Intraoperative Margin Assessment in Oral and Oropharyngeal Cancer Using Label-Free Fluorescence Lifetime Imaging and Machine Learning

Artificial intelligence in head and neck surgery: Potential applications and future perspectives

Artificial intelligence (AI) has the potential to improve the surgical treatment of patients with head and neck cancer. AI algorithms can analyse a wide range of data, including images, voice, molecular expression and raw clinical data. In the field of oncology, there are numerous AI practical applications, including diagnostics and treatment. AI can also develop predictive models to assess prognosis, overall survival, the likelihood of occult metastases, risk of complications and hospital length of stay.

Explainable Early Prediction of Gestational Diabetes Biomarkers by Combining Medical Background and Wearable Devices: A Pilot Study With a Cohort Group in South Africa

This study aims to explore the potential of Internet of Things (IoT) devices and explainable Artificial Intelligence (AI) techniques in predicting biomarker values associated with GDM when measured 13-16 weeks prior to diagnosis. We developed a system that forecasts biomarkers such as LDL, HDL, triglycerides, cholesterol, HbA1c, and results from the Oral Glucose Tolerance Test (OGTT) including fasting glucose, 1-hour, and 2-hour post-load glucose values. These biomarker values are predicted based on sensory measurements collected around week 12 of pregnancy, including continuous glucose levels, short physical movement recordings, and medical background information. To the best of our knowledge, this is the first study to forecast GDM-associated biomarker values 13 to 16 weeks prior to the GDM screening test, using continuous glucose monitoring devices, a wristband for activity detection, and medical background data. We applied machine learning models, specifically Decision Tree and Random Forest Regressors, along with Coupled-Matrix Tensor Factorisation (CMTF) and Elastic Net techniques, examining all possible combinations of these methods across different data modalities. The results demonstrated good performance for most biomarkers. On average, the models achieved Mean Squared Error (MSE) between 0.29 and 0.42 and Mean Absolute Error (MAE) between 0.23 and 0.45 for biomarkers like HDL, LDL, cholesterol, and HbA1c. For the OGTT glucose values, the average MSE ranged from 0.95 to 2.44, and the average MAE ranged from 0.72 to 0.91. Additionally, the utilisation of CMTF with Alternating Least Squares technique yielded slightly better results (0.16 MSE and 0.07 MAE on average) compared to the well-known Elastic Net feature selection technique. While our study was conducted with a limited cohort in South Africa, our findings offer promising indications regarding the potential for predicting biomarker values in pregnant women through the integration of wearable devices and medical background data in the analysis. Nevertheless, further validation on a larger, more diverse cohort is imperative to substantiate these encouraging results.

Clinical applications of artificial intelligence in robotic surgery

Artificial intelligence (AI) is revolutionizing nearly every aspect of modern life. In the medical field, robotic surgery is the sector with some of the most innovative and impactful advancements. In this narrative review, we outline recent contributions of AI to the field of robotic surgery with a particular focus on intraoperative enhancement. AI modeling is allowing surgeons to have advanced intraoperative metrics such as force and tactile measurements, enhanced detection of positive surgical margins, and even allowing for the complete automation of certain steps in surgical procedures. AI is also Query revolutionizing the field of surgical education. AI modeling applied to intraoperative surgical video feeds and instrument kinematics data is allowing for the generation of automated skills assessments. AI also shows promise for the generation and delivery of highly specialized intraoperative surgical feedback for training surgeons. Although the adoption and integration of AI show promise in robotic surgery, it raises important, complex ethical questions. Frameworks for thinking through ethical dilemmas raised by AI are outlined in this review. AI enhancements in robotic surgery is some of the most groundbreaking research happening today, and the studies outlined in this review represent some of the most exciting innovations in recent years.

Fibre-based fluorescence-lifetime imaging microscopy: a real-time biopsy guidance tool for suspected lung cancer

Lung cancer is the most common cause of cancer-related deaths worldwide. Early detection improves outcomes, however, existing sampling techniques are associated with suboptimal diagnostic yield and procedure-related complications. Autofluorescence-based fluorescence-lifetime imaging microscopy (FLIM), a technique which measures endogenous fluorophore decay rates, may aid identification of optimal biopsy sites in suspected lung cancer. Our fibre-based fluorescence-lifetime imaging system, utilising 488 nm excitation, which is deliverable via existing diagnostic platforms, enables real-time visualisation and lifetime analysis of distal alveolar lung structure. We evaluated the diagnostic accuracy of the fibre-based fluorescence-lifetime imaging system to detect changes in fluorescence lifetime in freshly resected ex vivo lung cancer and adjacent healthy tissue as a first step towards future translation. The study compares paired non-small cell lung cancer (NSCLC) and non-cancerous tissues with gold standard diagnostic pathology to assess the performance of the technique. Paired NSCLC and non-cancerous lung tissues were obtained from thoracic resection patients (N=21). A clinically compatible 488 nm fluorescence-lifetime endomicroscopy platform was used to acquire simultaneous fluorescence intensity and lifetime images. Fluorescence lifetimes were calculated using a computationally-lightweight, rapid lifetime determination method. Fluorescence lifetime was significantly reduced in ex vivo lung cancer, compared with non-cancerous lung tissue [mean ± standard deviation (SD), 1.79±0.40 vs. 2.15±0.26 ns, P<0.0001], and fluorescence intensity images demonstrated distortion of alveolar elastin autofluorescence structure. Fibre-based fluorescence-lifetime imaging demonstrated good performance characteristics for distinguishing lung cancer, from adjacent non-cancerous tissue, with 81.0% sensitivity and 71.4% specificity. Our novel fibre-based fluorescence-lifetime imaging system, which enables label-free imaging and quantitative lifetime analysis, discriminates ex vivo lung cancer from adjacent healthy tissue. This minimally invasive technique has potential to be translated as a real-time biopsy guidance tool, capable of optimising diagnostic accuracy in lung cancer.

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, and robustness. Inspired by the concept of Edge Artificial Intelligence (Edge AI), we propose a robust approach that enables fast FLI with no degradation of accuracy. This approach couples a recurrent neural network (RNN), which is trained to estimate the fluorescence lifetime directly from raw timestamps without building histograms, to SPAD TCSPC systems, thereby drastically reducing transfer data volumes and hardware resource utilization, and enabling real-time FLI acquisition. We train two variants of the RNN on a synthetic dataset and compare the results to those obtained using center-of-mass method (CMM) and least squares fitting (LS fitting). Results demonstrate that two RNN variants, gated recurrent unit (GRU) and long short-term memory (LSTM), are comparable to CMM and LS fitting in terms of accuracy, while outperforming them in the presence of background noise by a large margin. To explore the ultimate limits of the approach, we derive the Cramer-Rao lower bound of the measurement, showing that RNN yields lifetime estimations with near-optimal precision. To demonstrate real-time operation, we build a FLI microscope based on an existing SPAD TCSPC system comprising a 32[Formula: see text]32 SPAD sensor named Piccolo. Four quantized GRU cores, capable of processing up to 4 million photons per second, are deployed on the Xilinx Kintex-7 FPGA that controls the Piccolo. Powered by the GRU, the FLI setup can retrieve real-time fluorescence lifetime images at up to 10 frames per second. The proposed FLI system is promising and ideally suited for biomedical applications, including biological imaging, biomedical diagnostics, and fluorescence-assisted surgery, etc.

Applications of machine learning in time-domain fluorescence lifetime imaging: a review

Many medical imaging modalities have benefited from recent advances in Machine Learning (ML), specifically in deep learning, such as neural networks. Computers can be trained to investigate and enhance medical imaging methods without using valuable human resources. In recent years, Fluorescence Lifetime Imaging (FLIm) has received increasing attention from the ML community. FLIm goes beyond conventional spectral imaging, providing additional lifetime information, and could lead to optical histopathology supporting real-time diagnostics. However, most current studies do not use the full potential of machine/deep learning models. As a developing image modality, FLIm data are not easily obtainable, which, coupled with an absence of standardisation, is pushing back the research to develop models which could advance automated diagnosis and help promote FLIm. In this paper, we describe recent developments that improve FLIm image quality, specifically time-domain systems, and we summarise sensing, signal-to-noise analysis and the advances in registration and low-level tracking. We review the two main applications of ML for FLIm: lifetime estimation and image analysis through classification and segmentation. We suggest a course of action to improve the quality of ML studies applied to FLIm. Our final goal is to promote FLIm and attract more ML practitioners to explore the potential of lifetime imaging.

First-in-human Evaluation of a Prostate-specific Membrane Antigen-targeted Near-infrared Fluorescent Small Molecule for Fluorescence-based Identification of Prostate Cancer in Patients with High-risk Prostate Cancer Undergoing Robotic-assisted Prostatectomy

BACKGROUND

Men with high-risk prostate cancer undergoing surgery likely recur due to failure to completely excise regional and/or local disease.

OBJECTIVE

The first-in-human evaluation of safety, pharmacokinetics, and exploratory efficacy of IS-002, a novel near-infrared prostate-specific membrane antigen (PSMA)-targeted fluorescence imaging agent, designed for intraoperative prostate cancer visualization.

DESIGN, SETTING, AND PARTICIPANTS

A phase 1, single-center, dose-escalation study was conducted in 24 men with high-risk prostate cancer scheduled for robotic-assisted radical prostatectomy with (extended) pelvic lymph node dissection using the da Vinci surgical system.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

Adverse events (AEs), vital signs, complete blood count, complete metabolic panel, urinalysis, and electrocardiogram were assessed over a 14-d period and compared with baseline. The pharmacokinetic profile of IS-002 was determined. Diagnostic accuracy was assessed for exploratory efficacy.

RESULTS AND LIMITATIONS

AEs predominantly included discoloration of urine (n = 22/24; expected, related, grade 1). There were no grade ≥2 AEs. IS-002 Cmax and area under the curve increased with increasing dose. Plasma concentrations declined rapidly in a biphasic manner, with the median terminal half-lives ranging from 5.0 to 7.6 h, independent of dose and renal function. At 25 μg/kg, the exploratory efficacy readouts for the negative and positive predictive values were, 97% and 45% for lymph nodes, and 100% and 80% for residual/locoregional disease detection, respectively.

CONCLUSIONS

IS-002 is safe and well tolerated, and has the potential to enable intraoperative tumor detection that could not be identified using standard imaging.

PATIENT SUMMARY

IS-002 is a new imaging agent that specifically targets the prostate-specific membrane antigen receptor. In this study, we tested IS-002 for the first time in men with high-risk prostate cancer undergoing surgery and found that IS-002 is safe, is cleared from the body quickly, and potentially allows identification of prostate cancer in areas that would not be identified by conventional white light imaging.

Point Projection Mapping System for Tracking, Registering, Labeling, and Validating Optical Tissue Measurements

The validation of newly developed optical tissue-sensing techniques for tumor detection during cancer surgery requires an accurate correlation with the histological results. Additionally, such an accurate correlation facilitates precise data labeling for developing high-performance machine learning tissue-classification models. In this paper, a newly developed Point Projection Mapping system will be introduced, which allows non-destructive tracking of the measurement locations on tissue specimens. Additionally, a framework for accurate registration, validation, and labeling with the histopathology results is proposed and validated on a case study. The proposed framework provides a more-robust and accurate method for the tracking and validation of optical tissue-sensing techniques, which saves time and resources compared to the available conventional techniques.

Trends in Positive Surgical Margins in cT3-T4 Oral Cavity Squamous Cell Carcinoma

OBJECTIVE

Positive surgical margins in oral cavity squamous cell carcinoma are associated with cost escalation, treatment intensification, and greater risk of recurrence and mortality. The positive margin rate has been decreasing for cT1-T2 oral cavity cancer over the past 2 decades. We aim to evaluate positive margin rates in cT3-T4 oral cavity cancer over time, and determine factors associated with positive margins.

STUDY DESIGN

Retrospective analysis of a national database.

SETTING

National Cancer Database 2004 to 2018.

METHODS

All adult patients diagnosed between 2004 and 2018 who underwent primary curative intent surgery for previously untreated cT3-T4 oral cavity cancer with known margin status were included. Logistic univariable and multivariable regression analyses were performed to identify factors associated with positive margins.

RESULTS

Among 16,326 patients with cT3 or cT4 oral cavity cancer, positive margins were documented in 2932 patients (18.1%). Later year of treatment was not significantly associated with positive margins (odds ratio [OR] 0.98, 95% confidence interval [CI] 0.96-1.00). The proportion of patients treated at academic centers increased over time (OR 1.02, 95% CI 1.01-1.03). On multivariable analysis, positive margins were significantly associated with hard palate primary, cT4 tumors, advancing N stage, lymphovascular invasion, poorly differentiated histology, and treatment at nonacademic or low-volume centers.

CONCLUSION

Despite increased treatment at academic centers for locally advanced oral cavity cancer, there has been no significant decrease in positive margin rates which remains high at 18.1%. Novel techniques for margin planning and assessment may be required to decrease positive margin rates in locally advanced oral cavity cancer.

Enhancing head and neck tumor management with artificial intelligence: Integration and perspectives

Head and neck tumors (HNTs) constitute a multifaceted ensemble of pathologies that primarily involve regions such as the oral cavity, pharynx, and nasal cavity. The intricate anatomical structure of these regions poses considerable challenges to efficacious treatment strategies. Despite the availability of myriad treatment modalities, the overall therapeutic efficacy for HNTs continues to remain subdued. In recent years, the deployment of artificial intelligence (AI) in healthcare practices has garnered noteworthy attention. AI modalities, inclusive of machine learning (ML), neural networks (NNs), and deep learning (DL), when amalgamated into the holistic management of HNTs, promise to augment the precision, safety, and efficacy of treatment regimens. The integration of AI within HNT management is intricately intertwined with domains such as medical imaging, bioinformatics, and medical robotics. This article intends to scrutinize the cutting-edge advancements and prospective applications of AI in the realm of HNTs, elucidating AI's indispensable role in prevention, diagnosis, treatment, prognostication, research, and inter-sectoral integration. The overarching objective is to stimulate scholarly discourse and invigorate insights among medical practitioners and researchers to propel further exploration, thereby facilitating superior therapeutic alternatives for patients.

Anatomy-Specific Classification Model Using Label-Free FLIm to Aid Intraoperative Surgical Guidance of Head and Neck Cancer

Intraoperative identification of head and neck cancer tissue is essential to achieve complete tumor resection and mitigate tumor recurrence. Mesoscopic fluorescence lifetime imaging (FLIm) of intrinsic tissue fluorophores emission has demonstrated the potential to demarcate the extent of the tumor in patients undergoing surgical procedures of the oral cavity and the oropharynx. Here, we report FLIm-based classification methods using standard machine learning models that account for the diverse anatomical and biochemical composition across the head and neck anatomy to improve tumor region identification. Three anatomy-specific binary classification models were developed (i.e., "base of tongue," "palatine tonsil," and "oral tongue"). FLIm data from patients (N = 85) undergoing upper aerodigestive oncologic surgery were used to train and validate the classification models using a leave-one-patient-out cross-validation method. These models were evaluated for two classification tasks: (1) to discriminate between healthy and cancer tissue, and (2) to apply the binary classification model trained on healthy and cancer to discriminate dysplasia through transfer learning. This approach achieved superior classification performance compared to models that are anatomy-agnostic; specifically, a ROC-AUC of 0.94 was for the first task and 0.92 for the second. Furthermore, the model demonstrated detection of dysplasia, highlighting the generalization of the FLIm-based classifier. Current findings demonstrate that a classifier that accounts for tumor location can improve the ability to accurately identify surgical margins and underscore FLIm's potential as a tool for surgical guidance in head and neck cancer patients, including those subjects of robotic surgery.

Pulse-sampling fluorescence lifetime imaging: evaluation of photon economy

This Letter presents an experimental study comparing the photon rate and photon economy of pulse sampling fluorescence lifetime imaging (PS-FLIm) with the conventional time-correlated single photon counting (TCSPC) technique. We found that PS-FLIm has a significantly higher photon detection rate (200 MHz) compared with TCSPC (2-8 MHz) but lower photon economy (4-5 versus 1-1.3). The main factor contributing to the lower photon economy in PS-FLIm is laser pulse variability. These results demonstrate that PS-FLIm offers 25× faster imaging speed than TCSPC while maintaining room light rejection in clinical settings. This makes PS-FLIm a robust technique for clinical applications.

Machine Learning and Artificial Intelligence in Surgical Research

Machine learning, a subtype of artificial intelligence, is an emerging field of surgical research dedicated to predictive modeling. From its inception, machine learning has been of interest in medical and surgical research. Built on traditional research metrics for optimal success, avenues of research include diagnostics, prognosis, operative timing, and surgical education, in a variety of surgical subspecialties. Machine learning represents an exciting and developing future in the world of surgical research that will not only allow for more personalized and comprehensive medical care.

Intraoperative Imaging Techniques to Improve Surgical Resection Margins of Oropharyngeal Squamous Cell Cancer: A Comprehensive Review of Current Literature

Inadequate resection margins in head and neck squamous cell carcinoma surgery necessitate adjuvant therapies such as re-resection and radiotherapy with or without chemotherapy and imply increasing morbidity and worse prognosis. On the other hand, taking larger margins by extending the resection also leads to avoidable increased morbidity. Oropharyngeal squamous cell carcinomas (OPSCCs) are often difficult to access; resections are limited by anatomy and functionality and thus carry an increased risk for close or positive margins. Therefore, there is a need to improve intraoperative assessment of resection margins. Several intraoperative techniques are available, but these often lead to prolonged operative time and are only suitable for a subgroup of patients. In recent years, new diagnostic tools have been the subject of investigation. This study reviews the available literature on intraoperative techniques to improve resection margins for OPSCCs. A literature search was performed in Embase, PubMed, and Cochrane. Narrow band imaging (NBI), high-resolution microendoscopic imaging, confocal laser endomicroscopy, frozen section analysis (FSA), ultrasound (US), computed tomography scan (CT), (auto) fluorescence imaging (FI), and augmented reality (AR) have all been used for OPSCC. NBI, FSA, and US are most commonly used and increase the rate of negative margins. Other techniques will become available in the future, of which fluorescence imaging has high potential for use with OPSCC.

Advances in the intraoperative delineation of malignant glioma margin

Surgery plays a critical role in the treatment of malignant glioma. However, due to the infiltrative growth and brain shift, it is difficult for neurosurgeons to distinguish malignant glioma margins with the naked eye and with preoperative examinations. Therefore, several technologies were developed to determine precise tumor margins intraoperatively. Here, we introduced four intraoperative technologies to delineate malignant glioma margin, namely, magnetic resonance imaging, fluorescence-guided surgery, Raman histology, and mass spectrometry. By tracing their detecting principles and developments, we reviewed their advantages and disadvantages respectively and imagined future trends.

Autofluorescence Image-Guided Endoscopy in the Management of Upper Aerodigestive Tract Tumors

At this juncture, autofluorescence and narrow-band imaging have resurfaced in the medicine arena in parallel with current technology advancement. The emergence of newly developed optical instrumentation in addition to the discovery of new fluorescence biomolecules have contributed to a refined management of diseases and tumors, especially in the management of upper aerodigestive tract tumors. The advancement in multispectral imaging and micro-endoscopy has also escalated the trends further in the setting of the management of this tumor, in order to gain not only the best treatment outcomes but also facilitate early tumor diagnosis. This includes the usage of autofluorescence endoscopy for screening, diagnosis and treatment of this tumor. This is crucial, as microtumoral deposit at the periphery of the gross tumor can be only assessed via an enhanced endoscopy and even more precisely with autofluorescence endoscopic techniques. Overall, with this new technique, optimum management can be achieved for these patients. Hence, the treatment outcomes can be improved and patients are able to attain better prognosis and survival.

Squamous Cell Carcinoma of Skin Cancer Margin Classification From Digital Histopathology Images Using Deep Learning

Objectives

Now a days, squamous cell carcinoma (SCC) margin assessment is done by examining histopathology images and inspection of whole slide images (WSI) using a conventional microscope. This is time-consuming, tedious, and depends on experts’ experience which may lead to misdiagnosis and mistreatment plans. This study aims to develop a system for the automatic diagnosis of skin cancer margin for squamous cell carcinoma from histopathology microscopic images by applying deep learning techniques.

Methods

The system was trained, validated, and tested using histopathology images of SCC cancer locally acquired from Jimma Medical Center Pathology Department from seven different skin sites using an Olympus digital microscope. All images were preprocessed and trained with transfer learning pre-trained models by fine-tuning the hyper-parameter of the selected models.

Results

The overall best training accuracy of the models become 95.3%, 97.1%, 89.8%, and 89.9% on EffecientNetB0, MobileNetv2, ResNet50, VGG16 respectively. In addition to this, the best validation accuracy of the models was 94.7%, 91.8%, 87.8%, and 86.7% respectively. The best testing accuracy of the models at the same epoch was 95.2%, 91.5%, 87%, and 85.5% respectively. From these models, EfficientNetB0 showed the best average training and testing accuracy than the other models.

Conclusions

The system assists the pathologist during the margin assessment of SCC by decreasing the diagnosis time from an average of 25 minutes to less than a minute.

Intraoperative delineation of p16+ oropharyngeal carcinoma of unknown primary origin with fluorescence lifetime imaging: Preliminary report

BACKGROUND

This study evaluated whether fluorescence lifetime imaging (FLIm), coupled with standard diagnostic workups, could enhance primary lesion detection in patients with p16+ head and neck squamous cell carcinoma of the unknown primary (HNSCCUP).

METHODS

FLIm was integrated into transoral robotic surgery to acquire optical data on six HNSCCUP patients' oropharyngeal tissues. An additional 55-patient FLIm dataset, comprising conventional primary tumors, trained a machine learning classifier; the output predicted the presence and location of HNSCCUP for the six patients. Validation was performed using histopathology.

RESULTS

Among the six HNSCCUP patients, p16+ occult primary was surgically identified in three patients, whereas three patients ultimately had no identifiable primary site in the oropharynx. FLIm correctly detected HNSCCUP in all three patients (ROC-AUC: 0.90 ± 0.06), and correctly predicted benign oropharyngeal tissue for the remaining three patients. The mean sensitivity was 95% ± 3.5%, and specificity 89% ± 12.7%.

CONCLUSIONS

FLIm may be a useful diagnostic adjunct for detecting HNSCCUP.

Intraoperative In Vivo Imaging Modalities in Head and Neck Cancer Surgical Margin Delineation: A Systematic Review

Surgical margin status is one of the strongest prognosticators in predicting patient outcomes in head and neck cancer, yet head and neck surgeons continue to face challenges in the accurate detection of these margins with the current standard of care. Novel intraoperative imaging modalities have demonstrated great promise for potentially increasing the accuracy and efficiency in surgical margin delineation. In this current study, we collated and analyzed various intraoperative imaging modalities utilized in head and neck cancer to evaluate their use in discriminating malignant from healthy tissues. The authors conducted a systematic database search through PubMed/Medline, Web of Science, and EBSCOhost (CINAHL). Study screening and data extraction were performed and verified by the authors, and more studies were added through handsearching. Here, intraoperative imaging modalities are described, including optical coherence tomography, narrow band imaging, autofluorescence, and fluorescent-tagged probe techniques. Available sensitivities and specificities in delineating cancerous from healthy tissues ranged from 83.0% to 100.0% and 79.2% to 100.0%, respectively, across the different imaging modalities. Many of these initial studies are in small sample sizes, with methodological differences that preclude more extensive quantitative comparison. Thus, there is impetus for future larger studies examining and comparing the efficacy of these intraoperative imaging technologies.

A layer-level multi-scale architecture for lung cancer classification with fluorescence lifetime imaging endomicroscopy

In this paper, we introduce our unique dataset of fluorescence lifetime imaging endo/microscopy (FLIM), containing over 100,000 different FLIM images collected from 18 pairs of cancer/non-cancer human lung tissues of 18 patients by our custom fibre-based FLIM system. The aim of providing this dataset is that more researchers from relevant fields can push forward this particular area of research. Afterwards, we describe the best practice of image post-processing suitable per the dataset. In addition, we propose a novel hierarchically aggregated multi-scale architecture to improve the binary classification performance of classic CNNs. The proposed model integrates the advantages of multi-scale feature extraction at different levels, where layer-wise global information is aggregated with branch-wise local information. We integrate the proposal, namely ResNetZ, into ResNet, and appraise it on the FLIM dataset. Since ResNetZ can be configured with a shortcut connection and the aggregations by Addition or Concatenation, we first evaluate the impact of different configurations on the performance. We thoroughly examine various ResNetZ variants to demonstrate the superiority. We also compare our model with a feature-level multi-scale model to illustrate the advantages and disadvantages of multi-scale architectures at different levels.

Fast Analysis of Time-Domain Fluorescence Lifetime Imaging via Extreme Learning Machine

We present a fast and accurate analytical method for fluorescence lifetime imaging microscopy (FLIM), using the extreme learning machine (ELM). We used extensive metrics to evaluate ELM and existing algorithms. First, we compared these algorithms using synthetic datasets. The results indicate that ELM can obtain higher fidelity, even in low-photon conditions. Afterwards, we used ELM to retrieve lifetime components from human prostate cancer cells loaded with gold nanosensors, showing that ELM also outperforms the iterative fitting and non-fitting algorithms. By comparing ELM with a computational efficient neural network, ELM achieves comparable accuracy with less training and inference time. As there is no back-propagation process for ELM during the training phase, the training speed is much higher than existing neural network approaches. The proposed strategy is promising for edge computing with online training.

Deep learning in macroscopic diffuse optical imaging

SIGNIFICANCE

Biomedical optics system design, image formation, and image analysis have primarily been guided by classical physical modeling and signal processing methodologies. Recently, however, deep learning (DL) has become a major paradigm in computational modeling and has demonstrated utility in numerous scientific domains and various forms of data analysis.

AIM

We aim to comprehensively review the use of DL applied to macroscopic diffuse optical imaging (DOI).

APPROACH

First, we provide a layman introduction to DL. Then, the review summarizes current DL work in some of the most active areas of this field, including optical properties retrieval, fluorescence lifetime imaging, and diffuse optical tomography.

RESULTS

The advantages of using DL for DOI versus conventional inverse solvers cited in the literature reviewed herein are numerous. These include, among others, a decrease in analysis time (often by many orders of magnitude), increased quantitative reconstruction quality, robustness to noise, and the unique capability to learn complex end-to-end relationships.

CONCLUSIONS

The heavily validated capability of DL's use across a wide range of complex inverse solving methodologies has enormous potential to bring novel DOI modalities, otherwise deemed impractical for clinical translation, to the patient's bedside.

Current Trends in Precision Medicine and Next-Generation Sequencing in Head and Neck Cancer

OPINION STATEMENT

As the field of oncology enters the era of precision medicine and targeted therapies, we have come to realize that there may be no single "magic bullet" for patients with head and neck cancer. While immune check point inhibitors and some targeted therapeutics have shown great promise in improving oncologic outcomes, the current standard of care in most patients with head and neck squamous cell carcinoma (HNSCC) remains a combination of surgery, radiation, and/or cytotoxic chemotherapy. Nevertheless, advances in precision medicine, next-generation sequencing (NGS), and targeted therapies have a potential future in the treatment of HNSCC. These roles include increased patient treatment stratification based on predictive biomarkers or targetable mutations and novel combinatorial regimens with existing HNSCC treatments. There remain challenges to precision medicine and NGS in HNSCC, including intertumor and intratumor heterogeneity, challenging targets, and need for further trials validating the utility of NGS and precision medicine. Additionally, there is a need for evidence-based practice guidelines to assist clinicians on how to appropriately incorporate NGS in care for HNSCC. In this review, we describe the current state of precision medicine and NGS in HNSCC and opportunities for future advances in this challenging but important field.

End-to-End Neural Network for Feature Extraction and Cancer Diagnosis of In Vivo Fluorescence Lifetime Images of Oral Lesions

In contrast to previous studies that focused on classical machine learning algorithms and hand-crafted features, we present an end-to-end neural network classification method able to accommodate lesion heterogeneity for improved oral cancer diagnosis using multispectral autofluorescence lifetime imaging (maFLIM) endoscopy. Our method uses an autoencoder framework jointly trained with a classifier designed to handle overfitting problems with reduced databases, which is often the case in healthcare applications. The autoencoder guides the feature extraction process through the reconstruction loss and enables the potential use of unsupervised data for domain adaptation and improved generalization. The classifier ensures the features extracted are task-specific, providing discriminative information for the classification task. The data-driven feature extraction method automatically generates task-specific features directly from fluorescence decays, eliminating the need for iterative signal reconstruction. We validate our proposed neural network method against support vector machine (SVM) baselines, with our method showing a 6.5%-8.3% increase in sensitivity. Our results show that neural networks that implement data-driven feature extraction provide superior results and enable the capacity needed to target specific issues, such as inter-patient variability and the heterogeneity of oral lesions.Clinical relevance- We improve standard classification algorithms for in vivo diagnosis of oral cancer lesions from maFLIm for clinical use in cancer screening, reducing unnecessary biopsies and facilitating early detection of oral cancer.

Applied machine learning in cancer research: A systematic review for patient diagnosis, classification and prognosis

Artificial Intelligence (AI) has recently altered the landscape of cancer research and medical oncology using traditional Machine Learning (ML) algorithms and cutting-edge Deep Learning (DL) architectures. In this review article we focus on the ML aspect of AI applications in cancer research and present the most indicative studies with respect to the ML algorithms and data used. The PubMed and dblp databases were considered to obtain the most relevant research works of the last five years. Based on a comparison of the proposed studies and their research clinical outcomes concerning the medical ML application in cancer research, three main clinical scenarios were identified. We give an overview of the well-known DL and Reinforcement Learning (RL) methodologies, as well as their application in clinical practice, and we briefly discuss Systems Biology in cancer research. We also provide a thorough examination of the clinical scenarios with respect to disease diagnosis, patient classification and cancer prognosis and survival. The most relevant studies identified in the preceding year are presented along with their primary findings. Furthermore, we examine the effective implementation and the main points that need to be addressed in the direction of robustness, explainability and transparency of predictive models. Finally, we summarize the most recent advances in the field of AI/ML applications in cancer research and medical oncology, as well as some of the challenges and open issues that need to be addressed before data-driven models can be implemented in healthcare systems to assist physicians in their daily practice.

Machine-Learning Assisted Discrimination of Precancerous and Cancerous from Healthy Oral Tissue Based on Multispectral Autofluorescence Lifetime Imaging Endoscopy

Multispectral autofluorescence lifetime imaging (maFLIM) can be used to clinically image a plurality of metabolic and biochemical autofluorescence biomarkers of oral epithelial dysplasia and cancer. This study tested the hypothesis that maFLIM-derived autofluorescence biomarkers can be used in machine-learning (ML) models to discriminate dysplastic and cancerous from healthy oral tissue. Clinical widefield maFLIM endoscopy imaging of cancerous and dysplastic oral lesions was performed at two clinical centers. Endoscopic maFLIM images from 34 patients acquired at one of the clinical centers were used to optimize ML models for automated discrimination of dysplastic and cancerous from healthy oral tissue. A computer-aided detection system was developed and applied to a set of endoscopic maFLIM images from 23 patients acquired at the other clinical center, and its performance was quantified in terms of the area under the receiver operating characteristic curve (ROC-AUC). Discrimination of dysplastic and cancerous from healthy oral tissue was achieved with an ROC-AUC of 0.81. This study demonstrates the capabilities of widefield maFLIM endoscopy to clinically image autofluorescence biomarkers that can be used in ML models to discriminate dysplastic and cancerous from healthy oral tissue. Widefield maFLIM endoscopy thus holds potential for automated in situ detection of oral dysplasia and cancer.

Fluorescence Guided Surgery

Fluorescence guided surgery (FGS) is an imaging technique that allows the surgeon to visualise different structures and types of tissue during a surgical procedure that may not be as visible under white light conditions. Due to the many potential advantages of fluorescence guided surgery compared to more traditional clinical imaging techniques such as its higher contrast and sensitivity, less subjective use, and ease of instrument operation, the research interest in fluorescence guided surgery continues to grow over various key aspects such as fluorescent probe development and surgical system development as well as its potential clinical applications. This review looks to summarise some of the emerging opportunities and developments that have already been made in fluorescence guided surgery in recent years while highlighting its advantages as well as limitations that need to be overcome in order to utilise the full potential of fluorescence within the surgical environment.

Real-time cancer diagnosis of breast cancer using fluorescence lifetime endoscopy based on the pH

A biopsy is often performed for the diagnosis of cancer during a surgical operation. In addition, pathological biopsy is required to discriminate the margin between cancer tissues and normal tissues in surgical specimens. In this study, we presented a novel method for discriminating between tumor and normal tissues using fluorescence lifetime endoscopy (FLE). We demonstrated the relationship between the fluorescence lifetime and pH in fluorescein using the proposed fluorescence lifetime measurement system. We also showed that cancer could be diagnosed based on this relationship by assessing differences in pH based fluorescence lifetime between cancer and normal tissues using two different types of tumor such as breast tumors (MDA-MB-361) and skin tumors (A375), where cancer tissues have ranged in pH from 4.5 to 7.0 and normal tissues have ranged in pH from 7.0 to 7.4. To support this approach, we performed hematoxylin and eosin (H&E) staining test of normal and cancer tissues within a certain area. From these results, we showed the ability to diagnose a cancer using FLE technique, which were consistent with the diagnosis of a cancer with H&E staining test. In summary, the proposed pH-based FLE technique could provide a real time, in vivo, and in-situ clinical diagnostic method for the cancer surgical and could be presented as an alternative to biopsy procedures.

Machine learning in dental, oral and craniofacial imaging: a review of recent progress

Artificial intelligence has been emerging as an increasingly important aspect of our daily lives and is widely applied in medical science. One major application of artificial intelligence in medical science is medical imaging. As a major component of artificial intelligence, many machine learning models are applied in medical diagnosis and treatment with the advancement of technology and medical imaging facilities. The popularity of convolutional neural network in dental, oral and craniofacial imaging is heightening, as it has been continually applied to a broader spectrum of scientific studies. Our manuscript reviews the fundamental principles and rationales behind machine learning, and summarizes its research progress and its recent applications specifically in dental, oral and craniofacial imaging. It also reviews the problems that remain to be resolved and evaluates the prospect of the future development of this field of scientific study.

Intraoperative Mapping of Parathyroid Glands Using Fluorescence Lifetime Imaging

BACKGROUND

Hypoparathyroidism is a common complication following thyroidectomy. There is a need for technology to aid surgeons in identifying the parathyroid glands. In contrast to near infrared technologies, fluorescence lifetime imaging (FLIm) is not affected by ambient light and may be valuable in identifying parathyroid tissue, but has never been evaluated in this capacity.

METHODS

We used FLIm to measure the UV induced (355 nm) time-resolved autofluorescence signatures (average lifetimes in 3 spectral emission channels) of thyroid, parathyroid, lymphoid and adipose tissue in 21 patients undergoing thyroid and parathyroid surgery. The Mann-Whitney U test was used to assess the ability of FLIm to discriminate normocellular parathyroid from each of the other tissues. Various machine learning classifiers (random forests, neural network, support vector machine) were then evaluated to recognize parathyroid through a leave-one-out cross-validation.

RESULTS

Statistically significant differences in average lifetime were observed between parathyroid and each of the other tissue types in spectral channels 2 and 3 respectively. The largest change was observed between adipose tissue and parathyroid (P < 0.001), while less pronounced but still significant changes were observed when comparing parathyroid with lymphoid tissue (P < 0.05) and thyroid (P < 0.01). A random forest classifier trained on average lifetimes was found to detect parathyroid tissue with 100% sensitivity and 93% specificity at the acquisition run level.

CONCLUSION

We found that FLIm derived parameters can distinguish the parathyroid glands and other adjacent tissue types and has promise in scanning the surgical field to identify parathyroid tissue in real-time.