Diagnosis of colorectal cancer using Raman spectroscopy of laser-trapped single living epithelial cells

A single-cell diagnostic technique for epithelial cancers is developed by utilizing laser trapping and Raman spectroscopy to differentiate cancerous and normal epithelial cells. Single-cell suspensions were prepared from surgically removed human colorectal tissues following standard primary culture protocols and examined in a near-infrared laser-trapping Raman spectroscopy system, where living epithelial cells were investigated one by one. A diagnostic model was built on the spectral data obtained from 8 patients and validated by the data from 2 new patients. Our technique has potential applications from epithelial cancer diagnosis to the study of cell dynamics of carcinogenesis. (c) 2006 Optical Society of America.

Highly sensitive determination of the methylated p16 gene in cancer patients by microchip electrophoresis

The p16 tumor suppressor gene is inactivated by promoter region hypermethylation in many types of tumor. Recent studies showed that aberrant methylation of the p16 gene is an early event in many tumors, especially in lung cancer, and may constitute a new biomarker for early detection and monitoring of prevention trials. We detected tumor-associated aberrant hypermethylation of the p16 gene in plasma and tissue DNA from 153 specimens using a modified semi-nested methylation-specific PCR (MSP) combining plastic microchip electrophoresis or slab gel electrophoresis, respectively. Specimens were from 79 lung cancer patients, 15 abdominal tumor patients, 30 positive controls and 30 negative controls. The results showed that the positive rate obtained by microchip electrophoresis was more than 26.6% higher and the same speciticity was kept when compared with slab gel electrophoresis. The microchip electrophoresis can rapidly and accurately analyze the PCR products of methylated DNA and obviously improve the positive rate of diagnosis of cancer patients when compared with gel electrophoresis. This method with the high assay sensitivity might be used for detection of methylation of p16 gene and even to facilitate early diagnosis of cancer patients. (C) 2004 Elsevier B.V. All rights reserved.

Artificial neural network classification based on high-performance liquid chromatography of urinary and serum nucleosides for the clinical diagnosis of cancer

Nucleosides in human urine and serum have frequently been studied as a possible biomedical marker for cancer, acquired immune deficiency syndrome (AIDS) and the whole-body turnover of RNAs. Fifteen normal and modified nucleosides were determined in 69 urine and 42 serum samples using high-performance liquid chromatography (HPLC). Artificial neural networks have been used as a powerful pattern recognition tool to distinguish cancer patients from healthy persons. The recognition rate for the training set reached 100%. In the validating set, 95.8 and 92.9% of people were correctly classified into cancer patients and healthy persons when urine and serum were used as the sample for measuring the nucleosides. The results show that the artificial neural network technique is better than principal component analysis for the classification of healthy persons and cancer patients based on nucleoside data. (C) 2002 Elsevier Science B.V. All rights reserved.

Artificial neural network applied to diagnosis of lung cancer

Artificial neural network(ANN) approach was applied to classification of normal persons and lung cancer patients based on the metal content of hair and serum samples obtained by inductively coupled plasma atomic emission spectrometry (ICP-AES) for the two groups. This method was verified with independent prediction samples and can be used as an aiding means of the diagnosis of lung cancer. The case of predictive classification with one element missing in the prediction samples was studied in details, The significance of elements in hair and serum samples for classification prediction was also investigated.

A Cancer Recognition Method Based on DNA Microarray

The accurate cancer classification is of great importance in clinical treatment. Recently, the DNA microarray technology provides a promising approach to the diagnosis and prognosis of cancer types. However, it has no perfect method for the multiclass classification problem. The difficulty lies in the fact that the data are of high dimensionality with small sample size. This paper proposed an automatic classification method of multiclass cancers based on Biomimetic pattern recognition (BPR). To the public GCM data set, the average correct classification rate reaches 80% under the condition that the correct rejection rate is 81%.

Application of probabilistic neural network in the clinical diagnosis of cancers based on clinical chemistry data

As a recently developed and powerful classification tool, probabilistic neural network was used to distinguish cancer patients from healthy persons according to the levels of nucleosides in human urine. Two datasets (containing 32 and 50 patterns, respectively) were investigated and the total consistency rate obtained was 100% for dataset 1 and 94% for dataset 2. To evaluate the performance of probabilistic neural network, linear discriminant analysis and learning vector quantization network, were also applied to the classification problem. The results showed that the predictive ability of the probabilistic neural network is stronger than the others in this study. Moreover, the recognition rate for dataset 2 can achieve to 100% if combining, these three methods together, which indicated the promising potential of clinical diagnosis by combining different methods. (C) 2002 Elsevier Science B.V. All rights reserved.

Characteristic infrared spectroscopic patterns in the protein bands of human breast cancer tissue

Infrared (IR) spectra of normal, hyperplasia, fibroadenoma and carcinoma tissues of human breast obtained from 96 patients have been determined and analyzed statistically. Several spectral differences were detected in the frequency regions of N-H stretching, amide I, II and III bands: (1) the bands in the region 3000-3600cm-1 shifted to lower frequencies for the carcinomatous tissue; (2) the A(3300)/A(3075) absorbance ratio was significantly higher for the fibroadenoma than for the other types of tissues; (3) the frequency of the a-helix amide I band decreased for the malignant tissue, while the corresponding beta -sheet amide I band frequency increased; (4) the A(1657)/A(1635) and A(1553)/A(1540) absorbance ratios were the highest for fibroadenoma and carcinoma tissues; (5) the A(1680)/A(1657) absorbance ratio decreased significantly in the order of normal > hyperplasia > fibroadenoma > carcinoma; (6) the A(1651)/A(1545) absorbance ratio increased slightly for the fibroadenoma and the carcinoma tissues; (7) the bands at 1204 and 1278 cm(-1), assigned to the vibrational modes of the collagen, did not appear in the original spectra as resolved peaks and were distinctly stronger in the deconvoluted spectra of the carcinoma tissue and (8) the A(1657)/A(1204) and A(1657)/A(1278) absorbance ratios, both yielding information on the relative content of collagen, increased in the order of normal < hyperplasia < carcinoma < fibroadenoma. The said differences imply that the information is useful for the diagnosis of breast cancer and malignant breast abnormalities, and may serve as a basis for further studies on conformational changes in tissue proteins during carcinogenesis. (C) 2001 Elsevier Science B.V. All rights reserved.