AI Article Synopsis
- This study looks at how to better find mistakes when doctors look at cancer scans over time, so they don't miss or wrongly identify tumors.
- It tested two ways of checking the scans: one done by experienced doctors and another one using a computer program that helps find problems automatically.
- The results showed that both methods found a lot of missed and misidentified tumors, with the computer method being especially good at it, helping doctors evaluate cancer better.
Article Abstract
Purpose: Missed and misidentified neoplastic lesions in longitudinal studies of oncology patients are pervasive and may affect the evaluation of the disease status. Two newly identified patterns of lesion changes, lone lesions and non-consecutive lesion changes, may help radiologists to detect these lesions. This study evaluated a new interpretation revision workflow of lesion annotations in three or more consecutive scans based on these suspicious patterns.
Methods: The interpretation revision workflow was evaluated on manual and computed lesion annotations in longitudinal oncology patient studies. For the manual revision, a senior radiologist and a senior neurosurgeon (the readers) manually annotated the lesions in each scan and later revised their annotations to identify missed and misidentified lesions with the workflow using the automatically detected patterns. For the computerized revision, lesion annotations were first computed with a previously trained nnU-Net and were then automatically revised with an AI-based method that automates the workflow readers' decisions. The evaluation included 67 patient studies with 2295 metastatic lesions in lung (19 patients, 83 CT scans, 1178 lesions), liver (18 patients, 77 CECT scans, 800 lesions) and brain (30 patients, 102 T1W-Gad MRI scans, 317 lesions).
Results: Revision of the manual lesion annotations revealed 120 missed lesions and 20 misidentified lesions in 31 out of 67 (46%) studies. The automatic revision reduced the number of computed missed lesions by 55 and computed misidentified lesions by 164 in 51 out of 67 (76%) studies.
Conclusion: Automatic analysis of three or more consecutive volumetric scans helps find missed and misidentified lesions and may improve the evaluation of temporal changes of oncological lesions.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.ejrad.2024.111530 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Application and interpretation of core elements of the 2015 NMOSD diagnostic criteria in routine clinical practice.
Front Immunol
December 2024
Department of Neurology, University of Virginia, Charlottesville, VA, United States.
Background: We evaluated comprehension and application of the 2015 neuromyelitis optica spectrum disorder (NMOSD) criteria core elements by neurologists in Latin America (LATAM) who routinely diagnose and care for NMOSD patients by (i) identifying typical/suggestive NMOSD syndromes, (ii) detecting typical MRI NMOSD lesions and meeting MRI dissemination in space (DIS) criteria, and (iii) evaluating historical symptoms suggestive of NMOSD.
Methods: We conducted an anonymous, voluntary, self-administered web- and case-based survey cross-sectional study from October 2023 to January 2024 of neurologists identified through the LACTRIMS database. Questions were presented first through iterative clinical cases or imaging, followed by questions directly evaluating comprehension of definitions.
Microbiological aspects and clinical impact of lower lung field tuberculosis: An observational cohort study in Peru.
Int J Infect Dis
January 2025
Department of Global Health and Social Medicine, Harvard Medical School, Boston, MA, USA; Division of Global Health Equity, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA; Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA. Electronic address:
Article Synopsis
- Approximately 40% of global tuberculosis cases go undiagnosed, with lower lung field TB (LLF TB) frequently misidentified as other lung issues, causing treatment delays.
- An observational study in Lima, Peru, found that among 1316 pulmonary TB patients, 6% had LLF TB, which tended to be smear-negative, indicating a less typical presentation of the disease.
- LLF TB patients showed less improvement in their respiratory health after 2 months of treatment, yet they had better final treatment outcomes compared to those with non-LLF TB, highlighting the need for optimized care for this specific group.
Misidentified Metastases: Diagnosing and Managing Pyogenic Liver Abscesses in a Breast Cancer Survivor.
Am J Case Rep
September 2024
Department of Internal Medicine, Piedmont Athens Regional Medical Centre, Athen, GA, USA.
BACKGROUND Pyogenic liver abscesses are collections of pus of varying sizes within the liver. They are rare and often overlooked in developed countries, and if left untreated, they can be life-threatening. Therefore, early detection and treatment are crucial for favorable outcomes.
View Article and Find Full Text PDFFirst report of causing soybean anthracnose in Brazil.
Plant Dis
July 2024
University of Sao Paulo Luiz de Queiroz College of Agriculture, Plant Pathology and Nematology, Piracicaba, São Paulo, Brazil;
Article Synopsis
- Soybean is one of the top five global food crops, with Brazil producing approximately 42% of the world's supply, but its production faces challenges from diseases like anthracnose.
- In 2013, anthracnose symptoms, such as brown lesions, were found in soybean fields in Brazil, leading to a detailed sampling process for identifying the pathogen.
- In 2023, a specific fungal isolate was reactivated and characterized for its genetic makeup using various molecular techniques and the findings were recorded in the GenBank database.
The significance of multimodality approach in the management of non-lesional drug-resistant focal parietal lobe epilepsies.
Epilepsia Open
August 2024
Department of Neurology, University of Virginia School of Medicine, Charlottesville, Virginia, USA.
Due to extensive connectivity of the parietal lobe, non-lesional drug-resistant (DRE) parietal lobe epilepsies (PLEs) are difficult to localize and often imitate other epilepsies. Therefore, patients with PLEs have low rates of seizure freedom following epilepsy surgery. Previous studies have highlighted the need to combine EEG and semiology for more accurate localization of PLEs.
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!