Bronchial lesion is a rare site for tuberculosis. It can mimic lung cancer especially when sputum- smear is negative, and this be a cause of a delay in diagnosis, that can be made later on by a culture of Koch bacillus or after a bronchial biopsy. Through these 4 cases reports, the authors recall the ethiopathogenic hypotheses of this lesion and review the radiologic, clinical and prognostic features of these unusual forms of TB.
Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
Semi-Supervised Learning Allows for Improved Segmentation With Reduced Annotations of Brain Metastases Using Multicenter MRI Data.
J Magn Reson Imaging
January 2025
Department of Radiology, Ålesund Hospital, Møre og Romsdal Hospital Trust, Ålesund, Norway.
Background: Deep learning-based segmentation of brain metastases relies on large amounts of fully annotated data by domain experts. Semi-supervised learning offers potential efficient methods to improve model performance without excessive annotation burden.
Purpose: This work tests the viability of semi-supervision for brain metastases segmentation.
Introduction: A pancreatic neuroendocrine tumour (NET) originates from the neuroendocrine cells responsible for producing and releasing hormones. They are uncommon findings, mainly seen arising from the head of the pancreas and their appearances may vary among different imaging modalities.
Case Report: Interesting case of an asymptomatic patient with an incidental finding of a pancreatic lesion and its variable appearances across different modalities and final histology findings.
Generation of deep learning based virtual non-contrast CT using dual-layer dual-energy CT and its application to planning CT for radiotherapy.
PLoS One
January 2025
Department of Radiation Oncology, Seoul National University Hospital, Seoul, Republic of Korea.
This paper presents a novel approach for generating virtual non-contrast planning computed tomography (VNC-pCT) images from contrast-enhanced planning CT (CE-pCT) scans using a deep learning model. Unlike previous studies, which often lacked sufficient data pairs of contrast-enhanced and non-contrast CT images, we trained our model on dual-energy CT (DECT) images, using virtual non-contrast CT (VNC CT) images as outputs instead of true non-contrast CT images. We used a deterministic method to convert CE-pCT images into pseudo DECT images for model application.
View Article and Find Full Text PDFInpatient autopsy rate and associated factors in a Chinese megacity: a population-based retrospective cohort study.
BMJ Open
January 2025
Vanke School of Public Health, Tsinghua University, Beijing, China
Objectives: This study investigated the autopsy rate of hospital deaths in Shenzhen megacity and identified factors that may impact the decision to perform an autopsy in hospital deaths.
Design: This is a population-based retrospective cohort study.
Setting: Shenzhen is a megacity in China with a population of more than 17 million and a total of 151 hospitals.
sc-SPLASH provides ultra-efficient reference-free discovery in barcoded single-cell sequencing.
bioRxiv
December 2024
Department of Biomedical Data Science, Stanford University, Stanford, 94305, USA.
Typical high-throughput single-cell RNA-sequencing (scRNA-seq) analyses are primarily conducted by (pseudo)alignment, through the lens of annotated gene models, and aimed at detecting differential gene expression. This misses diversity generated by other mechanisms that diversify the transcriptome such as splicing and V(D)J recombination, and is blind to sequences missing from imperfect reference genomes. Here, we present sc-SPLASH, a highly efficient pipeline that extends our SPLASH framework for statistics-first, reference-free discovery to barcoded scRNA-seq (10x Chromium) and spatial transcriptomics (10x Visium); we also provide its optimized module for preprocessing and -mer counting in barcoded data, BKC, as a standalone tool.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!