[Support vector machine based high intensity focused ultrasound beam lesion degree classification and recognition].

Ultrasound based tissue thermal lesion non-invasive detection is of great significance in high intensity focused ultrasound (HIFU) clinical application. In this paper, we propose a sub-pixel method to quantify the ultrasound image change caused by HIFU as correlation-distance. The support vector machine (SVM) was trained by using correlation distance as samples, and the recognition effect was tested. Results showed that sub-pixel cross-correlation vector field could reflect the ablation lesions position. SVM based classification method can recognize HIFU beam lesion degree effectively.

Quantitative multispectral photoacoustic tomography and wavelength optimization.

We describe a reconstruction method that allows direct recovery of tissue chromophore concentrations and acoustic velocity using tomographic multi-spectral photoacoustic measurements. The method is tested in detail using extensive simulated data. Criteria for choosing optimum wavelength sets are analyzed for simultaneous reconstruction of tissue functional and acoustic properties.

Multispectral quantitative photoacoustic imaging of osteoarthritis in finger joints.

We present in vivo experimental evidence that multispectral quantitative photoacoustic tomography (qPAT) has the potential to detect osteoarthritis (OA) in the finger joints. In this pilot study, two OA patients and three healthy volunteers were enrolled, and their distal interphalangeal (DIP) joints were examined photoacoustically by a multispectral PAT scanner. Images of tissue physiological/functional parameters including oxyhemoglobin, deoxyhemoglobin, oxygen saturation, and water content, along with the tissue acoustic velocity of all the examined joints, were simultaneously recovered using a finite element reconstruction algorithm for multispectral photoacoustic measurements. The recovered multispectral photoacoustic images show that the OA joints have significantly elevated water content, decreased oxygen saturation, and increased acoustic velocity compared to the normal joints.

Quantitative two-dimensional photoacoustic tomography of osteoarthritis in the finger joints.

We present for the first time in vivo experimental evidence that quantitative photoacoustic tomography (qPAT) has the potential to detect osteoarthritis (OA) in the finger joints. In this pilot study, 2 OA patients and 4 healthy volunteers were enrolled, and their distal interphalangeal (DIP) joints were examined photoacoustically by a PAT scanner. Tissue absorption coefficient images of all the examined joints, which were unavailable from the conventional PAT, were recovered using our finite element based qPAT approach. The recovered quantitative photoacoustic images revealed significant differences in the tissue absorption coefficient of the joint cavity (cartilage and synovial fluid) between the OA and normal joints.

[Study of the methods of wavelet feature extraction and neural network classification of fluorescence spectra to improve the diagnostic rate of colonic earlier stage cancer].

In order to improve the diagnostic rate of earlier stage colonic cancer with laser-induced 5-ALA-Pp IX fluorescence spectra, a novel method of extraction of fluorescence spectral feature using wavelet analysis and classification using artificial neural network trained with resilient back-propagation algorithm (R-BPNN) was developed. 504 spectra were collected from 8 normal SD rats, and 20 1,2-DMH-induced SD colon cancer models and 12 second generation rats of induced rats. 150 min later trail intravenous injections of 5-ALA dose of 25 mg x kg(-1) body weight (BW), and fluorescence spectra excited with 370 nm Ti-laser were collected in vivo. After preprocessing, 12 feature variants were extracted with wavelet analysis. With R-BPNN, all spectra were classified into two categories: normal or abnormal, which included dysplasia, early carcinoma (EC) and advanced carcinoma (AC). The sensitivity and specificity were 98.91% and 97.2% respectively. The accuracy of discriminating dysplasia, early carcinoma, and advanced carcinoma from normal tissue were 91.3%, 98.9% and 98.8 respectively. The result indicated that this method could effectively and easily diagnoses earlier stage colonic carcinomas.

Neural network classification of laser-induced 5-ALA-PpIX fluorescence spectra using adaptive principal component extraction.

A novel method of feature extraction and classification of fluorescence spectra using neural network was developed in order to improve the diagnostic rate of earlier stage colonic carcinomas with Laser-induced 5-ALA-PpIX fluorescence spectra. 150 min after trail intravenous injections of 5-ALA dose of 25mg/kg body weight (BW) to 40 rats,504 fluorescence spectra excited with 370nm Ti-Laser were collected in vivo, which included 183 normal, 69 dysplasia (DYS), 87 early cancer (EC) and 165 advanced cancer (AC). After preprocessing, 6 principal components were extracted using adaptive principal component extraction (APEX). With BP neural network trained with resilient back-propagation algorithm (RBPNN), all spectra were divided into two categories: normal or abnormal, which included DYS, EC and AC. The sensitivity and specificity were 96.57% and 95.08% respectively. The accuracy of discriminating DYS and EC and AC from normal tissue were 92.75% and 98.85% and 96.36% respectively. The result indicated that this method could effectively diagnose earlier stage colonic carcinomas.

[Study of a multivariate statistical 5-ALA-based discrimination method for fluorescence spectra of colonic tissue of SD rats].

In order to diagnosis colon early cancer with laser-induced 5-ALA-PpIX fluorescence spectra, a multivariate statistical method to distinguish these fluorescence spectra acquired in vivo was developed. 343 spectra were collected from 8 normal SD rats, and 20 1,2-DMH-induced SD colon cancer models, and 12 second generation rats of induced rats. 150 min after trail intravenous injections of 5-ALA at a dose of 25 mg x kg(-1) BW, fluorescence spectra excited with 370 nm Ti-laser were collected in vivo. All spectra were divided into a calibration group and a prediction group. After preprocessing, 4 principal components were extracted with PCA. And then, discrimination models were built by stepwise multivariate logistic regression (SMLR) on calibration group. 3 pathological styles were combined each other, and then 3 SMLR models were derived. Normal tissues were classified from early cancers and advanced cancers with sensitivity of 100% and 98.4%, and specificity of 96% and 100%, and accuracy of 98% and 99.2% on prediction group, respectively. The multivariate statistical discrimination method of PCA and SMLR together can effectively distinguish normal tissues from early cancers and advanced cancers with high sensitivity and specificity by means of systemic 5-ALA at low dose. Laser induced fluorescence 5-ALA-based technique is promising for the detection of colonic early cancer.