22 March 2024 in IEEE Access
Objective : Chromosome karyotyping is an important yet labor-intensive procedure for diagnosing genetic diseases. Automating such a procedure drastically reduces the manual work of cytologists and increases congenital disease diagnosing precision. Researchers have contributed to chromosome segmentation and classification for decades. However, very few studies integrate the two tasks as a unified, fully automatic procedure or achieved a promising performance. Methods : This paper addresses the gap by presenting: (1) A novel chromosome segmentation module named ChrRender, with the idea of rendering the chromosome instances by combining rich global features from the backbone and coarse mask prediction from Mask R-CNN. (2) A devised chromosome classification module named ChrNet4 that pays more attention to channel-wise dependencies from aggregated informative features and calibrating the channel interdependence. (3) An integrated Render-Attention-Architecture to accomplish fully automatic karyotyping with segmentation and classification modules. (4) A strategy for eliminating differences between training data and segmentation output data to be classified. Results : These proposed methods are implemented in three ways on the public Q-band BioImLab dataset and a G-band private dataset. The results indicate promising performance: (1) on the joint karyotyping task, which predicts a karyotype image by first segmenting an original microscopical image, then classifying each segmentation output with a precision of 89.75% and 94.22% on the BioImLab and private dataset, respectively; (2) On the separate task with two datasets, ChrRender obtained AP50 of 96.652% and 96.809% for segmentation, ChrNet4 achieved 95.24% and 94.07% for classification, respectively. The COCO format annotation files of BioImLab used in this paper are available at https://github.com/Alex17swim/BioImLab Conclusions : The study introduces an integrated workflow to predict a karyotyping image from a Microscopical Chromosome Image. With state-of-the-art performance on a public dataset, the proposed Render-Attention-Architecture has accomplished fully automatic chromosome karyotyping.
22 September 2025 in International Journal of Educational Research
5 June 2024 in Higher Education Quarterly
The problem of gender disparity in computer science and engineering has persisted despite longstanding efforts made in higher education. This study drew data from ten female computer science and engineering faculty in China and Italy to demonstrate the gender‐specific challenges they face. The researcher applied positioning theory to analyse female faculty's motherhood experiences. Findings suggest that the dual mother‐and‐educator role conflict in the intersectional space of work and family can be both a burden and an asset to female faculty. As a burden, the sociocultural expectations of the mother's role drive females to take on primary childcare responsibilities. It leads to significant barriers to female faculty's career advancements. As an asset, the study finds that the female faculty's motherhood experience allowed them to generate new insights into their identities as educators and teaching practices. Their learning from motherhood prompts them to reflect and gain an appreciation of their educator identity. Such realisation enables them to improve their teaching practices and interactions with students. The study offers policy recommendations for higher education institutions to support female faculty navigating the dual roles of mother and educator. Finally, the researcher discusses the limitations and directions for future study.
3 April 2023 in Distance Education
This study investigated how student effort and the course design influenced an online internship in China. A cohort of 95 postgraduate students became distance learners in a credit-bearing internship course due to COVID-19. The course leader applied the action learning framework to prompt student online collaboration and group inquiry. The framework assumes the importance of self-reliant learner autonomy in virtual internships. After the course, researchers analyzed the effects of self-directed learning with technology on a multidimensional community of inquiry in a virtual environment. The study also identified students’ narratives that explain how self-directed learning with technology interacted with three elements of virtual communities of inquiry: social, cognitive, and teaching. Findings explain how virtual internships can be facilitated through a community of inquiry model. Educators and practitioners may consider the model to demonstrate student-staff partnerships (Fitzgerald et al., 2020 Fitzgerald, R. , Huijser, H. , Meth, D. , & Neilan, K. (2020). Student-staff partnerships in academic development: the course design studio as a model for sustainable course-wide impact. International Journal for Academic Development, 25(2), 134–146. https://doi.org/10.1080/1360144X.2019.1631170 [Taylor & Francis Online], [Web of Science ®] , [Google Scholar] ) to achieve quality transformation of internships from face-to-face mode to distance education.
31 March 2023 in The Asia-Pacific Education Researcher