Image Analysis in Histopathology and Cytopathology: From Early Days to Current Perspectives

Abstract

Both pathology and cytopathology still rely on recognizing microscopical morphologic features, and image analysis plays a crucial role, enabling the identification, categorization, and characterization of different tissue types, cell populations, and disease states within microscopic images. Historically, manual methods have been the primary approach, relying on expert knowledge and experience of pathologists to interpret microscopic tissue samples. Early image analysis methods were often constrained by computational power and the complexity of biological samples. The advent of computers and digital imaging technologies challenged the exclusivity of human eye vision and brain computational skills, transforming the diagnostic process in these fields. The increasing digitization of pathological images has led to the application of more objective and efficient computer-aided analysis techniques. Significant advancements were brought about by the integration of digital pathology, machine learning, and advanced imaging technologies. The continuous progress in machine learning and the increasing availability of digital pathology data offer exciting opportunities for the future. Furthermore, artificial intelligence has revolutionized this field, enabling predictive models that assist in diagnostic decision making. The future of pathology and cytopathology is predicted to be marked by advancements in computer-aided image analysis. The future of image analysis is promising, and the increasing availability of digital pathology data will invariably lead to enhanced diagnostic accuracy and improved prognostic predictions that shape personalized treatment strategies, ultimately leading to better patient outcomes.

Keywords: cytopathology; digital image analysis; microscopy; pathology.

Figure 1

The number of PubMed-indexed articles using the search terms ‘digital image analysis’, ‘digital image analysis histopathology’, and ‘digital image analysis cytopathology/cytology’.

Figure 2

The number of PubMed-indexed articles using the search terms ‘artificial intelligence image analysis’, and ‘deep learning image analysis’.

Figure 3

Major landmarks and publications that had a significant impact on digital image analysis (SIFT: Scale Invariant Feature Transform; SURF: Speeded-Up Robust Features; WSI: Whole Slide Image). More details and references in the text [21,22,23,24,25,26,27].

Figure 4

Color-based segmentation of malignant lymphoma CD34+ endothelial cells (DAB chromogen, ImageJ (v1.8.0); (A): Original image, before segmentation; (B): The result after color-based segmentation; images used with permission [51]).

Figure 5

Nuclear contour tracing and thresholding using ImageJ, papillary thyroid carcinoma FNA smear, and Papanicolaou stain. (A): Original image; (B): Manual tracing of four tumor cell nuclei (1–4); (C): Binary image appearance after thresholding.

Figure 5

Nuclear contour tracing and thresholding using ImageJ, papillary thyroid carcinoma FNA smear, and Papanicolaou stain. (A): Original image; (B): Manual tracing of four tumor cell nuclei (1–4); (C): Binary image appearance after thresholding.