Current Issue : April-June Volume : 2025 Issue Number : 2 Articles : 5 Articles
Breast cancer is the most prevalent cancer worldwide, affecting both low- and middleincome countries, with a growing number of cases. In 2024, about 310,720 women in the U.S. are projected to receive an invasive breast cancer diagnosis, alongside 56,500 cases of ductal carcinoma in situ (DCIS). Breast cancer occurs in every country of the world in women at any age after puberty but with increasing rates in later life. About 65% of women with the BRCA1 and 45% with the BRCA2 gene variants develop breast cancer by age 70. While these genes account for 5% of breast cancers, their prevalence is higher in certain populations. Advances in early detection, personalised medicine, and AI-driven diagnostics are improving outcomes by enabling a more precise analysis, reducing recurrence, and minimising treatment side effects. Our paper aims to explore the vast applications of artificial intelligence within the diagnosis and treatment of breast cancer and how these advancements can contribute to elevating patient care as well as discussing the potential drawbacks of such integrations into modern medicine. We structured our paper as a non-systematic review and utilised Google Scholar and PubMed databases to review literature regarding the incorporation of AI in the diagnosis and treatment of non-palpable breast masses. AI is revolutionising breast cancer management by enhancing imaging, pathology, and personalised treatment. In imaging, AI can improve the detection of cancer in mammography, MRIs, and ultrasounds, rivalling expert radiologists in accuracy. In pathology, AI enhances biomarker detection, improving HER2 and Ki67 assessments. Personalised medicine benefits from AI’s predictive power, aiding risk stratification and treatment response. AI also shows promise in triple-negative breast cancer management, offering better prognosis and subtype classification. However, challenges include data variability, ethical concerns, and real-world validation. Despite limitations, AI integration offers significant potential in improving breast cancer diagnosis, prognosis, and treatment outcomes....
This paper investigates spatial computing, which is a pathological transformational modern technology that integrates the physical and digital realms and has the potential to revolutionize pathology healthcare. Pathology as a medical specialist plays a crucial role in patient care by providing essential information for diagnosis, treatment planning, and disease monitoring. It studies and diagnoses diseases by examining tissues, organs, bodily fluids, and cells. Pathology is a broad field with three main branches: Anatomic pathology, Clinical pathology, and Molecular pathology. This study investigates the possibilities of spatial computing in radiography and clinical pathology with emphasis on diagnosis accuracy, medical education, workflow efficiency, and the outcomes in the patients. Augmented Reality (AR) medical devices guide pathologists in real-time during diagnostics procedures. The digital reproduction of tissue samples to allow pathologists to examine specimens in three dimensions is a significant utilization of spatial computing in virtual microscopy. This process allows remote collaboration between pathologists and laboratories, provides health informatics as seen in electronic health records (EHRs), improves diagnosis, and presents a platform with learning experiences in the medical field. Patients can interact with three-dimensional simulations of their anatomy, which helps them make more educated treatment decisions provided via the pathology findings and treatment alternatives in an immersive format. As this technology advances, its potential to transform pathology practice and improve patient care remains high. This review describes technological perspectives and discusses the statistical methods, clinical applications, potential obstacles, and directions of spatial computing in clinical pathology....
Despite the existence of established standards and guidelines for pathology reporting, many pathology reports are still written in unstructured free text. Extracting information from these reports and formatting it according to a standard is crucial for consistent interpretation. Automated information extraction from unstructured pathology reports is a challenging task, as it requires accurately interpreting medical terminologies and context-dependent details. In this work, we present a practical approach for automatically extracting information from unstructured pathology reports or scanned paper reports utilising a large multimodal model. This framework uses context-aware prompting strategies to extract values of individual fields, such as grade, size, etc. from pathology reports. A unique feature of the proposed approach is that it assigns a confidence value indicating the correctness of the model’s extraction for each field and generates a structured report in line with national pathology guidelines in human and machine-readable formats. We have analysed the extraction performance in terms of accuracy and kappa scores, and the quality of the confidence scores assigned by the model. We have also evaluated the prognostic value of the extracted fields and feature embeddings of the raw text. Results showed that the model can accurately extract information with an accuracy and kappa score up to 0.99 and 0.98, respectively. Our results indicate that confidence scores are an effective indicator of the correctness of the extracted information achieving an area under the receiver operating characteristic curve up to 0.93 thus enabling automatic flagging of extraction errors. Our analysis further reveals that, as expected, information extracted from pathology reports is highly prognostically relevant. The framework demo is available at: https://labieb.dcs.warwick.ac.uk/. Information extracted from pathology reports of colorectal cancer cases in the cancer genome atlas using the proposed approach and its code are available at: https://github. com/EtharZaid/Labieb....
The histopathology workforce is a cornerstone of cancer diagnostics and is essential to the delivery of cancer services and patient care. The workforce has been subject to significant pressures over recent years, and this review considers them in the UK and internationally. These pressures include declining pathologist numbers, the increasing age of the workforce, and greater workload volume and complexity. Forecasts of the workforce’s future in numerous countries are also not favourable – although this is not universal. Some in the field suggest that the effects of these pressures are already coming to bear, such as the financial costs of the additional measures needed to maintain clinical services. There is also some evidence of a detrimental impact on service delivery, patient care and pathologists themselves. Various solutions have been considered, including increasing the number of training places, enhancing recruitment, shortening pathology training and establishing additional support roles within pathology departments. A few studies have examined the effect of some of these solutions. However, the broader extent of their implementation and impact, if any, remains to be determined. In this regard, it is critical that future endeavours should focus on gaining a better understanding of the benefits of implemented workforce solutions, as well as obtaining more detailed and updated pathology workforce numbers. With a concentrated effort in these areas, the future of the pathology workforce could become brighter in the face of the increased demands on its services....
Background: Esophageal cancer (EC) is the sixth leading cause of cancer-related mortality worldwide, continuing to be a significant public health concern. The purpose of this study is to assess the impact of staging and histopathology of EC on associated mortality. The study also aims to further investigate clinical characteristics, prognostic factors, and survival outcomes in patients diagnosed with EC between 2010 and 2017. Furthermore, we analyzed the interaction between tumor histology and staging and the risk of mortality. Methods: A total of 24,011 patients diagnosed with EC between 2010 and 2017 in the United States were enrolled from the Surveillance, Epidemiology, and End Results (SEER) database. Demographic parameters, tumor stage, and histologic subtypes were analyzed and associated overall mortality (OM) and cancer-specific mortality (CSM) were measured across all subgroups. Covariates reaching the level of statistical significance, demonstrable by a p-value equal to or less than 0.01, were incorporated into a multivariate Cox proportional hazards model. A hazard ratio greater than 1 was indicative of an increased risk of mortality in the presence of the variable under discussion. Additionally, the study explores the interaction between histology and tumor stage on outcomes. Results: The majority of patients were male (80.13%) and non-Hispanic white (77.87%), with a predominant age at diagnosis of between 60 and 79 years (59.86%). Adenocarcinoma was the most common tumor subtype (68.17%), and most patients were diagnosed at a distant stage (41.29%). Multivariate analysis revealed higher mortality risks for males, older patients, unmarried individuals, and those with advanced-stage tumors. Higher income, receiving radiation or chemotherapy, and undergoing surgery were associated with lower mortality. Tumor subtype significantly influenced mortality, with squamous cell carcinoma and neuroendocrine tumors showing higher hazard ratios compared to adenocarcinoma. Adenocarcinoma is linked to a poorer prognosis at advanced stages, whereas the opposite trend is observed for SCC. Conclusions: The study identifies significant demographic and clinicopathologic factors influencing mortality in esophageal cancer patients, highlighting the importance of early diagnosis and treatment intervention. Future research should focus on tailored treatment strategies to improve survival outcomes in high-risk groups and to understand the interaction between tumor histology and tumor stage....
Loading....