Laboratory Investigation最新文献

In digital pathology, accurate mitosis detection in histopathological images is critical for cancer diagnosis and prognosis. However, this remains challenging due to the inherent variability in cell morphology and the domain shift problem. This study introduces ConvNext Mitosis Identification-You Only Look Once (CNMI-YOLO), a new 2-stage deep learning method that uses the YOLOv7 architecture for cell detection and the ConvNeXt architecture for cell classification. The goal is to improve the identification of mitosis in different types of cancers. We utilized the Mitosis Domain Generalization Challenge 2022 data set in the experiments to ensure the model’s robustness and success across various scanners, species, and cancer types. The CNMI-YOLO model demonstrates superior performance in accurately detecting mitotic cells, significantly outperforming existing models in terms of precision, recall, and F1 score. The CNMI-YOLO model achieved an F1 score of 0.795 on the Mitosis Domain Generalization Challenge 2022 and demonstrated robust generalization with F1 scores of 0.783 and 0.759 on the external melanoma and sarcoma test sets, respectively. Additionally, the study included ablation studies to evaluate various object detection and classification models, such as Faster-RCNN and Swin Transformer. Furthermore, we assessed the model’s robustness performance on unseen data, confirming its ability to generalize and its potential for real-world use in digital pathology, using soft tissue sarcoma and melanoma samples not included in the training data set.

Lymph node status is a key factor in determining stage, treatment, and prognosis in cancers. Small lymph nodes in fat-rich gastrointestinal and breast cancer specimens are easily missed in conventional sampling methods. This study examined the effectiveness of the degreasing pretreatment with dimethyl sulfoxide (DMSO) in lymph node detection and its impact on the analysis of clinical treatment–related proteins and molecules. Thirty-three cases of gastrointestinal cancer specimens from radical gastrectomy and 63 cases of breast cancer specimens from modified radical mastectomy were included. After routine sampling of lymph nodes, the specimens were immersed in DMSO for 30 minutes for defatting. We assessed changes in the number of detected lymph nodes and pN staging in 33 gastrointestinal cancer specimens and 37 breast cancer specimens. In addition, we analyzed histologic characteristics, Masson trichrome special staining, and immunohistochemistry (gastrointestinal cancer: MMR, HER2, and PD-L1; breast cancer: ER, PR, AR, HER2, Ki-67, and PD-L1). Molecular status was evaluated for colorectal cancer (KRAS, NRAS, BRAF, and microsatellite instability) and breast cancer (HER2) in gastrointestinal cancer specimens and the remaining 26 breast cancer specimens. Compared with conventional sampling, DMSO pretreatment increased the detection rate of small lymph nodes (gastrointestinal cancer: P < .001; breast cancer: P < .001) and improved pN staging in 1 case each of gastric cancer, colon cancer, and rectal cancer (3/33; 9.1%). No significant difference in the morphology, special staining, protein, and molecular status of cancer tissue after DMSO treatment was found. Based on these results and our institutional experience, we recommend incorporating DMSO degreasing pretreatment into clinical pathologic sampling practices.

This study used artificial intelligence (AI)-based analysis to investigate the immune microenvironment in endometrial cancer (EC). We aimed to evaluate the potential of AI-based immune metrics as prognostic biomarkers. In total, 296 cases with EC were classified into 4 molecular subtypes: polymerase epsilon ultramutated (POLEmut), mismatch repair deficiency (MMRd), p53 abnormal (p53abn), and no specific molecular profile (NSMP). AI-based methods were used to evaluate the following immune metrics: total tumor-infiltrating lymphocytes (TIL), intratumoral TIL, stromal TIL, and tumor cells using Lunit SCOPE IO, as well as CD4+, CD8+, and FOXP3+ T cells using immunohistochemistry (IHC) by QuPath. These 7 immune metrics were used to perform unsupervised clustering. PD-L1 22C3 IHC expression was also evaluated. Clustering analysis demonstrated 3 distinct immune microenvironment groups: immune active, immune desert, and tumor dominant. The immune-active group was highly prevalent in POLEmut, and it was also seen in other molecular subtypes. Although the immune-desert group was more frequent in NSMP and p53mut, it was also detected in MMRd and POLEmut. POLEmut showed the highest levels of CD4+ and CD8+ T cells, total TIL, intratumoral TIL, and stromal TIL with the lowest levels of FOXP3+/CD8+ ratio. In contrast, p53abn in the immune-active group showed higher FOXP3+/CD4+ and FOXP3+/CD8+ ratios. The immune-active group was associated with favorable overall survival and recurrence-free survival. In the NSMP subtype, a significant association was observed between immune active and better recurrence-free survival. The PD-L1 22C3 combined positive score (CPS) showed significant differences among the 3 groups, with the immune-active group having the highest median CPS and frequency of CPS ≥ 1%. The immune microenvironment of EC was variable within molecular subtypes. Within the same immune microenvironment group, significant differences in immune metrics and T cell composition were observed according to molecular subtype. AI-based immune microenvironment groups served as prognostic markers in ECs, with the immune-active group associated with favorable outcomes.

Tumor–stroma ratio (TSR) has been recognized as a valuable prognostic indicator in various solid tumors. This study aimed to examine the clinicopathologic relevance of TSR in Merkel cell carcinoma (MCC) using artificial intelligence (AI)-based parameterization of the stromal landscape and validate TSR scores generated by our AI model against those assessed by humans. One hundred twelve MCC cases with whole-slide images were collected from 4 different institutions. Whole-slide images were first partitioned into 128 × 128-pixel “mini-patches,” then classified using a novel framework, termed pre-tumor and stroma (Pre-TOAST) and TOAST, whose output equaled the probability of the minipatch representing tumor cells rather than stroma. Hierarchical random samplings of 50 minipatches per region were performed throughout 50 regions per slide. TSR and tumor–stroma landscape (TSL) parameters were estimated using the maximum-likelihood algorithm. Receiver operating characteristic curves showed that the area under the curve value of Pre-TOAST in discriminating classes of interest including tumor cells, collagenous stroma, and lymphocytes from nonclasses of interest including hemorrhage, space, and necrosis was 1.00. The area under the curve value of TOAST in differentiating tumor cells from related stroma was 0.93. MCC stroma was categorized into TSR high (TSR ≥ 50%) and TSR low (TSR < 50%) using both AI- and human pathology–based methods. The AI-based TSR-high subgroup exhibited notably shorter metastasis-free survival (MFS) with a statistical significance of P = .029. Interestingly, pathologist-determined TSR subgroups lacked statistical significance in recurrence-free survival, MFS, and overall survival (P > .05). Density-based spatial clustering of applications with noise analysis identified the following 2 distinct TSL clusters: TSL1 and TSL2. TSL2 showed significantly shorter recurrence-free survival (P = .045) and markedly reduced MFS (P < .001) compared with TSL1. TSL classification appears to offer better prognostic discrimination than traditional TSR evaluation in MCC. TSL can be reliably calculated using an AI-based classification framework and predict various prognostic features of MCC.

Benign prostatic hyperplasia (BPH) is a common condition marked by the enlargement of the prostate gland, which often leads to significant urinary symptoms and a decreased quality of life. The development of clinically relevant animal models is crucial for understanding the pathophysiology of BPH and improving treatment options. This study aims to establish a patient-derived xenograft (PDX) model using benign prostatic tissues to explore the molecular and cellular mechanisms of BPH. PDXs were generated by implanting fresh BPH (transition zone) and paired normal (peripheral zone) prostate tissue from 8 patients under the renal capsule of immunodeficient male mice. Tissue weight, architecture, cellular proliferation, apoptosis, prostate-specific marker expression, and molecular profiles of PDXs were assessed after 1 week and 1, 2, or 3 months of implantation by immunohistochemistry, enzyme-linked immunosorbent assay, transcriptomics, and proteomics. Responses to finasteride, a standard-of-care therapy, were evaluated. PDXs maintained histologic and molecular characteristics of the parental human tissues. BPH, but not normal PDXs, demonstrated significant increases in weight and cellular proliferation, particularly at 1 month. Molecular profiling revealed specific gene and protein expression patterns correlating with BPH pathophysiology. Specifically, an increased immune and stress response was observed at 1 week, followed by increased expression of proliferation markers and BPH-specific stromal signaling molecules, such as BMP5 and CXCL13, at 1 month. Graft stabilization to preimplant characteristics was apparent between 2 and 3 months. Treatment with finasteride reduced proliferation, increased apoptosis, and induced morphologic changes consistent with therapeutic responses observed in human BPH. Our PDX model recapitulates the morphologic, histologic, and molecular features of human BPH, offering a significant advancement in modeling the complex interactions of cell types in BPH microenvironments. These PDXs respond to therapeutic intervention as expected, providing a valuable tool for preclinical testing of new therapeutics that will improve the well-being of BPH patients.

The high mortality rate of esophageal squamous cell carcinoma (ESCC) is exacerbated by the absence of early diagnostic markers. The pronounced heterogeneity of mutations in ESCC renders copy number alterations (CNAs) more prevalent among patients. The identification of CNA genes within esophageal squamous dysplasia (ESD), a precancerous stage of ESCC, is crucial for advancing early detection efforts. Utilization of liquid biopsies via droplet-based digital PCR (ddPCR) offers a novel strategy for detecting incipient tumor traces. This study undertook a thorough investigation of CNA profiles across ESCC development stages, integrating data from existing databases and prior investigations to pinpoint and confirm CNA markers conducive to early detection of ESCC. Targeted sequencing was employed to select potential early detection genes, followed by the establishment of prediction models for ESCC early detection using ddPCR. Our analysis revealed widespread CNAs during the ESD stage, mirroring the CNA landscape observed in ESCC. A total of 40 CNA genes were identified as highly frequent in both ESCC and ESD lesions, through a comprehensive gene-level CNA analysis encompassing ESD and ESCC tissues, ESCC cell lines, and pan-cancer data sets. Subsequent validation of 5 candidate markers via ddPCR underscored the efficacy of combined predictive models encompassing PIK3CA, SOX2, EGFR, MYC, and CCND1 in early ESCC screening, as evidenced by the area-under-the-curve values exceeding 0.92 (P < .0001) across various detection contexts. The findings highlighted the significant utility of CNA genes in the early screening of ESCC, presenting robust models that could facilitate early detection, broad-scale population screening, and adjunctive diagnosis.

Merkel cell carcinoma (MCC) is an aggressive cutaneous neuroendocrine carcinoma. Checkpoint inhibitor immunotherapy plays an essential role in management of advanced MCC; however, predictors of immunotherapy response remain poorly defined. Syngeneic mouse models suitable for testing novel immunotherapy and combination therapy approaches are likely to soon become available and will require assays for evaluating the tumor microenvironment (TME). Multiplex immunofluorescence (mIF) is a powerful approach to characterize the TME for understanding immunotherapy responses and immune surveillance. In this method article, we provide detailed instructions on assay development for mIF, using as examples 2 new mIF panels for TME investigations of human and murine MCC tumors. Specifically, we demonstrate panels that allow simultaneous visualization of the Merkel cell master transcription factor SOX2 for tumor cell identification, alongside T-cell markers (CD3, CD8, and FOXP3), macrophage markers (F4/80 for mouse and CD163 for human tumors), together with the checkpoint marker PD-L1 for human tumors, and the myeloid-derived suppressor cell marker Arg1 for mouse tumors. We provide detailed protocols for investigators to incorporate these mIF panels into their investigations of human and murine MCC. We also provide fundamental guidance for mIF assay development that will be broadly useful for investigators who consider modifying the panels presented in this study or developing their own mIF panels.

The assessment of chemotherapy response in osteosarcoma (OS), based on the average percentage of viable cells, is limited, as it overlooks the spatial heterogeneity of tumor cell response (foci of resistant cells), immune microenvironment, and bone microarchitecture. Despite the resulting positive classification for response to chemotherapy, some patients experience early metastatic recurrence, demonstrating that our conventional tools for evaluating treatment response are insufficient. We studied the interactions between tumor cells, immune cells (lymphocytes, histiocytes, and osteoclasts), and bone extracellular matrix (ECM) in 18 surgical resection samples of OS using multiplex and conventional immunohistochemistry (IHC: CD8, CD163, CD68, and SATB2), combined with multiscale characterization approaches in territories of good and poor response (GRT/PRT) to treatment. GRT and PRT were defined as subregions with <10% and ≥10% of viable tumor cells, respectively. Local correlations between bone ECM porosity and density of immune cells were assessed in these territories. Immune cell density was then correlated to overall patient survival. Two patterns were identified for histiocytes and osteoclasts. In poor responder patients, CD68 osteoclast density exceeded that of CD163 histiocytes but was not related to bone ECM load. Conversely, in good responder patients, CD163 histiocytes were more numerous than CD68 osteoclasts. For both of them, a significant negative local correlation with bone ECM porosity was found (P < ,01). Moreover, in PRT, multinucleated osteoclasts were rounded and intermingled with tumor cells, whereas in GRT, they were elongated and found in close contact with bone trabeculae. CD8 levels were always low in metastatic patients, and those initially considered good responders rapidly died from their disease. The specific recruitment of histiocytes and osteoclasts within the bone ECM, and the level of CD8 represent new features of OS response to treatment. The associated prognostic signatures should be integrated into the therapeutic stratification algorithm of patients after surgery.

The advent of affordable technology has significantly influenced the practice of digital pathology, leading to its growing adoption within the pathology community. This review article aimed to outline the latest developments in digital pathology, the cutting-edge advancements in artificial intelligence (AI) applications within this field, and the pertinent United States regulatory frameworks. The content is based on a thorough analysis of original research articles and official United States Federal guidelines. Findings from our review indicate that several Food and Drug Administration-approved digital scanners and image management systems are establishing a solid foundation for the seamless integration of advanced technologies into everyday pathology workflows, which may reduce device and operational costs in the future. AI is particularly transforming the way morphologic diagnoses are automated, notably in cancers like prostate and colorectal, within screening initiatives, albeit challenges such as data privacy issues and algorithmic biases remain. The regulatory environment, shaped by standards from the Food and Drug Administration, Centers for Medicare & Medicaid Services/Clinical Laboratory Improvement Amendments, and College of American Pathologists, is evolving to accommodate these innovations while ensuring safety and reliability. Centers for Medicare & Medicaid Services/Clinical Laboratory Improvement Amendments have issued policies to allow pathologists to review and render diagnoses using digital pathology remotely. Moreover, the introduction of new digital pathology Current Procedural Terminology codes designed to complement existing pathology Current Procedural Terminology codes is facilitating reimbursement processes. Overall, these advancements are heralding a new era in pathology that promises enhanced diagnostic precision and efficiency through digital and AI technologies, potentially improving patient care as well as bolstering educational and research activities.