Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networks

Super-resolution label-free volumetric vibrational imaging

Innovations in high-resolution optical imaging have allowed visualization of nanoscale biological structures and connections. However, super-resolution fluorescence techniques, including both optics-oriented and sample-expansion based, are limited in quantification and throughput especially in tissues from photobleaching or quenching of the fluorophores, and low-efficiency or non-uniform delivery of the probes. Here, we report a general sample-expansion vibrational imaging strategy, termed VISTA, for scalable label-free high-resolution interrogations of protein-rich biological structures with resolution down to 78 nm. VISTA achieves decent three-dimensional image quality through optimal retention of endogenous proteins, isotropic sample expansion, and deprivation of scattering lipids. Free from probe-labeling associated issues, VISTA offers unbiased and high-throughput tissue investigations. With correlative VISTA and immunofluorescence, we further validated the imaging specificity of VISTA and trained an image-segmentation model for label-free multi-component and volumetric prediction of nucleus, blood vessels, neuronal cells and dendrites in complex mouse brain tissues. VISTA could hence open new avenues for versatile biomedical studies.

Machine Vision for Real-Time Intraoperative Anatomic Guidance: A Proof-of-Concept Study in Endoscopic Pituitary Surgery

BACKGROUND

Current intraoperative orientation methods either rely on preoperative imaging, are resource-intensive to implement, or difficult to interpret. Real-time, reliable anatomic recognition would constitute another strong pillar on which neurosurgeons could rest for intraoperative orientation.

OBJECTIVE

To assess the feasibility of machine vision algorithms to identify anatomic structures using only the endoscopic camera without prior explicit anatomo-topographic knowledge in a proof-of-concept study.

METHODS

We developed and validated a deep learning algorithm to detect the nasal septum, the middle turbinate, and the inferior turbinate during endoscopic endonasal approaches based on endoscopy videos from 23 different patients. The model was trained in a weakly supervised manner on 18 and validated on 5 patients. Performance was compared against a baseline consisting of the average positions of the training ground truth labels using a semiquantitative 3-tiered system.

RESULTS

We used 367 images extracted from the videos of 18 patients for training, as well as 182 test images extracted from the videos of another 5 patients for testing the fully developed model. The prototype machine vision algorithm was able to identify the 3 endonasal structures qualitatively well. Compared to the baseline model based on location priors, the algorithm demonstrated slightly but statistically significantly (P < .001) improved annotation performance.

CONCLUSION

Automated recognition of anatomic structures in endoscopic videos by means of a machine vision model using only the endoscopic camera without prior explicit anatomo-topographic knowledge is feasible. This proof of concept encourages further development of fully automated software for real-time intraoperative anatomic guidance during surgery.

Detection of glioma infiltration at the tumor margin using quantitative stimulated Raman scattering histology

In the management of diffuse gliomas, the identification and removal of tumor at the infiltrative margin remains a central challenge. Prior work has demonstrated that fluorescence labeling tools and radiographic imaging are useful surgical adjuvants with macroscopic resolution. However, they lose sensitivity at the tumor margin and have limited clinical utility for lower grade histologies. Fiber-laser based stimulated Raman histology (SRH) is an optical imaging technique that provides microscopic tissue characterization of unprocessed tissues. It remains unknown whether SRH of tissues taken from the infiltrative glioma margin will identify microscopic residual disease. Here we acquired glioma margin specimens for SRH, histology, and tumor specific tissue characterization. Generalized linear mixed models were used to evaluate agreement. We find that SRH identified residual tumor in 82 of 167 margin specimens (49%), compared to IHC confirming residual tumor in 72 of 128 samples (56%), and H&E confirming residual tumor in 82 of 169 samples (49%). Intraobserver agreements between all 3 modalities were confirmed. These data demonstrate that SRH detects residual microscopic tumor at the infiltrative glioma margin and may be a promising tool to enhance extent of resection.

Examining the effect of explanation on satisfaction and trust in AI diagnostic systems

BACKGROUND

Artificial Intelligence has the potential to revolutionize healthcare, and it is increasingly being deployed to support and assist medical diagnosis. One potential application of AI is as the first point of contact for patients, replacing initial diagnoses prior to sending a patient to a specialist, allowing health care professionals to focus on more challenging and critical aspects of treatment. But for AI systems to succeed in this role, it will not be enough for them to merely provide accurate diagnoses and predictions. In addition, it will need to provide explanations (both to physicians and patients) about why the diagnoses are made. Without this, accurate and correct diagnoses and treatments might otherwise be ignored or rejected.

METHOD

It is important to evaluate the effectiveness of these explanations and understand the relative effectiveness of different kinds of explanations. In this paper, we examine this problem across two simulation experiments. For the first experiment, we tested a re-diagnosis scenario to understand the effect of local and global explanations. In a second simulation experiment, we implemented different forms of explanation in a similar diagnosis scenario.

RESULTS

Results show that explanation helps improve satisfaction measures during the critical re-diagnosis period but had little effect before re-diagnosis (when initial treatment was taking place) or after (when an alternate diagnosis resolved the case successfully). Furthermore, initial "global" explanations about the process had no impact on immediate satisfaction but improved later judgments of understanding about the AI. Results of the second experiment show that visual and example-based explanations integrated with rationales had a significantly better impact on patient satisfaction and trust than no explanations, or with text-based rationales alone. As in Experiment 1, these explanations had their effect primarily on immediate measures of satisfaction during the re-diagnosis crisis, with little advantage prior to re-diagnosis or once the diagnosis was successfully resolved.

CONCLUSION

These two studies help us to draw several conclusions about how patient-facing explanatory diagnostic systems may succeed or fail. Based on these studies and the review of the literature, we will provide some design recommendations for the explanations offered for AI systems in the healthcare domain.

Clinical integration of machine learning for curative-intent radiation treatment of patients with prostate cancer

Machine learning (ML) holds great promise for impacting healthcare delivery; however, to date most methods are tested in 'simulated' environments that cannot recapitulate factors influencing real-world clinical practice. We prospectively deployed and evaluated a random forest algorithm for therapeutic curative-intent radiation therapy (RT) treatment planning for prostate cancer in a blinded, head-to-head study with full integration into the clinical workflow. ML- and human-generated RT treatment plans were directly compared in a retrospective simulation with retesting (n = 50) and a prospective clinical deployment (n = 50) phase. Consistently throughout the study phases, treating physicians assessed ML- and human-generated RT treatment plans in a blinded manner following a priori defined standardized criteria and peer review processes, with the selected RT plan in the prospective phase delivered for patient treatment. Overall, 89% of ML-generated RT plans were considered clinically acceptable and 72% were selected over human-generated RT plans in head-to-head comparisons. RT planning using ML reduced the median time required for the entire RT planning process by 60.1% (118 to 47 h). While ML RT plan acceptability remained stable between the simulation and deployment phases (92 versus 86%), the number of ML RT plans selected for treatment was significantly reduced (83 versus 61%, respectively). These findings highlight that retrospective or simulated evaluation of ML methods, even under expert blinded review, may not be representative of algorithm acceptance in a real-world clinical setting when patient care is at stake.

Mesoscopic fluorescence lifetime imaging: Fundamental principles, clinical applications and future directions

Fluorescence lifetime imaging (FLIm) is an optical spectroscopic imaging technique capable of real-time assessments of tissue properties in clinical settings. Label-free FLIm is sensitive to changes in tissue structure and biochemistry resulting from pathological conditions, thus providing optical contrast to identify and monitor the progression of disease. Technical and methodological advances over the last two decades have enabled the development of FLIm instrumentation for real-time, in situ, mesoscopic imaging compatible with standard clinical workflows. Herein, we review the fundamental working principles of mesoscopic FLIm, discuss the technical characteristics of current clinical FLIm instrumentation, highlight the most commonly used analytical methods to interpret fluorescence lifetime data and discuss the recent applications of FLIm in surgical oncology and cardiovascular diagnostics. Finally, we conclude with an outlook on the future directions of clinical FLIm.

Initial Evaluation of Rapid, Direct-to-Digital Prostate Biopsy Pathology

CONTEXT.—

Pathologist interobserver discordance is significant in grading of prostate cancer, limiting reliability. Diagnostic reproducibility may be improved with digital images, but adoption faces workflow, cost, and quality challenges. A novel digital method using an alternative tissue processing approach and novel laser microscopy system potentially addresses these issues.

OBJECTIVE.—

To evaluate the capability of this new method for primary diagnostic interpretation in clinical prostate biopsy specimens.

DESIGN.—

Forty patients with a high likelihood of prostate cancer based on magnetic resonance imaging consented to investigational core biopsy. A subset of samples was used for direct comparison of physical slide preparation effects and time-tracking determination with multiphoton microscopy. Twenty samples were processed for diagnostic comparison between multilevel digital slides and subsequently produced physical slides. A reference diagnosis based on all data was established using grade groups. Level of diagnostic match and requests for immunohistochemistry were compared between physical and digital diagnoses. Immunohistochemical staining and length measurements were secondary outcomes.

RESULTS.—

Interpretations based on direct multiphoton imaging yielded diagnoses that were at least as accurate as standard histology; cancer diagnosis correlation was 89% (51 of 57) by physical slides and 95% (53 of 56) by multiphoton microscopy. Grade-level concordance was 73% (44 of 60) by either method. Immunohistochemistry for routine prostate cancer-associated markers on these alternatively processed tissues was unaffected. Alternatively processed tissues resulted in longer measured core and cancer lengths, suggestive of improved orientation and visualization.

CONCLUSIONS.—

Findings support high potential for complete interpretation of prostate core biopsies using solely multiphoton microscopy of intact specimens, with potential diagnostic benefits as well as reduced processing time and reduced processing complexity.

Microsecond fingerprint stimulated Raman spectroscopic imaging by ultrafast tuning and spatial-spectral learning

Label-free vibrational imaging by stimulated Raman scattering (SRS) provides unprecedented insight into real-time chemical distributions. Specifically, SRS in the fingerprint region (400-1800 cm-1) can resolve multiple chemicals in a complex bio-environment. However, due to the intrinsic weak Raman cross-sections and the lack of ultrafast spectral acquisition schemes with high spectral fidelity, SRS in the fingerprint region is not viable for studying living cells or large-scale tissue samples. Here, we report a fingerprint spectroscopic SRS platform that acquires a distortion-free SRS spectrum at 10 cm-1 spectral resolution within 20 µs using a polygon scanner. Meanwhile, we significantly improve the signal-to-noise ratio by employing a spatial-spectral residual learning network, reaching a level comparable to that with 100 times integration. Collectively, our system enables high-speed vibrational spectroscopic imaging of multiple biomolecules in samples ranging from a single live microbe to a tissue slice.

EGFR-targeted intraoperative fluorescence imaging detects high-grade glioma with panitumumab-IRDye800 in a phase 1 clinical trial

Rationale: First-line therapy for high-grade gliomas (HGGs) includes maximal safe surgical resection. The extent of resection predicts overall survival, but current neuroimaging approaches lack tumor specificity. The epidermal growth factor receptor (EGFR) is a highly expressed HGG biomarker. We evaluated the safety and feasibility of an anti-EGFR antibody, panitumuab-IRDye800, at subtherapeutic doses as an imaging agent for HGG. Methods: Eleven patients with contrast-enhancing HGGs were systemically infused with panitumumab-IRDye800 at a low (50 mg) or high (100 mg) dose 1-5 days before surgery. Near-infrared fluorescence imaging was performed intraoperatively and ex vivo, to identify the optimal tumor-to-background ratio by comparing mean fluorescence intensities of tumor and histologically uninvolved tissue. Fluorescence was correlated with preoperative T1 contrast, tumor size, EGFR expression and other biomarkers. Results: No adverse events were attributed to panitumumab-IRDye800. Tumor fragments as small as 5 mg could be detected ex vivo and detection threshold was dose dependent. In tissue sections, panitumumab-IRDye800 was highly sensitive (95%) and specific (96%) for pathology confirmed tumor containing tissue. Cellular delivery of panitumumab-IRDye800 was correlated to EGFR overexpression and compromised blood-brain barrier in HGG, while normal brain tissue showed minimal fluorescence. Intraoperative fluorescence improved optical contrast in tumor tissue within and beyond the T1 contrast-enhancing margin, with contrast-to-noise ratios of 9.5 ± 2.1 and 3.6 ± 1.1, respectively. Conclusions: Panitumumab-IRDye800 provided excellent tumor contrast and was safe at both doses. Smaller fragments of tumor could be detected at the 100 mg dose and thus more suitable for intraoperative imaging.

In Silico Mathematical Modelling for Glioblastoma: A Critical Review and a Patient-Specific Case

Glioblastoma extensively infiltrates the brain; despite surgery and aggressive therapies, the prognosis is poor. A multidisciplinary approach combining mathematical, clinical and radiological data has the potential to foster our understanding of glioblastoma evolution in every single patient, with the aim of tailoring therapeutic weapons. In particular, the ultimate goal of biomathematics for cancer is the identification of the most suitable theoretical models and simulation tools, both to describe the biological complexity of carcinogenesis and to predict tumor evolution. In this report, we describe the results of a critical review about different mathematical models in neuro-oncology with their clinical implications. A comprehensive literature search and review for English-language articles concerning mathematical modelling in glioblastoma has been conducted. The review explored the different proposed models, classifying them and indicating the significative advances of each one. Furthermore, we present a specific case of a glioblastoma patient in which our recently proposed innovative mechanical model has been applied. The results of the mathematical models have the potential to provide a relevant benefit for clinicians and, more importantly, they might drive progress towards improving tumor control and patient's prognosis. Further prospective comparative trials, however, are still necessary to prove the impact of mathematical neuro-oncology in clinical practice.

Deep Neural Network for Differentiation of Brain Tumor Tissue Displayed by Confocal Laser Endomicroscopy

Background

Reliable on site classification of resected tumor specimens remains a challenge. Implementation of high-resolution confocal laser endoscopic techniques (CLEs) during fluorescence-guided brain tumor surgery is a new tool for intraoperative tumor tissue visualization. To overcome observer dependent errors, we aimed to predict tumor type by applying a deep learning model to image data obtained by CLE.

Methods

Human brain tumor specimens from 25 patients with brain metastasis, glioblastoma, and meningioma were evaluated within this study. In addition to routine histopathological analysis, tissue samples were stained with fluorescein ex vivo and analyzed with CLE. We trained two convolutional neural networks and built a predictive level for the outputs.

Results

Multiple CLE images were obtained from each specimen with a total number of 13,972 fluorescein based images. Test accuracy of 90.9% was achieved after applying a two-class prediction for glioblastomas and brain metastases with an area under the curve (AUC) value of 0.92. For three class predictions, our model achieved a ratio of correct predicted label of 85.8% in the test set, which was confirmed with five-fold cross validation, without definition of confidence. Applying a confidence rate of 0.999 increased the prediction accuracy to 98.6% when images with substantial artifacts were excluded before the analysis. 36.3% of total images met the output criteria.

Conclusions

We trained a residual network model that allows automated, on site analysis of resected tumor specimens based on CLE image datasets. Further in vivo studies are required to assess the clinical benefit CLE can have.

Emerging principles of brain immunology and immune checkpoint blockade in brain metastases

Brain metastases are the most common type of brain tumours, harbouring an immune microenvironment that can in principle be targeted via immunotherapy. Elucidating some of the immunological intricacies of brain metastases has opened a therapeutic window to explore the potential of immune checkpoint inhibitors in this globally lethal disease. Multiple lines of evidence suggest that tumour cells hijack the immune regulatory mechanisms in the brain for the benefit of their own survival and progression. Nonetheless, the role of the immune checkpoint in the complex interplays between cancers cells and T cells and in conferring resistance to therapy remains under investigation. Meanwhile, early phase trials with immune checkpoint inhibitors have reported clinical benefit in patients with brain metastases from melanoma and non-small cell lung cancer. In this review, we explore the workings of the immune system in the brain, the immunology of brain metastases, and the current status of immune checkpoint inhibitors in the treatment of brain metastases.

AI-based pathology predicts origins for cancers of unknown primary

Cancer of unknown primary (CUP) origin is an enigmatic group of diagnoses in which the primary anatomical site of tumour origin cannot be determined^1,2. This poses a considerable challenge, as modern therapeutics are predominantly specific to the primary tumour³. Recent research has focused on using genomics and transcriptomics to identify the origin of a tumour^4-9. However, genomic testing is not always performed and lacks clinical penetration in low-resource settings. Here, to overcome these challenges, we present a deep-learning-based algorithm-Tumour Origin Assessment via Deep Learning (TOAD)-that can provide a differential diagnosis for the origin of the primary tumour using routinely acquired histology slides. We used whole-slide images of tumours with known primary origins to train a model that simultaneously identifies the tumour as primary or metastatic and predicts its site of origin. On our held-out test set of tumours with known primary origins, the model achieved a top-1 accuracy of 0.83 and a top-3 accuracy of 0.96, whereas on our external test set it achieved top-1 and top-3 accuracies of 0.80 and 0.93, respectively. We further curated a dataset of 317 cases of CUP for which a differential diagnosis was assigned. Our model predictions resulted in concordance for 61% of cases and a top-3 agreement of 82%. TOAD can be used as an assistive tool to assign a differential diagnosis to complicated cases of metastatic tumours and CUPs and could be used in conjunction with or in lieu of ancillary tests and extensive diagnostic work-ups to reduce the occurrence of CUP.

Cancer Surgery 2.0: Guidance by Real-Time Molecular Technologies

In vivo cancer margin delineation during surgery remains a major challenge. Despite the availability of several image guidance techniques and intraoperative assessment, clear surgical margins and debulking efficiency remain scarce. For this reason, there is particular interest in developing rapid intraoperative tools with high sensitivity and specificity to help guide cancer surgery in vivo. Recently, several emerging technologies including intraoperative mass spectrometry have paved the way for molecular guidance in a clinical setting. We evaluate these techniques and assess their relevance for intraoperative surgical guidance and how they can transform the future of molecular cancer surgery, diagnostics, patient management and care.

Deep learning provides high accuracy in automated chondrocyte viability assessment in articular cartilage using nonlinear optical microscopy

Chondrocyte viability is a crucial factor in evaluating cartilage health. Most cell viability assays rely on dyes and are not applicable for in vivo or longitudinal studies. We previously demonstrated that two-photon excited autofluorescence and second harmonic generation microscopy provided high-resolution images of cells and collagen structure; those images allowed us to distinguish live from dead chondrocytes by visual assessment or by the normalized autofluorescence ratio. However, both methods require human involvement and have low throughputs. Methods for automated cell-based image processing can improve throughput. Conventional image processing algorithms do not perform well on autofluorescence images acquired by nonlinear microscopes due to low image contrast. In this study, we compared conventional, machine learning, and deep learning methods in chondrocyte segmentation and classification. We demonstrated that deep learning significantly improved the outcome of the chondrocyte segmentation and classification. With appropriate training, the deep learning method can achieve 90% accuracy in chondrocyte viability measurement. The significance of this work is that automated imaging analysis is possible and should not become a major hurdle for the use of nonlinear optical imaging methods in biological or clinical studies.

Intraoperative molecular imaging clinical trials: a review of 2020 conference proceedings

SIGNIFICANCE

Surgery is often paramount in the management of many solid organ malignancies because optimal resection is a major factor in disease-specific survival. Cancer surgery has multiple challenges including localizing small lesions, ensuring negative surgical margins around a tumor, adequately staging patients by discriminating positive lymph nodes, and identifying potential synchronous cancers. Intraoperative molecular imaging (IMI) is an emerging potential tool proposed to address these issues. IMI is the process of injecting patients with fluorescent-targeted contrast agents that highlight cancer cells prior to surgery. Over the last 5 to 7 years, enormous progress has been achieved in tracer development, near-infrared camera approvals, and clinical trials. Therefore, a second biennial conference was organized at the University of Pennsylvania to gather surgical oncologists, scientists, and experts to discuss new investigative findings in the field. Our review summarizes the discussions from the conference and highlights findings in various clinical and scientific trials.

AIM

Recent advances in IMI were presented, and the importance of each clinical trial for surgical oncology was critically assessed. A major focus was to elaborate on the clinical endpoints that were being utilized in IMI trials to advance the respective surgical subspecialties.

APPROACH

Principal investigators presenting at the Perelman School of Medicine Abramson Cancer Center's second clinical trials update on IMI were selected to discuss their clinical trials and endpoints.

RESULTS

Multiple phase III, II, and I trials were discussed during the conference. Since the approval of 5-ALA for commercial use in neurosurgical malignancies, multiple tracers and devices have been developed to address common challenges faced by cancer surgeons across numerous specialties. Discussants also presented tracers that are being developed for delineation of normal anatomic structures that can serve as an adjunct during surgical procedures.

CONCLUSIONS

IMI is increasingly being recognized as an improvement to standard oncologic surgical resections and will likely advance the art of cancer surgery in the coming years. The endpoints in each individual surgical subspecialty are varied depending on how IMI helps each specialty solve their clinical challenges.

Special Series Guest Editorial: Artificial Intelligence and Machine Learning in Biomedical Optics

Guest editors Behrouz Shabestri, Mark Anastasio, Baowei Fei, and Frédéric Leblond provide an overview of the JBO Special Series on Artificial Intelligence Machine Learning in Biomedical Optics.

Real-time intraoperative glioma diagnosis using fluorescence imaging and deep convolutional neural networks

Purpose

Surgery is the predominant treatment modality of human glioma but suffers difficulty on clearly identifying tumor boundaries in clinic. Conventional practice involves neurosurgeon’s visual evaluation and intraoperative histological examination of dissected tissues using frozen section, which is time-consuming and complex. The aim of this study was to develop fluorescent imaging coupled with artificial intelligence technique to quickly and accurately determine glioma in real-time during surgery.

Methods

Glioma patients (N = 23) were enrolled and injected with indocyanine green for fluorescence image–guided surgery. Tissue samples (N = 1874) were harvested from surgery of these patients, and the second near-infrared window (NIR-II, 1000–1700 nm) fluorescence images were obtained. Deep convolutional neural networks (CNNs) combined with NIR-II fluorescence imaging (named as FL-CNN) were explored to automatically provide pathological diagnosis of glioma in situ in real-time during patient surgery. The pathological examination results were used as the gold standard.

Results

The developed FL-CNN achieved the area under the curve (AUC) of 0.945. Comparing to neurosurgeons’ judgment, with the same level of specificity >80%, FL-CNN achieved a much higher sensitivity (93.8% versus 82.0%, P < 0.001) with zero time overhead. Further experiments demonstrated that FL-CNN corrected >70% of the errors made by neurosurgeons. FL-CNN was also able to rapidly predict grade and Ki-67 level (AUC 0.810 and 0.625) of tumor specimens intraoperatively.

Conclusion

Our study demonstrates that deep CNNs are better at capturing important information from fluorescence images than surgeons’ evaluation during patient surgery. FL-CNN is highly promising to provide pathological diagnosis intraoperatively and assist neurosurgeons to obtain maximum resection safely.

Trial registration

ChiCTR ChiCTR2000029402. Registered 29 January 2020, retrospectively registered

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05326-y.

Non-invasive cell classification using the Paint Raman Express Spectroscopy System (PRESS)

Raman scattering represents the distribution and abundance of intracellular molecules, including proteins and lipids, facilitating distinction between cellular states non-invasively and without staining. However, the scattered light obtained from cells is faint and cells have complex structures, making it difficult to obtain a Raman spectrum covering the entire cell in a short time using conventional methods. This also prevents efficient label-free cell classification. In the present study, we developed the Paint Raman Express Spectroscopy System, which uses two fast-rotating galvano mirrors to obtain spectra from a wide area of a cell. By using this system and applying machine learning, we were able to acquire broad spectra of a variety of human and mouse cell types, including pluripotent stem cells and confirmed that each cell type can be classified with high accuracy. Moreover, we classified different activation states of human T cells, despite their similar morphology. This system could be used for rapid and low-cost drug evaluation and quality management for drug screening in cell-based assays.

Microcalcification-Based Tumor Malignancy Evaluation in Fresh Breast Biopsies with Hyperspectral Stimulated Raman Scattering

Precise evaluation of breast tumor malignancy based on tissue calcifications has important practical value in the disease diagnosis, as well as the understanding of tumor development. Traditional X-ray mammography provides the overall morphologies of the calcifications but lacks intrinsic chemical information. In contrast, spontaneous Raman spectroscopy offers detailed chemical analysis but lacks the spatial profiles. Here, we applied hyperspectral stimulated Raman scattering (SRS) microscopy to extract both the chemical and morphological features of the microcalcifications, based on the spectral and spatial domain analysis. A total of 211 calcification sites from 23 patients were imaged with SRS, and the results were analyzed with a support vector machine (SVM) based classification algorithm. With optimized combinations of chemical and geometrical features of microcalcifications, we were able to reach a precision of 98.21% and recall of 100.00% for classifying benign and malignant cases, significantly improved from the pure spectroscopy or imaging based methods. Our findings may provide a rapid means to accurately evaluate breast tumor malignancy based on fresh tissue biopsies.

Artificial intelligence in cancer research: learning at different levels of data granularity

From genome-scale experimental studies to imaging data, behavioral footprints, and longitudinal healthcare records, the convergence of big data in cancer research and the advances in Artificial Intelligence (AI) is paving the way to develop a systems view of cancer. Nevertheless, this biomedical area is largely characterized by the co-existence of big data and small data resources, highlighting the need for a deeper investigation about the crosstalk between different levels of data granularity, including varied sample sizes, labels, data types, and other data descriptors. This review introduces the current challenges, limitations, and solutions of AI in the heterogeneous landscape of data granularity in cancer research. Such a variety of cancer molecular and clinical data calls for advancing the interoperability among AI approaches, with particular emphasis on the synergy between discriminative and generative models that we discuss in this work with several examples of techniques and applications.

Stimulated Raman Histology for Rapid Intraoperative Diagnosis of Gliomas

BACKGROUND

Intraoperative pathologic diagnosis traditionally involves frozen section histopathology, which may be labor and time intensive. Indeed, a technique that streamlines the acquisition and evaluation of intraoperative histologic data may expedite surgical decision-making and shorten operative time. Stimulated Raman histology (SRH) is an emerging technology that allows for more rapid acquisition and interpretation of intraoperative histopathologic data.

METHODS

A blinded, prospective cohort study was performed for 82 patients undergoing resection for a central nervous system tumor. Of these, 21 patients were diagnosed with glioma either intraoperatively or postoperatively on permanent section histology and included in this study. Time to diagnosis (TTD) and diagnostic accuracy relative to permanent section (the gold standard) were compared between SRH-based diagnosis and conventional frozen section histology. Diagnostic concordance with permanent section was also compared between frozen histopathology and SRH diagnosis.

RESULTS

Diagnostic accuracy was not significantly different between methods (P = 1.00). Diagnostic concordance was not significantly different between methods when comparing 95% confidence intervals for kappa values (κ = 0.215; κ = 0.297; κ = 0.369). Lastly, mean TTD was significantly shorter with SRH-based diagnosis compared with frozen section (43 vs. 9.7 minutes, P < 0.0001). SRH was able to identify key features associated with varying glioma types.

CONCLUSIONS

SRH allows for rapid intraoperative diagnosis without sacrificing diagnostic accuracy. SRH may serve as a promising adjuvant to conventional histopathology to expedite intraoperative pathology consultation and surgical decision-making.

Recent progress of surface-enhanced Raman spectroscopy for subcellular compartment analysis

Organelles are involved in many cell life activities, and their metabolic or functional disorders are closely related to apoptosis, neurodegenerative diseases, cardiovascular diseases, and the development and metastasis of cancers. The explorations of subcellular structures, microenvironments, and their abnormal conditions are conducive to a deeper understanding of many pathological mechanisms, which are expected to achieve the early diagnosis and the effective therapy of diseases. Organelles are also the targeted locations of drugs, and they play significant roles in many targeting therapeutic strategies. Surface-enhanced Raman spectroscopy (SERS) is a powerful analytical tool that can provide the molecular fingerprint information of subcellular compartments and the real-time cellular dynamics in a non-invasive and non-destructive way. This review aims to summarize the recent advances of SERS studies on subcellular compartments, including five parts. The introductions of SERS and subcellular compartments are given. SERS is promising in subcellular compartment studies due to its molecular specificity and high sensitivity, and both of which highly match the high demands of cellular/subcellular investigations. Intracellular SERS is mainly cataloged as the labeling and label-free methods. For subcellular targeted detections and therapies, how to internalize plasmonic nanoparticles or nanostructure in the target locations is a key point. The subcellular compartment SERS detections, SERS measurements of isolated organelles, investigations of therapeutic mechanisms from subcellular compartments and microenvironments, and integration of SERS diagnosis and treatment are sequentially presented. A perspective view of the subcellular SERS studies is discussed from six aspects. This review provides a comprehensive overview of SERS applications in subcellular compartment researches, which will be a useful reference for designing the SERS-involved therapeutic systems.

Designing deep learning studies in cancer diagnostics

The number of publications on deep learning for cancer diagnostics is rapidly increasing, and systems are frequently claimed to perform comparable with or better than clinicians. However, few systems have yet demonstrated real-world medical utility. In this Perspective, we discuss reasons for the moderate progress and describe remedies designed to facilitate transition to the clinic. Recent, presumably influential, deep learning studies in cancer diagnostics, of which the vast majority used images as input to the system, are evaluated to reveal the status of the field. By manipulating real data, we then exemplify that much and varied training data facilitate the generalizability of neural networks and thus the ability to use them clinically. To reduce the risk of biased performance estimation of deep learning systems, we advocate evaluation in external cohorts and strongly advise that the planned analyses, including a predefined primary analysis, are described in a protocol preferentially stored in an online repository. Recommended protocol items should be established for the field, and we present our suggestions.

Towards in-vivo label-free detection of brain tumor margins with epi-illumination tomographic quantitative phase imaging

Brain tumor surgery involves a delicate balance between maximizing the extent of tumor resection while minimizing damage to healthy brain tissue that is vital for neurological function. However, differentiating between tumor, particularly infiltrative disease, and healthy brain in-vivo remains a significant clinical challenge. Here we demonstrate that quantitative oblique back illumination microscopy (qOBM)-a novel label-free optical imaging technique that achieves tomographic quantitative phase imaging in thick scattering samples-clearly differentiates between healthy brain tissue and tumor, including infiltrative disease. Data from a bulk and infiltrative brain tumor animal model show that qOBM enables quantitative phase imaging of thick fresh brain tissues with remarkable cellular and subcellular detail that closely resembles histopathology using hematoxylin and eosin (H&E) stained fixed tissue sections, the gold standard for cancer detection. Quantitative biophysical features are also extracted from qOBM which yield robust surrogate biomarkers of disease that enable (1) automated tumor and margin detection with high sensitivity and specificity and (2) facile visualization of tumor regions. Finally, we develop a low-cost, flexible, fiber-based handheld qOBM device which brings this technology one step closer to in-vivo clinical use. This work has significant implications for guiding neurosurgery by paving the way for a tool that delivers real-time, label-free, in-vivo brain tumor margin detection.

Unsupervised content-preserving transformation for optical microscopy

The development of deep learning and open access to a substantial collection of imaging data together provide a potential solution for computational image transformation, which is gradually changing the landscape of optical imaging and biomedical research. However, current implementations of deep learning usually operate in a supervised manner, and their reliance on laborious and error-prone data annotation procedures remains a barrier to more general applicability. Here, we propose an unsupervised image transformation to facilitate the utilization of deep learning for optical microscopy, even in some cases in which supervised models cannot be applied. Through the introduction of a saliency constraint, the unsupervised model, named Unsupervised content-preserving Transformation for Optical Microscopy (UTOM), can learn the mapping between two image domains without requiring paired training data while avoiding distortions of the image content. UTOM shows promising performance in a wide range of biomedical image transformation tasks, including in silico histological staining, fluorescence image restoration, and virtual fluorescence labeling. Quantitative evaluations reveal that UTOM achieves stable and high-fidelity image transformations across different imaging conditions and modalities. We anticipate that our framework will encourage a paradigm shift in training neural networks and enable more applications of artificial intelligence in biomedical imaging.

Label-free histological imaging of tissues using Brillouin light scattering contrast

Brillouin light scattering offers a unique label-free approach to measure biomechanical properties non-invasively. While this technique is used in biomechanical analysis of cells and tissues, its potential for visualizing structural features of tissues based on the biomechanical contrast has not been much exploited. Here, we present high-resolution Brillouin microscopy images of four basic tissue types: muscular, connective, epithelial, and nervous tissues. The Brillouin contrast distinguishes between muscle fiber cells and endomysium in skeletal muscle and reveals chondrocytes along with spatially varying stiffness of the extracellular matrix in articular cartilage. The hydration-sensitive contrast can visualize the stratum corneum, epidermis, and dermis in the skin epithelium. In brain tissues, the Brillouin images show the mechanical heterogeneity across the cortex and deeper regions. This work demonstrates the versatility of using the Brillouin shift as histological contrast for examining intact tissue substructures via longitudinal modulus without the need for laborious tissue processing steps.

Advances in stimulated Raman scattering imaging for tissues and animals

Stimulated Raman scattering (SRS) microscopy has emerged in the last decade as a powerful optical imaging technology with high chemical selectivity, speed, and subcellular resolution. Since the invention of SRS microscopy, it has been extensively employed in life science to study composition, structure, metabolism, development, and disease in biological systems. Applications of SRS in research and the clinic have generated new insights in many fields including neurobiology, tumor biology, developmental biology, metabolomics, pharmacokinetics, and more. Herein we review the advances and applications of SRS microscopy imaging in tissues and animals, as well as envision future applications and development of SRS imaging in life science and medicine.

Clear cell renal cell carcinoma detection by multimodal photoacoustic tomography

There is a need for accurate and rapid detection of renal cancer in clinic. Here, we integrated photoacoustic tomography (PAT) with ultrasound imaging in a single system, which achieved tissue imaging depth about 3 mm and imaging speed about 3.5 cm²/min. We used the wavelength at 1197 nm to map lipid distribution in normal renal tissues and clear cell renal cell carcinoma (ccRCC) tissues collected from 19 patients undergone nephrectomy. Our results indicated that the photoacoustic signal from lipids was significantly higher in ccRCC tissues than that in normal tissues. Moreover, based on the quantification of lipid area ratio, we were able to differentiate normal and ccRCC with 100 % sensitivity, 80 % specificity, and area under receiver operating characteristic curve of 0.95. Our findings demonstrate that multimodal PAT can differentiate normal and ccRCC by integrating the morphologic information from ultrasound and lipid amount information from vibrational PAT.

Rapid Intraoperative Diagnosis of Meningiomas using Stimulated Raman Histology

BACKGROUND

Frozen section is a time- and labor-intensive method for intraoperative pathologic diagnosis. As a result, there exists a need to expedite and streamline the acquisition and interpretation of diagnostic histologic data to inform surgical decision making. Stimulated Raman histology (SRH) is an emerging technology that may serve to expedite the acquisition and interpretation of histologic data in the operating room.

METHODS

A blinded, prospective cohort study of 82 patients undergoing resection for tumors of the central nervous system was performed. Twenty-six patients with diagnoses of meningioma on SRH, frozen, or permanent section were included in this subanalysis. Diagnostic time and accuracy of stimulated SRH histology images were compared with the gold standard (frozen section). Agreement of SRH and frozen section diagnosis with permanent section (true) diagnosis was also compared.

RESULTS

Mean time-to-diagnosis was significantly shorter for SRH-mediated diagnosis compared with frozen section (9.2 vs. 35.8, P < 0.0001). Diagnostic accuracy was not significantly different between methods (P = 0.15). Diagnostic agreement was not significantly different between SRH versus frozen, SRH versus permanent, or frozen versus permanent section methods (P = 0.5, P = 0.5, P = 1.00).

CONCLUSIONS

SRH is a promising adjuvant technology that may expedite intraoperative neuropathologic consult without sacrificing diagnostic accuracy.

Updates on Surgical Management and Advances for Brain Tumors

PURPOSE OF REVIEW

This review summarizes the modern approach to surgical management of malignant brain tumors, highlighting new technology and multimodal treatment paradigms.

RECENT FINDINGS

Outcomes in patients with glioblastoma are strongly correlated with extent of initial surgical resection. Intraoperative MRI, 5-ALA, and neuronavigation are surgical tools that can help achieve a maximal safe resection. Stereotactic radiosurgery and brachytherapy can be used to enhance local control for brain metastases in conjunction with surgery, while combinatorial approaches are increasingly employed in patients with multiple metastases. Advances in surgical techniques allow for minimally invasive approaches, including the use of tubular retractors, endoscopes, and laser interstitial thermal therapy. Primary and metastatic brain tumors require a multimodal, multidisciplinary approach to treatment. Surgical resection can be paired with radiation for metastases to maximize tumor control, expanding systemic options. Technological innovations have improved the safety of surgical resection, while expanding the surgical options and indications for treatment.

Deep Learning for Biospectroscopy and Biospectral Imaging: State-of-the-Art and Perspectives

With the advances in instrumentation and sampling techniques, there is an explosive growth of data from molecular and cellular samples. The call to extract more information from the large data sets has greatly challenged the conventional chemometrics method. Deep learning, which utilizes very large data sets for finding hidden features therein and for making accurate predictions for a wide range of applications, has been applied in an unbelievable pace in biospectroscopy and biospectral imaging in the recent 3 years. In this Feature, we first introduce the background and basic knowledge of deep learning. We then focus on the emerging applications of deep learning in the data preprocessing, feature detection, and modeling of the biological samples for spectral analysis and spectroscopic imaging. Finally, we highlight the challenges and limitations in deep learning and the outlook for future directions.

Recent advances in the use of stimulated Raman scattering in histopathology

Stimulated Raman histopathology (SRH) utilises the intrinsic vibrational properties of lipids, proteins and nucleic acids to generate contrast providing rapid image acquisition that allows visualisation of histopathological features. It is currently being trialled in the intraoperative setting, where the ability to image unprocessed samples rapidly and with high resolution offers several potential advantages over the use of conventional haematoxylin and eosin stained images. Here we review recent advances in the field including new updates in instrumentation and computer aided diagnosis. We also discuss how other non-linear modalities can be used to provide additional diagnostic contrast which together pave the way for enhanced histopathology and open up possibilities for in vivo pathology.

[Artificial intelligence in neurocritical care]

Artificial intelligence (AI) has been introduced into medicine and an AI-assisted medicine will be the future that we should help to shape. In particular, supervised, unsupervised, and reinforcement learning will be the main methods to play a role in the implementation of AI. Severely ill patients admitted to the intensive care unit (ICU) are closely monitored in order to be able to quickly respond to any changes. These monitoring data can be used to train AI models to predict critical phases in advance, making an earlier reaction possible. To achieve this a large amount of clinical data are needed in order to train models and an external validation on independent cohorts should take place. Prospective studies with treatment of patients admitted to the ICU with AI assistance should show that they provide a benefit for patients. We present the most important resources from de-identified (anonymized) patient data on open-source use for AI research in intensive care medicine. The focus is on neurological diseases in the ICU, therefore, we provide an overview of existing models for prediction of outcome, vasospasms, intracranial pressure and levels of consciousness. To introduce the advantages of AI in the clinical routine, more AI-based models with larger datasets will be needed. To achieve this international cooperation is absolutely necessary. Clinical centers associated with universities are needed to provide a constant validation of applied models as these models can change during use or a bias can develop during the training. A strong commitment to AI research is important for Germany, not only with respect to academic achievements but also in the light of a rapidly growing influence of AI on the economy.

Attitudes of the Surgical Team Toward Artificial Intelligence in Neurosurgery: International 2-Stage Cross-Sectional Survey

BACKGROUND

Artificial intelligence (AI) has the potential to disrupt how we diagnose and treat patients. Previous work by our group has demonstrated that the majority of patients and their relatives feel comfortable with the application of AI to augment surgical care. The aim of this study was to similarly evaluate the attitudes of surgeons and the wider surgical team toward the role of AI in neurosurgery.

METHODS

In a 2-stage cross sectional survey, an initial open-question qualitative survey was created to determine the perspective of the surgical team on AI in neurosurgery including surgeons, anesthetists, nurses, and operating room practitioners. Thematic analysis was performed to develop a second-stage quantitative survey that was distributed via social media. We assessed the extent to which they agreed and were comfortable with real-world AI implementation using a 5-point Likert scale.

RESULTS

In the first-stage survey, 33 participants responded. Six main themes were identified: imaging interpretation and preoperative diagnosis, coordination of the surgical team, operative planning, real-time alert of hazards and complications, autonomous surgery, and postoperative management and follow-up. In the second stage, 100 participants responded. Responders somewhat agreed or strongly agreed about AI being used for imaging interpretation (62%), operative planning (82%), coordination of the surgical team (70%), real-time alert of hazards and complications (85%), and autonomous surgery (66%). The role of AI within postoperative management and follow-up was less agreeable (49%).

CONCLUSIONS

This survey highlights that the majority of surgeons and the wider surgical team both agree and are comfortable with the application of AI within neurosurgery.

Artificial intelligence neuropathologist for glioma classification using deep learning on hematoxylin and eosin stained slide images and molecular markers

BACKGROUND

Pathological diagnosis of glioma subtypes is essential for treatment planning and prognosis. Standard histological diagnosis of glioma is based on postoperative hematoxylin and eosin stained slides by neuropathologists. With advancing artificial intelligence (AI), the aim of this study was to determine whether deep learning can be applied to glioma classification.

METHODS

A neuropathological diagnostic platform is designed comprising a slide scanner and deep convolutional neural networks (CNNs) to classify 5 major histological subtypes of glioma to assist pathologists. The CNNs were trained and verified on over 79 990 histological patch images from 267 patients. A logical algorithm is used when molecular profiles are available.

RESULTS

A new model of the squeeze-and-excitation block DenseNet with weighted cross-entropy (named SD-Net_WCE) is developed for the glioma classification task, which learns the recognizable features of glioma histology CNN-based independent diagnostic testing on data from 56 patients with 17 262 histological patch images demonstrated patch level accuracy of 86.5% and patient level accuracy of 87.5%. Histopathological classifications could be further amplified to integrated neuropathological diagnosis by 2 molecular markers (isocitrate dehydrogenase and 1p/19q).

CONCLUSION

The model is capable of solving multiple classification tasks and can satisfactorily classify glioma subtypes. The system provides a novel aid for the integrated neuropathological diagnostic workflow of glioma.

CardioNet: a manually curated database for artificial intelligence-based research on cardiovascular diseases

Background

Cardiovascular diseases (CVDs) are difficult to diagnose early and have risk factors that are easy to overlook. Early prediction and personalization of treatment through the use of artificial intelligence (AI) may help clinicians and patients manage CVDs more effectively. However, to apply AI approaches to CVDs data, it is necessary to establish and curate a specialized database based on electronic health records (EHRs) and include pre-processed unstructured data.

Methods

To build a suitable database (CardioNet) for CVDs that can utilize AI technology, contributing to the overall care of patients with CVDs. First, we collected the anonymized records of 748,474 patients who had visited the Asan Medical Center (AMC) or Ulsan University Hospital (UUH) because of CVDs. Second, we set clinically plausible criteria to remove errors and duplication. Third, we integrated unstructured data such as readings of medical examinations with structured data sourced from EHRs to create the CardioNet. We subsequently performed natural language processing to structuralize the significant variables associated with CVDs because most results of the principal CVD-related medical examinations are free-text readings. Additionally, to ensure interoperability for convergent multi-center research, we standardized the data using several codes that correspond to the common data model. Finally, we created the descriptive table (i.e., dictionary of the CardioNet) to simplify access and utilization of data for clinicians and engineers and continuously validated the data to ensure reliability.

Results

CardioNet is a comprehensive database that can serve as a training set for AI models and assist in all aspects of clinical management of CVDs. It comprises information extracted from EHRs and results of readings of CVD-related digital tests. It consists of 27 tables, a code-master table, and a descriptive table.

Conclusions

CardioNet database specialized in CVDs was established, with continuing data collection. We are actively supporting multi-center research, which may require further data processing, depending on the subject of the study. CardioNet will serve as the fundamental database for future CVD-related research projects.

Diagnosing Hirschsprung disease by detecting intestinal ganglion cells using label-free hyperspectral microscopy

Hirschsprung disease (HD) is a congenital disorder in the distal colon that is characterized by the absence of nerve ganglion cells in the diseased tissue. The primary treatment for HD is surgical intervention with resection of the aganglionic bowel. The accurate identification of the aganglionic segment depends on the histologic evaluation of multiple biopsies to determine the absence of ganglion cells in the tissue, which can be a time-consuming procedure. We investigate the feasibility of using a combination of label-free optical modalities, second harmonic generation (SHG); two-photon excitation autofluorescence (2PAF); and Raman spectroscopy (RS), to accurately locate and identify ganglion cells in murine intestinal tissue without the use of exogenous labels or dyes. We show that the image contrast provided by SHG and 2PAF signals allows for the visualization of the overall tissue morphology and localization of regions that may contain ganglion cells, while RS provides detailed multiplexed molecular information that can be used to accurately identify specific ganglion cells. Support vector machine, principal component analysis and linear discriminant analysis classification models were applied to the hyperspectral Raman data and showed that ganglion cells can be identified with a classification accuracy higher than 95%. Our findings suggest that a near real-time intraoperative histology method can be developed using these three optical modalities together that can aid pathologists and surgeons in rapid, accurate identification of ganglion cells to guide surgical decisions with minimal human intervention.

The Neurosurgeon's Armamentarium for Gliomas: An Update on Intraoperative Technologies to Improve Extent of Resection

Maximal safe resection is the standard of care in the neurosurgical treatment of high-grade gliomas. To aid surgeons in the operating room, adjuvant techniques and technologies centered around improving intraoperative visualization of tumor tissue have been developed. In this review, we will discuss the most advanced technologies, specifically fluorescence-guided surgery, intraoperative imaging, neuromonitoring modalities, and microscopic imaging techniques. The goal of these technologies is to improve detection of tumor tissue beyond what conventional microsurgery has permitted. We describe the various advances, the current state of the literature that have tested the utility of the different adjuvants in clinical practice, and future directions for improving intraoperative technologies.

An antibody-free liver cancer screening approach based on nanoplasmonics biosensing chips via spectrum-based deep learning

The clinical needs of rapidly screening liver cancer in large populations have asked for a facile and low-cost point-of-care testing (POCT) method. We present a nanoplasmonics biosensing chip (NBC) that would empower antibody-free detection with simplified analysis procedures for POCT. The cheaply fabricable NBC consists of multiple silver nanoparticle-decorated ZnO nanorods on cellulose filter paper and would enable one-drop blood tests through surface-enhanced Raman spectroscopy (SERS) detection. In this work, utilizing such an NBC and deep neural network (DNN) modeling, a direct serological detection platform was constructed for automatically identifying liver cancer within minutes. This chip could enhance Raman signals enough to be applied to POCT. A classification DNN model was established by spectrum-based deep learning with 1140 serum SERS spectra in equal proportions from hepatocellular carcinoma (HCC) patients and healthy individuals, achieving an identification accuracy of 91% on an external validation set of 100 spectra (50 HCC versus 50 healthy). The intelligent platform, based on the biosensing chip and DNN, has the potential for clinical applications and generalizable use in quickly screening or detecting other types of cancer.

State-of-the-art reviews predictive modeling in adult spinal deformity: applications of advanced analytics

Adult spinal deformity (ASD) is a complex and heterogeneous disease that can severely impact patients' lives. While it is clear that surgical correction can achieve significant improvement of spinopelvic parameters and quality of life measures in adults with spinal deformity, there remains a high risk of complication associated with surgical approaches to adult deformity. Over the past decade, utilization of surgical correction for ASD has increased dramatically as deformity correction techniques have become more refined and widely adopted. Along with this increase in surgical utilization, there has been a massive undertaking by spine surgeons to develop more robust models to predict postoperative outcomes in an effort to mitigate the relatively high complication rates. A large part of this revolution within spine surgery has been the gradual adoption of predictive analytics harnessing artificial intelligence through the use of machine learning algorithms. The development of predictive models to accurately prognosticate patient outcomes following ASD surgery represents a dramatic improvement over prior statistical models which are better suited for finding associations between variables than for their predictive utility. Machine learning models, which offer the ability to make more accurate and reproducible predictions, provide surgeons with a wide array of practical applications from augmenting clinical decision making to more wide-spread public health implications. The inclusion of these advanced computational techniques in spine practices will be paramount for improving the care of patients, by empowering both patients and surgeons to more specifically tailor clinical decisions to address individual health profiles and needs.

Biophotonic technologies for assessment of breast tumor surgical margins-A review

Breast conserving surgery (BCS) offering similar surgical outcomes as mastectomy while retaining breast cosmesis is becoming increasingly popular for the management of early stage breast cancers. However, its association with reoperation rates of 20% to 40% following incomplete tumor removal warrants the need for a fast and accurate intraoperative surgical margin assessment tool that offers cellular, structural and molecular information of the whole specimen surface to a clinically relevant depth. Biophotonic technologies are evolving to qualify as such an intraoperative tool for clinical assessment of breast cancer surgical margins at the microscopic and macroscopic scale. Herein, we review the current research in the application of biophotonic technologies such as photoacoustic imaging, Raman spectroscopy, multimodal multiphoton imaging, diffuse optical imaging and fluorescence imaging using medically approved dyes for breast cancer detection and/or tumor subtype differentiation toward intraoperative assessment of surgical margins in BCS specimens, and possible challenges in their route to clinical translation.

Intraoperative DNA methylation classification of brain tumors impacts neurosurgical strategy

BACKGROUND

Brain tumor surgery must balance the benefit of maximal resection against the risk of inflicting severe damage. The impact of increased resection is diagnosis-specific. However, the precise diagnosis is typically uncertain at surgery due to limitations of imaging and intraoperative histomorphological methods. Novel and accurate strategies for brain tumor classification are necessary to support personalized intraoperative neurosurgical treatment decisions. Here, we describe a fast and cost-efficient workflow for intraoperative classification of brain tumors based on DNA methylation profiles generated by low coverage nanopore sequencing and machine learning algorithms.

METHODS

We evaluated 6 independent cohorts containing 105 patients, including 50 pediatric and 55 adult patients. Ultra-low coverage whole-genome sequencing was performed on nanopore flow cells. Data were analyzed using copy number variation and ad hoc random forest classifier for the genome-wide methylation-based classification of the tumor.

RESULTS

Concordant classification was obtained between nanopore DNA methylation analysis and a full neuropathological evaluation in 93 of 105 (89%) cases. The analysis demonstrated correct diagnosis in 6/6 cases where frozen section evaluation was inconclusive. Results could be returned to the operating room at a median of 97 min (range 91-161 min). Precise classification of the tumor entity and subtype would have supported modification of the surgical strategy in 12 out of 20 patients evaluated intraoperatively.

CONCLUSION

Intraoperative nanopore sequencing combined with machine learning diagnostics was robust, sensitive, and rapid. This strategy allowed DNA methylation-based classification of the tumor to be returned to the surgeon within a timeframe that supports intraoperative decision making.

Review of Stimulated Raman Scattering Microscopy Techniques and Applications in the Biosciences

Stimulated Raman scattering (SRS) microscopy is a nonlinear optical imaging method for visualizing chemical content based on molecular vibrational bonds. Featuring high speed, high resolution, high sensitivity, high accuracy, and 3D sectioning, SRS microscopy has made tremendous progress toward biochemical information acquisition, cellular function investigation, and label-free medical diagnosis in the biosciences. In this review, the principle of SRS, system design, and data analysis are introduced, and the current innovations of the SRS system are reviewed. In particular, combined with various bio-orthogonal Raman tags, the applications of SRS microscopy in cell metabolism, tumor diagnosis, neuroscience, drug tracking, and microbial detection are briefly examined. The future prospects for SRS microscopy are also shared.

The Practical Application of Emerging Technologies Influencing the Diagnosis and Care of Patients With Primary Brain Tumors

Over the past decade, a variety of new and innovative technologies has led to important advances in the diagnosis and management of patients with primary malignant brain tumors. New approaches to surgical navigation and tumor localization, advanced imaging to define tumor biology and treatment response, and the widespread adoption of a molecularly defined integrated diagnostic paradigm that complements traditional histopathologic diagnosis continue to impact the day-to-day care of these patients. In the neuro-oncology clinic, discussions with patients about the role of tumor treating fields (TTFields) and the incorporation of next-generation sequencing (NGS) data into therapeutic decision-making are now a standard practice. This article summarizes newer applications of technology influencing the pathologic, neuroimaging, neurosurgical, and medical management of patients with malignant primary brain tumors.