Artificial-intelligence-based molecular classification of diffuse gliomas using rapid, label-free optical imaging

Predicting prognosis for epithelial ovarian cancer patients receiving bevacizumab treatment with CT-based deep learning

Epithelial ovarian cancer (EOC) presents considerable difficulties in prognostication and treatment strategy development. Bevacizumab, an anti-angiogenic medication, has demonstrated potential in enhancing progression-free survival (PFS) in EOC patients. Nevertheless, the identification of individuals at elevated risk of disease progression following treatment remains a challenging task. This study was to develop and validate a deep learning (DL) model using retrospectively collected computed tomography (CT) plain scans of inoperable and recurrent EOC patients receiving bevacizumab treatment diagnosed between January 2013 and January 2024. A total of 525 patients from three different institutions were retrospectively included in the study and divided into training set (N = 400), internal test set (N = 97) and external test set (N = 28). The model's performance was evaluated using Harrell's C-index. Patients were categorized into high-risk and low-risk group based on a predetermined cutoff in the training set. Additionally, a multimodal model was evaluated, incorporating the risk score generated by the DL model and the pretreatment level of carbohydrate antigen 125 as input variables. The Net Reclassification Improvement (NRI) metric quantified the reclassification performance of our optimal model in comparison to the International Federation of Gynecology and Obstetrics (FIGO) staging model. The results indicated that DL model achieved a PFS predictive C-index of 0.73 in the internal test set and a C-index of 0.61 in the external test set, along with hazard ratios of 34.24 in the training set (95% CI: 21.7, 54.1; P < 0.001) and 8.16 in the internal test set (95% CI: 2.5, 26.8; P < 0.001). The multimodal model demonstrated a C-index of 0.76 in the internal test set and a C-index of 0.64 in the external test set. Comparative analysis against FIGO staging revealed an NRI of 0.06 (P < 0.001) for the multimodal model. The model presents opportunities for prognostic assessment, treatment strategizing, and ongoing patient monitoring.

Illuminating the future of precision cancer surgery with fluorescence imaging and artificial intelligence convergence

Real-time and accurate guidance for tumor resection has long been anticipated by surgeons. In the past decade, the flourishing material science has made impressive progress in near-infrared fluorophores that may fulfill this purpose. Fluorescence imaging-guided surgery shows great promise for clinical application and has undergone widespread evaluations, though it still requires continuous improvements to transition this technique from bench to bedside. Concurrently, the rapid progress of artificial intelligence (AI) has revolutionized medicine, aiding in the screening, diagnosis, and treatment of human doctors. Incorporating AI helps enhance fluorescence imaging and is poised to bring major innovations to surgical guidance, thereby realizing precision cancer surgery. This review provides an overview of the principles and clinical evaluations of fluorescence-guided surgery. Furthermore, recent endeavors to synergize AI with fluorescence imaging were presented, and the benefits of this interdisciplinary convergence were discussed. Finally, several implementation strategies to overcome technical hurdles were proposed to encourage and inspire future research to expedite the clinical application of these revolutionary technologies.

Radical surgical resection with molecular margins is associated with improved survival in IDH wild-type glioblastoma

BACKGROUND

Survival is variable in patients with glioblastoma IDH wild-type (GBM), even after comparable surgical resection of radiographically detectable disease, highlighting the limitations of radiographic assessment of infiltrative tumor anatomy. The majority of postsurgical progressive events are failures within 2 cm of the resection margin, motivating supramaximal resection strategies to improve local control. However, which patients benefit from such radical resections remains unknown.

METHODS

We developed a predictive model to identify which IDH wild-type GBMs are amenable to radiographic gross-total resection (GTR). We then investigated whether GBM survival heterogeneity following GTR is correlated with microscopic tumor burden by analyzing tumor cell content at the surgical margin with a rapid qPCR-based method for detection of TERT promoter mutation.

RESULTS

Our predictive model for achievable GTR, developed on retrospective radiographic and molecular data of GBM patients undergoing resection, had an area under the curve of 0.83, sensitivity of 62%, and specificity of 90%. Prospective analysis of this model in 44 patients found that 89% of patients were correctly predicted to achieve a residual volume (RV) < 4.9cc. Of the 44 prospective patients undergoing rapid qPCR TERT promoter mutation analysis at the surgical margin, 7 had undetectable TERT mutation, of which 5 also had a GTR (RV < 1cc). In these 5 patients at 30 months follow-up, 75% showed no progression, compared to 0% in the group with TERT mutations detected at the surgical margin (P = .02).

CONCLUSIONS

These findings identify a subset of patients with GBM that may derive local control benefits from radical resection to undetectable molecular margins.

Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning

PURPOSE

Recent artificial intelligence algorithms aided intraoperative decision-making via stimulated Raman histology (SRH) during craniotomy. This study assesses deep learning algorithms for rapid intraoperative diagnosis from SRH images in small stereotactic-guided brain biopsies. It defines a minimum tissue sample size threshold to ensure diagnostic accuracy.

EXPERIMENTAL DESIGN

A prospective single-center study examined 121 SRH images from 84 patients with unclear intracranial lesions undergoing stereotactic brain biopsy. Unprocessed, label-free samples were imaged using a portable fiber laser Raman scattering microscope. Three deep learning models were tested to (i) identify tumorous/nontumorous tissue as qualitative biopsy control; (ii) subclassify into high-grade glioma (central nervous system World Health Organization grade 4), diffuse low-grade glioma (central nervous system World Health Organization grades 2-3), metastases, lymphoma, or gliosis; and (iii) molecularly subtype IDH and 1p/19q statuses of adult-type diffuse gliomas. Model predictions were evaluated against frozen section analysis and final neuropathologic diagnoses.

RESULTS

The first model identified tumorous/nontumorous tissue with 91.7% accuracy. Sample size on slides impacted accuracy in brain tumor subclassification (81.6%, κ = 0.72 frozen section; 73.9%, κ = 0.61 second model), with SRH images being smaller than hematoxylin and eosin images (4.1 ± 2.5 mm2 vs. 16.7 ± 8.2 mm2, P < 0.001). SRH images with more than 140 high-quality patches and a mean squeezed sample of 5.26 mm2 yielded 89.5% accuracy in subclassification and 93.9% in molecular subtyping of adult-type diffuse gliomas.

CONCLUSIONS

Artificial intelligence-based SRH image analysis is non-inferior to frozen section analysis in detecting and subclassifying brain tumors during small stereotactic-guided biopsies once a critical squeezed sample size is reached. Beyond frozen section analysis, it enables valid molecular glioma subtyping, allowing faster treatment decisions in the future; however, refinement is needed for long-term application.

Fast intraoperative detection of primary CNS lymphoma and differentiation from common CNS tumors using stimulated Raman histology and deep learning

Accurate intraoperative diagnosis is crucial for differentiating between primary CNS lymphoma (PCNSL) and other CNS entities, guiding surgical decision-making, but represents significant challenges due to overlapping histomorphological features, time constraints, and differing treatment strategies. We combined stimulated Raman histology (SRH) with deep learning to address this challenge. We imaged unprocessed, label-free tissue samples intraoperatively using a portable Raman scattering microscope, generating virtual H&E-like images within less than three minutes. We developed a deep learning pipeline called RapidLymphoma based on a self-supervised learning strategy to (1) detect PCNSL, (2) differentiate from other CNS entities, and (3) test the diagnostic performance in a prospective international multicenter cohort and two additional independent test cohorts. We trained on 54,000 SRH patch images sourced from surgical resections and stereotactic-guided biopsies, including various CNS tumor/non-tumor lesions. Training and test data were collected from four tertiary international medical centers. The final histopathological diagnosis served as ground-truth. In the prospective test cohort of PCNSL and non-PCNSL entities (n=160), RapidLymphoma achieved an overall balanced accuracy of 97.81% ±0.91, non-inferior to frozen section analysis in detecting PCNSL (100% vs. 78.94%). The additional test cohorts (n=420, n=59) reached balanced accuracy rates of 95.44% ±0.74 and 95.57% ±2.47 in differentiating IDH-wildtype diffuse gliomas and various brain metastasis from PCNSL. Visual heatmaps revealed RapidLymphoma's capabilities to detect class-specific histomorphological key features. RapidLymphoma is valid and reliable in detecting PCNSL and differentiating from other CNS entities within three minutes, as well as visual feedback in an intraoperative setting. This leads to fast clinical decision-making and further treatment strategy planning.

Enhancing neuro-oncology care through equity-driven applications of artificial intelligence

The disease course and clinical outcome for brain tumor patients depend not only on the molecular and histological features of the tumor but also on the patient's demographics and social determinants of health. While current investigations in neuro-oncology have broadly utilized artificial intelligence (AI) to enrich tumor diagnosis and more accurately predict treatment response, postoperative complications, and survival, equity-driven applications of AI have been limited. However, AI applications to advance health equity in the broader medical field have the potential to serve as practical blueprints to address known disparities in neuro-oncologic care. In this consensus review, we will describe current applications of AI in neuro-oncology, postulate viable AI solutions for the most pressing inequities in neuro-oncology based on broader literature, propose a framework for the effective integration of equity into AI-based neuro-oncology research, and close with the limitations of AI.

Matrix metalloproteinase 9 expression and glioblastoma survival prediction using machine learning on digital pathological images

This study aimed to apply pathomics to predict Matrix metalloproteinase 9 (MMP9) expression in glioblastoma (GBM) and investigate the underlying molecular mechanisms associated with pathomics. Here, we included 127 GBM patients, 78 of whom were randomly allocated to the training and test cohorts for pathomics modeling. The prognostic significance of MMP9 was assessed using Kaplan-Meier and Cox regression analyses. PyRadiomics was used to extract the features of H&E-stained whole slide images. Feature selection was performed using the maximum relevance and minimum redundancy (mRMR) and recursive feature elimination (RFE) algorithms. Prediction models were created using support vector machines (SVM) and logistic regression (LR). The performance was assessed using ROC analysis, calibration curve assessment, and decision curve analysis. MMP9 expression was elevated in patients with GBM. This was an independent prognostic factor for GBM. Six features were selected for the pathomics model. The area under the curves (AUCs) of the training and test subsets were 0.828 and 0.808, respectively, for the SVM model and 0.778 and 0.754, respectively, for the LR model. The C-index and calibration plots exhibited effective estimation abilities. The pathomics score calculated using the SVM model was highly correlated with overall survival time. These findings indicate that MMP9 plays a crucial role in GBM development and prognosis. Our pathomics model demonstrated high efficacy for predicting MMP9 expression levels and prognosis of patients with GBM.

Convolutional neural network advances in demosaicing for fluorescent cancer imaging with color-near-infrared sensors

Significance

Single-chip imaging devices featuring vertically stacked photodiodes and pixelated spectral filters are advancing multi-dye imaging methods for cancer surgeries, though this innovation comes with a compromise in spatial resolution. To mitigate this drawback, we developed a deep convolutional neural network (CNN) aimed at demosaicing the color and near-infrared (NIR) channels, with its performance validated on both pre-clinical and clinical datasets.

Aim

We introduce an optimized deep CNN designed for demosaicing both color and NIR images obtained using a hexachromatic imaging sensor.

Approach

A residual CNN was fine-tuned and trained on a dataset of color images and subsequently assessed on a series of dual-channel, color, and NIR images to demonstrate its enhanced performance compared with traditional bilinear interpolation.

Results

Our optimized CNN for demosaicing color and NIR images achieves a reduction in the mean square error by 37% for color and 40% for NIR, respectively, and enhances the structural dissimilarity index by 37% across both imaging modalities in pre-clinical data. In clinical datasets, the network improves the mean square error by 35% in color images and 42% in NIR images while enhancing the structural dissimilarity index by 39% in both imaging modalities.

Conclusions

We showcase enhancements in image resolution for both color and NIR modalities through the use of an optimized CNN tailored for a hexachromatic image sensor. With the ongoing advancements in graphics card computational power, our approach delivers significant improvements in resolution that are feasible for real-time execution in surgical environments.

Combination of MRI-based prediction and CRISPR/Cas12a-based detection for IDH genotyping in glioma

Early identification of IDH mutation status is of great significance in clinical therapeutic decision-making in the treatment of glioma. We demonstrate a technological solution to improve the accuracy and reliability of IDH mutation detection by combining MRI-based prediction and a CRISPR-based automatic integrated gene detection system (AIGS). A model was constructed to predict the IDH mutation status using whole slices in MRI scans with a Transformer neural network, and the predictive model achieved accuracies of 0.93, 0.87, and 0.84 using the internal and two external test sets, respectively. Additionally, CRISPR/Cas12a-based AIGS was constructed, and AIGS achieved 100% diagnostic accuracy in terms of IDH detection using both frozen tissue and FFPE samples in one hour. Moreover, the feature attribution of our predictive model was assessed using GradCAM, and the highest correlations with tumor cell percentages in enhancing and IDH-wildtype gliomas were found to have GradCAM importance (0.65 and 0.5, respectively). This MRI-based predictive model could, therefore, guide biopsy for tumor-enriched, which would ensure the veracity and stability of the rapid detection results. The combination of our predictive model and AIGS improved the early determination of IDH mutation status in glioma patients. This combined system of MRI-based prediction and CRISPR/Cas12a-based detection can be used to guide biopsy, resection, and radiation for glioma patients to improve patient outcomes.

In vivo organoid growth monitoring by stimulated Raman histology

Patient-derived tumor organoids have emerged as a crucial tool for assessing the efficacy of chemotherapy and conducting preclinical drug screenings. However, the conventional histological investigation of these organoids necessitates their devitalization through fixation and slicing, limiting their utility to a single-time analysis. Here, we use stimulated Raman histology (SRH) to demonstrate non-destructive, label-free virtual staining of 3D organoids, while preserving their viability and growth. This novel approach provides contrast similar to conventional staining methods, allowing for the continuous monitoring of organoids over time. Our results demonstrate that SRH transforms organoids from one-time use products into repeatable models, facilitating the efficient selection of effective drug combinations. This advancement holds promise for personalized cancer treatment, allowing for the dynamic assessment and optimization of chemotherapy treatments in patient-specific contexts.

Viewing early life without labels: optical approaches for imaging the early embryo†

Embryo quality is an important determinant of successful implantation and a resultant live birth. Current clinical approaches for evaluating embryo quality rely on subjective morphology assessments or an invasive biopsy for genetic testing. However, both approaches can be inherently inaccurate and crucially, fail to improve the live birth rate following the transfer of in vitro produced embryos. Optical imaging offers a potential non-invasive and accurate avenue for assessing embryo viability. Recent advances in various label-free optical imaging approaches have garnered increased interest in the field of reproductive biology due to their ability to rapidly capture images at high resolution, delivering both morphological and molecular information. This burgeoning field holds immense potential for further development, with profound implications for clinical translation. Here, our review aims to: (1) describe the principles of various imaging systems, distinguishing between approaches that capture morphological and molecular information, (2) highlight the recent application of these technologies in the field of reproductive biology, and (3) assess their respective merits and limitations concerning the capacity to evaluate embryo quality. Additionally, the review summarizes challenges in the translation of optical imaging systems into routine clinical practice, providing recommendations for their future development. Finally, we identify suitable imaging approaches for interrogating the mechanisms underpinning successful embryo development.

Label-free optical imaging for brain cancer assessment

Advances in label-free optical imaging offer a promising avenue for brain cancer assessment, providing high-resolution, real-time insights without the need for radiation or exogeneous agents. These cost-effective and intricately detailed techniques overcome the limitations inherent in magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET) scans by offering superior resolution and more readily accessible imaging options. This comprehensive review explores a variety of such methods, including photoacoustic imaging (PAI), optical coherence tomography (OCT), Raman imaging, and IR microscopy. It focuses on their roles in the detection, diagnosis, and management of brain tumors. By highlighting recent advances in these imaging techniques, the review aims to underscore the importance of label-free optical imaging in enhancing early detection and refining therapeutic strategies for brain cancer.

Accurate and rapid molecular subgrouping of high-grade glioma via deep learning-assisted label-free fiber-optic Raman spectroscopy

Molecular genetics is highly related with prognosis of high-grade glioma. Accordingly, the latest WHO guideline recommends that molecular subgroups of the genes, including IDH, 1p/19q, MGMT, TERT, EGFR, Chromosome 7/10, CDKN2A/B, need to be detected to better classify glioma and guide surgery and treatment. Unfortunately, there is no preoperative or intraoperative technology available for accurate and comprehensive molecular subgrouping of glioma. Here, we develop a deep learning-assisted fiber-optic Raman diagnostic platform for accurate and rapid molecular subgrouping of high-grade glioma. Specifically, a total of 2,354 fingerprint Raman spectra was obtained from 743 tissue sites (astrocytoma: 151; oligodendroglioma: 150; glioblastoma (GBM): 442) of 44 high-grade glioma patients. The convolutional neural networks (ResNet) model was then established and optimized for molecular subgrouping. The mean area under receiver operating characteristic curves (AUC) for identifying the molecular subgroups of high-grade glioma reached 0.904, with mean sensitivity of 83.3%, mean specificity of 85.0%, mean accuracy of 83.3%, and mean time expense of 10.6 s. The diagnosis performance using ResNet model was shown to be superior to PCA-SVM and UMAP models, suggesting that high dimensional information from Raman spectra would be helpful. In addition, for the molecular subgroups of GBM, the mean AUC reached 0.932, with mean sensitivity of 87.8%, mean specificity of 83.6%, and mean accuracy of 84.1%. Furthermore, according to saliency maps, the specific Raman features corresponding to tumor-associated biomolecules (e.g. nucleic acid, tyrosine, tryptophan, cholesteryl ester, fatty acid, and collagen) were found to contribute to the accurate molecular subgrouping. Collectively, this study opens up new opportunities for accurate and rapid molecular subgrouping of high-grade glioma, which would assist optimal surgical resection and instant post-operative decision-making.

Optical fiber biosensors toward in vivo detection

This review takes stock of the various optical fiber-based biosensors that could be used for in vivo applications. We discuss the characteristics that biosensors must have to be suitable for such applications and the corresponding transduction modes. In particular, we focus on optical fiber biosensors based on fluorescence, evanescent wave, plasmonics, interferometry, and Raman phenomenon. The operational principles, implemented solutions, and performances are described and debated. The different sensing configurations, such as the side- and tip-based fiber biosensors, are illustrated, and their adaptation for in vivo measurements is discussed. The required implementation of multiplexed biosensing on optical fibers is shown. In particular, the use of multi-fiber assemblies, one of the most optimal configurations for multiplexed detection, is discussed. Different possibilities for multiple localized functionalizations on optical fibers are presented. A final section is devoted to the practical in vivo use of fiber-based biosensors, covering regulatory, sterilization, and packaging aspects. Finally, the trends and required improvements in this promising and emerging field are analyzed and discussed.

Noninvasive Molecular Subtyping of Pediatric Low-Grade Glioma with Self-Supervised Transfer Learning

Purpose To develop and externally test a scan-to-prediction deep learning pipeline for noninvasive, MRI-based BRAF mutational status classification for pediatric low-grade glioma. Materials and Methods This retrospective study included two pediatric low-grade glioma datasets with linked genomic and diagnostic T2-weighted MRI data of patients: Dana-Farber/Boston Children's Hospital (development dataset, n = 214 [113 (52.8%) male; 104 (48.6%) BRAF wild type, 60 (28.0%) BRAF fusion, and 50 (23.4%) BRAF V600E]) and the Children's Brain Tumor Network (external testing, n = 112 [55 (49.1%) male; 35 (31.2%) BRAF wild type, 60 (53.6%) BRAF fusion, and 17 (15.2%) BRAF V600E]). A deep learning pipeline was developed to classify BRAF mutational status (BRAF wild type vs BRAF fusion vs BRAF V600E) via a two-stage process: (a) three-dimensional tumor segmentation and extraction of axial tumor images and (b) section-wise, deep learning-based classification of mutational status. Knowledge-transfer and self-supervised approaches were investigated to prevent model overfitting, with a primary end point of the area under the receiver operating characteristic curve (AUC). To enhance model interpretability, a novel metric, center of mass distance, was developed to quantify the model attention around the tumor. Results A combination of transfer learning from a pretrained medical imaging-specific network and self-supervised label cross-training (TransferX) coupled with consensus logic yielded the highest classification performance with an AUC of 0.82 (95% CI: 0.72, 0.91), 0.87 (95% CI: 0.61, 0.97), and 0.85 (95% CI: 0.66, 0.95) for BRAF wild type, BRAF fusion, and BRAF V600E, respectively, on internal testing. On external testing, the pipeline yielded an AUC of 0.72 (95% CI: 0.64, 0.86), 0.78 (95% CI: 0.61, 0.89), and 0.72 (95% CI: 0.64, 0.88) for BRAF wild type, BRAF fusion, and BRAF V600E, respectively. Conclusion Transfer learning and self-supervised cross-training improved classification performance and generalizability for noninvasive pediatric low-grade glioma mutational status prediction in a limited data scenario. Keywords: Pediatrics, MRI, CNS, Brain/Brain Stem, Oncology, Feature Detection, Diagnosis, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2024.

Virtual Staining of Nonfixed Tissue Histology

Surgical pathology workflow involves multiple labor-intensive steps, such as tissue removal, fixation, embedding, sectioning, staining, and microscopic examination. This process is time-consuming and costly and requires skilled technicians. In certain clinical scenarios, such as intraoperative consultations, there is a need for faster histologic evaluation to provide real-time surgical guidance. Currently, frozen section techniques involving hematoxylin and eosin (H&E) staining are used for intraoperative pathology consultations. However, these techniques have limitations, including a turnaround time of 20 to 30 minutes, staining artifacts, and potential tissue loss, negatively impacting accurate diagnosis. To address these challenges, researchers are exploring alternative optical imaging modalities for rapid microscopic tissue imaging. These modalities differ in optical characteristics, tissue preparation requirements, imaging equipment, and output image quality and format. Some of these imaging methods have been combined with computational algorithms to generate H&E-like images, which could greatly facilitate their adoption by pathologists. Here, we provide a comprehensive, organ-specific review of the latest advancements in emerging imaging modalities applied to nonfixed human tissue. We focused on studies that generated H&E-like images evaluated by pathologists. By presenting up-to-date research progress and clinical utility, this review serves as a valuable resource for scholars and clinicians, covering some of the major technical developments in this rapidly evolving field. It also offers insights into the potential benefits and drawbacks of alternative imaging modalities and their implications for improving patient care.

Artificial intelligence in neurology: opportunities, challenges, and policy implications

Neurological conditions are the leading cause of disability and mortality combined, demanding innovative, scalable, and sustainable solutions. Brain health has become a global priority with adoption of the World Health Organization's Intersectoral Global Action Plan in 2022. Simultaneously, rapid advancements in artificial intelligence (AI) are revolutionizing neurological research and practice. This scoping review of 66 original articles explores the value of AI in neurology and brain health, systematizing the landscape for emergent clinical opportunities and future trends across the care trajectory: prevention, risk stratification, early detection, diagnosis, management, and rehabilitation. AI's potential to advance personalized precision neurology and global brain health directives hinges on resolving core challenges across four pillars-models, data, feasibility/equity, and regulation/innovation-through concerted pursuit of targeted recommendations. Paramount actions include swift, ethical, equity-focused integration of novel technologies into clinical workflows, mitigating data-related issues, counteracting digital inequity gaps, and establishing robust governance frameworks balancing safety and innovation.

Electro-Optical Multiclassification Platform for Minimizing Occasional Inaccuracy in Point-of-Care Biomarker Detection

On-site diagnostic tests that accurately identify disease biomarkers lay the foundation for self-healthcare applications. However, these tests routinely rely on single-mode signals and suffer from insufficient accuracy, especially for multiplexed point-of-care tests (POCTs) within a few minutes. Here, this work develops a dual-mode multiclassification diagnostic platform that integrates an electrochemiluminescence sensor and a field-effect transistor sensor in a microfluidic chip. The microfluidic channel guides the testing samples to flow across electro-optical sensor units, which produce dual-mode readouts by detecting infectious biomarkers of tuberculosis (TB), human rhinovirus (HRV), and group B streptococcus (GBS). Then, machine-learning classifiers generate three-dimensional (3D) hyperplanes to diagnose different diseases. Dual-mode readouts derived from distinct mechanisms enhance the anti-interference ability physically, and machine-learning-aided diagnosis in high-dimensional space reduces the occasional inaccuracy mathematically. Clinical validation studies with 501 unprocessed samples indicate that the platform has an accuracy approaching 99%, higher than the 77%-93% accuracy of rapid point-of-care testing technologies at 100% statistical power (>150 clinical tests). Moreover, the diagnosis time is 5 min without a trade-off of accuracy. This work solves the occasional inaccuracy issue of rapid on-site diagnosis, endowing POCT systems with the same accuracy as laboratory tests and holding unique prospects for complicated scenes of personalized healthcare.

Artificial intelligence in neuro-oncology: advances and challenges in brain tumor diagnosis, prognosis, and precision treatment

This review delves into the most recent advancements in applying artificial intelligence (AI) within neuro-oncology, specifically emphasizing work on gliomas, a class of brain tumors that represent a significant global health issue. AI has brought transformative innovations to brain tumor management, utilizing imaging, histopathological, and genomic tools for efficient detection, categorization, outcome prediction, and treatment planning. Assessing its influence across all facets of malignant brain tumor management- diagnosis, prognosis, and therapy- AI models outperform human evaluations in terms of accuracy and specificity. Their ability to discern molecular aspects from imaging may reduce reliance on invasive diagnostics and may accelerate the time to molecular diagnoses. The review covers AI techniques, from classical machine learning to deep learning, highlighting current applications and challenges. Promising directions for future research include multimodal data integration, generative AI, large medical language models, precise tumor delineation and characterization, and addressing racial and gender disparities. Adaptive personalized treatment strategies are also emphasized for optimizing clinical outcomes. Ethical, legal, and social implications are discussed, advocating for transparency and fairness in AI integration for neuro-oncology and providing a holistic understanding of its transformative impact on patient care.

The genetic architecture of multimodal human brain age

The complex biological mechanisms underlying human brain aging remain incompletely understood. This study investigated the genetic architecture of three brain age gaps (BAG) derived from gray matter volume (GM-BAG), white matter microstructure (WM-BAG), and functional connectivity (FC-BAG). We identified sixteen genomic loci that reached genome-wide significance (P-value < 5×10-8). A gene-drug-disease network highlighted genes linked to GM-BAG for treating neurodegenerative and neuropsychiatric disorders and WM-BAG genes for cancer therapy. GM-BAG displayed the most pronounced heritability enrichment in genetic variants within conserved regions. Oligodendrocytes and astrocytes, but not neurons, exhibited notable heritability enrichment in WM and FC-BAG, respectively. Mendelian randomization identified potential causal effects of several chronic diseases on brain aging, such as type 2 diabetes on GM-BAG and AD on WM-BAG. Our results provide insights into the genetics of human brain aging, with clinical implications for potential lifestyle and therapeutic interventions. All results are publicly available at https://labs.loni.usc.edu/medicine .

Preliminary Evidence of the Use of Generative AI in Health Care Clinical Services: Systematic Narrative Review

BACKGROUND

Generative artificial intelligence tools and applications (GenAI) are being increasingly used in health care. Physicians, specialists, and other providers have started primarily using GenAI as an aid or tool to gather knowledge, provide information, train, or generate suggestive dialogue between physicians and patients or between physicians and patients' families or friends. However, unless the use of GenAI is oriented to be helpful in clinical service encounters that can improve the accuracy of diagnosis, treatment, and patient outcomes, the expected potential will not be achieved. As adoption continues, it is essential to validate the effectiveness of the infusion of GenAI as an intelligent technology in service encounters to understand the gap in actual clinical service use of GenAI.

OBJECTIVE

This study synthesizes preliminary evidence on how GenAI assists, guides, and automates clinical service rendering and encounters in health care The review scope was limited to articles published in peer-reviewed medical journals.

METHODS

We screened and selected 0.38% (161/42,459) of articles published between January 1, 2020, and May 31, 2023, identified from PubMed. We followed the protocols outlined in the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to select highly relevant studies with at least 1 element on clinical use, evaluation, and validation to provide evidence of GenAI use in clinical services. The articles were classified based on their relevance to clinical service functions or activities using the descriptive and analytical information presented in the articles.

RESULTS

Of 161 articles, 141 (87.6%) reported using GenAI to assist services through knowledge access, collation, and filtering. GenAI was used for disease detection (19/161, 11.8%), diagnosis (14/161, 8.7%), and screening processes (12/161, 7.5%) in the areas of radiology (17/161, 10.6%), cardiology (12/161, 7.5%), gastrointestinal medicine (4/161, 2.5%), and diabetes (6/161, 3.7%). The literature synthesis in this study suggests that GenAI is mainly used for diagnostic processes, improvement of diagnosis accuracy, and screening and diagnostic purposes using knowledge access. Although this solves the problem of knowledge access and may improve diagnostic accuracy, it is oriented toward higher value creation in health care.

CONCLUSIONS

GenAI informs rather than assisting or automating clinical service functions in health care. There is potential in clinical service, but it has yet to be actualized for GenAI. More clinical service-level evidence that GenAI is used to streamline some functions or provides more automated help than only information retrieval is needed. To transform health care as purported, more studies related to GenAI applications must automate and guide human-performed services and keep up with the optimism that forward-thinking health care organizations will take advantage of GenAI.

A transferrin receptor targeting dual-modal MR/NIR fluorescent imaging probe for glioblastoma diagnosis

The prognosis of glioblastoma (GBM) remains challenging, primarily due to the lack of a precise, effective imaging technique for comprehensively characterization. Addressing GBM diagnostic challenges, our study introduces an innovative dual-modal imaging that merges near-infrared (NIR) fluorescent imaging with magnetic resonance imaging (MRI). This method employs superparamagnetic iron oxide nanoparticles coated with NIR fluorescent dyes, specifically Cyanine 7, and targeted peptides. This synthetic probe facilitates MRI functionality through superparamagnetic iron oxide nanoparticles, provides NIR imaging capability via Cyanine 7 and enhances tumor targeting trough peptide interactions, offering a comprehensive diagnostic tool for GBM. Notably, the probe traverses the blood-brain barrier, targeting GBM in vivo via peptides, producing clear and discernible images in both modalities. Cytotoxicity and histopathology assessments confirm the probe's favorable safety profile. These findings suggest that the dual-modal MR\NIR fluorescent imaging probe could revolutionize GBM prognosis and survival rates, which can also be extended to other tumors type.

Temporal change of DNA methylation subclasses between matched newly diagnosed and recurrent glioblastoma

The longitudinal transition of phenotypes is pivotal in glioblastoma treatment resistance and DNA methylation emerged as an important tool for classifying glioblastoma phenotypes. We aimed to characterize DNA methylation subclass heterogeneity during progression and assess its clinical impact. Matched tissues from 47 glioblastoma patients were subjected to DNA methylation profiling, including CpG-site alterations, tissue and serum deconvolution, mass spectrometry, and immunoassay. Effects of clinical characteristics on temporal changes and outcomes were studied. Among 47 patients, 8 (17.0%) had non-matching classifications at recurrence. In the remaining 39 cases, 28.2% showed dominant DNA methylation subclass transitions, with 72.7% being a mesenchymal subclass. In general, glioblastomas with a subclass transition showed upregulated metabolic processes. Newly diagnosed glioblastomas with mesenchymal transition displayed increased stem cell-like states and decreased immune components at diagnosis and exhibited elevated immune signatures and cytokine levels in serum. In contrast, tissue of recurrent glioblastomas with mesenchymal transition showed increased immune components but decreased stem cell-like states. Survival analyses revealed comparable outcomes for patients with and without subclass transitions. This study demonstrates a temporal heterogeneity of DNA methylation subclasses in 28.2% of glioblastomas, not impacting patient survival. Changes in cell state composition associated with subclass transition may be crucial for recurrent glioblastoma targeted therapies.

Intraoperative Integrated Diagnostic System for Malignant Central Nervous System Tumors

PURPOSE

The 2021 World Health Organization (WHO) classification of central nervous system (CNS) tumors uses an integrated approach involving histopathology and molecular profiling. Because majority of adult malignant brain tumors are gliomas and primary CNS lymphomas (PCNSL), rapid differentiation of these diseases is required for therapeutic decisions. In addition, diffuse gliomas require molecular information on single-nucleotide variants (SNV), such as IDH1/2. Here, we report an intraoperative integrated diagnostic (i-ID) system to classify CNS malignant tumors, which updates legacy frozen-section (FS) diagnosis through incorporation of a qPCR-based genotyping assay.

EXPERIMENTAL DESIGN

FS evaluation, including GFAP and CD20 rapid IHC, was performed on adult malignant CNS tumors. PCNSL was diagnosed through positive CD20 and negative GFAP immunostaining. For suspected glioma, genotyping for IDH1/2, TERT SNV, and CDKN2A copy-number alteration was routinely performed, whereas H3F3A and BRAF SNV were assessed for selected cases. i-ID was determined on the basis of the 2021 WHO classification and compared with the permanent integrated diagnosis (p-ID) to assess its reliability.

RESULTS

After retrospectively analyzing 153 cases, 101 cases were prospectively examined using the i-ID system. Assessment of IDH1/2, TERT, H3F3AK27M, BRAFV600E, and CDKN2A alterations with i-ID and permanent genomic analysis was concordant in 100%, 100%, 100%, 100%, and 96.4%, respectively. Combination with FS and intraoperative genotyping assay improved diagnostic accuracy in gliomas. Overall, i-ID matched with p-ID in 80/82 (97.6%) patients with glioma and 18/19 (94.7%) with PCNSL.

CONCLUSIONS

The i-ID system provides reliable integrated diagnosis of adult malignant CNS tumors.

Artificial intelligence in neuro-oncology

Artificial intelligence (AI) describes the application of computer algorithms to the solution of problems that have traditionally required human intelligence. Although formal work in AI has been slowly advancing for almost 70 years, developments in the last decade, and particularly in the last year, have led to an explosion of AI applications in multiple fields. Neuro-oncology has not escaped this trend. Given the expected integration of AI-based methods to neuro-oncology practice over the coming years, we set to provide an overview of existing technologies as they are applied to the neuropathology and neuroradiology of brain tumors. We highlight current benefits and limitations of these technologies and offer recommendations on how to appraise novel AI-tools as they undergo consideration for integration into clinical workflows.

Rapid visualization of PD-L1 expression level in glioblastoma immune microenvironment via machine learning cascade-based Raman histopathology

INTRODUCTION

Combination immunotherapy holds promise for improving survival in responsive glioblastoma (GBM) patients. Programmed death-ligand 1 (PD-L1) expression in immune microenvironment (IME) is the most important predictive biomarker for immunotherapy. Due to the heterogeneous distribution of PD-L1, post-operative histopathology fails to accurately capture its expression in residual tumors, making intra-operative diagnosis crucial for GBM treatment strategies. However, the current methods for evaluating the expression of PD-L1 are still time-consuming.

OBJECTIVE

To overcome the PD-L1 heterogeneity and enable rapid, accurate, and label-free imaging of PD-L1 expression level in GBM IME at the tissue level.

METHODS

We proposed a novel intra-operative diagnostic method, Machine Learning Cascade (MLC)-based Raman histopathology, which uses a coordinate localization system (CLS), hierarchical clustering analysis (HCA), support vector machine (SVM), and similarity analysis (SA). This method enables visualization of PD-L1 expression in glioma cells, CD8+ T cells, macrophages, and normal cells in addition to the tumor/normal boundary. The study quantified PD-L1 expression levels using the tumor proportion, combined positive, and cellular composition scores (TPS, CPS, and CCS, respectively) based on Raman data. Furthermore, the association between Raman spectral features and biomolecules was examined biochemically.

RESULTS

The entire process from signal collection to visualization could be completed within 30 min. In an orthotopic glioma mouse model, the MLC-based Raman histopathology demonstrated a high average accuracy (0.990) for identifying different cells and exhibited strong concordance with multiplex immunofluorescence (84.31 %) and traditional pathologists' scoring (R2 ≥ 0.9). Moreover, the peak intensities at 837 and 874 cm-1 showed a positive linear correlation with PD-L1 expression level.

CONCLUSIONS

This study introduced a new and extendable diagnostic method to achieve rapid and accurate visualization of PD-L1 expression in GBM IMB at the tissular level, leading to great potential in GBM intraoperative diagnosis for guiding surgery and post-operative immunotherapy.

Rapid intraoperative multi-molecular diagnosis of glioma with ultrasound radio frequency signals and deep learning

BACKGROUND

Molecular diagnosis is crucial for biomarker-assisted glioma resection and management. However, some limitations of current molecular diagnostic techniques prevent their widespread use intraoperatively. With the unique advantages of ultrasound, this study developed a rapid intraoperative molecular diagnostic method based on ultrasound radio-frequency signals.

METHODS

We built a brain tumor ultrasound bank with 169 cases enrolled since July 2020, of which 43483 RF signal patches from 67 cases with a pathological diagnosis of glioma were a retrospective cohort for model training and validation. IDH1 and TERT promoter (TERTp) mutations and 1p/19q co-deletion were detected by next-generation sequencing. We designed a spatial-temporal integration model (STIM) to diagnose the three molecular biomarkers, thus establishing a rapid intraoperative molecular diagnostic system for glioma, and further analysed its consistency with the fifth edition of the WHO Classification of Tumors of the Central Nervous System (WHO CNS5). We tested STIM in 16-case prospective cohorts, which contained a total of 10384 RF signal patches. Two other RF-based classical models were used for comparison. Further, we included 20 cases additional prospective data for robustness test (ClinicalTrials.govNCT05656053).

FINDINGS

In the retrospective cohort, STIM achieved a mean accuracy and AUC of 0.9190 and 0.9650 (95% CI, 0.94-0.99) respectively for the three molecular biomarkers, with a total time of 3 s and a 96% match to WHO CNS5. In the prospective cohort, the diagnostic accuracy of STIM is 0.85 ± 0.04 (mean ± SD) for IDH1, 0.84 ± 0.05 for TERTp, and 0.88 ± 0.04 for 1p/19q. The AUC is 0.89 ± 0.02 (95% CI, 0.84-0.94) for IDH1, 0.80 ± 0.04 (95% CI, 0.71-0.89) for TERTp, and 0.85 ± 0.06 (95% CI, 0.73-0.98) for 1p/19q. Compared to the second best available method based on RF signal, the diagnostic accuracy of STIM is improved by 16.70% and the AUC is improved by 19.23% on average.

INTERPRETATION

STIM is a rapid, cost-effective, and easy-to-manipulate AI method to perform real-time intraoperative molecular diagnosis. In the future, it may help neurosurgeons designate personalized surgical plans and predict survival outcomes.

FUNDING

A full list of funding bodies that contributed to this study can be found in the Acknowledgements section.

Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment

Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep learning and machine learning in the healthcare sector and the availability of highly specialized cancer datasets. Here, we review new artificial intelligence approaches and how they are being used in oncology. We describe how artificial intelligence might be used in the detection, prognosis, and administration of cancer treatments and introduce the use of the latest large language models such as ChatGPT in oncology clinics. We highlight artificial intelligence applications for omics data types, and we offer perspectives on how the various data types might be combined to create decision-support tools. We also evaluate the present constraints and challenges to applying artificial intelligence in precision oncology. Finally, we discuss how current challenges may be surmounted to make artificial intelligence useful in clinical settings in the future.

The Genetic Architecture of Multimodal Human Brain Age

The complex biological mechanisms underlying human brain aging remain incompletely understood, involving multiple body organs and chronic diseases. In this study, we used multimodal magnetic resonance imaging and artificial intelligence to examine the genetic architecture of the brain age gap (BAG) derived from gray matter volume (GM-BAG, N=31,557 European ancestry), white matter microstructure (WM-BAG, N=31,674), and functional connectivity (FC-BAG, N=32,017). We identified sixteen genomic loci that reached genome-wide significance (P-value<5×10-8). A gene-drug-disease network highlighted genes linked to GM-BAG for treating neurodegenerative and neuropsychiatric disorders and WM-BAG genes for cancer therapy. GM-BAG showed the highest heritability enrichment for genetic variants in conserved regions, whereas WM-BAG exhibited the highest heritability enrichment in the 5' untranslated regions; oligodendrocytes and astrocytes, but not neurons, showed significant heritability enrichment in WM and FC-BAG, respectively. Mendelian randomization identified potential causal effects of several exposure variables on brain aging, such as type 2 diabetes on GM-BAG (odds ratio=1.05 [1.01, 1.09], P-value=1.96×10-2) and AD on WM-BAG (odds ratio=1.04 [1.02, 1.05], P-value=7.18×10-5). Overall, our results provide valuable insights into the genetics of human brain aging, with clinical implications for potential lifestyle and therapeutic interventions. All results are publicly available at the MEDICINE knowledge portal: https://labs.loni.usc.edu/medicine.

Unlocking glioma genetics with deep learning

The AI era in medicine has ushered in new opportunities to improve the diagnosis and treatment of human disease. CHARM, an AI algorithm described in this issue,1 has the potential to streamline molecular classification, intraoperative diagnosis, surgical decision making, and trial enrollment for glioma patients.

Machine learning for cryosection pathology predicts the 2021 WHO classification of glioma

BACKGROUND

Timely and accurate intraoperative cryosection evaluations remain the gold standard for guiding surgical treatments for gliomas. However, the tissue-freezing process often generates artifacts that make histologic interpretation difficult. In addition, the 2021 WHO Classification of Tumors of the Central Nervous System incorporates molecular profiles in the diagnostic categories, so standard visual evaluation of cryosections alone cannot completely inform diagnoses based on the new classification system.

METHODS

To address these challenges, we develop the context-aware Cryosection Histopathology Assessment and Review Machine (CHARM) using samples from 1,524 glioma patients from three different patient populations to systematically analyze cryosection slides.

FINDINGS

Our CHARM models successfully identified malignant cells (AUROC = 0.98 ± 0.01 in the independent validation cohort), distinguished isocitrate dehydrogenase (IDH)-mutant tumors from wild type (AUROC = 0.79-0.82), classified three major types of molecularly defined gliomas (AUROC = 0.88-0.93), and identified the most prevalent subtypes of IDH-mutant tumors (AUROC = 0.89-0.97). CHARM further predicts clinically important genetic alterations in low-grade glioma, including ATRX, TP53, and CIC mutations, CDKN2A/B homozygous deletion, and 1p/19q codeletion via cryosection images.

CONCLUSIONS

Our approaches accommodate the evolving diagnostic criteria informed by molecular studies, provide real-time clinical decision support, and will democratize accurate cryosection diagnoses.

FUNDING

Supported in part by the National Institute of General Medical Sciences grant R35GM142879, the Google Research Scholar Award, the Blavatnik Center for Computational Biomedicine Award, the Partners' Innovation Discovery Grant, and the Schlager Family Award for Early Stage Digital Health Innovations.

Advances in computational and translational approaches for malignant glioma

Gliomas are the most common primary brain tumors in adults and carry a dismal prognosis for patients. Current standard-of-care for gliomas is comprised of maximal safe surgical resection following by a combination of chemotherapy and radiation therapy depending on the grade and type of tumor. Despite decades of research efforts directed towards identifying effective therapies, curative treatments have been largely elusive in the majority of cases. The development and refinement of novel methodologies over recent years that integrate computational techniques with translational paradigms have begun to shed light on features of glioma, previously difficult to study. These methodologies have enabled a number of point-of-care approaches that can provide real-time, patient-specific and tumor-specific diagnostics that may guide the selection and development of therapies including decision-making surrounding surgical resection. Novel methodologies have also demonstrated utility in characterizing glioma-brain network dynamics and in turn early investigations into glioma plasticity and influence on surgical planning at a systems level. Similarly, application of such techniques in the laboratory setting have enhanced the ability to accurately model glioma disease processes and interrogate mechanisms of resistance to therapy. In this review, we highlight representative trends in the integration of computational methodologies including artificial intelligence and modeling with translational approaches in the study and treatment of malignant gliomas both at the point-of-care and outside the operative theater in silico as well as in the laboratory setting.

Intraoperative microscopic autofluorescence detection and characterization in brain tumors using stimulated Raman histology and two-photon fluorescence

Introduction

The intrinsic autofluorescence of biological tissues interferes with the detection of fluorophores administered for fluorescence guidance, an emerging auxiliary technique in oncological surgery. Yet, autofluorescence of the human brain and its neoplasia is sparsely examined. This study aims to assess autofluorescence of the brain and its neoplasia on a microscopic level by stimulated Raman histology (SRH) combined with two-photon fluorescence.

Methods

With this experimentally established label-free microscopy technique unprocessed tissue can be imaged and analyzed within minutes and the process is easily incorporated in the surgical workflow. In a prospective observational study, we analyzed 397 SRH and corresponding autofluorescence images of 162 samples from 81 consecutive patients that underwent brain tumor surgery. Small tissue samples were squashed on a slide for imaging. SRH and fluorescence images were acquired with a dual wavelength laser (790 nm and 1020 nm) for excitation. In these images tumor and non-tumor regions were identified by a convolutional neural network that reliably differentiates between tumor, healthy brain tissue and low quality SRH images. The identified areas were used to define regions.of- interests (ROIs) and the mean fluorescence intensity was measured.

Results

In healthy brain tissue, we found an increased mean autofluorescence signal in the gray (11.86, SD 2.61, n=29) compared to the white matter (5.99, SD 5.14, n=11, p<0.01) and in the cerebrum (11.83, SD 3.29, n=33) versus the cerebellum (2.82, SD 0.93, n=7, p<0.001), respectively. The signal of carcinoma metastases, meningiomas, gliomas and pituitary adenomas was significantly lower (each p<0.05) compared to the autofluorescence in the cerebrum and dura, and significantly higher (each p<0.05) compared to the cerebellum. Melanoma metastases were found to have a higher fluorescent signal (p<0.01) compared to cerebrum and cerebellum.

Discussion

In conclusion we found that autofluorescence in the brain varies depending on the tissue type and localization and differs significantly among various brain tumors. This needs to be considered for interpreting photon signal during fluorescence-guided brain tumor surgery.