FR-MIL: Distribution Re-calibration based Multiple Instance Learning with Transformer for Whole Slide Image Classification.

In digital pathology, whole slide images (WSI) are crucial for cancer prognostication and treatment planning. WSI classification is generally addressed using multiple instance learning (MIL), alleviating the challenge of processing billions of pixels and curating rich annotations. Though recent MIL approaches leverage variants of the attention mechanism to learn better representations, they scarcely study the properties of the data distribution itself i.e., different staining and acquisition protocols resulting in intra-patch and inter-slide variations. In this work, we first introduce a distribution re-calibration strategy to shift the feature distribution of a WSI bag (instances) using the statistics of the max-instance (critical) feature. Second, we enforce class (bag) separation via a metric loss assuming that positive bags exhibit larger magnitudes than negatives. We also introduce a generative process leveraging Vector Quantization (VQ) for improved instance discrimination i.e., VQ helps model bag latent factors for improved classification. To model spatial and context information, a position encoding module (PEM) is employed with transformer-based pooling by multi-head self-attention (PMSA). Evaluation of popular WSI benchmark datasets reveals our approach improves over state-of-the-art MIL methods. Further, we validate the general applicability of our method on classic MIL benchmark tasks and for point cloud classification with limited points https://github.com/PhilipChicco/FRMIL.

Clinical practice recommendations for the use of next-generation sequencing in patients with solid cancer: a joint report from KSMO and KSP.

In recent years, next-generation sequencing (NGS)-based genetic testing has become crucial in cancer care. While its primary objective is to identify actionable genetic alterations to guide treatment decisions, its scope has broadened to encompass aiding in pathological diagnosis and exploring resistance mechanisms. With the ongoing expansion in NGS application and reliance, a compelling necessity arises for expert consensus on its application in solid cancers. To address this demand, the forthcoming recommendations not only provide pragmatic guidance for the clinical use of NGS but also systematically classify actionable genes based on specific cancer types. Additionally, these recommendations will incorporate expert perspectives on crucial biomarkers, ensuring informed decisions regarding circulating tumor DNA panel testing.

Expression of CD163 and major histocompatibility complex class I as diagnostic markers for idiopathic inflammatory myopathies.

BACKGROUND: To develop an inflammation-related immunohistochemistry marker-based algorithm that confers higher diagnostic ability for idiopathic inflammatory myopathies (IIMs) than IIM-related histopathologic features. METHODS: Muscle biopsy tissues from 129 IIM patients who met the 2017 EULAR/ACR criteria and 73 control tissues from patients with non-inflammatory myopathies or healthy muscle specimens were evaluated for histological features and immunostaining results of CD3, CD4, CD8, CD20, CD68, CD163, MX1, MHC class I, MHC class II, and HLA-DR. Diagnostic algorithms for IIM were developed based on the results of the classification and regression tree (CART) analysis, which used immunostaining results as predictor variables for classifying patients with IIMs. RESULTS: In the analysis set (IIM, n = 129; control, n = 73), IIM-related histopathologic features had a diagnostic accuracy of 87.6% (sensitivity 80.6%; specificity 100.0%) for IIMs. Notably, muscular expression of CD163 (99.2% vs. 20.8%, p < 0.001) and MHC class I (87.6% vs. 23.1%, p < 0.001) was significantly higher in the IIM group than in controls. Based on the CART analysis results, we developed an algorithm combining CD163 and MHC class I expression that conferred a diagnostic accuracy of 95.5% (sensitivity 96.1%; specificity 94.5%). In addition, our algorithm was able to correctly diagnose IIM in 94.1% (16/17) of patients who did not meet the 2017 EUALR/ACR criteria but were diagnosed as having IIMs by an expert physician. CONCLUSIONS: Combination of CD163 and MHC class I muscular expression may be useful in diagnosing IIMs.

Enrichment of infection-associated bacteria in the low biomass brain bacteriota of Alzheimer's disease patients.

Alzheimer's disease (AD) is a neurodegenerative disease accompanied by neuroimmune inflammation in the frontal cortex and hippocampus. Recently, the presence of bacteria in AD-affected brains has been documented, prompting speculation about their potential role in AD-associated neuroinflammation. However, the characterization of bacteriota in human brains affected by AD remains inconclusive. This study aimed to investigate potential associations between specific bacteria and AD pathology by examining brain tissues from AD-associated neurodegenerative regions (frontal cortex and hippocampus) and the non-AD-associated hypothalamus. Employing 16S rRNA gene sequencing, 30 postmortem brain tissue samples from four individuals with normal brain histology (N) and four AD patients were analyzed, along with three blank controls. A remarkably low biomass characterized the brain bacteriota, with their overall structures delineated primarily by brain regions rather than the presence of AD. While most analyzed parameters exhibited no significant distinction in the brain bacteriota between the N and AD groups, the unique detection of Cloacibacterium normanense in the AD-associated neurodegenerative regions stood out. Additionally, infection-associated bacteria, as opposed to periodontal pathogens, were notably enriched in AD brains. This study's findings provide valuable insights into potential link between bacterial infection and neuroinflammation in AD.