1
|
Chen H, Tan C, Lin Z, Chen M, Cheng B. Applying virtual sample generation and ensemble modeling for improving the spectral diagnosis of cancer. SPECTROCHIMICA ACTA. PART A, MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2024; 318:124518. [PMID: 38796889 DOI: 10.1016/j.saa.2024.124518] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/19/2024] [Revised: 05/11/2024] [Accepted: 05/23/2024] [Indexed: 05/29/2024]
Abstract
Cancer diagnosis plays a key role in facilitating treatment and improving survival rates of patients. The combination of near-infrared (NIR) spectroscopy with data-driven algorithms offers a rapid and cost-effective approach for such a task. Due to the limitations of objective cases, the number of tumor samples is usually smaller, and the resulting dataset exhibit the issues of class imbalance, which has a more serious impact on the performance of diagnostic models. To deal with class imbalance and improve the sensitivity, this work investigates the feasibility of NIR spectroscopy combined with virtual sample generation (VSG) as well as ensemble strategy for developing diagnostic models. Based on preliminary experiment, several learning algorithms such as discriminant analysis (DA) and partial least square-discriminant analysis (PLS-DA) are screened out as algorithms for constructing prediction models. Three algorithms of VSG including synthetic minority oversampling technique (SMOTE), Borderline-SMOTE and adaptive synthetic sampling (ADASYN) are used for experiment. A fixed sample subset composed of 27 cancer samples and 54 normal samples are hold out as the test set. Three training sets containing 5, 10, 25 minority class samples and 54 majority class samples are used for model development. The experimental result indicates that overall, with PLS-DA algorithm, all VSG approaches can significantly improve the sensitivity of cancer diagnosis for all cases of training sets with different minority samples, but ADASYN performs the best. It reveals that the integration of NIR, PLS-DA, and ADASYN is a promising tool package for developing diagnosis methods.
Collapse
Affiliation(s)
- Hui Chen
- Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan 644000, China; Hospital, Yibin University, Yibin, Sichuan 644000, China
| | - Chao Tan
- Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan 644000, China; College of Materials and Chemical Engineering, Yibin University, Yibin, Sichuan 644000, China.
| | - Zan Lin
- Department of Knee Sports Injury, Sichuan Province Orthopedic Hospital, Chengdu, Sichuan 610041, China
| | - Maoxian Chen
- Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan 644000, China
| | - Bin Cheng
- Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan 644000, China
| |
Collapse
|
2
|
Insights into Biochemical Sources and Diffuse Reflectance Spectral Features for Colorectal Cancer Detection and Localization. Cancers (Basel) 2022; 14:cancers14225715. [PMID: 36428806 PMCID: PMC9688116 DOI: 10.3390/cancers14225715] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2022] [Revised: 11/07/2022] [Accepted: 11/09/2022] [Indexed: 11/23/2022] Open
Abstract
Colorectal cancer (CRC) is the third most common and second most deadly type of cancer worldwide. Early detection not only reduces mortality but also improves patient prognosis by allowing the use of minimally invasive techniques to remove cancer while avoiding major surgery. Expanding the use of microsurgical techniques requires accurate diagnosis and delineation of the tumor margins in order to allow complete excision of cancer. We have used diffuse reflectance spectroscopy (DRS) to identify the main optical CRC biomarkers and to optimize parameters for the integration of such technologies into medical devices. A total number of 2889 diffuse reflectance spectra were collected in ex vivo specimens from 47 patients. Short source-detector distance (SDD) and long-SDD fiber-optic probes were employed to measure tissue layers from 0.5 to 1 mm and from 0.5 to 1.9 mm deep, respectively. The most important biomolecules contributing to differentiating DRS between tissue types were oxy- and deoxy-hemoglobin (Hb and HbO2), followed by water and lipid. Accurate tissue classification and potential DRS device miniaturization using Hb, HbO2, lipid and water data were achieved particularly well within the wavelength ranges 350-590 nm and 600-1230 nm for the short-SDD probe, and 380-400 nm, 420-610 nm, and 650-950 nm for the long-SDD probe.
Collapse
|
3
|
Mamede AP, Santos IP, Batista de Carvalho ALM, Figueiredo P, Silva MC, Marques MPM, Batista de Carvalho LAE. Breast cancer or surrounding normal tissue? A successful discrimination by FTIR or Raman microspectroscopy. Analyst 2022; 147:4919-4932. [DOI: 10.1039/d2an00622g] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/20/2023]
Abstract
Breast cancer is a type of cancer with the highest incidence worldwide in 2021, with early diagnosis and rapid treatment intervention being the reasons for the decreasing mortality rate associated with the disease.
Collapse
Affiliation(s)
- Adriana P. Mamede
- “Unidade de I&D Química-Física Molecular” (QFM-UC) Department of Chemistry, University of Coimbra, Coimbra, Portugal
| | - Inês P. Santos
- “Unidade de I&D Química-Física Molecular” (QFM-UC) Department of Chemistry, University of Coimbra, Coimbra, Portugal
| | - Ana L. M. Batista de Carvalho
- “Unidade de I&D Química-Física Molecular” (QFM-UC) Department of Chemistry, University of Coimbra, Coimbra, Portugal
| | - Paulo Figueiredo
- Pathology Department, Portuguese Institute of Oncology Francisco Gentil (IPOFG), Coimbra, Portugal
| | - Maria C. Silva
- Surgery Department, Portuguese Institute of Oncology Francisco Gentil (IPOFG), Coimbra, Portugal
| | - Maria P. M. Marques
- “Unidade de I&D Química-Física Molecular” (QFM-UC) Department of Chemistry, University of Coimbra, Coimbra, Portugal
- Department of Life Sciences, University of Coimbra, Coimbra, Portugal
| | | |
Collapse
|
4
|
Nogueira MS, Maryam S, Amissah M, Lu H, Lynch N, Killeen S, O’Riordain M, Andersson-Engels S. Evaluation of wavelength ranges and tissue depth probed by diffuse reflectance spectroscopy for colorectal cancer detection. Sci Rep 2021; 11:798. [PMID: 33436684 PMCID: PMC7804163 DOI: 10.1038/s41598-020-79517-2] [Citation(s) in RCA: 24] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2020] [Accepted: 12/04/2020] [Indexed: 01/29/2023] Open
Abstract
Colorectal cancer (CRC) is the third most common type of cancer worldwide and the second most deadly. Recent research efforts have focused on developing non-invasive techniques for CRC detection. In this study, we evaluated the diagnostic capabilities of diffuse reflectance spectroscopy (DRS) for CRC detection by building 6 classification models based on support vector machines (SVMs). Our dataset consists of 2889 diffuse reflectance spectra collected from freshly excised ex vivo tissues of 47 patients over wavelengths ranging from 350 and 1919 nm with source-detector distances of 630-µm and 2500-µm to probe different depths. Quadratic SVMs were used and performance was evaluated using twofold cross-validation on 10 iterations of randomized training and test sets. We achieved (93.5 ± 2.4)% sensitivity, (94.0 ± 1.7)% specificity AUC by probing the superficial colorectal tissue and (96.1 ± 1.8)% sensitivity, (95.7 ± 0.6)% specificity AUC by sampling deeper tissue layers. To the best of our knowledge, this is the first DRS study to investigate the potential of probing deeper tissue layers using larger SDD probes for CRC detection in the luminal wall. The data analysis showed that using a broader spectrum and longer near-infrared wavelengths can improve the diagnostic accuracy of CRC as well as probing deeper tissue layers.
Collapse
Affiliation(s)
- Marcelo Saito Nogueira
- grid.7872.a0000000123318773Tyndall National Institute, Lee Maltings, Dyke Parade, Cork, Ireland ,grid.7872.a0000000123318773Department of Physics, University College Cork, College Road, Cork, Ireland
| | - Siddra Maryam
- grid.7872.a0000000123318773Tyndall National Institute, Lee Maltings, Dyke Parade, Cork, Ireland ,grid.7872.a0000000123318773Department of Physics, University College Cork, College Road, Cork, Ireland
| | - Michael Amissah
- grid.7872.a0000000123318773Tyndall National Institute, Lee Maltings, Dyke Parade, Cork, Ireland ,grid.7872.a0000000123318773Department of Physics, University College Cork, College Road, Cork, Ireland
| | - Huihui Lu
- grid.7872.a0000000123318773Tyndall National Institute, Lee Maltings, Dyke Parade, Cork, Ireland
| | - Noel Lynch
- grid.411785.e0000 0004 0575 9497Department of Surgery, Mercy University Hospital, Cork, Ireland
| | - Shane Killeen
- grid.411785.e0000 0004 0575 9497Department of Surgery, Mercy University Hospital, Cork, Ireland
| | - Micheal O’Riordain
- grid.411785.e0000 0004 0575 9497Department of Surgery, Mercy University Hospital, Cork, Ireland
| | - Stefan Andersson-Engels
- grid.7872.a0000000123318773Tyndall National Institute, Lee Maltings, Dyke Parade, Cork, Ireland ,grid.7872.a0000000123318773Department of Physics, University College Cork, College Road, Cork, Ireland
| |
Collapse
|
5
|
Ehlen L, Zabarylo UJ, Speichinger F, Bogomolov A, Belikova V, Bibikova O, Artyushenko V, Minet O, Beyer K, Kreis ME, Kamphues C. Synergy of Fluorescence and Near-Infrared Spectroscopy in Detection of Colorectal Cancer. J Surg Res 2019; 242:349-356. [PMID: 31132626 DOI: 10.1016/j.jss.2019.05.011] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2018] [Revised: 04/08/2019] [Accepted: 05/02/2019] [Indexed: 02/07/2023]
Abstract
BACKGROUND Colorectal cancer is one of the most common malignancies worldwide. There is an urgent need for simple and fast methods to improve tumor detection in the diagnostic and intraoperative setting to avoid complications and provide objective information in distinguishing malignant and benign colorectal tissue. Optical spectroscopy methods have recently shown a great potential for this discrimination in different organs. MATERIALS AND METHODS In this pilot study, fluorescence emission spectra (excitation: 473 nm) and diffuse reflectance spectra (DRS) of normal and tumor tissues from resected colorectal cancer specimen were measured using fiber optical probes in an ex vivo setting, and the data were subjected to multivariate analysis. RESULTS Substantial spectral differences were found in the fluorescence and DRS spectra of colorectal cancer tissue in comparison to benign tissue. The diagnostic potential of a multimode optical system combining both spectroscopic methods was investigated by mathematical combination. Compared with the individual techniques, a higher sensitivity of the joint DRS-fluorescence optical system in the discrimination between malignant and benign colorectal tissue could be observed. CONCLUSIONS In the pilot study presented herein, a quick and reliable method to differentiate malignant and benign colorectal tissue ex vivo with different spectroscopic techniques using spectral fiber probes could be established. Joint fluorescence and near-infrared spectroscopy had a higher sensitivity in tissue discrimination and showed to be a promising combination of two spectroscopic methods. Further studies using the synergic effect of fluorescence and DRS spectroscopy are needed to transfer these findings into the in vivo situation.
Collapse
Affiliation(s)
- Lukas Ehlen
- Department of General, Visceral and Vascular Surgery, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Urszula J Zabarylo
- Center for Diagnostic and Interventional Radiology and Nuclear Medicine, Charité - Universitätsmedizin Berlin, Berlin, Germany; Berlin Brandenburg School of Regenerative Therapies, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Fiona Speichinger
- Department of General, Visceral and Vascular Surgery, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Andrey Bogomolov
- Laboratory of Multivariate Analysis and Global Modelling, Samara State Technical University, Samara, Russia
| | - Valerya Belikova
- Laboratory of Multivariate Analysis and Global Modelling, Samara State Technical University, Samara, Russia
| | | | | | - Olaf Minet
- Center for Diagnostic and Interventional Radiology and Nuclear Medicine, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Katharina Beyer
- Department of General, Visceral and Vascular Surgery, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Martin E Kreis
- Department of General, Visceral and Vascular Surgery, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Carsten Kamphues
- Department of General, Visceral and Vascular Surgery, Charité - Universitätsmedizin Berlin, Berlin, Germany.
| |
Collapse
|
6
|
Chen H, Tan C, Lin Z, Wu T. Rapid Determination of Cotton Content in Textiles by Near-Infrared Spectroscopy and Interval Partial Least Squares. ANAL LETT 2018. [DOI: 10.1080/00032719.2018.1448853] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/17/2022]
Affiliation(s)
- Hui Chen
- Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan, China
- Hospital, Yibin University, Yibin, Sichuan, China
| | - Chao Tan
- Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan, China
| | - Zan Lin
- Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan, China
- Department of Orthopedics, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Tong Wu
- Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan, China
| |
Collapse
|