In clinical routine, the quality of whole-slide images plays a key role in the pathologist’s diagnosis, and suboptimal staining may be a limiting factor. The stain normalization process helps to solve this problem through the standardization of color appearance of a source image with respect to a target image with optimal chromatic features. The analysis is focused on the evaluation of the following parameters assessed by two experts on original and normalized slides: (i) perceived color quality, (ii) diagnosis for the patient, (iii) diagnostic confidence and (iv) time required for diagnosis. Results show a statistically significant increase in color quality in the normalized images for both experts (p < 0.0001). Regarding prostate cancer assessment, the average times for diagnosis are significantly lower for normalized images than original ones (first expert: 69.9 s vs. 77.9 s with p < 0.0001; second expert: 37.4 s vs. 52.7 s with p < 0.0001), and at the same time, a statistically significant increase in diagnostic confidence is proven. The improvement of poor-quality images and greater clarity of diagnostically important details in normalized slides demonstrate the potential of stain normalization in the routine practice of prostate cancer assessment.
25 October 2023 in International Journal of Imaging Systems and Technology
Multiple myeloma disrupts normal blood cell production, requiring early detection due to the increased risk of bone metastases. Although various artificial intelligence (AI) methods have been developed to assist pathologists, they often lack comprehensive metrics to measure both detection and segmentation errors. This study presents a hybrid framework that combines deep learning and heuristic techniques to achieve accurate instance segmentation of individual plasma cells in Giemsa‐stained cytology images. Our proposed network, called cyto‐Knet, incorporates an innovative color‐balancing method as a preprocessing step to standardize the appearance of cytological images. Our network leverages a 4‐class segmentation strategy with conditional kernels to enhance segmentation performance and accuracy. Additionally, a marker‐based watershed algorithm is employed in the postprocessing step to address the challenge of merged objects. Extensive validation at both pixel and object‐based levels demonstrates superior performance compared with state‐of‐the‐art techniques. Our method achieves pixel‐based metrics (precision, recall, and F1‐score) of approximately 0.90. The object‐based evaluation reveals an average Dice coefficient of 0.9130 and an aggregated Jaccard index of 0.8237. Importantly, our solution is designed for integration into an end‐to‐end system for diagnosis support and can be easily extended to other applications.
4 September 2024 in International Journal of Imaging Systems and Technology
Histological staining plays a crucial role in anatomic pathology for the analysis of biological tissues and the formulation of diagnostic reports. Traditional methods like hematoxylin and eosin (H&E) primarily offer morphological information but lack insight into functional details, such as the expression of biomarkers indicative of cellular activity. To overcome this limitation, we propose a computational approach to synthesize virtual immunohistochemical (IHC) stains from H&E input, transferring imaging features across staining domains. Our approach comprises two stages: (i) a multi‐stage registration framework ensuring precise alignment of cellular and subcellular structures between the source H&E and target IHC stains, and (ii) a deep learning‐based generative model which incorporates functional attributes from the target IHC stain by learning cell‐to‐cell mappings from paired training data. We evaluated our approach of virtual restaining H&E slides to simulate IHC staining for phospho‐histone H3, on inguinal lymph node and bladder tissues. Blind pathologist assessments and quantitative metrics validated the diagnostic quality of the synthetic slides. Notably, mitotic counts derived from synthetic images exhibited a strong correlation with physical staining. Moreover, global and stain‐specific metrics confirmed the high quality of the synthetic IHC images generated by our approach. This methodology represents an important advance in automated functional restaining, achieved through robust registration and a model trained on precisely paired H&E and IHC data to transfer functions cell‐by‐cell. Our approach forms the basis for multiparameter histology analysis and comprehensive cohort staining using only digitized H&E slides.
5 August 2025 in Computer Vision and Image Understanding