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.

A fully automated and explainable algorithm for predicting malignant transformation in oral epithelial dysplasia.

Oral epithelial dysplasia (OED) is a premalignant histopathological diagnosis given to lesions of the oral cavity. Its grading suffers from significant inter-/intra-observer variability, and does not reliably predict malignancy progression, potentially leading to suboptimal treatment decisions. To address this, we developed an artificial intelligence (AI) algorithm, that assigns an Oral Malignant Transformation (OMT) risk score based on the Haematoxylin and Eosin (H&E) stained whole slide images (WSIs). Our AI pipeline leverages an in-house segmentation model to detect and segment both nuclei and epithelium. Subsequently, a shallow neural network utilises interpretable morphological and spatial features, emulating histological markers, to predict progression. We conducted internal cross-validation on our development cohort (Sheffield; n = 193 cases) and independent validation on two external cohorts (Birmingham and Belfast; n = 89 cases). On external validation, the proposed OMTscore achieved an AUROC = 0.75 (Recall = 0.92) in predicting OED progression, outperforming other grading systems (Binary: AUROC = 0.72, Recall = 0.85). Survival analyses showed the prognostic value of our OMTscore (C-index = 0.60, p = 0.02), compared to WHO (C-index = 0.64, p = 0.003) and binary grades (C-index = 0.65, p < 0.001). Nuclear analyses elucidated the presence of peri-epithelial and intra-epithelial lymphocytes in highly predictive patches of transforming cases (p < 0.001). This is the first study to propose a completely automated, explainable, and externally validated algorithm for predicting OED transformation. Our algorithm shows comparable-to-human-level performance, offering a promising solution to the challenges of grading OED in routine clinical practice.

Assessment of Ki-67 and mitoses in pituitary neuroendocrine tumours-Consistency counts.

Pituitary neuroendocrine tumour Ki-67 proliferation index varies according to the number of tumour cells assessed. Consistent Ki-67 scoring approaches and re-evaluation of the recommended Ki-67 3% cut-off are required to clarify controversies in pituitary neuroendocrine tumour Ki-67 proliferation index assessment.

Insights on epidemiology, morbidity and mortality of Cushing's disease in Northern Ireland.

Cushing's disease is a rare condition that occurs due to an adrenocorticotrophin-producing corticotrophinoma arising from the pituitary gland. The consequent hypercortisolaemia results in multisystem morbidity and mortality. This study aims to report incidence, clinicopathological characteristics, remission outcomes and mortality in a regional pituitary neurosurgical cohort of patients diagnosed with Cushing's disease in Northern Ireland (NI) from 2000 to 2019. Clinical, biochemical and radiological data from a cohort of patients operated for Cushing's disease were retrospectively collected and analysed. Fifty-three patients were identified, resulting in an estimated annual incidence of Cushing's disease of 1.39-1.57 per million population per year. Females accounted for 72% (38/53) of the cohort. The majority (74%, 39/53) of corticotrophinomas were microadenomas and in 44% (17/39) of these no tumour was identified on preoperative magnetic resonance imaging. Histopathological characterisation was similarly difficult, with no tumour being identified in the histopathological specimen in 40% (21/53) of cases. Immediate postoperative remission rates were 53% and 66% when considering serum morning cortisol cut-offs of ≤ 50 nmol/L (1.8 µg/dL) and ≤ 138 nmol/L (5 µg/dL), respectively, in the week following pituitary surgery. Approximately 70% (37/53) of patients achieved longer-term remission with a single pituitary surgery. Three patients had recurrent disease. Patients with Cushing's disease had a significantly higher mortality rate compared to the NI general population (standardised mortality ratio 8.10, 95% CI 3.3-16.7, P < 0.001). Annual incidence of Cushing's disease in NI is consistent with other Northern European cohorts. Functioning corticotrophinomas are a clinically, radiologically and histopathologically elusive disease with increased mortality compared to the general population.

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.

Analysis of SARS-CoV-2 antibody seroprevalence in Northern Ireland during 2020-2021.

Background: With the spread of SARS-CoV-2 impacting upon public health directly and socioeconomically, further information was required to inform policy decisions designed to limit virus spread during the pandemic. This study sought to contribute to serosurveillance work within Northern Ireland to track SARS-CoV-2 progression and guide health strategy. Methods: Sera/plasma samples from clinical biochemistry laboratories were analysed for anti-SARS-CoV-2 antibodies. Samples were assessed using an Elecsys anti-SARS-CoV-2 or anti-SARS-CoV-2 S ECLIA (Roche) on an automated cobas e 801 analyser. Samples were also assessed via an anti-SARS-CoV-2 ELISA (Euroimmun). A subset of samples assessed via the Elecsys anti-SARS-CoV-2 ECLIA were subsequently analysed in an ACE2 pseudoneutralisation assay using a V-PLEX SARS-CoV-2 Panel 7 for IgG and ACE2 (Meso Scale Diagnostics). Results: Across three testing rounds (June-July 2020, November-December 2020 and June-July 2021 (rounds 1-3 respectively)), 4844 residual sera/plasma specimens were assayed for anti-SARS-CoV-2 antibodies. Seropositivity rates increased across the study, peaking at 11.6 % (95 % CI 10.4 %-13.0 %) during round 3. Varying trends in SARS-CoV-2 seropositivity were noted based on demographic factors. For instance, highest rates of seropositivity shifted from older to younger demographics across the study period. In round 3, Alpha (B.1.1.7) variant neutralising antibodies were most frequently detected across age groups, with median concentration of anti-spike protein antibodies elevated in 50-69 year olds and anti-S1 RBD antibodies elevated in 70+ year olds, relative to other age groups. Conclusions: With seropositivity rates of <15 % across the assessment period, it can be concluded that the significant proportion of the Northern Ireland population had not yet naturally contracted the virus by mid-2021.

Encrypted federated learning for secure decentralized collaboration in cancer image analysis.

Artificial intelligence (AI) has a multitude of applications in cancer research and oncology. However, the training of AI systems is impeded by the limited availability of large datasets due to data protection requirements and other regulatory obstacles. Federated and swarm learning represent possible solutions to this problem by collaboratively training AI models while avoiding data transfer. However, in these decentralized methods, weight updates are still transferred to the aggregation server for merging the models. This leaves the possibility for a breach of data privacy, for example by model inversion or membership inference attacks by untrusted servers. Somewhat-homomorphically-encrypted federated learning (SHEFL) is a solution to this problem because only encrypted weights are transferred, and model updates are performed in the encrypted space. Here, we demonstrate the first successful implementation of SHEFL in a range of clinically relevant tasks in cancer image analysis on multicentric datasets in radiology and histopathology. We show that SHEFL enables the training of AI models which outperform locally trained models and perform on par with models which are centrally trained. In the future, SHEFL can enable multiple institutions to co-train AI models without forsaking data governance and without ever transmitting any decryptable data to untrusted servers.

Distinct Molecular Profiles of Sporadic Early-Onset Colorectal Cancer: A Population-Based Cohort and Systematic Review.

Background and Aims: The observed increase in the incidence of early-onset colorectal cancer (EOCRC) is being driven by sporadic cases, but the molecular characteristics of these tumors are not fully understood. Our objective was to investigate the prevalence of microsatellite instability (MSI) and selected mutations in sporadic EOCRC, and their association with survival. Methods: Firstly, we compared the prevalence of molecular characteristics and survival within a population-based cohort study of 652 stage II and III colon cancer patients in Northern Ireland, comparing sporadic early-onset (<50 years, n = 35) with older (60-69 years, n = 179) patients. Secondly, a systematic review for studies reporting the prevalence of MSI, mismatch repair deficiency (dMMR), or BRAF, KRAS, NRAS, PIK3CA, and TP53 mutations in sporadic EOCRC was conducted. A meta-analysis was performed to calculate pooled estimates of the prevalence of molecular features in sporadic EOCRC. Results: Firstly, within the cohort study, EOCRC patients did not have a significantly increased risk of colorectal cancer-specific death (adjusted hazard ratio 1.20; 95% confidence interval [CI] 0.61-2.39) compared with 60- to 69-year-olds. Second, 32 studies were included in the systematic review. The pooled analysis estimated a prevalence of 10% (95% CI 7%-14%) for MSI high/dMMR in sporadic EOCRC. BRAF and KRAS mutations had a prevalence of 1% (95% CI 0%-3%) and 32% (95% CI 23%-40%), respectively. Conclusion: The molecular characteristics of sporadic EOCRC differ from those of cancers in older adults, particularly regarding reduced prevalence of BRAF mutations. Ten percent of sporadic EOCRC display MSI high/dMMR. Further studies are needed to address survival in sporadic EOCRC cases and whether molecular profiles influence EOCRC outcomes in this patient group.

Consultoria psiquiatrica y psiquiatria de enlace / Psychiatric consultation and Liaison Psychiatry

Se recomienda la organización de un equipo de Psiquiatría de Enlace para establecer una mejor comunicación entre los servicios de un hospital general y el de Psiquiatría. Se cree que de esa manera disminurían las consultas de urgencia al Servicio de Psiquiatría, se establecerían diagnósticos psiquiátricos y somáticos adecuados, se reduciría el tiempo de hospitalización del paciente y la utilización de los servicios médicos completamentarios (rayos-X, laboratorio y farmacia). Además, disminuirían o atenuarían las enfermedades somáticas causadas o agravadas por problemas psíquicos, se promoverían técnicas terapéuticas más avanzadas y más beneficiosas para el paciente, al lograrse una integración biológica, psíquica y social, y se estimularía a los profesionales de la medicina a dar importancia a todos los aspectos de la enfermedad que pueden ayudarlo a realizar una actividad profesional más eficiente y de mejor calidad