Comparison of MRS and DWI in the diagnosis of prostate cancer based on sextant analysis.

PURPOSE: To evaluate apparent diffusion coefficient (ADC) value, metabolic ratio ((Cho + Cr)/Cit) and the combination of the two in identifying prostate malignant regions. MATERIALS AND METHODS: Fifty-six consecutive patients with prostate biopsy results were retrospectively recruited in this study. Transrectal ultrasound-guided (TRUS) systemic prostate biopsies were used as a standard of reference. Mean ADC value and mean metabolic ratio (MMR) were calculated within each benign sextant region or malignant region. The efficiency of these two indices in prostate cancer (PCa) diagnosis is estimated in Fisher linear discriminant analysis (FLDA). The area under the receiver operating characteristic (ROC) curve was used to evaluate the distinguishing capacity of mean ADC, MMR, and the combination of the two in differentiating between noncancerous and cancerous cases. RESULTS: There were significant differences for mean ADC value and MMR between malignant and benign regions. Weights of mean ADC value obtained by FLDA were much higher than those of MMR. In differentiating malignant regions, both ADC alone and combined ADC and metabolic ratio performed significantly better than MMR alone. However, accuracy improvements were not significant by using combined ADC and MMR than ADC alone. CONCLUSION: DWI is more efficient than MR spectroscopic (MRS) in the detection of PCa in this study. Combined ADC and MMR performed significantly better than MMR alone in distinguishing malignant from benign region in prostate peripheral zone.

[Application of artificial neural network to diagnosis of prostate cancer].

Prostatic carcinoma is the fifth most common cancer in the world and the second most common in men. It is quite important to early detect and diagnose prostate cancer to reduce the mortality. With the increasing of the diagnosis and treatment tasks of prostate cancer and the development of medical techniques, more and more clinical and lab examinations, biopsy and medical imaging techniques are included in the diagnosis of prostate cancer. Although these examination results are supplement to each other, there are contradictions among them at the same time. Artificial neural networks (ANNs) which can perform multifactorial analysis based on computational methodologies have been widely used in the prognosis of prostate cancer. The current application of ANNs is reviewed.

Classification of breast lesions based on a dual S-shaped logistic model in dynamic contrast enhanced magnetic resonance imaging.

This study proposes a novel dual S-shaped logistic model for automatically quantifying the characteristic kinetic curves of breast lesions and for distinguishing malignant from benign breast tumors on dynamic contrast enhanced (DCE) magnetic resonance (MR) images. D(α,ß) is the diagnostic parameter derived from the logistic model. Significant differences were found in D(α,ß) between the malignant benign groups. Fisher's Linear Discriminant analysis correctly classified more than 90% of the benign and malignant kinetic breast data using the derived diagnostic parameter (D(α,ß)). Receiver operating characteristic curve analysis of the derived diagnostic parameter (D(α,ß)) indicated high sensitivity and specificity to differentiate malignancy from benignancy. The dual S-shaped logistic model was effectively used to fit the kinetic curves of breast lesions in DCE-MR. Separation between benign and malignant breast lesions was achieved with sufficient accuracy by using the derived diagnostic parameter D(α,ß) as the lesion's feature. The proposed method therefore has the potential for computer-aided diagnosis in breast tumors.

Computerized characterization of prostate cancer by fractal analysis in MR images.

PURPOSE: To explore the potential of computerized characterization of prostate MR images by extracting the fractal features of texture and intensity distributions as indices in the differential diagnosis of prostate cancer. MATERIALS AND METHODS: MR T2-weighted images (T2WI) of 55 patients with pathologic results detected by ultrasound guided biopsy were collected and then divided in two groups, 27 with prostate cancer (PCa) and 28 with no histological abnormality. Texture fractal dimension (TFD) and histogram fractal dimension (HFD) were calculated to analyze complexity features of regions of Interest (ROIs) selected from the peripheral zone. Two-sample t-tests were performed to evaluate group differences for both parameters. Receiver operating characteristic (ROC) analysis was used to estimate the performance of TFD and HFD for discriminating PCa. RESULTS: Significant differences were found in both TFD and HFD between the two patient groups. The areas under the ROC curves of TFD and HFD were 0.691 and 0.966, respectively, in distinguishing prostatic carcinoma from normal peripheral zone. As characterized by the fractal indices, cancerous prostatic tissue exhibited smoother texture and lower variation in intensity distribution than normal prostatic tissue. CONCLUSION: The study suggests that TFD and HFD depict the changes in texture and intensity distribution associated with prostate cancer on T2WI. Both TFD and HFD provide promising quantitative indices for cancer identification. HFD performs better than TFD offering a more robust MR-based indicator in the diagnosis of prostatic carcinoma.