Multimodal medical image fusion is a method of integrating information from multiple image formats. Its aim is to provide useful and accurate information for doctors. Multi-channel pulse coupled neural network (m-PCNN) is a recently proposed fusion model. Compared with previous methods, this network can effectively manage various types of medical images. However, it has two drawbacks: lack of control to feed function and low-level automation. The improved multi-channel PCNN proposed in this paper can adjust the impact of feed function by linking strength and adaptively compute the weighting coefficients for each pixel. Experimental results demonstrated the effectiveness of the improved m-PCNN fusion model.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.3233/BME-130802 | DOI Listing |
J Med Case Rep
January 2025
Department of Surgery, Center for Endocrinology, Diabetes and Metabolism, Children's Hospital Los Angeles and Keck School of Medicine of USC, Los Angeles, CA, USA.
Background: Classic congenital adrenal hyperplasia, primarily due to 21-hydroxylase deficiency, leads to impaired cortisol and aldosterone production and excess adrenal androgens. Lifelong glucocorticoid therapy is required, often necessitating supraphysiological doses in youth to manage androgen excess and growth acceleration. These patients experience higher obesity rates, hypertension, and glucose metabolism issues, complicating long-term health management.
View Article and Find Full Text PDFNPJ Digit Med
January 2025
Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea.
Polysomnography (PSG) is crucial for diagnosing sleep disorders, but manual scoring of PSG is time-consuming and subjective, leading to high variability. While machine-learning models have improved PSG scoring, their clinical use is hindered by the 'black-box' nature. In this study, we present SleepXViT, an automatic sleep staging system using Vision Transformer (ViT) that provides intuitive, consistent explanations by mimicking human 'visual scoring'.
View Article and Find Full Text PDFNPJ Precis Oncol
January 2025
Eötvös Loránd University, Department of Physics of Complex Systems, Budapest, Hungary.
Patients with High-Grade Serous Ovarian Cancer (HGSOC) exhibit varied responses to treatment, with 20-30% showing de novo resistance to platinum-based chemotherapy. While hematoxylin-eosin (H&E)-stained pathological slides are used for routine diagnosis of cancer type, they may also contain diagnostically useful information about treatment response. Our study demonstrates that combining H&E-stained whole slide images (WSIs) with proteomic signatures using a multimodal deep learning framework significantly improves the prediction of platinum response in both discovery and validation cohorts.
View Article and Find Full Text PDFZhonghua Nei Ke Za Zhi
February 2025
Department of Endocrinology, the First Affiliated Hospital of Chongqing Medical University, Chongqing400016, China.
Zhonghua Bing Li Xue Za Zhi
February 2025
Department of Pathology, Foshan Traditional Chinese Medicine Hospital, Foshan 528000, China.
To investigate the clinicopathological and genetic features of infantile rhabdomyofibrosarcoma (IRFS) with EGFR kinase domain duplication (EGFR-KDD). The clinical, morphological and immunohistochemical features of three IRFS with EGFR-KDD diagnosed from January 2022 to January 2024 at Department of Pathology, Foshan Traditional Chinese Medicine Hospital, Foshan, China were retrospectively analyzed using PCR or next generation sequencing technique; and related literature was reviewed. There were 1 male and 2 females, aged at presentation ranging from 1 to 4 years.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!