Nuclei classification provides valuable information for histopathology image analysis. However, the large variations in the appearance of different nuclei types cause difficulties in identifying nuclei. Most neural network based methods are affected by the local receptive field of convolutions, and pay less attention to the spatial distribution of nuclei or the irregular contour shape of a nucleus. In this paper, we first propose a novel polygon-structure feature learning mechanism that transforms a nucleus contour into a sequence of points sampled in order, and employ a recurrent neural network that aggregates the sequential change in distance between key points to obtain learnable shape features. Next, we convert a histopathology image into a graph structure with nuclei as nodes, and build a graph neural network to embed the spatial distribution of nuclei into their representations. To capture the correlations between the categories of nuclei and their surrounding tissue patterns, we further introduce edge features that are defined as the background textures between adjacent nuclei. Lastly, we integrate both polygon and graph structure learning mechanisms into a whole framework that can extract intra and inter-nucleus structural characteristics for nuclei classification. Experimental results show that the proposed framework achieves significant improvements compared to the previous methods. Code and data are made available via https://github.com/lhaof/SENC.

Background: Tertiary lymphoid structures (TLSs) exert a crucial role in the tumor microenvironment (TME), impacting tumor development, immune escape, and drug resistance. Nonetheless, the heterogeneity of TLSs in colorectal cancer (CRC) and their impact on prognosis and treatment response remain unclear. Methods: The authors collected genome, transcriptome, clinicopathological information, and digital pathology images from multiple sources. An unsupervised clustering algorithm was implemented to determine diverse TLS patterns in CRC based on the expression levels of 39 TLS signature genes (TSGs). Comprehensive explorations of heterogeneity encompassing mutation landscape, TME, biological characteristics, response to immunotherapy, and drug resistance were conducted using multiomics data. TLSscore was then developed to quantitatively assess TLS patterns of individuals for further clinical applicability. Results: Three distinct TLS patterns were identified in CRC. Cluster 1 exhibited upregulation of proliferation-related pathways, high metabolic activity, and intermediate prognosis, while Cluster 2 displayed activation of stromal and carcinogenic pathways and a worse prognosis. Both Cluster 1 and Cluster 2 may potentially benefit from adjuvant chemotherapy. Cluster 3, characterized by the activation of immune regulation and activation pathways, demonstrated a favorable prognosis and enhanced responsiveness to immunotherapy. The authors subsequently employed a regularization algorithm to construct the TLSscore based on nine core genes. Patients with lower TLSscore trended to prolonged prognosis and a more prominent presence of TLSs, which may benefit from immunotherapy. Conversely, those with higher TLSscore exhibited increased benefits from adjuvant chemotherapy. Conclusions: The authors identified distinct TLS patterns in CRC and characterized their heterogeneity through multiomics analyses. The TLSscore held promise for guiding clinical decision-making and further advancing the field of personalized medicine in CRC.

Nuclei segmentation is critical for computational pathology analysis. Most previous methods employ pixel-wise classification or regression for automatic nuclei segmentation, without describing nucleus instances as individual entities at the feature level. To address the above limitation, we propose an instance-aware multi-task learning framework that strengthens a pixel-wise prediction branch with an instance-wise prediction branch. The instance-wise prediction branch leverages learnable cell-level queries, enabling the model to capture positional information and visual representations for individual nuclei. Concretely, we introduce an instance-disentangling feature learning module that effectively aligns the embeddings of the object-level queries with pixel-wise decoder features from the first branch. Further, we design a dual-branch unified post-processing algorithm that aggregates the complementary outputs of both branches for computing the instance segmentation results. Experimental results demonstrate that our framework achieves competitive performance on a wide range of nuclei segmentation benchmarks. The code and model weights are released in https://github.com/lhaof/IML .

Nuclei classification provides valuable information for histopathology image analysis. However, the large variations in the appearance of different nuclei types cause difficulties in identifying nuclei. Most neural network based methods are affected by the local receptive field of convolutions, and pay less attention to the spatial distribution of nuclei or the irregular contour shape of a nucleus. In this paper, we first propose a novel polygon-structure feature learning mechanism that transforms a nucleus contour into a sequence of points sampled in order, and employ a recurrent neural network that aggregates the sequential change in distance between key points to obtain learnable shape features. Next, we convert a histopathology image into a graph structure with nuclei as nodes, and build a graph neural network to embed the spatial distribution of nuclei into their representations. To capture the correlations between the categories of nuclei and their surrounding tissue patterns, we further introduce edge features that are defined as the background textures between adjacent nuclei. Lastly, we integrate both polygon and graph structure learning mechanisms into a whole framework that can extract intra and inter-nucleus structural characteristics for nuclei classification. Experimental results show that the proposed framework achieves significant improvements compared to the state-of-the-art methods.

The pathognomonic genetic alteration in Burkitt lymphoma (BL) is the immunoglobulin ( IG )- MYC translocation, causing intense nuclear MYC expression in almost all cases. Rare cases harbor MYC rearrangements yet lack detectable MYC protein expression. In this study, we report 8 cases of MYC protein–negative sporadic BL (MYC⁻ sBL). These cases accounted for 1.4% (8/574) of all sporadic BL cases. The median age was 10 years (range: 5 to 77 y), with a male-to-female ratio of 3:1. The majority (62.5%, 5/8) presented with advanced-stage disease (III/IV), and 25.0% (2/8) had bone marrow involvement. Morphologically, all cases met the World Health Organization (WHO) diagnostic criteria for BL, characterized by monotonous medium-sized cells with a typical “starry sky” pattern. Immunophenotypically, all cases exhibited a germinal center B-cell phenotype with nearly 100% Ki-67 positivity. Notably, MUM1 was positive in 50.0% (4/8) of cases, while Epstein-Barr virus (EBV)-encoded RNA (EBER) was positive in only 25.0% (2/8). Despite fluorescence in situ hybridization (FISH)-confirmed MYC rearrangement and the absence of BCL2 or BCL6 abnormalities, MYC protein expression was undetectable. Furthermore, patients with MYC⁻ sBL exhibited significantly inferior overall survival (OS) compared with those with MYC protein–positive sporadic BL (MYC ⁺ sBL) ( P <0.0001, HR=404.1). These findings confirm that MYC⁻ sBL is a rare but distinct clinicopathological entity associated with poor clinical outcomes, despite lacking unique histologic features. The molecular mechanisms underlying the absence of MYC protein expression remain to be investigated.