Broadband Hyperspectral Imaging for Breast Tumor Detection Using Spectral and Spatial Information

Overview

Journal Biomed Opt Express

Specialty Radiology

Date 2019 Oct 1

PMID 31565506

Citations 30

Authors

Esther Kho

Behdad Dashtbozorg

Lisanne L de Boer

Koen K Van de Vijver

Henricus J C M Sterenborg

Theo J M Ruers

Affiliations

Soon will be listed here.

Abstract

Complete tumor removal during breast-conserving surgery remains challenging due to the lack of optimal intraoperative margin assessment techniques. Here, we use hyperspectral imaging for tumor detection in fresh breast tissue. We evaluated different wavelength ranges and two classification algorithms; a pixel-wise classification algorithm and a convolutional neural network that combines spectral and spatial information. The highest classification performance was obtained using the full wavelength range (450-1650 nm). Adding spatial information mainly improved the differentiation of tissue classes within the malignant and healthy classes. High sensitivity and specificity were accomplished, which offers potential for hyperspectral imaging as a margin assessment technique to improve surgical outcome.

Citing Articles

Systematic Meta-Analysis of Computer-Aided Detection of Breast Cancer Using Hyperspectral Imaging.

Leung J, Karmakar R, Mukundan A, Thongsit P, Chen M, Chang W Bioengineering (Basel). 2024; 11(11).

PMID: 39593720 PMC: 11591395. DOI: 10.3390/bioengineering11111060.

Hyperspectral imaging with deep learning for quantification of tissue hemoglobin, melanin, and scattering.

Livecchi T, Jacques S, Subhash H, Pierce M J Biomed Opt. 2024; 29(9):093507.

PMID: 39247058 PMC: 11378079. DOI: 10.1117/1.JBO.29.9.093507.

Separating Surface Reflectance from Volume Reflectance in Medical Hyperspectral Imaging.

Jong L, Post A, Geldof F, Dashtbozorg B, Ruers T, Sterenborg H Diagnostics (Basel). 2024; 14(16).

PMID: 39202300 PMC: 11353750. DOI: 10.3390/diagnostics14161812.

SAHIS-Net: a spectral attention and feature enhancement network for microscopic hyperspectral cholangiocarcinoma image segmentation.

Zhang Y, Dong J Biomed Opt Express. 2024; 15(5):3147-3162.

PMID: 38855697 PMC: 11161366. DOI: 10.1364/BOE.519090.

Hyperspectral dark-field microscopy of human breast lumpectomy samples for tumor margin detection in breast-conserving surgery.

Hwang J, Cheney P, Kanick S, Le H, McClatchy 3rd D, Zhang H J Biomed Opt. 2024; 29(9):093503.

PMID: 38715717 PMC: 11075096. DOI: 10.1117/1.JBO.29.9.093503.

References

Merrill A, Tang R, Plichta J, Rai U, Coopey S, McEvoy M . Should New "No Ink On Tumor" Lumpectomy Margin Guidelines be Applied to Ductal Carcinoma In Situ (DCIS)? A Retrospective Review Using Shaved Cavity Margins. Ann Surg Oncol. 2016; 23(11):3453-3458. DOI: 10.1245/s10434-016-5251-y. View

Vos E, Jager A, Verhoef C, Voogd A, Koppert L . Overall survival in patients with a re-excision following breast conserving surgery compared to those without in a large population-based cohort. Eur J Cancer. 2015; 51(3):282-91. DOI: 10.1016/j.ejca.2014.12.003. View

Langhans L, Jensen M, Talman M, Vejborg I, Kroman N, Tvedskov T . Reoperation Rates in Ductal Carcinoma In Situ vs Invasive Breast Cancer After Wire-Guided Breast-Conserving Surgery. JAMA Surg. 2016; 152(4):378-384. PMC: 5470426. DOI: 10.1001/jamasurg.2016.4751. View

Neittaanmaki-Perttu N, Gronroos M, Tani T, Polonen I, Ranki A, Saksela O . Detecting field cancerization using a hyperspectral imaging system. Lasers Surg Med. 2013; 45(7):410-7. DOI: 10.1002/lsm.22160. View

Pardo A, Real E, Krishnaswamy V, Lopez-Higuera J, Pogue B, Conde O . Directional Kernel Density Estimation for Classification of Breast Tissue Spectra. IEEE Trans Med Imaging. 2016; 36(1):64-73. DOI: 10.1109/TMI.2016.2593948. View

Fei B, Lu G, Wang X, Zhang H, Little J, Patel M . Label-free reflectance hyperspectral imaging for tumor margin assessment: a pilot study on surgical specimens of cancer patients. J Biomed Opt. 2017; 22(8):1-7. PMC: 5572439. DOI: 10.1117/1.JBO.22.8.086009. View

Kho E, de Boer L, Van de Vijver K, Van Duijnhoven F, Vrancken Peeters M, Sterenborg H . Hyperspectral Imaging for Resection Margin Assessment during Cancer Surgery. Clin Cancer Res. 2019; 25(12):3572-3580. DOI: 10.1158/1078-0432.CCR-18-2089. View

Matthews B . Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta. 1975; 405(2):442-51. DOI: 10.1016/0005-2795(75)90109-9. View

Han Z, Zhang A, Wang X, Sun Z, Wang M, Xie T . In vivo use of hyperspectral imaging to develop a noncontact endoscopic diagnosis support system for malignant colorectal tumors. J Biomed Opt. 2016; 21(1):16001. DOI: 10.1117/1.JBO.21.1.016001. View

10.

Maloney B, McClatchy D, Pogue B, Paulsen K, Wells W, Barth R . Review of methods for intraoperative margin detection for breast conserving surgery. J Biomed Opt. 2018; 23(10):1-19. PMC: 6210801. DOI: 10.1117/1.JBO.23.10.100901. View

11.

Butler-Henderson K, Lee A, Price R, Waring K . Intraoperative assessment of margins in breast conserving therapy: a systematic review. Breast. 2014; 23(2):112-9. DOI: 10.1016/j.breast.2014.01.002. View

12.

Lu G, Little J, Wang X, Zhang H, Patel M, Griffith C . Detection of Head and Neck Cancer in Surgical Specimens Using Quantitative Hyperspectral Imaging. Clin Cancer Res. 2017; 23(18):5426-5436. PMC: 5649622. DOI: 10.1158/1078-0432.CCR-17-0906. View

13.

St John E, Al-Khudairi R, Ashrafian H, Athanasiou T, Takats Z, Hadjiminas D . Diagnostic Accuracy of Intraoperative Techniques for Margin Assessment in Breast Cancer Surgery: A Meta-analysis. Ann Surg. 2016; 265(2):300-310. DOI: 10.1097/SLA.0000000000001897. View

14.

de Boer L, Molenkamp B, Bydlon T, Hendriks B, Wesseling J, Sterenborg H . Fat/water ratios measured with diffuse reflectance spectroscopy to detect breast tumor boundaries. Breast Cancer Res Treat. 2015; 152(3):509-18. DOI: 10.1007/s10549-015-3487-z. View

15.

Merrill A, Coopey S, Tang R, McEvoy M, Specht M, Hughes K . Implications of New Lumpectomy Margin Guidelines for Breast-Conserving Surgery: Changes in Reexcision Rates and Predicted Rates of Residual Tumor. Ann Surg Oncol. 2015; 23(3):729-34. DOI: 10.1245/s10434-015-4916-2. View

16.

Versteegden D, Keizer L, Schlooz-Vries M, Duijm L, Wauters C, Strobbe L . Performance characteristics of specimen radiography for margin assessment for ductal carcinoma in situ: a systematic review. Breast Cancer Res Treat. 2017; 166(3):669-679. DOI: 10.1007/s10549-017-4475-2. View

17.

Dietterich . Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms. Neural Comput. 1998; 10(7):1895-1923. DOI: 10.1162/089976698300017197. View

18.

Denstedt M, Bjorgan A, Milanic M, Randeberg L . Wavelet based feature extraction and visualization in hyperspectral tissue characterization. Biomed Opt Express. 2015; 5(12):4260-80. PMC: 4285604. DOI: 10.1364/BOE.5.004260. View

19.

Nachabe R, Evers D, Hendriks B, Lucassen G, van der Voort M, Rutgers E . Diagnosis of breast cancer using diffuse optical spectroscopy from 500 to 1600 nm: comparison of classification methods. J Biomed Opt. 2011; 16(8):087010. DOI: 10.1117/1.3611010. View

20.

Alrahbi S, Chan P, Ho B, Seah M, Chen J, Tan E . Extent of margin involvement, lymphovascular invasion, and extensive intraductal component predict for residual disease after wide local excision for breast cancer. Clin Breast Cancer. 2015; 15(3):219-26. DOI: 10.1016/j.clbc.2014.12.004. View