Canine mammary cancer diagnosis from quantitative properties of nonlinear optical images

Abstract

We present nonlinear microscopy imaging results and analysis from canine mammary cancer biopsies. Second harmonic generation imaging allows information of the collagen structure in the extracellular matrix that together with the fluorescence of the cell regions of the biopsies form a base for comprehensive image analysis. We demonstrate an automated image analysis method to classify the histological type of canine mammary cancer using a range of parameters extracted from the images. The software developed for image processing and analysis allows for the extraction of the collagen fibre network and the cell regions of the images. Thus, the tissue properties are obtained after the segmentation of the image and the metrics are measured specifically for the collagen and the cell regions. A linear discriminant analysis including all the extracted metrics allowed to clearly separate between the healthy and cancerous tissue with a 91%-accuracy. Also, a 61%-accuracy was achieved for a comparison of healthy and three histological cancer subtypes studied.

Navigating the Collagen Jungle: The Biomedical Potential of Fiber Organization in Cancer

“…To be noted, curvelet transform [76] can yield an optimal multiscale directional representation of the collagen fiber image, and has been used in our quantification studies to directly track local fiber orientation change or enhance fiber edges for later individual fiber extraction [77]. Machine learning has emerged as a powerful tool to identify discriminative fiber features [78] and can classify images into pre-determined categories (e.g., normal or abnormal tissues, lower and higher grades of cancer) based on either explicitly calculated fiber features [79] or implicit fiber patterns [80][81][82] in the collagen fiber images. Automated quantification approaches are promising to improve assessment accuracy of prognostic variables in clinical pathologic practice, and also expand research possibilities by enabling the measurement of larger areas of interest and greater numbers of samples than with current, manually intensive imaging technologies.…”

“…Automated quantification approaches are promising to improve assessment accuracy of prognostic variables in clinical pathologic practice, and also expand research possibilities by enabling the measurement of larger areas of interest and greater numbers of samples than with current, manually intensive imaging technologies. Some most frequently cited or recently emerged open-source tools include Fiji plugins of OrientationJ [66], Ridge Detection [83], FibrilTool [84], TWOMBLI [85], MATLAB-based CytoSpectre [68], CurveAlign [77,86,87] and CT-FIRE [75,77], and Python-based PyFibre [79]. Users are recommended to follow the tutorials or protocols to test and choose a tool that best meets their needs.…”

Magnetic Resonance Imaging Features in Diagnosis of Breast Cancer and Evaluation of Effect of Epidermal Growth Factor Receptor-Targeted Therapy

“…At present, BC is mainly diagnosed by pathological examination or imaging examination [ 4 ]. A biopsy is a golden standard for the diagnosis of BC, but some in patients with tiny lesions, it is difficult to obtain biopsy tissue, and biopsy can also lead to paralytic fibrosis or even sclerotic mass of breast tissue [ 5 ].…”

Canine mammary cancer tumour behaviour and patient survival time are associated with collagen fibre characteristics

“…We implemented a comprehensive and robust image analysis methodology to extract the collagen fibre network and to quantify the properties of the collagen fibres and the cellular segments in the images. A software package was developed to perform an automated image segmentation into collagen and cellular regions 46 and to extract their parameters (available on GitHub 47 ). The measured parameters include the organization of the fibres, the number of fibres, the mean fibre length, the shape of the cellular segments and the proportion of the image area covered by fibres or cellular segments.…”