Search Results (150)

Bone marrow cell classification and nucleus segmentation in microscopic images are fundamental tasks for computer-aided diagnosis of lymphocytic leukemia. However, bone marrow cells from different subtypes exhibit high morphological similarity, and structural information is often constrained under optical microscopic imaging, posing challenges for stable and effective feature representation. To address this issue, we propose MTLL (Multitask Model on Lymphocytic Leukemia), a novel multitask approach that performs cell classification and nucleus segmentation within a unified network to exploit their complementary information. The model constructs a hybrid backbone for shared feature representation based on a CNN-Transformer architecture, in which Fuse-MBConv modules are tightly integrated with multilayer multi-scale transformers to enable deep fusion of local texture and global semantic information. For the segmentation branch, we design an AM (Atrous Multilayer Perceptron) decoder that combines atrous spatial pyramid pooling with multilayer perceptrons to fuse multi-scale information and accurately delineate nucleus boundaries. The classification branch incorporates prior knowledge of cell nuclei structures to capture subtle variations in cellular morphology and texture, thereby enhancing the model’s ability to distinguish between leukemia subtypes. Experimental results demonstrate that the MTLL model significantly outperforms existing advanced single-task and multi-task models in both lymphocytic leukemia classification and cell nucleus segmentation. These results validate the effectiveness of the multi-task feature-sharing strategy for lymphocytic leukemia diagnosis using bone marrow microscopic images. Full article

Accurate cell and nuclei segmentation remains challenging due to the sensitivity of classical graph-cut methods to parameter tuning. While deep learning models like U-Net offer strong performance, they require large annotated datasets and substantial GPU resources. This work presents a cost-effective alternative: a genetic programming (GP) framework that jointly optimizes unary cost functions and regularization parameters for graph-cut segmentation, coupled with automatic seed selection. Evaluation is conducted under two distinct protocols: (1) oracle-guided per-image optimization, establishing upper-bound performance (mean Dice 0.822, IoU 0.733), and (2) true generalization via train/test split, where expressions learned on 50 images are applied to 50 unseen images (mean Dice 0.695, IoU 0.588). The fixed-model generalization still significantly outperforms the baseline graph cut ($+0.158$ Dice, $p<0.001$). Cross-dataset validation on MoNuSeg (H&E histopathology) achieves a Dice score of 0.823 with the fixed GP model, significantly outperforming the baseline (+0.272). This result uses a single fixed model—the best-performing expression from BBBC038 training—applied in a zero-shot manner to MoNuSeg without any retraining or domain adaptation. All 100 images showed non-negative improvement under oracle optimization in the experiments. The method requires no GPU training, runs in 550 s per image for oracle search, and offers interpretable symbolic cost functions. Code and annotations are provided to ensure reproducibility. This approach offers a practical, interpretable alternative in resource-constrained biomedical imaging settings. Full article

Hyperspectral imaging (HSI) extends conventional histopathology by combining spatial morphology with rich spectral information that reflects tissue biochemical composition, offering new opportunities for quantitative tissue analysis. However, reliable spectral analysis requires accurate instance-level segmentation of cell nuclei to enable the construction of meaningful nuclear spectral databases. In this work, a comprehensive methodology for generating hyperspectral databases of cell nuclei from histopathological samples is presented, including hyperspectral acquisition, preprocessing, nucleus segmentation, and spectral signature extraction. Three nucleus segmentation methods are evaluated: a spectral-only approach based on pixel-wise hyperspectral signatures in the visible–VNIR range; a spatial-only approach using synthetic RGB images derived from hyperspectral cubes; and a combined spatial–spectral approach that jointly exploits spatial and spectral information. The methods are assessed on a proprietary dataset of 30 hyperspectral cubes of tumor and healthy histopathological brain tissue annotated by expert pathologists. The spectral-only method achieves a Dice similarity coefficient (DSC) of 61.89% and produces severe over-segmentation, with cell count deviations exceeding substantially the ground truth in healthy tissue. The spatial-only method attains the highest pixel-wise accuracy (78.97% DSC) but underestimates nucleus counts by approximately 30% in tumor regions due to nucleus merging. The spatial–spectral method achieves a DSC of 73.13% and a mean cell count deviation of 4%, providing more reliable instance-level separation. These findings demonstrate that pixel-wise accuracy alone is insufficient for hyperspectral nuclear database generation. Full article

Background/Objectives: Variations in staining styles—arising from differences in tissue preparation, scanners, and laboratory protocols—severely compromise the robustness of automated cell segmentation algorithms in digital pathology. Moreover, manual nucleus annotation is extremely labor-intensive, leading to a scarcity of large-scale, fully annotated datasets for supervised nucleus segmentation. This study proposes a novel framework that simultaneously mitigates staining variability and achieves high-accuracy nucleus segmentation using only minimal annotations. Methods: We present 3SGAN, a multi-task dual-branch generative adversarial network (GAN) that jointly performs stain normalization and nucleus segmentation in a semi-supervised manner. The framework adopts a teacher–student paradigm: a lightweight teacher model (AttCycle) equipped with attention gates generates reliable pseudo-labels, while a high-capacity student model (TransCycle) leveraging a hybrid CNN–Transformer architecture further refines performance. 3SGAN was trained and evaluated on a large dataset of 1408 Whole-Slide Images (WSIs) from two medical institutions, encompassing 101 distinct staining styles, with nucleus-level annotations required for only 5% of the data. Results: 3SGAN significantly outperformed state-of-the-art methods, achieving superior segmentation accuracy with an F1-score of 0.8140, mean IoU of 0.8201, and AJI of 0.6915. Simultaneously, it demonstrated substantial improvements in stain normalization quality, yielding a low RMSE of 0.0908, high PSNR of 21.0615, and SSIM of 0.8556 on the internal test set. External validation on independent MoNuSeg and PanNuke datasets, as well as on previously untested tumor-rich non-ROI regions from our in-house WSIs, confirmed strong generalizability with excellent stain normalization and top-tier segmentation accuracy across diverse staining protocols, tissue types, and pathological patterns. Conclusions: The proposed 3SGAN framework demonstrates that high-performance nucleus segmentation and stain normalization can be achieved with minimal annotation requirements, offering a practical and scalable solution for digital pathology applications across diverse clinical settings and staining protocols. Full article

Inherited retinal degenerations, such as retinitis pigmentosa, are a leading cause of irreversible vision loss, yet broadly effective treatments remain elusive. Impaired cellular waste clearance via autophagy–lysosomal pathways have been implicated in photoreceptor death, but the spatiotemporal dynamics of these processes during degeneration remain poorly understood. Using the rd10 mouse model of retinitis pigmentosa, we characterised autophagy–lysosomal dysfunction at key stages of photoreceptor degeneration (postnatal day P17, P22, P35) through super-resolution imaging of RFP-EGFP-LC3 reporter mice, Western blot, and bulk RNA sequencing. Autophagosome and autolysosome numbers were significantly elevated across all photoreceptor compartments (inner/outer segments, outer nuclear layer, outer plexiform layer) at P17, prior to significant photoreceptor nuclei loss. Autophagosome and autolysosome size progressively increased from P22 onwards, suggesting accumulation of unprocessed intracellular waste. Molecular analyses revealed downregulation of mTOR protein, upregulation of autophagy-related genes, and increased lysosomal processes from P17. These histological and molecular findings are consistent with early autophagy induction followed by overwhelmed degradative capacity. Our findings identify autophagy–lysosomal change as an early event in photoreceptor loss in the rd10 model, revealing a critical therapeutic window for mutation-independent interventions targeting cellular clearance pathways in inherited retinal degenerations. Full article

Background/Objectives: Accurate nuclear segmentation is a fundamental step in computational pathology, enabling reliable estimation of cellularity and nuclear morphology. However, segmentation models are typically evaluated under ideal imaging conditions, while real-world microscopy data are affected by staining variability, noise, and image degradation. This study aims to comparatively evaluate three representative convolutional architectures for nuclei segmentation, with emphasis on robustness and clinical relevance under perturbed imaging conditions. Methods: U-Net, Attention U-Net, and U-Net++ were trained and evaluated on the BBBC038 nuclei microscopy dataset using fixed train–validation–test splits. Robustness was assessed under three types of synthetic perturbations: Gaussian blur, additive noise, and color jitter. Segmentation performance was quantified using the Dice coefficient and Intersection-over-Union (IoU). Paired Wilcoxon signed-rank tests with Holm correction and Cliff’s delta were used for statistical comparison. In addition, clinically relevant nuclear descriptors—nuclear count, median nuclear area, area interquartile range (IQR), and nuclear density—were extracted from predicted masks, and descriptor stability was analyzed as relative deviation from clean conditions. Results: Under clean imaging conditions, Attention U-Net achieved the highest mean Dice score, while paired statistical analysis indicated that U-Net++ exhibited the most consistent performance across test samples. Under image perturbations, Attention U-Net demonstrated greater robustness to blur and noise, whereas U-Net++ showed superior stability under color variations. Descriptor-based analysis further indicated that U-Net++ preserved nuclear count and density most reliably under chromatic perturbations, while U-Net exhibited larger instability in nuclear count and density, particularly under noise. Conclusions: Architectural design choices strongly influence not only pixel-level segmentation accuracy but also the stability of clinically relevant nuclear morphology descriptors. Robustness evaluation under multiple perturbation types reveals important trade-offs between architectures that are not captured by clean-image benchmarks alone. These findings highlight the necessity of multi-level evaluation strategies combining overlap metrics, statistical testing, robustness analysis, and descriptor stability assessment for future benchmarking and clinically reliable deployment of nuclei segmentation systems. Full article

Clear-cell renal cell carcinoma (ccRCC) accounts for the majority of kidney cancer diagnoses and exhibits widely variable clinical behaviour. The dataset described here was generated to support the discovery of robust biomarkers of tumour cell-cycle arrest and to inform the risk-stratified management of ccRCC. We assembled four independent cohorts including 480 patients from the UK arm of the SORCE adjuvant trial, 300 patients from a surgically treated series in Korea, 120 patients from a retrospective Scottish cohort, and a paired primary–metastatic cohort comprising 62 patients. Formalin-fixed paraffin-embedded nephrectomy specimens were processed for routine hematoxylin and eosin (H&E) histology, and for multiplex immunofluorescence (mIF). The mIF panels detect the cyclin-dependent kinase inhibitor p21^CDKN1a, the DNA replication licencing factor MCM2, endoglin/CD105, Lamin B1 and nuclear DNA (Hoechst). Whole-slide images (WSIs) were acquired at high resolution, and artificial-intelligence pipelines were used to segment nuclei, classify individual cells into arrested phenotypes, and calculate the fraction of cells. Accompanying metadata include demographics, tumour stage, grade, Leibovich score, treatment arm (sorafenib/placebo), relapse events, and disease-free survival. All images and derived tables are released under a CC0 licence via the BioImage Archive, ensuring unrestricted reuse. This multi-cohort dataset provides a rich resource for studying cell-cycle arrest and proliferation markers, training image-analysis algorithms, and developing prognostic signatures in RCC. Full article

Introduction: Accurate nuclear segmentation is essential for the reliable diagnostic interpretation of fluorescence in situ hybridization (FISH) results. However, automated 2D digital algorithms often fail in samples with dense or overlapping nuclei, such as lymphomas, due to the loss of spatial depth information. Here, we tested if AI-based 3D nuclear segmentation can improve the accuracy, reproducibility, and diagnostic reliability of FISH reading in critical situations. Materials and Methods: Formalin-fixed follicular lymphoma sections were FISH-labeled for BCL2 gene rearrangements and digitally scanned in multilayer Z-stacks. The analytic performance in nuclear segmentation of the adaptive thresholding-based FISHQuant, and the freely accessible AI-based NucleAIzer, StarDist, and Cellpose algorithms, were compared to the eye control-based traditional FISH testing, primarily focusing on nuclear segmentation. Results: We revealed that the Cellpose algorithm showed limited sensitivity to low-intensity signals and the adaptive thresholding 2D segmentation, and FISHQuant struggled to resolve densely packed nuclei, occasionally underestimating their counts. In contrast, 3D segmentation across focal planes significantly improved the nuclear separation and signal localization. AI-driven 3D models, especially NucleAIzer and StarDist, showed improved precision, lower variance (VP/VS ≈ 0.96), and improved gene spot correlation (r > 0.82) across multiple focal planes. The similar average number of gene spots per cell nuclei in the AI-based analyses as the eye control counting, despite the elevated number of cell nuclei found with AI, validated the AI nuclear segmentation results. Conclusions: Inaccurate segmentation limits automated diagnostic FISH signal evaluation. Deep learning 3D approaches, particularly NucleAIzer and StarDist, may overcome thresholding and 2D constraints and improve the consistency of nuclear detection, resulting in better classification of pathogenetic gene aberrations with automated workflows in digital pathology. Full article

Recently, deep learning methods have seen major advancements and are preferred for medical image analysis. Clinically, deep learning techniques for cancer image analysis are among the main applications for early diagnosis, detection, and treatment. Consequently, segmentation of breast histology images is a key step towards diagnosing breast cancer. However, the use of deep learning methods for image analysis is constrained by challenging features in the histology images. These challenges include poor image quality, complex microscopic tissue structures, topological intricacies, and boundary/edge inhomogeneity. Furthermore, this leads to a limited number of images required for analysis. The U-Net model was introduced and gained significant traction for its ability to produce high-accuracy results with very few input images. Many modifications of the U-Net architecture exist. Therefore, this study proposes the watershed encoder–decoder neural network (WEDN) to segment cancerous lesions in supervised breast histology images. Pre-processing of supervised breast histology images via augmentation is introduced to increase the dataset size. The augmented dataset is further enhanced and segmented into the region of interest. Data enhancement methods such as thresholding, opening, dilation, and distance transform are used to highlight foreground and background pixels while removing unwanted parts from the image. Consequently, further segmentation via the connected component analysis method is used to combine image pixel components with similar intensity values and assign them their respective labeled binary masks. The watershed filling method is then applied to these labeled binary mask components to separate and identify the edges/boundaries of the regions of interest (cancerous lesions). This resultant image information is sent to the WEDN model network for feature extraction and learning via training and testing. Residual convolutional block layers of the WEDN model are the learnable layers that extract the region of interest (ROI), which is the cancerous lesion. The method was evaluated on 3000 images–watershed masks, an augmented dataset. The model was trained on 2400 training set images and tested on 600 testing set images. This proposed method produced significant results of $98.53\%$ validation accuracy, $96.98\%$ validation dice coefficient, and $97.84\%$ validation intersection over unit (IoU) metric scores. Full article

Accurate segmentation of nuclei and cytoplasm in cervical cytology images plays a pivotal role in characterizing cellular morphology. The primary challenge is to precisely delineate boundaries within densely clustered cells, which is complicated by low-contrast edges and irregular morphologies. This paper introduces a novel framework combining MaskDino architecture with Hausdorff distance loss, enhanced by a two-phase training strategy. The method begins by employing MaskDino for precise nucleus segmentation. Building on this foundation, the framework then enhances cytoplasmic boundary detection in cellular clusters by incorporating a Hausdorff distance loss, with weight transfer initialization ensuring feature consistency across tasks.. The symmetry between the nucleus and cytoplasm servers as a key morphological indicator for cell assessment, and our method provides a reliable basis for such analysis. Extensive experiments demonstrate that our method achieves state-of-the-art cytoplasm segmentation results on the ISBI2014 dataset, with absolute improvements of 2.9% in DSC, 1.6% in TPRp and 2.0% in FNRo. The performance of nucleus segmentation is better than the average level. These results validate the proposed framework’s effectiveness for improving cervical cancer screening through robust cellular segmentation. Full article

Cell nucleus segmentation in microscopy images is an initial step in the quantitative analysis of imaging data, which is crucial for diverse biological and biomedical applications. While traditional machine learning methodologies have demonstrated limitations, recent advances in U-Net models have yielded promising improvements. However, it is noteworthy that these models perform well on balanced datasets, where the ratio of background to foreground pixels is equal. Within the realm of microscopy image segmentation, state-of-the-art models often encounter challenges in accurately predicting small foreground entities such as nuclei. Moreover, the majority of these models exhibit large parameter sizes, predisposing them to overfitting issues. To overcome these challenges, this study introduces a novel architecture, called mA-UNet, designed to excel in predicting small foreground elements. Additionally, a data preprocessing strategy inspired by road segmentation approaches is employed to address dataset imbalance issues. The experimental results show that the MIoU score attained by the mA-UNet model stands at $95.50\%$, surpassing the nearest competitor, UNet++, on the 2018 Data Science Bowl dataset. Ultimately, our proposed methodology surpasses all other state-of-the-art models in terms of both quantitative and qualitative evaluations. The mA-UNet model is also implemented in VHDL on the Zynq UltraScale+ FPGA, demonstrating its ability to perform complex computations with minimal hardware resources, as well as its efficiency and scalability on advanced FPGA platforms. Full article

Background: Oral lichen planus (OLP) is a chronic inflammatory disease of unknown etiology. Its clinical and histopathological diagnosis remains challenging due to the variability of its manifestations and the subjectivity involved in interpretation. Objective: This study aimed to examine the relationship between different clinical phenotypes of OLP (reticular, erosive, and mixed) and histomorphological features obtained through digital analysis with semi-automated segmentation. Methods: A retrospective review of 100 OLP cases was conducted. Clinically, the samples were classified into three groups: 68 reticular, 16 erosive, and 16 mixed. Epithelial and connective tissue parameters were evaluated on hematoxylin–eosin-stained sections using digital tools and segmentation algorithms. Results: The erosive phenotype showed greater irregularity of suprabasal nuclei (p = 0.008) and a higher basal nucleus-to-cytoplasm ratio (p = 0.02). No significant differences were found among the groups regarding epithelial thickness or lymphocyte density (p > 0.05). Conclusions: The cellular alterations observed in the erosive subtype may reflect higher tissue activity and provide additional elements for its characterization. Digital morphometric analysis appears to be a promising complementary tool, although further studies are needed to confirm its diagnostic applicability. Full article

Upon activation, neutrophils perform three distinct functions: phagocytosis, degranulation of antimicrobial substances into the extracellular medium, and release of neutrophil extracellular traps. Determination of the nuclear area expansion of neutrophils activated to release neutrophil extracellular traps has become critical in demonstrating early neutrophil activation and has become standard. Here, we demonstrate an automated method for measuring nuclear area expansion in two different mammalian species: canine and bovine. For both species, neutrophils were isolated from peripheral blood and co-incubated with fresh spermatozoa for up to 120 min for canine neutrophil–spermatozoa and recently thawed cryopreserved spermatozoa up to 240 min for bovine neutrophil–spermatozoa. Fluorescence images were acquired using a TissueFAXS microscope and then analyzed using StrataQuest v.7.0 software. The images show the release of neutrophil extracellular traps upon activation with spermatozoa for both species, as evidenced by the co-localization of neutrophil elastase and DNA staining. Neutrophil nuclei were expanded as early as 15 min and were detected at up to 120 min in both species. Analysis by nuclei segmentation showed that the data sets generated for both species were reliable and consistent with previously published methods. The method was developed as an automated alternative for measuring the area expansion of neutrophil nuclei in different species. Full article

Accurate computer-aided cell detection in immunohistochemistry images of different tissues is essential for advancing digital pathology and enabling large-scale quantitative analysis. This paper presents a comprehensive comparison of six unsupervised segmentation methods against two supervised deep learning approaches for cell detection in immunohistochemistry images. The unsupervised methods are based on the continuity and similarity image properties, using techniques like clustering, active contours, graph cuts, superpixels, or edge detectors. The supervised techniques include the YOLO deep learning neural network and the U-Net architecture with heatmap-based localization for precise cell detection. All these methods were evaluated using leave-one-image-out cross-validation on the publicly available OIADB dataset, containing 40 oral tissue IHC images with over 40,000 manually annotated cells, assessed using precision, recall, and $F_1$-score metrics. The U-Net model achieved the highest performance for cell nuclei detection, an $F_1$-score of 75.3%, followed by YOLO with $F_1$ = 74.0%, while the unsupervised OralImmunoAnalyser algorithm achieved only $F_1$ = 46.4%. Although the two former are the best solutions for automatic pathological assessment in clinical environments, the latter could be useful for small research units without big computational resources. Full article

Background and Objective: Cervical cancer remains one of the leading causes of death among women worldwide, particularly in regions with limited access to early screening. Pap smear screening is the primary tool for early detection, but manual interpretation is labor-intensive, subjective, and prone to inconsistency and misdiagnosis. Accurate segmentation of cervical cell nuclei is essential for automated analysis but is often hampered by overlapping cells, poor contrast, and staining variability. This research aims to develop an improved algorithm for accurate cervical nucleus segmentation to support automated Pap smear analysis. Method: The proposed method involves a combination of adaptive gamma correction for contrast enhancement, followed by Otsu thresholding for segmentation. Post-processing is performed using adaptive morphological operations to refine the results. The system is evaluated using standard image quality assessment metrics and validated against ground truth annotations. Result: The results show a significant improvement in segmentation performance over conventional methods. The proposed algorithm achieved a Precision of 0.9965, an F-measure of 97.29%, and an Accuracy of 98.39%. The PSNR value of 16.62 indicates enhanced image clarity after preprocessing. The method also improved sensitivity, leading to better identification of nuclei boundaries. Advanced preprocessing techniques, including edge-preserving filters and multi-Otsu thresholding, contributed to more accurate cell separation. The segmentation method proved effective across varying cell overlaps and staining conditions. Comparative evaluations with traditional clustering methods confirmed its superior performance. Conclusions: The proposed algorithm delivers robust and accurate segmentation of cervical cell nuclei, addressing common challenges in Pap smear image analysis. It provides a consistent framework for automated screening tools. This work enhances diagnostic reliability in cervical cancer screening and offers a foundation for broader applications in medical image analysis. Full article