1
|
Bourdillon AT. Computer Vision-Radiomics & Pathognomics. Otolaryngol Clin North Am 2024; 57:719-751. [PMID: 38910065 DOI: 10.1016/j.otc.2024.05.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/25/2024]
Abstract
The role of computer vision in extracting radiographic (radiomics) and histopathologic (pathognomics) features is an extension of molecular biomarkers that have been foundational to our understanding across the spectrum of head and neck disorders. Especially within head and neck cancers, machine learning and deep learning applications have yielded advances in the characterization of tumor features, nodal features, and various outcomes. This review aims to overview the landscape of radiomic and pathognomic applications, informing future work to address gaps. Novel methodologies will be needed to potentially engineer ways of integrating multidimensional data inputs to examine disease features to guide prognosis comprehensively and ultimately clinical management.
Collapse
Affiliation(s)
- Alexandra T Bourdillon
- Department of Otolaryngology-Head & Neck Surgery, University of California-San Francisco, San Francisco, CA 94115, USA.
| |
Collapse
|
2
|
Komarova AD, Sinyushkina SD, Shchechkin ID, Druzhkova IN, Smirnova SA, Terekhov VM, Mozherov AM, Ignatova NI, Nikonova EE, Shirshin EA, Shimolina LE, Gamayunov SV, Shcheslavskiy VI, Shirmanova MV. Insights into metabolic heterogeneity of colorectal cancer gained from fluorescence lifetime imaging. eLife 2024; 13:RP94438. [PMID: 39197048 PMCID: PMC11357354 DOI: 10.7554/elife.94438] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/30/2024] Open
Abstract
Heterogeneity of tumor metabolism is an important, but still poorly understood aspect of tumor biology. Present work is focused on the visualization and quantification of cellular metabolic heterogeneity of colorectal cancer using fluorescence lifetime imaging (FLIM) of redox cofactor NAD(P)H. FLIM-microscopy of NAD(P)H was performed in vitro in four cancer cell lines (HT29, HCT116, CaCo2 and CT26), in vivo in the four types of colorectal tumors in mice and ex vivo in patients' tumor samples. The dispersion and bimodality of the decay parameters were evaluated to quantify the intercellular metabolic heterogeneity. Our results demonstrate that patients' colorectal tumors have significantly higher heterogeneity of energy metabolism compared with cultured cells and tumor xenografts, which was displayed as a wider and frequently bimodal distribution of a contribution of a free (glycolytic) fraction of NAD(P)H within a sample. Among patients' tumors, the dispersion was larger in the high-grade and early stage ones, without, however, any association with bimodality. These results indicate that cell-level metabolic heterogeneity assessed from NAD(P)H FLIM has a potential to become a clinical prognostic factor.
Collapse
Affiliation(s)
- Anastasia D Komarova
- Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical UniversityNizhny NovgorodRussian Federation
- Institute of Biology and Biomedicine, Lobachevsky State University of Nizhny NovgorodNizhny NovgorodRussian Federation
| | - Snezhana D Sinyushkina
- Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical UniversityNizhny NovgorodRussian Federation
| | - Ilia D Shchechkin
- Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical UniversityNizhny NovgorodRussian Federation
- Institute of Biology and Biomedicine, Lobachevsky State University of Nizhny NovgorodNizhny NovgorodRussian Federation
| | - Irina N Druzhkova
- Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical UniversityNizhny NovgorodRussian Federation
| | - Sofia A Smirnova
- Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical UniversityNizhny NovgorodRussian Federation
| | - Vitaliy M Terekhov
- Nizhny Novgorod Regional Oncologic HospitalNizhny NovgorodRussian Federation
| | - Artem M Mozherov
- Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical UniversityNizhny NovgorodRussian Federation
| | - Nadezhda I Ignatova
- Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical UniversityNizhny NovgorodRussian Federation
| | - Elena E Nikonova
- Laboratory of Clinical Biophotonics, Sechenov First Moscow State Medical UniversityMoscowRussian Federation
| | - Evgeny A Shirshin
- Laboratory of Clinical Biophotonics, Sechenov First Moscow State Medical UniversityMoscowRussian Federation
- Faculty of Physics, Lomonosov Moscow State UniversityMoscowRussian Federation
| | - Liubov E Shimolina
- Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical UniversityNizhny NovgorodRussian Federation
| | - Sergey V Gamayunov
- Nizhny Novgorod Regional Oncologic HospitalNizhny NovgorodRussian Federation
| | - Vladislav I Shcheslavskiy
- Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical UniversityNizhny NovgorodRussian Federation
- Becker&Hickl GmbHBerlinGermany
| | - Marina V Shirmanova
- Institute of Experimental Oncology and Biomedical Technologies, Privolzhsky Research Medical UniversityNizhny NovgorodRussian Federation
| |
Collapse
|
3
|
Gouzou D, Taimori A, Haloubi T, Finlayson N, Wang Q, Hopgood JR, Vallejo M. Applications of machine learning in time-domain fluorescence lifetime imaging: a review. Methods Appl Fluoresc 2024; 12:022001. [PMID: 38055998 PMCID: PMC10851337 DOI: 10.1088/2050-6120/ad12f7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Revised: 09/25/2023] [Accepted: 12/06/2023] [Indexed: 12/08/2023]
Abstract
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.
Collapse
Affiliation(s)
- Dorian Gouzou
- Dorian Gouzou and Marta Vallejo are with Institute of Signals, Sensors and Systems, School of Engineering and Physical Sciences, Heriot Watt University, Edinburgh, EH14 4AS, United Kingdom
| | - Ali Taimori
- Tarek Haloubi, Ali Taimori, and James R. Hopgood are with Institute for Imaging, Data and Communication, School of Engineering, University of Edinburgh, Edinburgh, EH9 3FG, United Kingdom
| | - Tarek Haloubi
- Tarek Haloubi, Ali Taimori, and James R. Hopgood are with Institute for Imaging, Data and Communication, School of Engineering, University of Edinburgh, Edinburgh, EH9 3FG, United Kingdom
| | - Neil Finlayson
- Neil Finlayson is with Institute for Integrated Micro and Nano Systems, School of Engineering, University ofEdinburgh, Edinburgh EH9 3FF, United Kingdom
| | - Qiang Wang
- Qiang Wang is with Centre for Inflammation Research, University of Edinburgh, Edinburgh, EH16 4TJ, United Kingdom
| | - James R Hopgood
- Tarek Haloubi, Ali Taimori, and James R. Hopgood are with Institute for Imaging, Data and Communication, School of Engineering, University of Edinburgh, Edinburgh, EH9 3FG, United Kingdom
| | - Marta Vallejo
- Dorian Gouzou and Marta Vallejo are with Institute of Signals, Sensors and Systems, School of Engineering and Physical Sciences, Heriot Watt University, Edinburgh, EH14 4AS, United Kingdom
| |
Collapse
|
4
|
Chen AM. Management of unknown primary head and neck cancer with radiation therapy in the era of human papillomavirus (HPV): No longer cutting down the tree to get an apple. Radiother Oncol 2023; 189:109952. [PMID: 37844736 DOI: 10.1016/j.radonc.2023.109952] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Revised: 10/07/2023] [Accepted: 10/10/2023] [Indexed: 10/18/2023]
Abstract
PURPOSE Given the central role that radiation has in the management of head and neck squamous cell carcinoma of unknown primary origin, it is imperative to review how treatment paradigms have been refined and continue to evolve in the modern era. METHODS AND MATERIALS This study was designed based on the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols (PRISMA-P) statement. A literature search of peer-reviewed publications was undertaken to identify works pertaining to the use of radiation for squamous cell carcinoma of unknown primary origin presenting as cervical lymph node metastases. Articles published from January 2002 to January 2023 with full text available on PubMed and restricted to the English language and human subjects were included. The full bibliographies of identified articles were reviewed and irrelevant studies were removed. RESULTS While such breakthroughs as intensity-modulated radiotherapy, positron emission tomography, biomarker testing with immune-histochemistry, and minimally invasive surgical techniques such as transoral robotic surgery have fundamentally changed the approach to this disease in recent decades, controversies still exist with respect to the manner in which radiation is delivered. Although the incidence of head and neck unknown primary cancer is relatively low, questions regarding the necessity of comprehensive radiation using the age-old standard method of targeting the bilateral necks and entire pharyngeal axis to encompass all putative sites of mucosal disease persist. CONCLUSIONS Prospective evidence is lacking, and the available studies have been complicated by such factors as the relatively limited sample sizes, as well as the variability in work-up, treatment, inclusion criteria, and follow-up. Regardless, advances in science and technology have ushered in more precise approaches with a high degree of customization, particularly given the increased proportion of patients presenting with human papillomavirus-related disease.
Collapse
Affiliation(s)
- Allen M Chen
- Department of Radiation Oncology, University of California, Irvine, Chao Family Comprehensive Cancer Center, Orange, CA 92868, USA.
| |
Collapse
|
5
|
Hassan MA, Weyers BW, Bec J, Fereidouni F, Qi J, Gui D, Bewley AF, Abouyared M, Farwell DG, Birkeland AC, Marcu L. Anatomy-Specific Classification Model Using Label-Free FLIm to Aid Intraoperative Surgical Guidance of Head and Neck Cancer. IEEE Trans Biomed Eng 2023; 70:2863-2873. [PMID: 37043314 PMCID: PMC10833893 DOI: 10.1109/tbme.2023.3266678] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/13/2023]
Abstract
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.
Collapse
|
6
|
The role of transoral surgery in the diagnosis of the carcinoma of unknown origin of the head and neck. Curr Opin Otolaryngol Head Neck Surg 2023; 31:129-133. [PMID: 36912225 DOI: 10.1097/moo.0000000000000880] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/14/2023]
Abstract
PURPOSE OF REVIEW The aim of this article is to update readers on the most recent evidence on the role of trans oral surgery (TOS) in the diagnosis of carcinoma of the unknown primary of the head and neck. RECENT FINDINGS Tongue base mucosectomy has an important role in identifying the primary in patients who have had negative imaging, PET CT scans and ipsilateral tonsillectomy. In patients with bilateral nodal disease, tongue base mucosectomy should precede tonsillectomy. There are several unanswered questions that remain regarding sequencing of operations and use of intraoperative frozen section. SUMMARY An evidence-based approach to diagnosis is important to ensure the highest detection rates, and least morbidity, in patients with head and neck carcinoma of the unknown primary.
Collapse
|
7
|
Intraoperative Imaging Techniques to Improve Surgical Resection Margins of Oropharyngeal Squamous Cell Cancer: A Comprehensive Review of Current Literature. Cancers (Basel) 2023; 15:cancers15030896. [PMID: 36765858 PMCID: PMC9913756 DOI: 10.3390/cancers15030896] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Revised: 01/24/2023] [Accepted: 01/26/2023] [Indexed: 02/04/2023] Open
Abstract
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.
Collapse
|
8
|
Mat Lazim N, Kandhro AH, Menegaldo A, Spinato G, Verro B, Abdullah B. Autofluorescence Image-Guided Endoscopy in the Management of Upper Aerodigestive Tract Tumors. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 20:159. [PMID: 36612479 PMCID: PMC9819287 DOI: 10.3390/ijerph20010159] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/25/2022] [Revised: 12/16/2022] [Accepted: 12/20/2022] [Indexed: 06/17/2023]
Abstract
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.
Collapse
Affiliation(s)
- Norhafiza Mat Lazim
- Department of Otorhinolaryngology-Head and Neck Surgery, School of Medical Sciences, Universiti Sains Malaysia, Health Campus, Kubang Kerian 16150, Malaysia
| | - Abdul Hafeez Kandhro
- Institute of Medical Technology, Jinnah Sindh Medical University, Karachi 75510, Pakistan
| | - Anna Menegaldo
- Department of Neurosciences, Section of Otolaryngology and Regional Centre for Head and Neck Cancer, University of Padova, 31100 Treviso, Italy
| | - Giacomo Spinato
- Department of Neurosciences, Section of Otolaryngology and Regional Centre for Head and Neck Cancer, University of Padova, 31100 Treviso, Italy
- Department of Surgery, Oncology and Gastroenterology, Section of Oncology and Immunology, University of Padova, 31100 Treviso, Italy
| | - Barbara Verro
- Division of Otorhinolaryngology, Department of Biomedicine, Neuroscience and Advanced Diagnostic, University of Palermo, 90127 Palermo, Italy
| | - Baharudin Abdullah
- Department of Otorhinolaryngology-Head and Neck Surgery, School of Medical Sciences, Universiti Sains Malaysia, Health Campus, Kubang Kerian 16150, Malaysia
| |
Collapse
|