Multiple analyses suggests texture features can indicate the presence of tumor in the prostate tissue.
Sérgio Augusto Santana SouzaLeonardo Oliveira ReisAllan Felipe Fattori AlvesLetícia Cotinguiba SilvaMaria Clara Korndorfer MedeirosDanilo Leite AndradeAthanase BillisJoão Luiz AmaroDaniel Lahan MartinsAndré Petean TrindadeJosé Ricardo Arruda MirandaDiana Rodrigues de PinaPublished in: Physical and engineering sciences in medicine (2022)
Several studies have demonstrated statistical and texture analysis abilities to differentiate cancerous from healthy tissue in magnetic resonance imaging. This study developed a method based on texture analysis and machine learning to differentiate prostate findings. Forty-eight male patients with PI-RADS classification and subsequent radical prostatectomy histopathological analysis were used as gold standard. Experienced radiologists delimited the regions of interest in magnetic resonance images. Six different groups of images were used to perform multiple analyses (seven analyses variations). Those analyses were outlined by specialists in urology as those of most significant importance for the classification. Forty texture features were extracted from each image and processed with Random Forest, Support Vector Machine, K-Nearest Neighbors, and Naive Bayes. Those seven analyses variation results were described in terms of area under the ROC curve (AUC), accuracy, F-score, precision and sensitivity. The highest AUC (93.7%) and accuracy (88.8%) were obtained when differentiating the group with both MRI and histopathology positive findings against the group with both negative MRI and histopathology. When differentiating the group with both MRI and histopathology positive findings versus the peripheral image zone group the AUC value was 86.6%. When differentiating the group with negative MRI/positive histopathology versus the group with both negative MRI and histopathology the AUC value was 80.7%. The evaluation of statistical and texture analysis promoted very suggestive indications for future work in prostate cancer suspicious regions. The method is fast for both region of interest selection and classification with machine learning and the result brings original contributions in the classification of different groups of patients. This tool is low-cost, and can be used to assist diagnostic decisions.
Keyphrases
- contrast enhanced
- magnetic resonance imaging
- prostate cancer
- deep learning
- machine learning
- magnetic resonance
- radical prostatectomy
- computed tomography
- diffusion weighted imaging
- artificial intelligence
- end stage renal disease
- convolutional neural network
- chronic kidney disease
- hiv infected
- ejection fraction
- climate change
- prognostic factors
- benign prostatic hyperplasia
- antiretroviral therapy