Search

The application of semi-supervised methodology to improve the classification performance of a Raman spectroscopic probe for the diagnosis of oesophageal cancer is described. It is well known that gold standard histopathology diagnosis can be highly subjective, particularly for diseases which have several stages, such as cancer. A ‘consensus’ pathology decision can be obtained to ensure a robust gold standard by obtaining a diagnosis from several experts and samples are then only included in standard classification models if they have been assigned the same pathology by all experts. This can result in a significant number of samples that are excluded from the analysis as no consensus was reached. In this work semi-supervised methodology was used to extend Principal Component Analysis followed by Linear Discriminant Analysis (PCA-LDA) to incorporate samples without consensus pathology when discriminating between benign and oesophageal cancer specimens measured using a Raman endoscopic probe ex vivo. We demonstrate that a fully semi-supervised approach improved sensitivity and specificity from 73% and 78% (PCA-LDA) to 78% and 84% (semi-supervised) for discriminating between intestinal metaplasia and dysplasia and from 44% and 66% (PCA-LDA) to 63% and 72% (semi-supervised) when discriminating between intestinal metaplasia and low grade dysplasia. [ABSTRACT FROM AUTHOR]

Early detection of (pre-)cancerous changes improves prognosis, therefore in the UK patients at high risk of developing gastrointestinal cancers are enrolled on endoscopic surveillance programmes or the Bowel Cancer Screening Programme. The current gold standard technique for the detection of pre-cancerous changes in the gastrointestinal tract is histopathological analysis of biopsy tissue collected at endoscopy. This relies upon subjective assessment of morphological changes within the excised tissue samples and poor targeting of pre-malignant lesions. Raman spectroscopy offers a number of potential advantages for in vivo assessment of tissue at endoscopy. The performance of a custom built Raman probe as a biopsy targeting tool has been evaluated using excised biopsy material. Multivariate classification models have been used to demonstrate the likely ability of a miniature, confocal, fibre optic Raman probe to be used as an optical biopsy tool at endoscopy to provide spectral information in clinically practicable timescales. This technique could facilitate improved targeting of excisional biopsy with associated clinical benefits.

Sentinel Lymph Node Biopsy has become the standard surgical procedure for the sampling of axillary lymph nodes in breast cancer. Intra operative node assessment is currently not offered to the majority of patients but would allow definitive axillary surgery to take place immediately. This would confer benefits both to the patient and to the healthcare system. Our experimental study aims to demonstrate that a Raman spectroscopy probe device could overcome many of the disadvantages of current intra-operative analysis techniques. 38 axillary lymph nodes, 25 negative and 13 positive from 20 patients undergoing breast surgery for invasive breast cancer were assessed using a commercially available Raman spectroscopy probe. Spectra were assessed using principal component fed linear discriminant analysis trained by the histopathology results. Leave one node out cross validation achieved a sensitivity of up to 92% and a specificity of up to 100% in differentiating between normal and metastatic lymph nodes.

Vibrational spectroscopy techniques have demonstrated potential to provide non-destructive, rapid, clinically relevant diagnostic information. Early detection is the most important factor in the prevention of cancer. Raman and infrared spectroscopy enable the biochemical signatures from biological tissues to be extracted and analysed. In conjunction with advanced chemometrics such measurements can contribute to the diagnostic assessment of biological material. This paper also illustrates the complementary advantage of using Raman and FTIR spectroscopy technologies together. Clinical requirements are increasingly met by technological developments which show promise to become a clinical reality. This review summarises recent advances in vibrational spectroscopy and their impact on the diagnosis of cancer.