1
|
Deep-Learning-Based Automated Identification and Visualization of Oral Cancer in Optical Coherence Tomography Images. Biomedicines 2023; 11:biomedicines11030802. [PMID: 36979780 PMCID: PMC10044902 DOI: 10.3390/biomedicines11030802] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2023] [Revised: 02/15/2023] [Accepted: 03/04/2023] [Indexed: 03/09/2023] Open
Abstract
Early detection and diagnosis of oral cancer are critical for a better prognosis, but accurate and automatic identification is difficult using the available technologies. Optical coherence tomography (OCT) can be used as diagnostic aid due to the advantages of high resolution and non-invasion. We aim to evaluate deep-learning-based algorithms for OCT images to assist clinicians in oral cancer screening and diagnosis. An OCT data set was first established, including normal mucosa, precancerous lesion, and oral squamous cell carcinoma. Then, three kinds of convolutional neural networks (CNNs) were trained and evaluated by using four metrics (accuracy, precision, sensitivity, and specificity). Moreover, the CNN-based methods were compared against machine learning approaches through the same dataset. The results show the performance of CNNs, with a classification accuracy of up to 96.76%, is better than the machine-learning-based method with an accuracy of 92.52%. Moreover, visualization of lesions in OCT images was performed and the rationality and interpretability of the model for distinguishing different oral tissues were evaluated. It is proved that the automatic identification algorithm of OCT images based on deep learning has the potential to provide decision support for the effective screening and diagnosis of oral cancer.
Collapse
|
2
|
Parikh AS, Yu VX, Flashner S, Okolo OB, Lu C, Henick BS, Momen-Heravi F, Puram SV, Teknos T, Pan Q, Nakagawa H. Patient-derived three-dimensional culture techniques model tumor heterogeneity in head and neck cancer. Oral Oncol 2023; 138:106330. [PMID: 36773387 PMCID: PMC10126876 DOI: 10.1016/j.oraloncology.2023.106330] [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: 09/14/2022] [Revised: 12/08/2022] [Accepted: 01/25/2023] [Indexed: 02/11/2023]
Abstract
Head and neck squamous cell carcinoma (HNSCC) outcomes remain stagnant, in part due to a poor understanding of HNSCC biology. The importance of tumor heterogeneity as an independent predictor of outcomes and treatment failure in HNSCC has recently come to light. With this understanding, 3D culture systems, including patient derived organoids (PDO) and organotypic culture (OTC), that capture this heterogeneity may allow for modeling and manipulation of critical subpopulations, such as p-EMT, as well as interactions between cancer cells and immune and stromal cells in the microenvironment. Here, we review work that has been done using PDO and OTC models of HNSCC, which demonstrates that these 3D culture models capture in vivo tumor heterogeneity and can be used to model tumor biology and treatment response in a way that faithfully recapitulates in vivo characteristics. As such, in vitro 3D culture models represent an important bridge between 2D monolayer culture and in vivo models such as patient derived xenografts.
Collapse
Affiliation(s)
- Anuraag S Parikh
- Department of Otolaryngology-Head and Neck Surgery, Columbia University, New York, NY, United States; Columbia University Vagelos College of Physicians and Surgeons, Columbia University, New York, NY, United States
| | - Victoria X Yu
- Department of Otolaryngology-Head and Neck Surgery, Columbia University, New York, NY, United States
| | - Samuel Flashner
- Division of Digestive and Liver Diseases, Department of Medicine, Columbia University, New York, NY, United States
| | - Ogoegbunam B Okolo
- Columbia University Vagelos College of Physicians and Surgeons, Columbia University, New York, NY, United States
| | - Chao Lu
- Department of Genetics and Development, Herbert Irving Comprehensive Cancer Center, Columbia University, New York, NY, United States
| | - Brian S Henick
- Division of Hematology/Oncology, Department of Medicine, Columbia Unversity, New York, NY, United States
| | - Fatemeh Momen-Heravi
- Columbia University College of Dental Medicine, Columbia University, New York, NY, United States
| | - Sidharth V Puram
- Department of Otolaryngology-Head and Neck Surgery, Washington University School of Medicine, St. Louis, MO, United States; Department of Genetics, Washington University School of Medicine, St. Louis, MO, United States
| | - Theodoros Teknos
- Department of Otolaryngology, Case Western Reserve University, Cleveland, OH, United States
| | - Quintin Pan
- Department of Otolaryngology, Case Western Reserve University, Cleveland, OH, United States
| | - Hiroshi Nakagawa
- Division of Digestive and Liver Diseases, Department of Medicine, Columbia University, New York, NY, United States.
| |
Collapse
|
3
|
Chen LC, Kuo S, Lloyd WR, Kim HM, Marcelo CL, Feinberg SE, Mycek MA. Optical Metric Assessed Engineered Tissues Over a Range of Viability States. Tissue Eng Part C Methods 2020; 25:305-313. [PMID: 30973066 DOI: 10.1089/ten.tec.2018.0344] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022] Open
Abstract
Many conventional methods to assess engineered tissue morphology and viability are destructive techniques with limited utility for tissue constructs intended for implantation in patients. Sterile label-free optical molecular imaging methods analyzed tissue endogenous fluorophores without staining, noninvasively and quantitatively assessing engineered tissue, in lieu of destructive assessment methods. The objective of this study is to further investigate label-free optical metrics and their correlation with destructive methods. Tissue-engineered constructs (n = 33 constructs) fabricated with primary human oral keratinocytes (n = 10 patients) under control, thermal stress, and rapamycin treatment manufacturing conditions exhibited a range of tissue viability states, as evaluated by quantitative histology scoring, WST-1 assay, Ki-67 immunostaining imaging, and label-free optical molecular imaging methods. Both histology sections of fixed tissues and cross-sectioned label-free optical images of living tissues provided quantitative spatially selective information on local tissue morphology, but optical methods noninvasively characterized both local tissue morphology and cellular viability at the same living tissue site. Furthermore, optical metrics noninvasively assessed living tissue viability with a statistical significance consistent with the destructive tissue assays WST-1 and histology. Over the range of cell viability states created experimentally, optical metrics noninvasively and quantitatively characterized living tissue viability and correlated with the destructive WST-1 tissue assay. By providing, under sterile conditions, noninvasive metrics that were comparable with conventional destructive tissue assays, label-free optical molecular imaging has the potential to monitor and assess engineered tissue construct viability before surgical implantation.
Collapse
Affiliation(s)
- Leng-Chun Chen
- 1 Department of Biomedical Engineering, University of Michigan College of Engineering and Medical School, Ann Arbor, Michigan
| | - Shiuhyang Kuo
- 2 Department of Oral and Maxillofacial Surgery, University of Michigan School of Dentistry, Ann Arbor, Michigan
| | - William R Lloyd
- 1 Department of Biomedical Engineering, University of Michigan College of Engineering and Medical School, Ann Arbor, Michigan
| | - Hyungjin Myra Kim
- 3 Center for Statistical Consultation and Research, University of Michigan School of Public Health, Ann Arbor, Michigan
| | - Cynthia L Marcelo
- 4 Department of Surgery, University of Michigan Medical School, Ann Arbor, Michigan
| | - Stephen E Feinberg
- 2 Department of Oral and Maxillofacial Surgery, University of Michigan School of Dentistry, Ann Arbor, Michigan.,4 Department of Surgery, University of Michigan Medical School, Ann Arbor, Michigan
| | - Mary-Ann Mycek
- 1 Department of Biomedical Engineering, University of Michigan College of Engineering and Medical School, Ann Arbor, Michigan
| |
Collapse
|
4
|
Ferreira LP, Gaspar VM, Mano JF. Decellularized Extracellular Matrix for Bioengineering Physiomimetic 3D in Vitro Tumor Models. Trends Biotechnol 2020; 38:1397-1414. [PMID: 32416940 DOI: 10.1016/j.tibtech.2020.04.006] [Citation(s) in RCA: 62] [Impact Index Per Article: 15.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2020] [Revised: 04/10/2020] [Accepted: 04/14/2020] [Indexed: 02/06/2023]
Abstract
Recent advances in the extraction and purification of decellularized extracellular matrix (dECM) obtained from healthy or malignant tissues open new avenues for engineering physiomimetic 3D in vitro tumor models, which closely recapitulate key biomolecular hallmarks and the dynamic cancer cell-ECM interactions in the tumor microenvironment. We review current and upcoming methodologies for chemical modification of dECM-based biomaterials and advanced bioprocessing into organotypic 3D solid tumor models. A comprehensive review of disruptive advances and shortcomings of exploring dECM-based biomaterials for recapitulating the native tumor-supporting matrix is also provided. We hope to drive the discussion on how 3D dECM testing platforms can be leveraged for generating microphysiological tumor surrogates that generate more robust and predictive data on therapeutic bioperformance.
Collapse
Affiliation(s)
- Luís P Ferreira
- Department of Chemistry, CICECO, Aveiro Institute of Materials, University of Aveiro, Campus Universitário de Santiago, 3810-193, Aveiro, Portugal
| | - Vítor M Gaspar
- Department of Chemistry, CICECO, Aveiro Institute of Materials, University of Aveiro, Campus Universitário de Santiago, 3810-193, Aveiro, Portugal.
| | - João F Mano
- Department of Chemistry, CICECO, Aveiro Institute of Materials, University of Aveiro, Campus Universitário de Santiago, 3810-193, Aveiro, Portugal.
| |
Collapse
|
5
|
In Vitro Organotypic Systems to Model Tumor Microenvironment in Human Papillomavirus (HPV)-Related Cancers. Cancers (Basel) 2020; 12:cancers12051150. [PMID: 32375253 PMCID: PMC7281263 DOI: 10.3390/cancers12051150] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2020] [Revised: 04/30/2020] [Accepted: 05/01/2020] [Indexed: 12/16/2022] Open
Abstract
Despite the well-known role of chronic human papillomavirus (HPV) infections in causing tumors (i.e., all cervical cancers and other human malignancies from the mucosal squamous epithelia, including anogenital and oropharyngeal cavity), its persistence is not sufficient for cancer development. Other co-factors contribute to the carcinogenesis process. Recently, the critical role of the underlying stroma during the HPV life cycle and HPV-induced disease have been investigated. The tumor stroma is a key component of the tumor microenvironment (TME), which is a specialized entity. The TME is dynamic, interactive, and constantly changing—able to trigger, support, and drive tumor initiation, progression, and metastasis. In previous years, in vitro organotypic raft cultures and in vivo genetically engineered mouse models have provided researchers with important information on the interactions between HPVs and the epithelium. Further development for an in-depth understanding of the interaction between HPV-infected tissue and the surrounding microenvironment is strongly required. In this review, we critically describe the HPV-related cancers modeled in vitro from the simplified ‘raft culture’ to complex three-dimensional (3D) organotypic models, focusing on HPV-associated cervical cancer disease platforms. In addition, we review the latest knowledge in the field of in vitro culture systems of HPV-associated malignancies of other mucosal squamous epithelia (anogenital and oropharynx), as well as rare cutaneous non-melanoma associated cancer.
Collapse
|
6
|
Affolter A, Hess J. [Preclinical models in head and neck tumors : Evaluation of cellular and molecular resistance mechanisms in the tumor microenvironment]. HNO 2017; 64:860-869. [PMID: 27837212 DOI: 10.1007/s00106-016-0276-x] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
Because head and neck squamous cell carcinomas (HNSCC) are characterized by a distinct intertumorigenic and intratumorigenic heterogeneity, they often show substantial differences in the response to established therapy strategies. At present, a multitude of biologics and new pharmacological compounds for targeted therapies are available that allow more efficient and less toxic treatment. There is increasing pressure to establish predictive assays not only for ex ante analysis of the individual patient response to combined chemoradiotherapy and targeted therapies but also for investigation of the efficacy of new drugs. In this respect it is essential to maintain the pathophysiological tissue composition as it is known that paracrine tumor-stroma cell interactions may influence tumor reactivity to treatment. More complex models for individualized sensitivity testing have recently been described and the results are promising to pave the way for personalized cancer therapy. This review article focuses on different systems for maintaining the tumor microenvironment and hence the individual cellular composition, such as 3D organotypic models, organotypic multicellular spheroids, patient-derived xenografts and ex vivo tissue cultures and discusses the advantages and disadvantages in terms of translation into clinical application.
Collapse
Affiliation(s)
- A Affolter
- Hals-Nasen-Ohren-Klinik des Universitätsklinikums Heidelberg, Im Neuenheimer Feld 400, 69120, Heidelberg, Deutschland.
| | - J Hess
- Hals-Nasen-Ohren-Klinik des Universitätsklinikums Heidelberg, Im Neuenheimer Feld 400, 69120, Heidelberg, Deutschland
| |
Collapse
|
7
|
Inglehart RC, Scanlon CS, D'Silva NJ. Reviewing and reconsidering invasion assays in head and neck cancer. Oral Oncol 2014; 50:1137-43. [PMID: 25448226 DOI: 10.1016/j.oraloncology.2014.09.010] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2014] [Revised: 09/11/2014] [Accepted: 09/17/2014] [Indexed: 01/21/2023]
Abstract
Head and neck squamous cell carcinomas (HNSCC) are malignant tumors that arise from the surface epithelium of the oral cavity, oropharynx and larynx, primarily due to exposure to chemical carcinogens or the human papilloma virus. Due to their location, dental practitioners are well-positioned to detect the lesions. Deadlier than lymphoma or melanoma, HNSCC is incompletely understood. For these reasons, dental practitioners and researchers are focused on understanding HNSCC and the processes driving it. One of these critical processes is invasion, the degradation of the basement membrane by HNSCC cells with subsequent movement into the underlying connective tissue, blood vessels or nerves. Cancer cells metastasize to distant sites via the blood vessels, lymphatics and nerves. Metastasis is associated with poor survival. Since invasion is essential for development and metastasis of HNSCC, it is essential to understand the mechanism(s) driving this process. Elucidation of the mechanisms involved will facilitate the development of targeted treatment, thereby accelerating development of precision/personalized medicine to treat HNSCC. Robust in vitro and in vivo assays are required to investigate the mechanistic basis of invasion. This review will focus on in vitro and in vivo assays used to study invasion in HNSCC, with special emphasis on some of the latest assays to study HNSCC.
Collapse
Affiliation(s)
- Ronald C Inglehart
- Department of Periodontics and Oral Medicine, School of Dentistry, University of Michigan, Ann Arbor, USA
| | - Christina S Scanlon
- Department of Periodontics and Oral Medicine, School of Dentistry, University of Michigan, Ann Arbor, USA
| | - Nisha J D'Silva
- Department of Periodontics and Oral Medicine, School of Dentistry, University of Michigan, Ann Arbor, USA; Department of Pathology, University of Michigan Medical School, University of Michigan, Ann Arbor, USA.
| |
Collapse
|
8
|
Chen LC, Lloyd WR, Kuo S, Kim HM, Marcelo CL, Feinberg SE, Mycek MA. The potential of label-free nonlinear optical molecular microscopy to non-invasively characterize the viability of engineered human tissue constructs. Biomaterials 2014; 35:6667-76. [PMID: 24854093 PMCID: PMC4106121 DOI: 10.1016/j.biomaterials.2014.04.080] [Citation(s) in RCA: 27] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2014] [Accepted: 04/22/2014] [Indexed: 12/27/2022]
Abstract
Nonlinear optical molecular imaging and quantitative analytic methods were developed to non-invasively assess the viability of tissue-engineered constructs manufactured from primary human cells. Label-free optical measures of local tissue structure and biochemistry characterized morphologic and functional differences between controls and stressed constructs. Rigorous statistical analysis accounted for variability between human patients. Fluorescence intensity-based spatial assessment and metabolic sensing differentiated controls from thermally-stressed and from metabolically-stressed constructs. Fluorescence lifetime-based sensing differentiated controls from thermally-stressed constructs. Unlike traditional histological (found to be generally reliable, but destructive) and biochemical (non-invasive, but found to be unreliable) tissue analyses, label-free optical assessments had the advantages of being both non-invasive and reliable. Thus, such optical measures could serve as reliable manufacturing release criteria for cell-based tissue-engineered constructs prior to human implantation, thereby addressing a critical regulatory need in regenerative medicine.
Collapse
Affiliation(s)
- Leng-Chun Chen
- Department of Biomedical Engineering, University of Michigan College of Engineering & Medical School, 1101 Beal Avenue, Ann Arbor, MI 48109-2110, USA.
| | - William R Lloyd
- Department of Biomedical Engineering, University of Michigan College of Engineering & Medical School, 1101 Beal Avenue, Ann Arbor, MI 48109-2110, USA.
| | - Shiuhyang Kuo
- Department of Oral and Maxillofacial Surgery, University of Michigan School of Dentistry, 1150 W. Medical Center Drive, Ann Arbor, MI 48109, USA.
| | - Hyungjin Myra Kim
- Center for Statistical Consultation and Research, University of Michigan School of Public Health, 915 E. Washington, Ann Arbor, MI 48109-1070, USA.
| | - Cynthia L Marcelo
- Department of Surgery, University of Michigan Medical School, 1150 W. Medical Center Drive, Ann Arbor, MI 48109, USA.
| | - Stephen E Feinberg
- Department of Oral and Maxillofacial Surgery, University of Michigan School of Dentistry, 1150 W. Medical Center Drive, Ann Arbor, MI 48109, USA; Department of Surgery, University of Michigan Medical School, 1150 W. Medical Center Drive, Ann Arbor, MI 48109, USA.
| | - Mary-Ann Mycek
- Department of Biomedical Engineering, University of Michigan College of Engineering & Medical School, 1101 Beal Avenue, Ann Arbor, MI 48109-2110, USA.
| |
Collapse
|