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

Toward cancer detection by label-free microscopic imaging in oncological surgery: Techniques, instrumentation and applications

This review examines the clinical application of label-free microscopy and spectroscopy, which are based on optical signals emitted by tissue components. Over the past three decades, a variety of techniques have been investigated with the aim of developing an in situ histopathology method that can rapidly and accurately identify tumor margins during surgical procedures. These techniques can be divided into two groups. One group encompasses techniques exploiting linear optical signals, and includes infrared and Raman microspectroscopy, and autofluorescence microscopy. The second group includes techniques based on nonlinear optical signals, including harmonic generation, coherent Raman scattering, and multiphoton autofluorescence microscopy. Some of these methods provide comparable information, while others are complementary. However, all of them have distinct advantages and disadvantages due to their inherent nature. The first part of the review provides an explanation of the underlying physics of the excitation mechanisms and a description of the instrumentation. It also covers endomicroscopy and data analysis, which are important for understanding the current limitations in implementing label-free techniques in clinical settings. The second part of the review describes the application of label-free microscopy imaging to improve oncological surgery with focus on brain tumors and selected gastrointestinal cancers, and provides a critical assessment of the current state of translation of these methods into clinical practice. Finally, the potential of confocal laser endomicroscopy for the acquisition of autofluorescence is discussed in the context of immediate clinical applications.

Context aware machine learning techniques for brain tumor classification and detection - A review

Background

Machine learning has tremendous potential in acute medical care, particularly in the field of precise medical diagnosis, prediction, and classification of brain tumors. Malignant gliomas, due to their aggressive growth and dismal prognosis, stand out among various brain tumor types. Recent advancements in understanding the genetic abnormalities that underlie these tumors have shed light on their histo-pathological and biological characteristics, which support in better classification and prognosis.

Objectives

This review aims to predict gene alterations and establish structured correlations among various tumor types, extending the prediction of genetic mutations and structures using the latest machine learning techniques. Specifically, it focuses on multi-modalities of Magnetic Resonance Imaging (MRI) and histopathology, utilizing Convolutional Neural Networks (CNN) for image processing and analysis.

Methods

The review encompasses the most recent developments in MRI, and histology image processing methods across multiple tumor classes, including Glioma, Meningioma, Pituitary, Oligodendroglioma, and Astrocytoma. It identifies challenges in tumor classification, segmentation, datasets, and modalities, employing various neural network architectures. A competitive analysis assesses the performance of CNN. Furthermore it also implies K-MEANS clustering to predict Genetic structure, Genes Clusters prediction and Molecular Alteration of various types and grades of tumors e.g. Glioma, Meningioma, Pituitary, Oligodendroglioma, and Astrocytoma.

Results

CNN and KNN structures, with their ability to extract highlights in image-based information, prove effective in tumor classification and segmentation, surmounting challenges in image analysis. Competitive analysis reveals that CNN and outperform others algorithms on publicly available datasets, suggesting their potential for precise tumor diagnosis and treatment planning.

Conclusion

Machine learning, especially through CNN and SVM algorithms, demonstrates significant potential in the accurate diagnosis and classification of brain tumors based on imaging and histo-pathological data. Further advancements in this area hold promise for improving the accuracy and efficiency of intra-operative tumor diagnosis and treatment.

Tumor-Homing Biomimetic Near-Infrared II SERS Probes for Targeted Intraoperative Resection Guidance of Orthotopic Glioblastoma

In vivo optical imaging holds great potential for surgical guidance with the ability to intraoperatively identify tumor lesions in a surgical bed and navigate their surgical excision in real time. Nevertheless, its full potential remains underexploited, mainly due to the dearth of high-performance optical probes. Herein, hybrid cell membrane-biomimetic near-infrared II surface-enhanced Raman spectroscopy (NIR-II SERS) probes are reported for intraoperative resection guidance of orthotopic glioblastoma. A novel class of plasmonic Au nanorod (AuNR)@Au-Ag frames is developed with remarkable plasmonic properties tunable beyond 1700 nm. We demonstrate the exceptional NIR-II SERS performance both in vitro and in vivo of the biomimetic NIR-II SERS probes created with AuNR@Au-Ag frames and hybrid cell membranes. The biomimetic NIR-II SERS probes are successfully applied in an orthotopic glioblastoma mouse model for intraoperative resection guidance with complete tumor removal and improved surgical outcomes. This study presents a promising strategy for precise NIR-II SERS surgical navigation.

Machine learning empowered coherent Raman imaging and analysis for biomedical applications

In situ and in vivo visualization and analysis of functional, endogenous biomolecules in living systems have generated a pivotal impact in our comprehension of biology and medicine. An increasingly adopted approach involves the utilization of molecular vibrational spectroscopy, which delivers notable advantages such as label-free imaging, high spectral density, high sensitivity, and molecule specificity. Nonetheless, analyzing and processing the intricate, multi-dimensional imaging data to extract interpretable and actionable information poses a fundamental obstacle. In contrast to conventional multivariate methods, machine learning has recently gained considerable attention for its capability of discerning essential features from massive datasets. Here, we present a comprehensive review of the latest advancements in the application of machine learning in the molecular spectroscopic imaging fields. We also discuss notable attributes of spectroscopic imaging modalities and explore their broader impact on other imaging techniques.

Computed Tomography-Image-Based Glioma Grading Using Radiomics and Machine Learning: A Proof-of-Principle Study

BACKGROUND/OBJECTIVES

In recent years, numerous studies have been published on determining the WHO grade of central nervous system (CNS) tumors using machine learning algorithms. These studies are usually based on magnetic resonance imaging (MRI) and sometimes also on positron emission tomography (PET) images. To date, however, there are virtually no corresponding studies based on routinely generated computed tomography (CT) images. The aim of our proof-of-concept study is to investigate whether machine learning-based tumor diagnosis is also possible using CT images.

METHODS

We investigate the differentiability of histologically confirmed low-grade and high-grade gliomas. Three conventional machine learning algorithms and a neural net are tested. In addition, we analyze which of the common imaging methods (MRI or CT) appears to be best suited for the diagnostic question under investigation when machine learning algorithms are used. For this purpose, we compare our results based on CT images with numerous studies based on MRI scans.

RESULTS

Our best-performing model includes six features and is obtained using univariate analysis for feature preselection and a Naive Bayes approach for model construction. Using independent test data, this model yields a mean AUC of 0.903, a mean accuracy of 0.839, a mean sensitivity of 0.807 and a mean specificity of 0.864.

CONCLUSIONS

Our results demonstrate that low-grade and high-grade gliomas can be differentiated with high accuracy using machine learning algorithms, not only based on the usual MRI scans, but also based on CT images. In the future, such CT-image-based models can help to further accelerate brain tumor diagnostics and to reduce the number of necessary biopsies.

Ultrabright contrast agents with synergistic Raman enhancements for precise intraoperative imaging and photothermal ablation of orthotopic tumor models

BACKGROUND

Intraoperative imaging is critical for achieving precise cancer resection. Among available techniques, Raman spectral imaging emerges as a promising modality due to its high spatial resolution and signal stability. However, its clinical application for in vivo imaging is limited by the inherently weak Raman scattering signal. To address this challenge, we developed a novel strategy that integrates two enhancement mechanisms into a single Raman contrast agent.

RESULTS

This contrast agent exploits the synergistic effects of an anisotropic gold nanorod and a polypyrrole-polydopamine hybrid, resulting in a substantial amplification of Raman signals. Consequently, the agent enables clear delineation of malignant tissues in both orthotopic and subcutaneous tumor models. Beyond its imaging capability, the agent also facilitates photothermal ablation, providing a long-term solution for suppressing tumor recurrence.

CONCLUSION

This study systematically evaluates the imaging performance of the synthesized Raman contrast agents across different tumor models and highlights the critical role of optimizing the aspect ratio of anisotropic agents for in vivo imaging. By offering a dual-function Raman contrast agent, this research advances the potential of Raman spectral imaging for intraoperative applications and clinical translation.

Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging

Predicting long-term recurrence of disease in breast cancer (BC) patients remains a significant challenge for patients with early stage disease who are at low to intermediate risk of relapse as determined using current clinical tools. Prognostic assays which utilize bulk transcriptomics ignore the spatial context of the cellular material and are, therefore, of limited value in the development of mechanistic models. In this study, Fourier-transform infrared (FTIR) chemical images of BC tissue were used to train deep learning models to predict future disease recurrence. A number of deep learning models were employed, with champion models employing two-dimensional and two-dimensional-separable convolutional networks found to have predictive performance of a ROC AUC of approximately 0.64, which compares well to other clinically used prognostic assays in this space. All-digital chemical imaging may therefore provide a label-free platform for histopathological prognosis in breast cancer, opening new horizons for future deployment of these technologies.

Brain tumour histopathology through the lens of deep learning: A systematic review

PROBLEM

Machine learning (ML)/Deep learning (DL) techniques have been evolving to solve more complex diseases, but it has been used relatively little in Glioblastoma (GBM) histopathological studies, which could benefit greatly due to the disease's complex pathogenesis.

AIM

Conduct a systematic review to investigate how ML/DL techniques have influenced the progression of brain tumour histopathological research, particularly in GBM.

METHODS

54 eligible studies were collected from the PubMed and ScienceDirect databases, and their information about the types of brain tumour/s used, types of -omics data used with histopathological data, origins of the data, types of ML/DL and its training and evaluation methodologies, and the ML/DL task it was set to perform in the study were extracted to inform us of trends in GBM-related ML/DL-based research.

RESULTS

Only 8 GBM-related studies in the eligible utilised ML/DL methodologies to gain deeper insights into GBM pathogenesis by contextualising histological data with -omics data. However, we report that these studies have been published more recently. The most popular ML/DL models used in GBM-related research are the SVM classifier and ResNet-based CNN architecture. Still, a considerable number of studies failed to state training and evaluative methodologies clearly.

CONCLUSION

There is a growing trend towards using ML/DL approaches to uncover relationships between biological and histopathological data to bring new insights into GBM, thus pushing GBM research forward. Much work still needs to be done to properly report the ML/DL methodologies to showcase the models' robustness and generalizability and ensure the models are reproducible.

Liver segmentation network based on detail enhancement and multi-scale feature fusion

Due to the low contrast of abdominal CT (Computer Tomography) images and the similar color and shape of the liver to other organs such as the spleen, stomach, and kidneys, liver segmentation presents significant challenges. Additionally, 2D CT images obtained from different angles (such as sagittal, coronal, and transverse planes) increase the diversity of liver morphology and the complexity of segmentation. To address these issues, this paper proposes a Detail Enhanced Convolution (DE Conv) to improve liver feature learning and thereby enhance liver segmentation performance. Furthermore, to enable the model to better learn liver features at different scales, a Multi-Scale Feature Fusion module (MSFF) is added to the skip connections in the model. The MSFF module enhances the capture of global features, thus improving the accuracy of the liver segmentation model. Through the aforementioned research, this paper proposes a liver segmentation network based on detail enhancement and multi-scale feature fusion (DEMF-Net). We conducted extensive experiments on the LiTS17 dataset, and the results demonstrate that the DEMF-Net model achieved significant improvements across various evaluation metrics. Therefore, the proposed DEMF-Net model can achieve precise liver segmentation.

Congress of Neurological Surgeons systematic review and evidence based guideline on neuropathology for WHO grade II diffuse glioma: update

QUESTIONS AND RECOMMENDATIONS FROM THE PRIOR VERSION OF THESE GUIDELINES WITHOUT CHANGE: TARGET POPULATION: Adult patients (age ≥ 18 years) who have suspected low-grade diffuse glioma.

QUESTION

What are the optimal neuropathological techniques to diagnose low-grade diffuse glioma in the adult?

RECOMMENDATION

Level I Histopathological analysis of a representative surgical sample of the lesion should be used to provide the diagnosis of low-grade diffuse glioma. Level III Both frozen section and cytopathologic/smear evaluation should be used to aid the intra-operative assessment of low-grade diffuse glioma diagnosis. A resection specimen is preferred over a biopsy specimen, to minimize the potential for sampling error issues.

TARGET POPULATION

Patients with histologically-proven WHO grade II diffuse glioma.

QUESTION

In adult patients (age ≥ 18 years) with histologically-proven WHO grade II diffuse glioma, is testing for IDH1 mutation (R132H and/or others) warranted? If so, is there a preferred method?

RECOMMENDATION

Level II IDH gene mutation assessment, via IDH1 R132H antibody and/or IDH1/2 mutation hotspot sequencing, is highly-specific for low-grade diffuse glioma, and is recommended as an additional test for classification and prognosis.

TARGET POPULATION

Patients with histologically-proven WHO grade II diffuse glioma.

QUESTION

In adult patients (age ≥ 18 years) with histologically-proven WHO grade II diffuse glioma, is testing for 1p/19q loss warranted? If so, is there a preferred method?

RECOMMENDATION

Level III 1p/19q loss-of-heterozygosity testing, by FISH, array-CGH or PCR, is recommended as an additional test in oligodendroglial cases for prognosis and potential treatment planning.

TARGET POPULATION

Patients with histologically proven WHO grade II diffuse glioma.

QUESTION

In adult patients (age > 18 years) with histologically-proven WHO grade II diffuse glioma, is methyl-guanine methyl-transferase (MGMT) promoter methylation testing warranted? If so, is there a preferred method?

RECOMMENDATION

There is insufficient evidence to recommend MGMT promoter methylation testing as a routine for low-grade diffuse gliomas. It is recommended that patients be enrolled in properly designed clinical trials to assess the value of this and related markers for this target population.

TARGET POPULATION

Patients with histologically-proven WHO grade II diffuse glioma.

QUESTION

In adult patients (age ≥ 18 years) with histologically proven WHO grade II diffuse glioma, is Ki-67/MIB1 immunohistochemistry warranted? If so, is there a preferred method to quantitate results?

RECOMMENDATION

Level III Ki67/MIB1 immunohistochemistry is recommended as an option for prognostic assessment.

NEW RECOMMENDATION

TARGET POPULATION: Adult patients (age ≥ 18 years) who have suspected WHO grade II diffuse glioma.

QUESTION

Is testing for ATRX mutations helpful for predicting survival and making treatment recommendations?

RECOMMENDATION

There is insufficient evidence to recommend ATRX mutation testing as a means of predicting survival or making treatment recommendations.

TARGET POPULATION

Adult patients (age ≥ 18 years) who have suspected WHO grade II diffuse glioma.

QUESTION

Does the addition of intraoperative optical histologic methods provide accuracy beyond the use of conventional histologic methods in diagnosis and management?

RECOMMENDATION

There is insufficient evidence at this time to suggest that intraoperative optical histologic methods offer increased diagnostic accuracy when compared to conventional techniques.

Metastatic brain tumors: from development to cutting-edge treatment

Metastatic brain tumors, also called brain metastasis (BM), represent a challenging complication of advanced tumors. Tumors that commonly metastasize to the brain include lung cancer and breast cancer. In recent years, the prognosis for BM patients has improved, and significant advancements have been made in both clinical and preclinical research. This review focuses on BM originating from lung cancer and breast cancer. We briefly overview the history and epidemiology of BM, as well as the current diagnostic and treatment paradigms. Additionally, we summarize multiomics evidence on the mechanisms of tumor occurrence and development in the era of artificial intelligence and discuss the role of the tumor microenvironment. Preclinically, we introduce the establishment of BM models, detailed molecular mechanisms, and cutting-edge treatment methods. BM is primarily treated with a comprehensive approach, including local treatments such as surgery and radiotherapy. For lung cancer, targeted therapy and immunotherapy have shown efficacy, while in breast cancer, monoclonal antibodies, tyrosine kinase inhibitors, and antibody-drug conjugates are effective in BM. Multiomics approaches assist in clinical diagnosis and treatment, revealing the complex mechanisms of BM. Moreover, preclinical agents often need to cross the blood-brain barrier to achieve high intracranial concentrations, including small-molecule inhibitors, nanoparticles, and peptide drugs. Addressing BM is imperative.

Foundation models for fast, label-free detection of glioma infiltration

A critical challenge in glioma treatment is detecting tumour infiltration during surgery to achieve safe maximal resection1-3. Unfortunately, safely resectable residual tumour is found in the majority of patients with glioma after surgery, causing early recurrence and decreased survival4-6. Here we present FastGlioma, a visual foundation model for fast (<10 s) and accurate detection of glioma infiltration in fresh, unprocessed surgical tissue. FastGlioma was pretrained using large-scale self-supervision (around 4 million images) on rapid, label-free optical microscopy, and fine-tuned to output a normalized score that indicates the degree of tumour infiltration within whole-slide optical images. In a prospective, multicentre, international testing cohort of patients with diffuse glioma (n = 220), FastGlioma was able to detect and quantify the degree of tumour infiltration with an average area under the receiver operating characteristic curve of 92.1 ± 0.9%. FastGlioma outperformed image-guided and fluorescence-guided adjuncts for detecting tumour infiltration during surgery by a wide margin in a head-to-head, prospective study (n = 129). The performance of FastGlioma remained high across diverse patient demographics, medical centres and diffuse glioma molecular subtypes as defined by the World Health Organization. FastGlioma shows zero-shot generalization to other adult and paediatric brain tumour diagnoses, demonstrating the potential for our foundation model to be used as a general-purpose adjunct for guiding brain tumour surgeries. These findings represent the transformative potential of medical foundation models to unlock the role of artificial intelligence in the care of patients with cancer.

Intraoperative margin assessment with near real time pathology during partial gland ablation of prostate cancer: A feasibility study

BACKGROUND

In-field or in-margin recurrence after partial gland cryosurgical ablation (PGCA) of prostate cancer (PCa) remains a limitation of the paradigm. Stimulated Raman histology (SRH) is a novel microscopic technique allowing real time, label-free, high-resolution microscopic images of unprocessed, un-sectioned tissue which can be interpreted by humans or artificial intelligence (AI). We evaluated surgical team and AI interpretation of SRH for real-time pathologic feedback in the planning and treatment of PCa with PGCA.

METHODS

About 12 participants underwent prostate mapping biopsies during PGCA of their PCa between January and June 2022. Prostate biopsies were immediately scanned in a SRH microscope at 20 microns depth using 2 Raman shifts to create SRH images which were interpreted by the surgical team intraoperatively to guide PGCA, and retrospectively assessed by AI. The cores were then processed, hematoxylin and eosin stained as per normal pathologic protocols and used for ground truth pathologic assessment.

RESULTS

Surgical team interpretation of SRH intraoperatively revealed 98.1% accuracy, 100% sensitivity, 97.3% specificity for identification of PCa, while AI showed a 97.9% accuracy, 100% sensitivity and 97.5% specificity for identification of clinically significant PCa. 3 participants' PGCA treatments were modified after SRH visualized PCa adjacent to an expected MRI predicted tumor margin or at an untreated cryosurgical margin.

CONCLUSION

SRH allows for accurate rapid identification of PCa in PB by a surgical team interpretation or AI. PCa tumor mapping and margin assessment during PGCA appears to be feasible and accurate. Further studies evaluating impact on clinical outcomes are warranted.

A novel recommender framework with chatbot to stratify heart attack risk

Cardiovascular diseases are a major cause of mortality and morbidity. Fast detection of life-threatening emergency events and an earlier start of the therapy would save many lives and reduce successive disabilities. Understanding the specific risk factors associated with heart attack and the degree of association is crucial in the clinical diagnosis. Considering the potential benefits of intelligent models in healthcare, many researchers have developed a variety of machine learning (ML)-based models to identify patients at risk of a heart attack. However, the common problem of previous works that used ML concepts was the lack of transparency in black-box models, which makes it difficult to understand how the model made the prediction. In this study, an automated smart recommender system (Explainable Artificial Intelligence) for heart attack prediction and risk stratification was developed. For the purpose, the CatBoost classifier was applied as the initial step. Then, the SHAP (SHapley Additive exPlanation) explainable algorithm was employed to determine reasons behind high or low risk classification. The recommender system can provide insights into the reasoning behind the predictions, including group-based and patient-specific explanations. In the final step, we integrated a Large Language Model (LLM) called BioMistral for chatting functionally to talk to users based on the model output as a digital doctor for consultation. Our smart recommender system achieved high accuracy in predicting a patient risk level with an average AUC of 0.88 and can explain the results transparently. Moreover, a Django-based online application that uses patient data to update medical information about an individual's heart attack risk was created. The LLM chatbot component would answer user questions about heart attacks and serve as a virtual companion on the route to heart health, our system also can locate nearby hospitals by applying Google Maps API and alert the users. The recommender system could improve patient management and lower heart attack risk while timely therapy aids in avoiding subsequent disabilities.

Unmixing Autoencoder for Image Reconstruction from Hyperspectral Data

Due to the complexity of samples and the limitations in spatial resolution, the spectra in hyperspectral imaging (HSI) are generally contributed to by multiple components, making univariate analysis ineffective. Although feature extraction methods have been applied, the chemical meaning of the compressed variables is difficult to interpret, limiting their further applications. An unmixing autoencoder (UAE) was developed in this work for the separation of the mixed spectra in HSI. The proposed model is composed of an encoder and a fully connected (FC) layer. The former is used to compress the input spectrum into several variables, and the latter is employed to reconstruct the spectrum. Combining reconstruction loss and sparse regularization, the weights and the spectral profiles of the components will be encoded in the compressed variables and the connection weights of FC, respectively. A simulated and three experimental HSI data sets were adopted to investigate the performance of the UAE model. The spectral components were successfully obtained, from which the handwriting under papers was revealed from the image of near-infrared (NIR) diffusive reflectance spectroscopy, and the images of lipids, proteins, and nucleic acids were reconstructed from the Raman and stimulated Raman scattering (SRS) images.

Advances in exosome plasmonic sensing: Device integration strategies and AI-aided diagnosis

Exosomes, as next-generation biomarkers, has great potential in tracking cancer progression. They face many detection limitations in cancer diagnosis. Plasmonic biosensors have attracted considerable attention at the forefront of exosome detection, due to their label-free, real-time, and high-sensitivity features. Their advantages in multiplex immunoassays of minimal liquid samples establish the leading position in various diagnostic studies. This review delineates the application principles of plasmonic sensing technologies, highlighting the importance of exosomes-based spectrum and image signals in disease diagnostics. It also introduces advancements in miniaturizing plasmonic biosensing platforms of exosomes, which can facilitate point-of-care testing for future healthcare. Nowadays, inspired by the surge of artificial intelligence (AI) for science and technology, more and more AI algorithms are being adopted to process the exosome spectrum and image data from plasmonic detection. Using representative algorithms of machine learning has become a mainstream trend in plasmonic biosensing research for exosome liquid biopsy. Typically, these algorithms process complex exosome datasets efficiently and establish powerful predictive models for precise diagnosis. This review further discusses critical strategies of AI algorithm selection in exosome-based diagnosis. Particularly, we categorize the AI algorithms into the interpretable and uninterpretable groups for exosome plasmonic detection applications. The interpretable AI enhances the transparency and reliability of diagnosis by elucidating the decision-making process, while the uninterpretable AI provides high diagnostic accuracy with robust data processing by a "black-box" working mode. We believe that AI will continue to promote significant progress of exosome plasmonic detection and mobile healthcare in the near future.

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

BACKGROUND

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.

METHODS

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 neoplastic/non-neoplastic lesions. Training and test data were collected from four tertiary international medical centers. The final histopathological diagnosis served as ground-truth.

RESULTS

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. 77.77%). 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.

CONCLUSIONS

RapidLymphoma proves reliable and valid for intraoperative PCNSL detection and differentiation from other CNS entities. It provides visual feedback within three minutes, enabling fast clinical decision-making and subsequent treatment strategy planning.

Optical-resolution parallel ultraviolet photoacoustic microscopy for slide-free histology

Intraoperative imaging of slide-free specimens is crucial for oncology surgeries, allowing surgeons to quickly identify tumor margins for precise surgical guidance. While high-resolution ultraviolet photoacoustic microscopy has been demonstrated for slide-free histology, the imaging speed is insufficient, due to the low laser repetition rate and the limited depth of field. To address these challenges, we present parallel ultraviolet photoacoustic microscopy (PUV-PAM) with simultaneous scanning of eight optical foci to acquire histology-like images of slide-free fresh specimens, improving the ultraviolet PAM imaging speed limited by low laser repetition rates. The PUV-PAM has achieved an imaging speed of 0.4 square millimeters per second (i.e., 4.2 minutes per square centimeter) at 1.3-micrometer resolution using a 50-kilohertz laser. In addition, we demonstrated the PUV-PAM with eight needle-shaped beams for an extended depth of field, allowing fast imaging of slide-free tissues with irregular surfaces. We believe that the PUV-PAM approach will enable rapid intraoperative photoacoustic histology and provide prospects for ultrafast optical-resolution PAM.

Artificial intelligence in surgical pathology - Where do we stand, where do we go?

Surgical and neuropathologists continuously search for new and disease-specific features, such as independent predictors of tumor prognosis or determinants of tumor entities and sub-entities. This is a task where artificial intelligence (AI)/machine learning (ML) systems could significantly contribute to help with tumor outcome prediction and the search for new diagnostic or treatment stratification biomarkers. AI systems are increasingly integrated into routine pathology workflows to improve accuracy, reproducibility, productivity and to reveal difficult-to-see features in complicated histological slides, including the quantification of important markers for tumor grading and staging. In this article, we review the infrastructure needed to facilitate digital and computational pathology. We address the barriers for its full deployment in the clinical setting and describe the use of AI in intraoperative or postoperative settings were frozen or formalin-fixed, paraffin-embedded materials are used. We also summarize quality assessment issues of slide digitization, new spatial biology approaches, and the determination of specific gene-expression from whole slide images. Finally, we highlight new innovative and future technologies, such as large language models, optical biopsies, and mass spectrometry imaging.

Explainable biology for improved therapies in precision medicine: AI is not enough

Technological advances and high-throughput bio-chemical assays are rapidly changing ways how we formulate and test biological hypotheses, and how we treat patients. Most complex diseases arise on a background of genetics, lifestyle and environment factors, and manifest themselves as a spectrum of symptoms. To fathom intricate biological processes and their changes from healthy to disease states, we need to systematically integrate and analyze multi-omics datasets, ontologies, and diverse annotations. Without proper management of such complex biological and clinical data, artificial intelligence (AI) algorithms alone cannot be effectively trained, validated, and successfully applied to provide trustworthy and patient-centric diagnosis, prognosis and treatment. Precision medicine requires to use multi-omics approaches effectively, and offers many opportunities for using AI, "big data" analytics, and integrative computational biology workflows. Advances in optical and biochemical assay technologies including sequencing, mass spectrometry and imaging modalities have transformed research by empowering us to simultaneously view all genes expressed, identify proteome-wide changes, and assess interacting partners of each individual protein within a dynamically changing biological system, at an individual cell level. While such views are already having an impact on our understanding of healthy and disease conditions, it remains challenging to extract useful information comprehensively and systematically from individual studies, ensure that signal is separated from noise, develop models, and provide hypotheses for further research. Data remain incomplete and are often poorly connected using fragmented biological networks. In addition, statistical and machine learning models are developed at a cohort level and often not validated at the individual patient level. Combining integrative computational biology and AI has the potential to improve understanding and treatment of diseases by identifying biomarkers and building explainable models characterizing individual patients. From systematic data analysis to more specific diagnostic, prognostic and predictive biomarkers, drug mechanism of action, and patient selection, such analyses influence multiple steps from prevention to disease characterization, and from prognosis to drug discovery. Data mining, machine learning, graph theory and advanced visualization may help identify diagnostic, prognostic and predictive biomarkers, and create causal models of disease. Intertwining computational prediction and modeling with biological experiments leads to faster, more biologically and clinically relevant discoveries. However, computational analysis results and models are going to be only as accurate and useful as correct and comprehensive are the networks, ontologies and datasets used to build them. High quality, curated data portals provide the necessary foundation for translational research. They help to identify better biomarkers, new drugs, precision treatments, and should lead to improved patient outcomes and their quality of life. Intertwining computational prediction and modeling with biological experiments, efficiently and effectively leads to more useful findings faster.

Artificial intelligence-aided data mining of medical records for cancer detection and screening

The application of artificial intelligence methods to electronic patient records paves the way for large-scale analysis of multimodal data. Such population-wide data describing deep phenotypes composed of thousands of features are now being leveraged to create data-driven algorithms, which in turn has led to improved methods for early cancer detection and screening. Remaining challenges include establishment of infrastructures for prospective testing of such methods, ways to assess biases given the data, and gathering of sufficiently large and diverse datasets that reflect disease heterogeneities across populations. This Review provides an overview of artificial intelligence methods designed to detect cancer early, including key aspects of concern (eg, the problem of data drift-when the underlying health-care data change over time), ethical aspects, and discrepancies between access to cancer screening in high-income countries versus low-income and middle-income countries.

Current research status of Raman spectroscopy in glioma detection

Glioma is the most common primary tumor of the nervous system. Conventional diagnostic methods for glioma often involve time-consuming or reliance on externally introduced materials. Consequently, there is an urgent need for rapid and reliable diagnostic techniques. Raman spectroscopy has emerged as a promising tool, offering rapid, accurate, and label-free analysis with high sensitivity and specificity in biomedical applications. In this review, the fundamental principles of Raman spectroscopy have been introduced, and then the progress of applying Raman spectroscopy in biomedical studies has been summarized, including the identification and typing of glioma. The challenges encountered in the clinical application of Raman spectroscopy for glioma have been discussed, and the prospects have also been envisioned.

Intraoperative label-free tissue diagnostics using a stimulated Raman histology imaging system with artificial intelligence: An initial experience

BACKGROUND

Accurate intraoperative tissue diagnostics could impact on decision making regarding the extent of resection (EOR) during brain tumor surgery. Stimulated Raman histology (SRH) is a label-free optical imaging method that uses different biochemical properties of tissue to generate a hematoxylin-eosin-like image and, in combination with an artificial intelligence-based image classifier, offers the opportunity to obtain rapid intraoperative tissue diagnoses.

OBJECTIVE

The goal of this study was to report on our initial experience with SRH to evaluate its accuracy in comparison to final tissue diagnosis.

MATERIALS & METHODS

We evaluated 70 consecutive adult cases with brain tumors. We compared results of the three different SRH classifier (diagnostic, molecular and tumor/non-tumor) to the respective final histopathological result. Similarly, we evaluated the isocitrate dehydrogenase (IDH) mutations in 18 patients using SRH. Lastly, we compared SRH results of samples taken from the tumor margins with early postoperative MRI. Prediction accuracy was evaluated by logistic regression and Receiver Operator Curve (ROC) analysis.

RESULTS

We included 19 gliomas, 9 metastases, 22 meningiomas and 14 other tumor entities. Regarding accuracy of intraoperative SRH predictions, regression analysis showed an Area Under the Curve (AUC) of 0.77 (95 % C.I. 0.64-0.89, p = 0.0008), suggesting agreement of predictions with final diagnosis. For specific tumor entities, variable accuracies were observed: The highest accuracy was obtained for meningiomas followed by high-grade glioma. IDH mutations were predicted with an AUC of 0.93 (95 % C.I. 0.88-0.98; p < 0.0001). The SRH examination of tissue samples from tumor margins corresponded with postoperative MRI in 4 out of 5 cases.

CONCLUSION

Our initial experience with SRH shows that this novel imaging technique is a promising approach to obtain rapid intraoperative tissue diagnosis to guide surgical decision making based on histology and cell-density. With further refinement of AI-based automated image classification and a better integration into the surgical workflow, prediction accuracy and reliability could be improved.

DSIFNet: Implicit feature network for nasal cavity and vestibule segmentation from 3D head CT

This study is dedicated to accurately segment the nasal cavity and its intricate internal anatomy from head CT images, which is critical for understanding nasal physiology, diagnosing diseases, and planning surgeries. Nasal cavity and it's anatomical structures such as the sinuses, and vestibule exhibit significant scale differences, with complex shapes and variable microstructures. These features require the segmentation method to have strong cross-scale feature extraction capabilities. To effectively address this challenge, we propose an image segmentation network named the Deeply Supervised Implicit Feature Network (DSIFNet). This network uniquely incorporates an Implicit Feature Function Module Guided by Local and Global Positional Information (LGPI-IFF), enabling effective fusion of features across scales and enhancing the network's ability to recognize details and overall structures. Additionally, we introduce a deep supervision mechanism based on implicit feature functions in the network's decoding phase, optimizing the utilization of multi-scale feature information, thus improving segmentation precision and detail representation. Furthermore, we constructed a dataset comprising 7116 CT volumes (including 1,292,508 slices) and implemented PixPro-based self-supervised pretraining to utilize unlabeled data for enhanced feature extraction. Our tests on nasal cavity and vestibule segmentation, conducted on a dataset comprising 128 head CT volumes (including 34,006 slices), demonstrate the robustness and superior performance of proposed method, achieving leading results across multiple segmentation metrics.

Image Quality Assessment and Reliability Analysis of Artificial Intelligence-Based Tumor Classification of Stimulated Raman Histology of Tumor Biobank Samples

BACKGROUND

Stimulated Raman histology (SRH) is a label-free optical imaging method for rapid intraoperative analysis of fresh tissue samples. Analysis of SRH images using Convolutional Neural Networks (CNN) has shown promising results for predicting the main histopathological classes of neurooncological tumors. Due to the relatively low number of rare tumor representations in CNN training datasets, a valid prediction of rarer entities remains limited. To develop new reliable analysis tools, larger datasets and greater tumor variety are crucial. One way to accomplish this is through research biobanks storing frozen tumor tissue samples. However, there is currently no data available regarding the pertinency of previously frozen tissue samples for SRH analysis. The aim of this study was to assess image quality and perform a comparative reliability analysis of artificial intelligence-based tumor classification using SRH in fresh and frozen tissue samples.

METHODS

In a monocentric prospective study, tissue samples from 25 patients undergoing brain tumor resection were obtained. SRH was acquired in fresh and defrosted samples of the same specimen after varying storage durations at -80 °C. Image quality was rated by an experienced neuropathologist, and prediction of histopathological diagnosis was performed using two established CNNs.

RESULTS

The image quality of SRH in fresh and defrosted tissue samples was high, with a mean image quality score of 1.96 (range 1-5) for both groups. CNN analysis showed high internal consistency for histo-(Cα 0.95) and molecular (Cα 0.83) pathological tumor classification. The results were confirmed using a dataset with samples from the local tumor biobank (Cα 0.91 and 0.53).

CONCLUSIONS

Our results showed that SRH appears comparably reliable in fresh and frozen tissue samples, enabling the integration of tumor biobank specimens to potentially improve the diagnostic range and reliability of CNN prediction tools.

Deep learning-driven macroscopic AI segmentation model for brain tumor detection via digital pathology: Foundations for terahertz imaging-based AI diagnostics

We used deep learning methods to develop an AI model capable of autonomously delineating cancerous regions in digital pathology images (H&E-stained images). By using a transgenic brain tumor model derived from the TS13-64 brain tumor cell line, we digitized a total of 187 H&E-stained images and annotated the cancerous regions in these images to compile a dataset. A deep learning approach was executed through DEEP:PHI, which abstracts Python coding complexities, thereby simplifying the execution of AI training protocols for users. By employing the Image Crop with Mask technique and patch generation method, we not only maintained an appropriate data class balance but also overcame the challenge of limited computing resources. This approach enabled us to successfully develop an AI training model that autonomously segments cancerous areas. This AI model enables the provision of guiding images for determining cancerous areas with minimal assistance from neuropathologists. In addition, the high-quality, large dataset curated for training using the proposed approach contributes to the development of novel terahertz imaging-based AI cancer diagnosis technologies and accelerates technological advancements.

Artificial Intelligence-Assisted Stimulated Raman Histology: New Frontiers in Vibrational Tissue Imaging

Frozen section biopsy, introduced in the early 1900s, still remains the gold standard methodology for rapid histologic evaluations. Although a valuable tool, it is labor-, time-, and cost-intensive. Other challenges include visual and diagnostic variability, which may complicate interpretation and potentially compromise the quality of clinical decisions. Raman spectroscopy, with its high specificity and non-invasive nature, can be an effective tool for dependable and quick histopathology. The most promising modality in this context is stimulated Raman histology (SRH), a label-free, non-linear optical process which generates conventional H&E-like images in short time frames. SRH overcomes limitations of conventional Raman scattering by leveraging the qualities of stimulated Raman scattering (SRS), wherein the energy gets transferred from a high-power pump beam to a probe beam, resulting in high-energy, high-intensity scattering. SRH's high resolution and non-requirement of preprocessing steps make it particularly suitable when it comes to intrasurgical histology. Combining SRH with artificial intelligence (AI) can lead to greater precision and less reliance on manual interpretation, potentially easing the burden of the overburdened global histopathology workforce. We review the recent applications and advances in SRH and how it is tapping into AI to evolve as a revolutionary tool for rapid histologic analysis.

Transformative applications of oculomics-based AI approaches in the management of systemic diseases: A systematic review

BACKGROUND

Systemic diseases, such as cardiovascular and cerebrovascular conditions, pose significant global health challenges due to their high mortality rates. Early identification and intervention in systemic diseases can substantially enhance their prognosis. However, diagnosing systemic diseases often necessitates complex, expensive, and invasive tests, posing challenges in their timely detection. Therefore, simple, cost-effective, and non-invasive methods for the management (such as screening, diagnosis, and monitoring) of systemic diseases are needed to reduce associated comorbidities and mortality rates.

AIM OF THE REVIEW

This systematic review examines the application of artificial intelligence (AI) algorithms in managing systemic diseases by analyzing ophthalmic features (oculomics) obtained from convenient, affordable, and non-invasive ophthalmic imaging.

KEY SCIENTIFIC CONCEPTS OF REVIEW

Our analysis demonstrates the promising accuracy of AI in predicting systemic diseases. Subgroup analysis reveals promising capabilities of oculomics-based AI for disease staging, while caution is warranted due to the possible overestimation of AI capabilities in low-quality studies. These systems are cost-effective and safe, with high rates of acceptance among patients and clinicians. This review underscores the potential of oculomics-based AI approaches in revolutionizing the management of systemic diseases.

Raman-based machine-learning platform reveals unique metabolic differences between IDHmut and IDHwt glioma

BACKGROUND

Formalin-fixed, paraffin-embedded (FFPE) tissue slides are routinely used in cancer diagnosis, clinical decision-making, and stored in biobanks, but their utilization in Raman spectroscopy-based studies has been limited due to the background coming from embedding media.

METHODS

Spontaneous Raman spectroscopy was used for molecular fingerprinting of FFPE tissue from 46 patient samples with known methylation subtypes. Spectra were used to construct tumor/non-tumor, IDH1WT/IDH1mut, and methylation-subtype classifiers. Support vector machine and random forest were used to identify the most discriminatory Raman frequencies. Stimulated Raman spectroscopy was used to validate the frequencies identified. Mass spectrometry of glioma cell lines and TCGA were used to validate the biological findings.

RESULTS

Here, we develop APOLLO (rAman-based PathOLogy of maLignant gliOma)-a computational workflow that predicts different subtypes of glioma from spontaneous Raman spectra of FFPE tissue slides. Our novel APOLLO platform distinguishes tumors from nontumor tissue and identifies novel Raman peaks corresponding to DNA and proteins that are more intense in the tumor. APOLLO differentiates isocitrate dehydrogenase 1 mutant (IDH1mut) from wild-type (IDH1WT) tumors and identifies cholesterol ester levels to be highly abundant in IDHmut glioma. Moreover, APOLLO achieves high discriminative power between finer, clinically relevant glioma methylation subtypes, distinguishing between the CpG island hypermethylated phenotype (G-CIMP)-high and G-CIMP-low molecular phenotypes within the IDH1mut types.

CONCLUSIONS

Our results demonstrate the potential of label-free Raman spectroscopy to classify glioma subtypes from FFPE slides and to extract meaningful biological information thus opening the door for future applications on these archived tissues in other cancers.

Correlation of Edema/Tumor Index With Histopathological Outcomes According to the WHO Classification of Cranial Tumors

BACKGROUND

Metastatic brain tumors are a prevalent challenge in neurosurgery, with vasogenic edema being a significant consequence of these lesions. Despite the critical role of peritumoral edema in prognosis and patient outcomes, few studies have quantified its diagnostic and prognostic implications. This study aims to evaluate the correlation between the edema/tumor index (ETI) and histopathological outcomes according to the 2021 WHO classification of cranial tumors.

METHODOLOGY

We conducted a retrospective analysis of Digital Imaging and Communications in Medicine (DICOM)-format magnetic resonance imaging (MRI) data from May 2023 to May 2024, applying manual 3D volumetric segmentation using Image Tool Kit-SNAP (ITK-SNAP, version 3.8.0, University of Pennsylvania) software. The ETI was calculated by dividing the volume of peritumoral edema by the tumor volume. The study included 60 patients, and statistical analyses were performed to assess the correlation between ETI and tumor histopathology, including Receiver Operating Characteristic (ROC) curve analysis for cutoff points.

RESULTS

A total of 60 patients were included in the study, with 27 males (45%) and 33 females (55%). The average tumor volume measured by 3D segmentation was 46.9 cubic centimeters (cc) (standard deviation [SD] ± 25.6), and the average peritumoral edema volume was 79 cc (SD ± 37.5) for malignant tumors. The ETI was calculated for each case. Malignant tumors (WHO grades 3 and 4) had a mean ETI of 1.6 (SD ± 1.2), while non-malignant tumors (WHO grades 1 and 2) had a mean ETI of 1.2 (SD ± 1.1), but this difference was not statistically significant (P = 0.51). ROC curve analysis for the ETI did not provide a reliable cutoff point for predicting tumor malignancy (area under the curve [AUC] = 0.59, P = 0.20). Despite the larger edema volume observed in malignant tumors, the ETI did not correlate significantly with the histopathological grade.

CONCLUSIONS

This study found no significant correlation between the ETI and the histopathological grade of brain tumors according to the 2021 WHO classification. While malignant tumors were associated with larger volumes of both tumor and peritumoral edema, the ETI did not prove to be a reliable predictor of tumor malignancy. Therefore, the ETI should not be used as a standalone metric for determining tumor aggressiveness or guiding clinical decision-making. Further studies with larger cohorts are required to better understand the potential prognostic value of the ETI in brain tumors.

Metabolic light absorption, scattering, and emission (MetaLASE) microscopy

Optical imaging of metabolism can provide key information about health and disease progression in cells and tissues; however, current methods have lacked gold-standard information about histological structure. Conversely, histology and virtual histology methods have lacked metabolic contrast. Here, we present metabolic light absorption, scattering, and emission (MetaLASE) microscopy, which rapidly provides a virtual histology and optical metabolic readout simultaneously. Hematoxylin-like nucleic contrast and eosin-like cytoplasmic contrast are obtained using photoacoustic remote sensing and ultraviolet reflectance microscopy, respectively. The same ultraviolet source excites endogenous Nicotinamide adenine dinucleotide (phosphate), flavin adenine dinucleotide, and collagen autofluorescence, providing a map of optical redox ratios to visualize metabolic variations including in areas of invasive carcinoma. Benign chronic inflammation and glands also are seen to exhibit hypermetabolism. MetaLASE microscopy offers promise for future applications in intraoperative margin analysis and in research applications where greater insights into metabolic activity could be correlated with cell and tissue types.

Current Applications of Raman Spectroscopy in Intraoperative Neurosurgery

BACKGROUND

Neurosurgery demands exceptional precision due to the brain's complex and delicate structures, necessitating precise targeting of pathological targets. Achieving optimal outcomes depends on the surgeon's ability to accurately differentiate between healthy and pathological tissues during operations. Raman spectroscopy (RS) has emerged as a promising innovation, offering real-time, in vivo non-invasive biochemical tissue characterization. This literature review evaluates the current research on RS applications in intraoperative neurosurgery, emphasizing its potential to enhance surgical precision and patient outcomes.

METHODS

Following PRISMA guidelines, a comprehensive systematic review was conducted using PubMed to extract relevant peer-reviewed articles. The inclusion criteria focused on original research discussing real-time RS applications with human tissue samples in or near the operating room, excluding retrospective studies, reviews, non-human research, and other non-relevant publications.

RESULTS

Our findings demonstrate that RS significantly improves tumor margin delineation, with handheld devices achieving high sensitivity and specificity. Stimulated Raman Histology (SRH) provides rapid, high-resolution tissue images comparable to traditional histopathology but with reduced time to diagnosis. Additionally, RS shows promise in identifying tumor types and grades, aiding precise surgical decision-making. RS techniques have been particularly beneficial in enhancing the accuracy of glioma surgeries, where distinguishing between tumor and healthy tissue is critical. By providing real-time molecular data, RS aids neurosurgeons in maximizing the extent of resection (EOR) while minimizing damage to normal brain tissue, potentially improving patient outcomes and reducing recurrence rates.

CONCLUSIONS

This review underscores the transformative potential of RS in neurosurgery, advocating for continued innovation and research to fully realize its benefits. Despite its substantial potential, further research is needed to validate RS's clinical utility and cost-effectiveness.

Extent of Resection Thresholds in Molecular Subgroups of Newly Diagnosed Isocitrate Dehydrogenase-Wildtype Glioblastoma

BACKGROUND AND OBJECTIVES

Maximizing the extent of resection (EOR) improves outcomes in glioblastoma (GBM). However, previous GBM studies have not addressed the EOR impact in molecular subgroups beyond IDH1/IDH2 status. In the current article, we evaluate whether EOR confers a benefit in all GBM subtypes or only in particular molecular subgroups.

METHODS

A retrospective cohort of newly diagnosed GBM isocitrate dehydrogenase (IDH)-wildtype undergoing resection were prospectively included in a database (n = 138). EOR and residual tumor volume (RTV) were quantified with semiautomated software. Formalin-fixed paraffin-embedded tumor tissues were analyzed by targeted next-generation sequencing. The association between recurrent genomic alterations and EOR/RTV was evaluated using a recursive partitioning analysis to identify thresholds of EOR or RTV that may predict survival. The Kaplan-Meier methods and multivariable Cox proportional hazards regression methods were applied for survival analysis.

RESULTS

Patients with EOR ≥88% experienced 44% prolonged overall survival (OS) in multivariable analysis (hazard ratio: 0.56, P = .030). Patients with alterations in the TP53 pathway and EOR <89% showed reduced OS compared to TP53 pathway altered patients with EOR>89% (10.5 vs 18.8 months; HR: 2.78, P = .013); however, EOR/RTV was not associated with OS in patients without alterations in the TP53 pathway. Meanwhile, in all patients with EOR <88%, PTEN -altered had significantly worse OS than PTEN -wildtype (9.5 vs 15.4 months; HR: 4.53, P < .001).

CONCLUSION

Our results suggest that a subset of molecularly defined GBM IDH-wildtype may benefit more from aggressive resections. Re-resections to optimize EOR might be beneficial in a subset of molecularly defined GBMs. Molecular alterations should be taken into consideration for surgical treatment decisions in GBM IDH-wildtype.

A ratiometric SERS strategy for the prediction of cancer cell proportion and guidance of glioma surgical resection

Rapid and accurate identification of tumor boundaries is critical for the cure of glioma, but it is difficult due to the invasive nature of glioma cells. This paper aimed to explore a rapid diagnostic strategy based on a label-free surface-enhanced Raman scattering (SERS) technique for the quantitative detection of glioma cell proportion intraoperatively. With silver nanoparticles as substrate, an in-depth SERS analysis was performed on simulated clinical samples containing normal brain tissue and different concentrations of patient-derived glioma cells. The results revealed two universal characteristic peaks of 655 and 717 cm-1, which strongly correlated with glioma cell proportion regardless of individual differences. Based on the intensity ratio of the two peaks, a ratiometric SERS strategy for the quantification of glioma cells was established by employing an artificial neuron network model and a polynomial regression model. Such a strategy accurately estimated the proportion of glioma cells in simulated clinical samples (R2 = 0.98) and frozen samples (R2 = 0.85). More importantly, it accurately facilitated the delineation of tumor margins in freshly obtained samples. Taken together, this SERS-based method ensured a rapid and more detailed identification of tumor margins during surgical resection, which could be beneficial for intraoperative decision-making and pathological evaluation.

Brain tumor detection and classification in MRI using hybrid ViT and GRU model with explainable AI in Southern Bangladesh

Brain tumor, a leading cause of uncontrolled cell growth in the central nervous system, presents substantial challenges in medical diagnosis and treatment. Early and accurate detection is essential for effective intervention. This study aims to enhance the detection and classification of brain tumors in Magnetic Resonance Imaging (MRI) scans using an innovative framework combining Vision Transformer (ViT) and Gated Recurrent Unit (GRU) models. We utilized primary MRI data from Bangabandhu Sheikh Mujib Medical College Hospital (BSMMCH) in Faridpur, Bangladesh. Our hybrid ViT-GRU model extracts essential features via ViT and identifies relationships between these features using GRU, addressing class imbalance and outperforming existing diagnostic methods. We extensively processed the dataset, and then trained the model using various optimizers (SGD, Adam, AdamW) and evaluated through rigorous 10-fold cross-validation. Additionally, we incorporated Explainable Artificial Intelligence (XAI) techniques-Attention Map, SHAP, and LIME-to enhance the interpretability of the model's predictions. For the primary dataset BrTMHD-2023, the ViT-GRU model achieved precision, recall, and F1-score metrics of 97%. The highest accuracies obtained with SGD, Adam, and AdamW optimizers were 81.66%, 96.56%, and 98.97%, respectively. Our model outperformed existing Transfer Learning models by 1.26%, as validated through comparative analysis and cross-validation. The proposed model also shows excellent performances with another Brain Tumor Kaggle Dataset outperforming the existing research done on the same dataset with 96.08% accuracy. The proposed ViT-GRU framework significantly improves the detection and classification of brain tumors in MRI scans. The integration of XAI techniques enhances the model's transparency and reliability, fostering trust among clinicians and facilitating clinical application. Future work will expand the dataset and apply findings to real-time diagnostic devices, advancing the field.

Therapeutic potentials and targeting strategies of quercetin on cancer cells: Challenges and future prospects

BACKGROUND

Every cell in the human body is vital because it maintains equilibrium and carries out a variety of tasks, including growth and development. These activities are carried out by a set of instructions carried by many different genes and organized into DNA. It is well recognized that some lifestyle decisions, like using tobacco, alcohol, UV, or multiple sexual partners, might increase one's risk of developing cancer. The advantages of natural products for any health issue are well known, and researchers are making attempts to separate flavonoid-containing substances from plants. Various parts of plants contain a phenolic compound called flavonoid. Quercetin, which belongs to the class of compounds known as flavones with chromone skeletal structure, has anti-cancer activity.

PURPOSE

The study was aimed at investigating the therapeutic action of the flavonoid quercetin on various cancer cells.

METHODS

The phrases quercetin, anti-cancer, nanoparticles, and cell line were used to search the data using online resources such as PubMed, and Google Scholar. Several critical previous studies have been included.

RESULTS

Quercetin inhibits various dysregulated signaling pathways that cause cancer cells to undergo apoptosis to exercise its anticancer effects. Numerous signaling pathways are impacted by quercetin, such as the Hedgehog system, Akt, NF-κB pathway, downregulated mutant p53, JAK/STAT, G1 phase arrest, Wnt/β-Catenin, and MAPK. There are downsides to quercetin, like hydrophobicity, first-pass effect, instability in the gastrointestinal tract, etc., because of which it is not well-established in the pharmaceutical industry. The solution to these drawbacks in the future is using bio-nanomaterials like chitosan, PLGA, liposomes, and silk fibroin as carriers, which can enhance the target specificity of quercetin. The first section of this review covers the specifics of flavonoids and quercetin; the second section covers the anti-cancer activity of quercetin; and the third section explains the drawbacks and conjugation of quercetin with nanoparticles for drug delivery by overcoming quercetin's drawback.

CONCLUSIONS

Overall, this review presented details about quercetin, which is a plant derivative with a promising molecular mechanism of action. They inhibit cancer by various mechanisms with little or no side effects. It is anticipated that plant-based materials will become increasingly relevant in the treatment of cancer.

Toward standardized brain tumor tissue processing protocols in neuro-oncology: a perspective for gliomas and beyond

Implementation of standardized protocols in neurooncology during the surgical resection of brain tumors is needed to advance the clinical treatment paradigms that use tissue for diagnosis, prognosis, bio-banking, and treatment. Currently recommendations on intraoperative tissue procurement only exist for diffuse gliomas but management of other brain tumor subtypes can also benefit from these protocols. Fresh tissue from surgical resection can now be used for intraoperative diagnostics and functional precision medicine assays. A multidisciplinary neuro-oncology perspective is critical to develop the best avenues for practical standardization. This perspective from the multidisciplinary Oncology Tissue Advisory Board (OTAB) discusses current advances, future directions, and the imperative of adopting standardized protocols for diverse brain tumor entities. There is a growing need for consistent operating room practices to enhance patient care, streamline research efforts, and optimize outcomes.

Science of science: A multidisciplinary field studying science

Science and knowledge are studied by researchers across many disciplines, examining how they are developed, what their current boundaries are and how we can advance them. By integrating evidence across disparate disciplines, the holistic field of science of science can address these foundational questions. This field illustrates how science is shaped by many interconnected factors: the cognitive processes of scientists, the historical evolution of science, economic incentives, institutional influences, computational approaches, statistical, mathematical and instrumental foundations of scientific inference, scientometric measures, philosophical and ethical dimensions of scientific concepts, among other influences. Achieving a comprehensive overview of a multifaceted field like the science of science requires pulling together evidence from the many sub-fields studying science across the natural and social sciences and humanities. This enables developing an interdisciplinary perspective of scientific practice, a more holistic understanding of scientific processes and outcomes, and more nuanced perspectives to how scientific research is conducted, influenced and evolves. It enables leveraging the strengths of various disciplines to create a holistic view of the foundations of science. Different researchers study science from their own disciplinary perspective and use their own methods, and there is a large divide between quantitative and qualitative researchers as they commonly do not read or cite research using other methodological approaches. A broader, synthesizing paper employing a qualitative approach can however help provide a bridge between disciplines by pulling together aspects of science (economic, scientometric, psychological, philosophical etc.). Such an approach enables identifying, across the range of fields, the powerful role of our scientific methods and instruments in shaping most aspects of our knowledge and science, whereas economic, social and historical influences help shape what knowledge we pursue. A unifying theory is then outlined for science of science - the new-methods-drive-science theory.

Towards next-generation diagnostic pathology: AI-empowered label-free multiphoton microscopy

Diagnostic pathology, historically dependent on visual scrutiny by experts, is essential for disease detection. Advances in digital pathology and developments in computer vision technology have led to the application of artificial intelligence (AI) in this field. Despite these advancements, the variability in pathologists' subjective interpretations of diagnostic criteria can lead to inconsistent outcomes. To meet the need for precision in cancer therapies, there is an increasing demand for accurate pathological diagnoses. Consequently, traditional diagnostic pathology is evolving towards "next-generation diagnostic pathology", prioritizing on the development of a multi-dimensional, intelligent diagnostic approach. Using nonlinear optical effects arising from the interaction of light with biological tissues, multiphoton microscopy (MPM) enables high-resolution label-free imaging of multiple intrinsic components across various human pathological tissues. AI-empowered MPM further improves the accuracy and efficiency of diagnosis, holding promise for providing auxiliary pathology diagnostic methods based on multiphoton diagnostic criteria. In this review, we systematically outline the applications of MPM in pathological diagnosis across various human diseases, and summarize common multiphoton diagnostic features. Moreover, we examine the significant role of AI in enhancing multiphoton pathological diagnosis, including aspects such as image preprocessing, refined differential diagnosis, and the prognostication of outcomes. We also discuss the challenges and perspectives faced by the integration of MPM and AI, encompassing equipment, datasets, analytical models, and integration into the existing clinical pathways. Finally, the review explores the synergy between AI and label-free MPM to forge novel diagnostic frameworks, aiming to accelerate the adoption and implementation of intelligent multiphoton pathology systems in clinical settings.

A Systematic Review of Real-Time Deep Learning Methods for Image-Based Cancer Diagnostics

Deep Learning (DL) drives academics to create models for cancer diagnosis using medical image processing because of its innate ability to recognize difficult-to-detect patterns in complex, noisy, and massive data. The use of deep learning algorithms for real-time cancer diagnosis is explored in depth in this work. Real-time medical diagnosis determines the illness or condition that accounts for a patient's symptoms and outward physical manifestations within a predetermined time frame. With a waiting period of anywhere between 5 days and 30 days, there are currently several ways, including screening tests, biopsies, and other prospective methods, that can assist in discovering a problem, particularly cancer. This article conducts a thorough literature review to understand how DL affects the length of this waiting period. In addition, the accuracy and turnaround time of different imaging modalities is evaluated with DL-based cancer diagnosis. Convolutional neural networks are critical for real-time cancer diagnosis, with models achieving up to 99.3% accuracy. The effectiveness and cost of the infrastructure required for real-time image-based medical diagnostics are evaluated. According to the report, generalization problems, data variability, and explainable DL are some of the most significant barriers to using DL in clinical trials. Making DL applicable for cancer diagnosis will be made possible by explainable DL.

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.

Exploring the Combination of Computer Vision and Surgical Neuroanatomy: A Workflow Involving Artificial Intelligence for the Identification of Skull Base Foramina

BACKGROUND

The skull base is a complex region in neurosurgery, featuring numerous foramina. Accurate identification of these foramina is imperative to avoid intraoperative complications and to facilitate educational progress in neurosurgical trainees. The intricate landscape of the skull base often challenges both clinicians and learners, necessitating innovative identification solutions. We aimed to develop a computer vision model that automates the identification and labeling of the skull base foramina from various image formats, enhancing surgical planning and educational outcomes.

METHODS

We employed a deep learning methodology, specifically using a convolutional neural network architecture. Our model was trained on a dataset comprising of 3560 high-resolution, annotated images of the skull base, taken from various perspectives and lighting conditions to ensure model generalizability. Model performance was quantitatively assessed using precision and recall metrics.

RESULTS

The convolutional neural network model demonstrated strong performance, achieving an average precision of 0.77. At a confidence threshold of 0.28, the model reached an optimal precision of 90.4% and a recall of 89.6%. Validation on an independent test set of images corroborated the model's capability to consistently and accurately identify and label multiple skull base foramina across diverse imaging scenarios.

CONCLUSIONS

This study successfully introduces a highly accurate computer vision model tailored for the identification of skull base foramina, illustrating the model's potential as a transformative tool in anatomical education and intraoperative structure visualization. The findings suggest promising avenues for future research into automated anatomical recognition models, suggesting a trajectory toward increasingly sophisticated aids in neurosurgical operations and education.

Artificial intelligence innovations in neurosurgical oncology: a narrative review

PURPOSE

Artificial Intelligence (AI) has become increasingly integrated clinically within neurosurgical oncology. This report reviews the cutting-edge technologies impacting tumor treatment and outcomes.

METHODS

A rigorous literature search was performed with the aid of a research librarian to identify key articles referencing AI and related topics (machine learning (ML), computer vision (CV), augmented reality (AR), virtual reality (VR), etc.) for neurosurgical care of brain or spinal tumors.

RESULTS

Treatment of central nervous system (CNS) tumors is being improved through advances across AI-such as AL, CV, and AR/VR. AI aided diagnostic and prognostication tools can influence pre-operative patient experience, while automated tumor segmentation and total resection predictions aid surgical planning. Novel intra-operative tools can rapidly provide histopathologic tumor classification to streamline treatment strategies. Post-operative video analysis, paired with rich surgical simulations, can enhance training feedback and regimens.

CONCLUSION

While limited generalizability, bias, and patient data security are current concerns, the advent of federated learning, along with growing data consortiums, provides an avenue for increasingly safe, powerful, and effective AI platforms in the future.

Precise Identification of Glioblastoma Micro-Infiltration at Cellular Resolution by Raman Spectroscopy

Precise identification of glioblastoma (GBM) microinfiltration, which is essential for achieving complete resection, remains an enormous challenge in clinical practice. Here, the study demonstrates that Raman spectroscopy effectively identifies GBM microinfiltration with cellular resolution in clinical specimens. The spectral differences between infiltrative lesions and normal brain tissues are attributed to phospholipids, nucleic acids, amino acids, and unsaturated fatty acids. These biochemical metabolites identified by Raman spectroscopy are further confirmed by spatial metabolomics. Based on differential spectra, Raman imaging resolves important morphological information relevant to GBM lesions in a label-free manner. The area under the receiver operating characteristic curve (AUC) for Raman spectroscopy combined with machine learning in detecting infiltrative lesions exceeds 95%. Most importantly, the cancer cell threshold identified by Raman spectroscopy is as low as 3 human GBM cells per 0.01 mm2. Raman spectroscopy enables the detection of previously undetectable diffusely infiltrative cancer cells, which holds potential value in guiding complete tumor resection in GBM patients.

Artificial intelligence to assist decision-making on pharmacotherapy: A feasibility study

Background

Artificial intelligence (AI) has the capability to analyze vast amounts of data and has been applied in various healthcare sectors. However, its effectiveness in aiding pharmacotherapy decision-making remains uncertain due to the intricate, patient-specific, and dynamic nature of this field.

Objective

This study sought to investigate the potential of AI in guiding pharmacotherapy decisions using clinical data such as diagnoses, laboratory results, and vital signs obtained from routine patient care.

Methods

Data of a previous study on medication therapy optimization was updated and adapted for the purpose of this study. Analysis was conducted using R software along with the tidymodels extension packages. The dataset was split into 74% for training and 26% for testing. Decision trees were selected as the primary model due to their simplicity, transparency, and interpretability. To prevent overfitting, bootstrapping techniques were employed, and hyperparameters were fine-tuned. Performance metrics such as areas under the curve and accuracies were computed.

Results

The study cohort comprised 101 elderly patients with multiple diagnoses and complex medication regimens. The AI model demonstrated prediction accuracies ranging from 38% to 100% for various cardiovascular drug classes. Laboratory data and vital signs could not be interpreted, as the effect and dependence were unclear for the model. The study revealed that the issue of AI lag time in responding to sudden changes could be addressed by manually adjusting decision trees, a task not feasible with neural networks.

Conclusion

In conclusion, the AI model exhibited promise in recommending appropriate medications for individual patients. While the study identified several obstacles during model development, most were successfully resolved. Future AI studies need to include the drug effect, not only the drug, if laboratory data is part of the decision. This could assist with interpreting their potential relationship. Human oversight and intervention remain essential for an AI-driven pharmacotherapy decision support system to ensure safe and effective patient care.

Progress and trends in neurological disorders research based on deep learning

In recent years, deep learning (DL) has emerged as a powerful tool in clinical imaging, offering unprecedented opportunities for the diagnosis and treatment of neurological disorders (NDs). This comprehensive review explores the multifaceted role of DL techniques in leveraging vast datasets to advance our understanding of NDs and improve clinical outcomes. Beginning with a systematic literature review, we delve into the utilization of DL, particularly focusing on multimodal neuroimaging data analysis-a domain that has witnessed rapid progress and garnered significant scientific interest. Our study categorizes and critically analyses numerous DL models, including Convolutional Neural Networks (CNNs), LSTM-CNN, GAN, and VGG, to understand their performance across different types of Neurology Diseases. Through particular analysis, we identify key benchmarks and datasets utilized in training and testing DL models, shedding light on the challenges and opportunities in clinical neuroimaging research. Moreover, we discuss the effectiveness of DL in real-world clinical scenarios, emphasizing its potential to revolutionize ND diagnosis and therapy. By synthesizing existing literature and describing future directions, this review not only provides insights into the current state of DL applications in ND analysis but also covers the way for the development of more efficient and accessible DL techniques. Finally, our findings underscore the transformative impact of DL in reshaping the landscape of clinical neuroimaging, offering hope for enhanced patient care and groundbreaking discoveries in the field of neurology. This review paper is beneficial for neuropathologists and new researchers in this field.

The oncological role of resection in newly diagnosed diffuse adult-type glioma defined by the WHO 2021 classification: a Review by the RANO resect group

Glioma resection is associated with prolonged survival, but neuro-oncological trials have frequently refrained from quantifying the extent of resection. The Response Assessment in Neuro-Oncology (RANO) resect group is an international, multidisciplinary group that aims to standardise research practice by delineating the oncological role of surgery in diffuse adult-type gliomas as defined per WHO 2021 classification. Favourable survival effects of more extensive resection unfold over months to decades depending on the molecular tumour profile. In tumours with a more aggressive natural history, supramaximal resection might correlate with additional survival benefit. Weighing the expected survival benefits of resection as dictated by molecular tumour profiles against clinical factors, including the introduction of neurological deficits, we propose an algorithm to estimate the oncological effects of surgery for newly diagnosed gliomas. The algorithm serves to select patients who might benefit most from extensive resection and to emphasise the relevance of quantifying the extent of resection in clinical trials.

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.

A Dual-Modal, Label-Free Raman Imaging Method for Rapid Virtual Staining of Large-Area Breast Cancer Tissue Sections

As one of the most common cancers, accurate, rapid, and simple histopathological diagnosis is very important for breast cancer. Raman imaging is a powerful technique for label-free analysis of tissue composition and histopathology, but it suffers from slow speed when applied to large-area tissue sections. In this study, we propose a dual-modal Raman imaging method that combines Raman mapping data with microscopy bright-field images to achieve virtual staining of breast cancer tissue sections. We validate our method on various breast tissue sections with different morphologies and biomarker expressions and compare it with the golden standard of histopathological methods. The results demonstrate that our method can effectively distinguish various types and components of tissues, and provide staining images comparable to stained tissue sections. Moreover, our method can improve imaging speed by up to 65 times compared to general spontaneous Raman imaging methods. It is simple, fast, and suitable for clinical applications.