Prostate cancer tissue classification by multiphoton imaging, automated image analysis and machine learning

Abstract

Prostate carcinoma, a slow-growing and often indolent tumour, is the second most commonly diagnosed cancer among men worldwide. The prognosis is mainly based on the Gleason system through prostate biopsy analysis. However, new treatment and monitoring strategies depend on a more precise diagnosis. Here, we present results by multiphoton imaging for prostate tumour samples from 120 patients that allow to obtain quantitative parameters leading to specific tumour aggressiveness signatures. An automated image analysis was developed to recognise and quantify stromal fibre and neoplastic cell regions in each image. The set of metrics was able to distinguish between non-neoplastic tissue and carcinoma areas by linear discriminant analysis and random forest with accuracy of 89% ± 3%, but between Gleason groups of only 46% ± 6%. The reactive stroma analysis improved the accuracy to 65% ± 5%, clearly demonstrating that stromal parameters should be considered as additional criteria for a more accurate diagnosis.

Prognostic significance of collagen signatures in pancreatic ductal adenocarcinoma obtained from second-harmonic generation imaging

“…MPM is a powerful tool in biomedical imaging, capable of capturing cells and extracellular matrix in tissues, providing exceptional resolution and imaging capability. Bodelon et al utilized this optical technique to investigate collagen fiber profiles in breast and discovered that collagen profiles were linked with the risk of breast cancer [ 33 ]; Rogart et al proved that MPM has the capacity to scrutinize gastrointestinal mucosa at the cellular level [ 34 ]; Cromey et al used multiphoton imaging technique to rapidly differentiate normal tissues from pancreatic cancer [ 35 ]; and Gomes et al combined multiphoton imaging with an automated image analysis to successfully recognise and quantify stromal fibers and neoplastic cell regions from MPM images of prostate cancer tissues [ 36 ]. Our study also indicates that MPM can label-free identify PDAC and thereby can assist in prognostic study.…”

Cell recognition based on features extracted by AFM and parameter optimization classifiers

“…15–18 However linear discriminant analysis and random forest which use the quantitative parameters of cancer cells with the invasive characteristics obtained by the automatic image analysis system achieved a recognition accuracy of about 89%. 19 The gradually maturing technology has made scientists aware that the screening and discrimination of morphological features are the key to cancer cell detection. 20 And the morphological features of cells rely on the microscopic imaging tools.…”