A classifier based on DSC-PWI metrics yields excellent accuracy rates and could be used as a support tool for radiologic diagnosis with clinician-friendly displays.

Clinical applications of skeletal muscle diffusion tensor imaging.

Diffusion tensor imaging (DTI) may allow the determination of new threshold values, based on water anisotropy, to differentiate between healthy muscle and various pathological processes. Additionally, it may quantify treatment monitoring or training effects. Most current studies have evaluated the potential of DTI of skeletal muscle to assess sports-related injuries or therapy, and training monitoring. Another critical area of application of this technique is the characterization and monitoring of primary and secondary myopathies. In this manuscript, we review the application of DTI in the evaluation of skeletal muscle in these and other novel clinical scenarios, with emphasis on the use of quantitative imaging-derived biomarkers. Finally, the main limitations of the introduction of DTI in the clinical setting and potential areas of future use are discussed.

How to do and evaluate DWI and DCE-MRI sequences for diabetic foot assessment.

MRI evaluation of the diabetic foot is still a challenge not only from an interpretative but also from a technical point of view. The incorporation of advanced sequences such as diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI into standard protocols for diabetic foot assessment could aid radiologists in differentiating between neuropathic osteoarthropathy (Charcot's foot) and osteomyelitis. This distinction is crucial as both conditions can coexist in diabetic patients, and they require markedly different clinical management and have distinct prognoses. Over the past decade, several studies have explored the effectiveness of DWI and dynamic contrast-enhanced MRI (DCE-MRI) in distinguishing between septic and reactive bone marrow, as well as soft tissue involvement in diabetic patients, yielding promising results. DWI, without the need for exogenous contrast, can provide insights into the cellularity of bone marrow and soft tissues. DCE-MRI allows for a more precise evaluation of soft tissue and bone marrow perfusion compared to conventional post-gadolinium imaging. The data obtained from these sequences will complement the traditional MRI approach in assessing the diabetic foot. The objective of this review is to familiarize readers with the fundamental concepts of DWI and DCE-MRI, including technical adjustments and practical tips for image interpretation in diabetic foot cases.

A handbook for beginners in skeletal muscle diffusion tensor imaging: physical basis and technical adjustments.

Magnetic resonance imaging (MRI) of skeletal muscle is routinely performed using morphological sequences to acquire anatomical information. Recently, there is an increasing interest in applying advanced MRI techniques that provide pathophysiologic information for skeletal muscle evaluation to complement standard morphologic information. Among these advanced techniques, diffusion tensor imaging (DTI) has emerged as a potential tool to explore muscle microstructure. DTI can noninvasively assess the movement of water molecules in well-organized tissues with anisotropic diffusion, such as skeletal muscle. The acquisition of DTI studies for skeletal muscle assessment requires specific technical adjustments. Besides, knowledge of DTI physical basis and skeletal muscle physiopathology facilitates the evaluation of this advanced sequence and both image and parameter interpretation. Parameters derived from DTI provide a quantitative assessment of muscle microstructure with potential to become imaging biomarkers of normal and pathological skeletal muscle. KEY POINTS: • Diffusion tensor imaging (DTI) allows to evaluate the three-dimensional movement of water molecules inside biological tissues. • The skeletal muscle structure makes it suitable for being evaluated with DTI. • Several technical adjustments have to be considered for obtaining robust and reproducible DTI studies for skeletal muscle assessment, minimizing potential artifacts.

New insights into the evaluation of peripheral nerves lesions: a survival guide for beginners.

PURPOSE: To perform a review of the physical basis of DTI and DCE-MRI applied to Peripheral Nerves (PNs) evaluation with the aim of providing readers the main concepts and tools to acquire these types of sequences for PNs assessment. The potential added value of these advanced techniques for pre-and post-surgical PN assessment is also reviewed in diverse clinical scenarios. Finally, a brief introduction to the promising applications of Artificial Intelligence (AI) for PNs evaluation is presented. METHODS: We review the existing literature and analyze the latest evidence regarding DTI, DCE-MRI and AI for PNs assessment. This review is focused on a practical approach to these advanced sequences providing tips and tricks for implementing them into real clinical practice focused on imaging postprocessing and their current clinical applicability. A summary of the potential applications of AI algorithms for PNs assessment is also included. RESULTS: DTI, successfully used in central nervous system, can also be applied for PNs assessment. DCE-MRI can help evaluate PN's vascularization and integrity of Blood Nerve Barrier beyond the conventional gadolinium-enhanced MRI sequences approach. Both approaches have been tested for PN assessment including pre- and post-surgical evaluation of PNs and tumoral conditions. AI algorithms may help radiologists for PN detection, segmentation and characterization with promising initial results. CONCLUSION: DTI, DCE-MRI are feasible tools for the assessment of PN lesions. This manuscript emphasizes the technical adjustments necessary to acquire and post-process these images. AI algorithms can also be considered as an alternative and promising choice for PN evaluation with promising results.

Technical Update on MR Neurography.

Imaging evaluation of peripheral nerves (PNs) is challenging. Magnetic resonance imaging (MRI) and ultrasonography are the modalities of choice in the imaging assessment of PNs. Both conventional MRI pulse sequences and advanced techniques have important roles. Routine MR sequences are the workhorse, with the main goal to provide superb anatomical definition and identify focal or diffuse nerve T2 signal abnormalities. Selective techniques, such as three-dimensional (3D) cranial nerve imaging (CRANI) or 3D NerveVIEW, allow for a more detailed evaluation of normal and pathologic states. These conventional pulse sequences have a limited role in the comprehensive assessment of pathophysiologic and ultrastructural abnormalities of PNs. Advanced functional MR neurography sequences, such as diffusion tensor imaging tractography or T2 mapping, provide useful and robust quantitative parameters that can be useful in the assessment of PNs on a microscopic level. This article offers an overview of various technical parameters, pulse sequences, and protocols available in the imaging of PNs and provides tips on avoiding potential pitfalls.

Teleworking beyond teleradiology: managing radiology departments during the COVID-19 outbreak.

Teleradiology solutions are playing an essential role during the COVID-19 outbreak. Activity at radiology departments must be maintained and adapted to this new situation beyond teleradiology. Teleworking should be extended to the rest of non-medical radiology department areas. A comprehensive perspective based on our own experience during the COVID-19 outbreak has been performed highlighting the value of teleworking for almost all areas implied in the workflow of radiology departments beyond radiologists. Personal and technical requirements for successfully adapting to this new scenario are discussed including the opportunities that this unprecedent situation is bringing for reorganizing workflow and developing new projects. KEY POINTS: • Teleradiology solutions are playing an essential role during the COVID-19 outbreak. • Teleworking should be extended to the rest of non-medical radiology department areas whenever possible.

RadioGraphics Update: Functional MR Neurography in Evaluation of Peripheral Nerve Trauma and Postsurgical Assessment.

Editor's Note.-Articles in the RadioGraphics Update section provide current knowledge to supplement or update information found in full-length articles previously published in RadioGraphics. Authors of the previously published article provide a brief synopsis that emphasizes important new information such as technological advances, revised imaging protocols, new clinical guidelines involving imaging, or updated classification schemes. Articles in this section are published solely online and are linked to the original article. ©RSNA, 2021.

Arterial spin labeling for head and neck lesion assessment: technical adjustments and clinical applications.

PURPOSE: Despite, currently, "state-of-the-art" magnetic resonance imaging (MRI) protocols for head and neck (H&N) lesion assessment incorporate perfusion sequences, these acquisitions require the intravenous injection of exogenous gadolinium-based contrast agents (GBCAs), which may have potential risks. Alternative techniques such as arterial spin labeling (ASL) can provide quantitative microvascular information similar to conventional perfusion sequences for H&N lesions evaluation, as a potential alternative without GBCA administration. METHODS: We review the existing literature and analyze the latest evidence regarding ASL in H&N area highlighting the technical adjustments needed for a proper ASL acquisition in this challenging region for lesion characterization, treatment monitoring, and tumor recurrence detection. RESULTS: ASL techniques, widely used for central nervous system lesions evaluation, can be also applied to the H&N region. Technical adjustments, especially regarding post-labeling delay, are mandatory to obtain robust and reproducible results. Several studies have demonstrated the feasibility of ASL in the H&N area including the orbits, skull base, paranasal sinuses, upper airway, salivary glands, and thyroid. CONCLUSION: ASL is a feasible technique for the assessment of H&N lesions without the need of GBCAs. This manuscript reviews ASL's physical basis, emphasizing the technical adjustments necessary for proper ASL acquisition in this unique and challenging anatomical region, and the main applications in evaluating H&N lesions.

Assessing Immunotherapy with Functional and Molecular Imaging and Radiomics.

Immunotherapy is changing the treatment paradigm for cancer and has introduced new challenges in medical imaging. Because not all patients benefit from immunotherapy, pretreatment imaging should be performed to identify not only prognostic factors but also factors that allow prediction of response to immunotherapy. Follow-up studies must allow detection of nonresponders, without confusion of pseudoprogression with real progression to prevent premature discontinuation of treatment that can benefit the patient. Conventional imaging techniques and classic tumor response criteria are limited for the evaluation of the unusual patterns of response that arise from the specific mechanisms of action of immunotherapy, so advanced imaging methods must be developed to overcome these shortcomings. The authors present the fundamentals of the tumor immune microenvironment and immunotherapy and how they influence imaging findings. They also discuss advances in functional and molecular imaging techniques for the assessment of immunotherapy in clinical practice, including their use to characterize immune phenotypes, assess patient prognosis and response to therapy, and evaluate immune-related adverse events. Finally, the development of radiomics and radiogenomics in these therapies and the future role of imaging biomarkers for immunotherapy are discussed. Online supplemental material is available for this article. ©RSNA, 2020.

Optimizing Diffusion-Tensor Imaging Acquisition for Spinal Cord Assessment: Physical Basis and Technical Adjustments.

Diffusion-tensor imaging (DTI) has been used in the assessment of the central nervous system for the past 3 decades and has demonstrated great utility for the functional assessment of normal and pathologic white matter. Recent technical advances have permitted the expansion of DTI applications to the spinal cord. MRI of the spinal cord has traditionally been limited to conventional sequences, which provide information regarding changes in the anatomic shape of a structure or its signal intensity, suggesting the presence of a pathologic entity. However, conventional MRI lacks the ability to provide pathophysiologic information. DTI of the spinal cord can deliver pathophysiologic information on a molecular basis and thereby has several adjunctive uses. These advantages have yet to be fully evaluated, and therefore spinal DTI lacks widespread adoption. The barriers to implementation include a lack of understanding of the underlying physics principles needed to make necessary technical adjustments to obtain diagnostic images, as well as the need for standardization of protocols and postprocessing methods. The authors provide a comprehensive review of the physics of spinal cord DTI and the technical adjustments required to obtain diagnostic images and describe tips and tricks for accurate postprocessing. The primary clinical applications for spinal cord DTI are reviewed. Online supplemental material is available for this article. ©RSNA, 2020 See discussion on this article by Smith.

Functional MR Neurography in Evaluation of Peripheral Nerve Trauma and Postsurgical Assessment.

Evaluation of traumatic peripheral nerve injuries has classically been based on clinical and electrophysiologic criteria. US and MRI have been widely used for morphologic assessment of nerve injury sites and concomitant lesions. In the past few years, morphologic MR neurography has significantly increased its clinical applications on the basis of three-dimensional or two-dimensional images with and without fat-suppression techniques. However, these sequences have a major drawback: absence of pathophysiologic information about functional integrity or axonal flow of peripheral nerves. In this scenario, functional MRI techniques such as diffusion-weighted imaging (DWI) or diffusion tensor imaging (DTI) can be used as a complementary tool in initial evaluation of peripheral nerve trauma or in assessment of trauma undergoing surgical repair. These approaches provide not only morphologic but also functional information about extent and degree of nerve impairment. Functional MR neurography can also be applied to selection, planning, and monitoring of surgical procedures that can be performed after traumatic peripheral nerve injuries, such as neurorrhaphy, nerve graft, or neurolysis, as it provides surgeons with valuable information about the functional status of the nerves involved and axonal flow integrity. The physical basis of DWI and DTI and the technical adjustments required for their appropriate performance for peripheral nerve evaluation are reviewed. Also, the clinical value of DWI and DTI in assessment of peripheral nerve trauma is discussed, enhancing their potential impact on selection, planning, and monitoring of surgical procedures employed for peripheral nerve repair. Online supplemental material is available for this article. ©RSNA, 2019.