KRASFormer: a fully vision transformer-based framework for predictingKRASgene mutations in histopathological images of colorectal cancer.

Detecting the Kirsten Rat Sarcoma Virus (KRAS) gene mutation is significant for colorectal cancer (CRC) patients. TheKRASgene encodes a protein involved in the epidermal growth factor receptor (EGFR) signaling pathway, and mutations in this gene can negatively impact the use of monoclonal antibodies in anti-EGFR therapy and affect treatment decisions. Currently, commonly used methods like next-generation sequencing (NGS) identifyKRASmutations but are expensive, time-consuming, and may not be suitable for every cancer patient sample. To address these challenges, we have developedKRASFormer, a novel framework that predictsKRASgene mutations from Haematoxylin and Eosin (H & E) stained WSIs that are widely available for most CRC patients.KRASFormerconsists of two stages: the first stage filters out non-tumor regions and selects only tumour cells using a quality screening mechanism, and the second stage predicts theKRASgene either wildtype' or mutant' using a Vision Transformer-based XCiT method. The XCiT employs cross-covariance attention to capture clinically meaningful long-range representations of textural patterns in tumour tissue andKRASmutant cells. We evaluated the performance of the first stage using an independent CRC-5000 dataset, and the second stage included both The Cancer Genome Atlas colon and rectal cancer (TCGA-CRC-DX) and in-house cohorts. The results of our experiments showed that the XCiT outperformed existing state-of-the-art methods, achieving AUCs for ROC curves of 0.691 and 0.653 on TCGA-CRC-DX and in-house datasets, respectively. Our findings emphasize three key consequences: the potential of using H & E-stained tissue slide images for predictingKRASgene mutations as a cost-effective and time-efficient means for guiding treatment choice with CRC patients; the increase in performance metrics of a Transformer-based model; and the value of the collaboration between pathologists and data scientists in deriving a morphologically meaningful model.

True-T - Improving T-cell response quantification with holistic artificial intelligence based prediction in immunohistochemistry images.

The immune response associated with oncogenesis and potential oncological ther- apeutic interventions has dominated the field of cancer research over the last decade. T-cell lymphocytes in the tumor microenvironment are a crucial aspect of cancer's adaptive immunity, and the quantification of T-cells in specific can- cer types has been suggested as a potential diagnostic aid. However, this is cur- rently not part of routine diagnostics. To address this challenge, we present a new method called True-T, which employs artificial intelligence-based techniques to quantify T-cells in colorectal cancer (CRC) using immunohistochemistry (IHC) images. True-T analyses the chromogenic tissue hybridization signal of three widely recognized T-cell markers (CD3, CD4, and CD8). Our method employs a pipeline consisting of three stages: T-cell segmentation, density estimation from the segmented mask, and prediction of individual five-year survival rates. In the first stage, we utilize the U-Net method, where a pre-trained ResNet-34 is em- ployed as an encoder to extract clinically relevant T-cell features. The segmenta- tion model is trained and evaluated individually, demonstrating its generalization in detecting the CD3, CD4, and CD8 biomarkers in IHC images. In the second stage, the density of T-cells is estimated using the predicted mask, which serves as a crucial indicator for patient survival statistics in the third stage. This ap- proach was developed and tested in 1041 patients from four reference diagnostic institutions, ensuring broad applicability. The clinical effectiveness of True-T is demonstrated in stages II-IV CRC by offering valuable prognostic information that surpasses previous quantitative gold standards, opening possibilities for po- tential clinical applications. Finally, to evaluate the robustness and broader ap- plicability of our approach without additional training, we assessed the universal accuracy of the CD3 component of the True-T algorithm across 13 distinct solid tumors.

Effect of bariatric and metabolic surgery on rheumatoid arthritis outcomes: A systematic review.

INTRODUCTION: Obesity is a growing and debilitating epidemic worldwide that is associated with an increased inflammation. It is often linked to rheumatic diseases and may impact negatively their natural history. The use of bariatric and metabolic surgery (BMS) has increased thanks to its positive effect on major comorbidities like diabetes type 2. This systematic review provides the most up-to-date published literature regarding the effect of BMS on outcomes in rheumatoid arthritis. METHODS: This systematic review followed the preferred reporting items for systematic reviews guidelines. Original articles from Pubmed, Embase and Cochrane, published until June 16th 2023, and tackling the effect of BMS on disease outcomes in patients with RA were included. RESULTS: Three studies met the inclusion criteria. They were published between 2015 and 2022. The total number of RA patients was 33193 and 6700 of them underwent BMS. Compared to non-surgical patients, weight loss after BMS was associated with lower disease activity outcomes at 12 months (p<0.05). Similarly, prior BMS in RA patients was significantly associated with reduced odds ratios for all the morbidities and in-hospital mortality compared with no prior BMS (36.5% vs 54.6%, OR = 0.45, 95% CI (0.42, 0.48), p< 0.001) and (0.4% vs 0.9%, OR = 0.41, 95% CI (0.27-0.61), p < 0.001) respectively. CONCLUSION: To conclude, published data indicate that BMS seems a promising alternative in reducing RA disease activity as well as morbidity and mortality in patients with obesity.

The first case of SARS-CoV-2-induced eosinophilic fasciitis.

Eosinophilic fasciitis (EF), also known as Shulman syndrome, is a rare auto-immune fibrosing disorder of the fascia. Etiopathogeny of EF is still unclear. Nowadays, it is widely known that severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) may induce hyper-stimulation of the immune system. Several cases with fasciitis and rhabdomyolysis induced by coronavirus disease 2019 vaccines have been reported in the literature. Herein, we report the first case of EF possibly triggered by SARS-CoV-2 infection. A 45-year-old Tunisian woman, with no medical history, presented to our department with severe widespread muscle pain noticed one month after a SARS-CoV-2 infection. Physical examination showed an induration of the skin and subcutaneous tissue of the arms, forearms and legs with a restricted joint mobility. The level of eosinophils was 430 E/mm3 (6.1%) [1-4%]. Electromyography and creatine kinase levels were normal. Myositis-related antibodies were negative. Magnetic resonance imaging of the left arm showed high-intensity signal and thickness of the fascia without evidence of muscle or bone involvement. A muscular biopsy from the right deltoid showed thickening and inflammation of the fascia. The patient received intraveinous injections of 1000 mg of methylprednisolone for 3 days with an oral relay of 1 mg/kg per day of prednisone equivalent during 4 weeks. At one-month follow-up, a significant improvement of the skin induration and myalgia was observed, with a disappearance of the biological inflammatory syndrome. This brief report suggests a potential link between SARS-CoV-2 infection and new-onset of auto-immune fasciitis.

Rheumatoid arthritis with concomitant fibromyalgia: The role of ultrasound in assessing disease activity.

INTRODUCTION: Fibromyalgia (FM) is a chronic painful condition frequently associated with rheumatoid arthritis (RA), which may falsely increase RA activity. The aim of our study was to compare clinical scoring and ultrasound (US) assessment in RA patients with concomitant FM with those without FM. METHODS: A cross-sectional study including patients with RA according to the ACR/EULAR 2010 criteria was conducted. Patients were divided into two groups: RA patients meeting ACR 2016 FM criteria (cases) and RA patients not meeting FM criteria (controls). Clinico-biological and US assessments of RA activity were performed on the same day for each patient. RESULTS: Eighty patients distributed into 40 patients in each group were recruited. Biologic DMARD prescription was more frequent in RA with FM patients than the control group (p = 0.04). DAS28 was significantly greater than DAS28 V3 in RA with FM group (p = 0.002). FM group had significantly less US synovitis (p = 0.035) and less Power Doppler (PD) activity (p = 0.035). Grey scale US score (p = 0.87) and DP US score (p = 0.162) were similar in the two groups. The correlation between the clinical and the ultrasonographic scores was strong to very strong in both groups with the strongest correlation found between DAS28 V3 and US DAS28 V3 (r = 0.95) in RA + FM group. CONCLUSION: Our study confirms the overestimation of disease activity by the clinical scores in RA with concomitant FM. DAS28 V3 score and US assessment would represent a better alternative.

ICOSeg: Real-Time ICOS Protein Expression Segmentation from Immunohistochemistry Slides Using a Lightweight Conv-Transformer Network.

In this article, we propose ICOSeg, a lightweight deep learning model that accurately segments the immune-checkpoint biomarker, Inducible T-cell COStimulator (ICOS) protein in colon cancer from immunohistochemistry (IHC) slide patches. The proposed model relies on the MobileViT network that includes two main components: convolutional neural network (CNN) layers for extracting spatial features; and a transformer block for capturing a global feature representation from IHC patch images. The ICOSeg uses an encoder and decoder sub-network. The encoder extracts the positive cell's salient features (i.e., shape, texture, intensity, and margin), and the decoder reconstructs important features into segmentation maps. To improve the model generalization capabilities, we adopted a channel attention mechanism that added to the bottleneck of the encoder layer. This approach highlighted the most relevant cell structures by discriminating between the targeted cell and background tissues. We performed extensive experiments on our in-house dataset. The experimental results confirm that the proposed model achieves more significant results against state-of-the-art methods, together with an 8× reduction in parameters.

Factors associated with the inflammatory process in pain in ankylosing spondylitis.

Introduction: sleep disorders, closely related to any chronic pain process, are frequent among patients with rheumatic diseases, mainly ankylosing spondylitis (AS). Our study aimed to determine the association between sleep disturbances and the inflammatory process in pain in AS patients compared with lower back pain (LBP) patients. We have additionally examined factors associated with sleep disorders among AS patients. Methods: we conducted a cross-sectional study among AS patients. Sociodemographic data, patient reported outcomes and disease characteristics were recorded. Sleep was assessed using the medical outcomes study sleep scale measure (MOS-SS). For psychological assessment, Beck anxiety (BAI) and depression index (BDI) was used. A multivariate logistic regression was performed to identify factors associated with sleep disorders. Results: the study included 50 patients with AS and 40 patients with low back pain. The most common affected domains among AS patients were inadequacy, sleep disturbance, and daily somnolence. The MOS-SS index was significantly higher in the AS group than in the control group (p<0.001). Sleep disorder was associated with age, female gender, analphabetism, patient-reported outcomes (all p<0.05), but was not associated with profession, comorbidities and smoking habits. In multivariate analysis, factors associated with sleep disruption were the duration of morning stiffness (MS), disease activity, bath ankylosing spondylitis metrology index (BASMI), ASQol, as well as anxiety and depression (odds ratio: 5.4(CI 95% 1.6-18.3), 9.9 (CI95%1.1-86); 6 (CI95%1.1-32); 13 (CI 95% 1.4-143.8); 15.7 (CI 95% 2.6-94.3); 14 (CI 95% 2-105.7) respectively, p<0.05 for each). Conclusion: our study highlighted the importance of sleep disorders among patients with AS with a predilection for inadequacy, sleep disturbance, and daily somnolence. Factors associated with sleep disruption were high disease activity, a longer duration of MS, an altered function and quality of life as well as anxiety and depression.

Management of chronic recurrent multifocal osteomyelitis: review and update on the treatment protocol.

INTRODUCTION: Chronic recurrent multifocal osteomyelitis (CRMO) is an autoinflammatory disorder primarily affecting children. It is characterized by a peripheral involvement of the metaphysis of long bones rather than axial involvement. Due to the scarcity of the disease, there are no guidelines regarding its management. AREAS COVERED: This review aims to provide an overview of the different therapeutic alternatives and recent protocols. For this reason, first-line and second-line treatment, as well as the impact of new therapies, are discussed in depth. We conducted a search through PubMed on the different aspects of CRMO. Outcomes were categorized as first and second-line treatments. EXPERT OPINION: Non-steroidal anti-inflammatory drugs remain the keystone of CRMO management and are proposed as the first-line treatment. In the case of vertebral involvement, bisphosphonate should be considered, even as a first-line treatment. Several case series and retrospective studies highlight the efficacy of anti-TNF agents. Their use could be an optimal treatment choice for CRMO with comorbid immune-mediated diseases. The potentially favorable effect of interleukin-1 antagonists remains to be determined.

Hyperparathyroidism: Unusual location of brown tumors.

Brown tumors (BTs) are due to a proliferation of multinucleated giant cells in osteolytic lesions. They complicate the course of hyperparathyroidism. Thanks to an early screening of bone metabolism disorders; BTs are nowadays rare bone manifestations. We demonstrate through these two cases reports unusual locations of BTs in hyperparathyroidism.

The effects of autoimmune rheumatic-related diseases on male reproductive health: A systematic review.

Autoimmune rheumatic-related diseases (ARRDs) have physical and psychological impact on patients, including their sexual life. While many studies have investigated fertility problems in females, data on males-related fertility are scarce, which explains the lack of guidance. The main objective of this systematic review was to evaluate the reproductive health in males with ARRDs. This systematic review followed the preferred reporting items for systematic reviews guidelines. Original articles from Pubmed and Scopus, published until September 16, 2021, and tackling the effects of ARRDs and/or ARRDs treatments on male fertility and/or pregnancy outcomes, were included. A total of twenty-five studies met the inclusion criteria. They were published between 1981 and 2018. The studied ARRDs were spondyloarthritis (n = 9), systematic lupus erythematosus (SLE, n = 6), Behcet disease (BD, n = 5), rheumatoid arthritis (RA, n = 5), antiphospholipid syndrome (n = 1), and dermatomyositis (n = 1). The most reported effects of ARRDs on fertility are i) high levels of reproductive hormones, mainly in RA and SLE; ii) impaired semen quality in SLE, spondyloarthritis, and BD; and iii) higher rate of varicocele in BD and spondyloarthritis. Regarding the treatments effects, i) conventional synthetic disease-modifying anti-rheumatic drugs (e.g.; methotrexate and salazopyrine) increase testosterone level, ii) cyclophosphamide impairs fertility, iii) anti-tumor necrosis factor agents are associated with improvement in semen quality, and iv) no increased number of miscarriages or congenital abnormalities in children fathered by BD was reported. To conclude, both ARRDs and their treatments alter fertility in males with ARRDs. In practice, in addition to the conventional semen analysis, screening for infertility seems legitimate in males with ARRDs.

A Means of Assessing Deep Learning-Based Detection of ICOS Protein Expression in Colon Cancer.

Biomarkers identify patient response to therapy. The potential immune-checkpoint biomarker, Inducible T-cell COStimulator (ICOS), expressed on regulating T-cell activation and involved in adaptive immune responses, is of great interest. We have previously shown that open-source software for digital pathology image analysis can be used to detect and quantify ICOS using cell detection algorithms based on traditional image processing techniques. Currently, artificial intelligence (AI) based on deep learning methods is significantly impacting the domain of digital pathology, including the quantification of biomarkers. In this study, we propose a general AI-based workflow for applying deep learning to the problem of cell segmentation/detection in IHC slides as a basis for quantifying nuclear staining biomarkers, such as ICOS. It consists of two main parts: a simplified but robust annotation process, and cell segmentation/detection models. This results in an optimised annotation process with a new user-friendly tool that can interact with1 other open-source software and assists pathologists and scientists in creating and exporting data for deep learning. We present a set of architectures for cell-based segmentation/detection to quantify and analyse the trade-offs between them, proving to be more accurate and less time consuming than traditional methods. This approach can identify the best tool to deliver the prognostic significance of ICOS protein expression.

A Rare Case of Hypophosphataemic Osteomalacia in von Recklinghausen Neurofibromatosis.

BACKGROUND: Neurofibromatosis type 1 (NF1), also known as von Recklinghausen disease, is a one of the more common hereditary autosomal disorders. However, osteomalacia in neurofibromatosis type 1 is very rare tumour-induced osteomalacia; fibroblast growth factor-23 is usually implicated. PATIENTS AND METHODS: We report the case of a patient with a history of von Recklinghausen neurofibromatosis who presented with hypophosphataemic osteomalacia. RESULTS: The patient was treated with high-dose calcitriol and oral phosphate with clinical improvement. CONCLUSION: Even though it is a rare entity, we must consider the diagnosis of hypophosphataemic osteomalacia in patients with neurofibromatosis in order to deliver appropriate treatment. LEARNING POINTS: Osteomalacia during von Recklinghausen disease is a rare presentation of an uncommon condition and has a poorly understood mechanism.The treatment of oncogenic osteomalacia includes tumour removal which, however, is not always possible.Administration of calcitriol alone is not sufficient and phosphorus intake is mandatory to improve symptoms.