.
Lung cancer is the leading cause of cancer-related deaths in the UK. Its high mortality rate is primarily due to its asymptomatic nature in the early stages, leading to late-stage diagnoses. However, effective early detection methods, such as Low-Dose Computed Tomography (LDCT), and treatments for early-stage disease make lung cancer an ideal candidate for screening. The UK Government aims to implement a national lung cancer screening programme targeting high-risk populations by 2029. This will significantly increase the workload on an already stretched radiology workforce, driving the adoption of computer-aided detection (CADe) systems to support radiologists. The datasets used to train these algorithms are typically drawn from previous lung cancer screening trials and studies (National Lung Screening Trial Research Team (2011); de Koning (2020)), which often lack balanced representation of protected groups, such as sex and ethnicity. This project examines whether training nodule detection algorithms on low-dose computed tomography (LDCT) scans from a London-based lung screening study, where these groups are typically under-represented, affects algorithm performance for under-represented categories. Our results indicate that overall performance remains equitable across all categories, even when trained on unbalanced datasets. The discriminative performance of deep learning-based pulmonary nodule detection algorithms is primarily driven by the composition of the dataset, specifically, the relative proportion of nodule types and sizes, rather than by protected attributes such as sex or ethnic group. The features learned from the nodules themselves drive detection outcomes, meaning that in populations where the prevalent nodule characteristics closely match the training data, performance is likely to be strong. While this study found no demographic disparities for nodule detection, there is no guarantee that this will be true across all populations, particularly those in populations where cancer risk predominates within different nodule distributions. This study provides an early assessment of performance variations of deep learning models across under-represented groups within a standard lung cancer screening dataset. While previous research has focused on improving how well nodule detection algorithms identify pulmonary nodules, this study uniquely focuses on demographic performance disparities and the impact of training data composition and algorithm design on model generalisability. The findings highlight critical considerations for the deployment of CADe systems in lung cancer screening, ensuring equitable performance across diverse patient populations. Our code is available at https://github.com/johnmccabe44/fairness-in-nodule-detection
This article proposes a compatibility assessment framework for specifying and narrowing down the Muslim states parties’ generic and vague reservations to the United Nations (UN) core human rights treaties and the corresponding equally generic and vague objections by non-Muslim states parties. These reservations and objections seem to be informed by misperceptions about human rights and Islamic law. I argue that human rights and Islamic law are, to a greater extent, compatible and further compatibility may be achieved by employing the proposed contextual interpretive approach: to interpret human rights and Islamic law in their historic and contemporary social contexts. I tested the framework by conducting a compatibility assessment of the foundations, objectives and purposes, jus cogens and nuṣūṣ , and the limitation schemes of human rights and Islamic law and found them to be compatible. This article aims to contribute to a better understanding of human rights and Islamic law, which would assist in maximising the application and enjoyment of human rights in the Muslim states and bolster cooperation in developing respect for and promoting human rights required under Articles 1 and 55 of the UN Charter.
Esta entrevista tem como objetivo apresentar os principais elementos necessários para a compreensão dos desafios e formas organizativas do Movimento dos Atingidos por Barragens (MAB), bem como apresentar pautas e debates a serem aprofundados acerca das mudanças climáticas e políticas públicas. Muito além dos grandes empreendimentos, a ampliação do número de atingidos e atingidas tem ocorrido expressivamente em razão das mudanças climáticas, fenômeno que agora é responsável pela aceleração do empobrecimento em massa de diversas famílias em regiões atingidas. Essa realidade impõe novos desafios em virtude da dificuldade de estabelecer a culpabilização dos crimes ambientais provocados pela ambição das razões acumuladoras, assim como pela ausência do próprio Estado ao não criar instituições preparadas para lidar com tais problemas. Apesar de seu significado histórico enquanto uma política popular vitoriosa e necessária, a Política Nacional de Direitos das Populações Atingidas por Barragens (PNAB) emerge como uma política que ainda precisa ser não apenas aprimorada para compreender o movimento dialético da sociedade, mas especialmente que demanda forças para que a sua implementação ocorra e as reparações de diferentes naturezas possam se materializar e o direito de populações sejam assegurados. As diferenças e desigualdades regionais também se destacam como ingredientes que devem ser considerados para que as análises desprezem suas especificidades e vulnerabilidades.
A number of the issues raised by Professor Kopelman in his Viewpoint are discussed and used to make recommendations that should enable psychiatrists better to assist the courts, uphold the expert witness's expectation of integrity, reduce the risk of judicial criticism and adverse publicity, provide clarity as to how to proceed when there is, or is perceived to be, a conflict between the duty as a doctor and the duty as an expert, particularly in cases involving safeguarding issues, and promote the medicolegal discourse necessary for the medical and legal professions to work together harmoniously in the interests of justice.
