AI Article Synopsis
- A study was conducted to assess how artificial intelligence (AI) can reduce reading time for digital breast tomosynthesis (DBT) while maintaining or improving accuracy in detecting lesions.
- The introduction of a deep learning AI system led to significant improvements: radiologists' detection performance (measured by AUC) increased from 0.795 to 0.852, and reading time decreased by about 52.7%.
- Overall, the use of AI not only enhanced sensitivity and specificity for detecting malignant lesions but also lowered the recall rate for non-cancer findings, indicating it could be a valuable tool in breast imaging.
Article Abstract
Purpose: To evaluate the use of artificial intelligence (AI) to shorten digital breast tomosynthesis (DBT) reading time while maintaining or improving accuracy.
Materials And Methods: A deep learning AI system was developed to identify suspicious soft-tissue and calcified lesions in DBT images. A reader study compared the performance of 24 radiologists (13 of whom were breast subspecialists) reading 260 DBT examinations (including 65 cancer cases) both with and without AI. Readings occurred in two sessions separated by at least 4 weeks. Area under the receiver operating characteristic curve (AUC), reading time, sensitivity, specificity, and recall rate were evaluated with statistical methods for multireader, multicase studies.
Results: Radiologist performance for the detection of malignant lesions, measured by mean AUC, increased 0.057 with the use of AI (95% confidence interval [CI]: 0.028, 0.087; < .01), from 0.795 without AI to 0.852 with AI. Reading time decreased 52.7% (95% CI: 41.8%, 61.5%; < .01), from 64.1 seconds without to 30.4 seconds with AI. Sensitivity increased from 77.0% without AI to 85.0% with AI (8.0%; 95% CI: 2.6%, 13.4%; < .01), specificity increased from 62.7% without to 69.6% with AI (6.9%; 95% CI: 3.0%, 10.8%; noninferiority < .01), and recall rate for noncancers decreased from 38.0% without to 30.9% with AI (7.2%; 95% CI: 3.1%, 11.2%; noninferiority < .01).
Conclusion: The concurrent use of an accurate DBT AI system was found to improve cancer detection efficacy in a reader study that demonstrated increases in AUC, sensitivity, and specificity and a reduction in recall rate and reading time.© RSNA, 2019See also the commentary by Hsu and Hoyt in this issue.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6677281 | PMC |
| http://dx.doi.org/10.1148/ryai.2019180096 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Genome-wide profiling of tRNA modifications by Induro-tRNAseq reveals coordinated changes.
Nat Commun
January 2025
Department of Biochemistry and Molecular Biology, Thomas Jefferson University, Philadelphia, PA, USA.
While all native tRNAs undergo extensive post-transcriptional modifications as a mechanism to regulate gene expression, mapping these modifications remains challenging. The critical barrier is the difficulty of readthrough of modifications by reverse transcriptases (RTs). Here we use Induro-a new group-II intron-encoded RT-to map and quantify genome-wide tRNA modifications in Induro-tRNAseq.
View Article and Find Full Text PDFMicroRNA-203-3p participates in antiviral immune response by negatively regulating TRAF3 in the rainbow trout (Oncorhynchus mykiss).
Fish Shellfish Immunol
January 2025
College of Animal Science and Technology, Gansu Agricultural University, Lanzhou, 730070, China.
MicroRNAs (miRNAs) are highly conserved endogenous non-coding RNAs that play a crucial role in fish immune response by regulating gene expression at the post-transcriptional level. In recent years, the viral diseases caused by infectious hematopoietic necrosis virus (IHNV) have caused significant economic losses in rainbow trout (Oncorhynchus mykiss) aquaculture, whereas the immune regulatory mechanisms of miRNAs involved in rainbow trout resistance to IHNV infection remains largely undefined. In this study, we analyzed the structural characteristics of Oncorhynchus mykiss tumor necrosis factor receptor-associated factor 3 (OmTRAF3) by bioinformatics software and explored the molecular mechanism of miR-203-3p in rainbow trout resistance to IHNV by regulating OmTRAF3 in vivo and in vitro.
View Article and Find Full Text PDFThe physiological mechanisms underlying consumer preferences towards organic food.
Appetite
January 2025
University of Parma, Department of Food and Drug, Italy; Italian Academy for Advanced Studies in America at Columbia University, New York, USA. Electronic address:
Previous research has shown that organic food labeling may lead consumers to biased processing of their preferences, the physiological mechanisms behind this phenomenon are not understood. For the first time, this manuscript combines consumer valuation and physiological measures to investigate the explicit and implicit preference dimensions of organic food. The explicit dimension was measured using the expected and actual degree of liking of two identical - but differently labeled - pear juices (organic and non-organic) while the implicit dimension was measured using the activity of the mylohyoid muscle (MM) and the 3D kinematics of the hand, and arm movements.
View Article and Find Full Text PDFAutomated spinopelvic measurements on radiographs with artificial intelligence: a multi-reader study.
Radiol Med
January 2025
Department of Radiology, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany.
Purpose: To develop an artificial intelligence (AI) algorithm for automated measurements of spinopelvic parameters on lateral radiographs and compare its performance to multiple experienced radiologists and surgeons.
Methods: On lateral full-spine radiographs of 295 consecutive patients, a two-staged region-based convolutional neural network (R-CNN) was trained to detect anatomical landmarks and calculate thoracic kyphosis (TK), lumbar lordosis (LL), sacral slope (SS), and sagittal vertical axis (SVA). Performance was evaluated on 65 radiographs not used for training, which were measured independently by 6 readers (3 radiologists, 3 surgeons), and the median per measurement was set as the reference standard.
Combining automation and expertise: A semi-automated approach to correcting eye-tracking data in reading tasks.
Behav Res Methods
January 2025
Department of Computer Science, Colby College, 4000 Mayflower Hill, Waterville, 04901, Maine, USA.
In reading tasks, drift can move fixations from one word to another or even another line, invalidating the eye-tracking recording. Manual correction is time-consuming and subjective, while automated correction is fast - yet limited in accuracy. In this paper, we present Fix8 (Fixate), an open-source GUI tool that offers a novel semi-automated correction approach for eye-tracking data in reading tasks.
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!