Motivation: While deep-learning algorithms have demonstrated outstanding performance in semantic image segmentation tasks, large annotation datasets are needed to create accurate models. Annotation of histology images is challenging due to the effort and experience required to carefully delineate tissue structures, and difficulties related to sharing and markup of whole-slide images.
Results: We recruited 25 participants, ranging in experience from senior pathologists to medical students, to delineate tissue regions in 151 breast cancer slides using the Digital Slide Archive. Inter-participant discordance was systematically evaluated, revealing low discordance for tumor and stroma, and higher discordance for more subjectively defined or rare tissue classes. Feedback provided by senior participants enabled the generation and curation of 20 000+ annotated tissue regions. Fully convolutional networks trained using these annotations were highly accurate (mean AUC=0.945), and the scale of annotation data provided notable improvements in image classification accuracy.
Availability And Implementation: Dataset is freely available at: https://goo.gl/cNM4EL.
Supplementary Information: Supplementary data are available at Bioinformatics online.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6748796 | PMC |
| http://dx.doi.org/10.1093/bioinformatics/btz083 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Primary bronchial leiomyosarcoma: a diagnostic challenge.
BMC Pulm Med
January 2025
Department of Pathology, Affiliated Hospital of Zunyi Medical University, Zunyi City, Guizhou Province, P.R. China.
Background: Pulmonary bronchial leiomyosarcoma is an extremely rare malignant tumour of the lung originating from the mesenchymal tissue. The retroperitoneal region is the most common site of leiomyosarcoma. It exhibits a high degree of malignancy and a poor prognosis, thereby highlighting the significance of early diagnosis of this disease.
View Article and Find Full Text PDFPredicting cell morphological responses to perturbations using generative modeling.
Nat Commun
January 2025
Department of Computational Health, Institute of Computational Biology, Helmholtz Zentrum München, Munich, Germany.
Advancements in high-throughput screenings enable the exploration of rich phenotypic readouts through high-content microscopy, expediting the development of phenotype-based drug discovery. However, analyzing large and complex high-content imaging screenings remains challenging due to incomplete sampling of perturbations and the presence of technical variations between experiments. To tackle these shortcomings, we present IMage Perturbation Autoencoder (IMPA), a generative style-transfer model predicting morphological changes of perturbations across genetic and chemical interventions.
View Article and Find Full Text PDF[Extramedullary hematopoiesis, a rare complication of sickle cell disease: A six-case series and literature review].
Rev Med Interne
January 2025
Service de médecine interne, centre national de référence des syndromes drépanocytaires majeurs de l'adulte, hôpital européen Georges-Pompidou, AP-HP, 20, rue Leblanc, 75015 Paris, France; Inserm U1163, laboratoire « Mécanismes cellulaires et moléculaires des désordres hématologiques et implications thérapeutiques », institut Imagine, université Paris-Cité, 75015 Paris, France; Laboratoire d'Excellence GR-Ex, 75015 Paris, France; Faculté de santé, université Paris-Cité, 75006 Paris, France. Electronic address:
Introduction: Extramedullary hematopoiesis (EMH) is very rarely described during sickle cell disease (SCD). Our aim was to describe six cases of EMH occurring in adult SCD patients and to conduct a literature review.
Methods: Retrospective, descriptive, and monocentric study, identifying all cases of EMH recorded in our cohort of adult SCD patients, up to April 2024.
A rare case of a horseshoe kidney with a single left-sided ureter presented with recurrent urinary tract infection.
Saudi Med J
January 2025
From the Department of Surgery (Ayed), from Department of Urology (Alwadai), King Abdullah Hospital, Ministry of Health, Bisha, Kingdom of Saudi Arabia, from the Department of Anatomy (Rezigalla), College of Medicine, University of Bisha.
The horseshoe kidney (HSK) is a common renal abnormality mostly asymptomatic. This may be linked to chromosomal and organ anomalies. A 27-year-old male patient presented with mild recurrent lower abdominal pain associated with dysuria.
View Article and Find Full Text PDFStatus in Brain Gliomas Can Be Predicted by the Spherical Mean MRI Technique.
AJNR Am J Neuroradiol
January 2025
Department of Neurosurgery and Neurooncology (M.M., A.B., T.M., D.K., D.N.), First Faculty of Medicine, Charles University and Military University Hospital, Prague, Czech Republic.
Background And Purpose: Diffuse gliomas, a heterogeneous group of primary brain tumors, have traditionally been stratified by histology, but recent insights into their molecular features, especially the mutation status, have fundamentally changed their classification and prognosis. Current diagnostic methods, still predominantly relying on invasive biopsy, necessitate the exploration of noninvasive imaging alternatives for glioma characterization.
Materials And Methods: In this prospective study, we investigated the utility of the spherical mean technique (SMT) in predicting the status and histologic grade of adult-type diffuse gliomas.
Want 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!