Dynamic AI-assisted Ipsilateral Tissue Matching for Digital Breast Tomosynthesis
Morrell, S. J.; Huetel, M.; Lucena, O. A. S.; Alfaro, C. R. V.; O'Brien, S.; Zuckerman, S.; Ourselin, S.; Cardoso, J.; Morel, J.; Conant, E.
Show abstract
Structured AbstractO_ST_ABSPurposeC_ST_ABSTo compare Digital Breast Tomosynthesis (DBT) tissue matching errors with and without artificial intelligence (AI) assistance to typical screen-detected breast tumor sizes, evaluating whether AI ameliorates lesion mislocalization beyond tumor boundaries, especially for nonexpert radiologists. The technology category is deep learning. Materials and MethodsThis multicenter retrospective feasibility study conducted in April 2022 - July 2023 included 12 radiologists (mean age, 42 years {+/-} 8) interpreting 94 lesion regions of interest in 30 women. Readers performed annotations with and without AI assistance after a minimum four-week washout period. The root mean square errors (RMSE) and maximum distance errors (MDE) were measured relative to consensus references. Stratifications included radiologist expertise ([≥] 5 vs < 5 years), lesion abnormal-ity, and AI warnings. The Wilcoxon signed-rank test was used to assess statistical significance. ResultsAcross all abnormal lesions, mean RMSE was 32% higher without AI (11.70mm vs 8.88mm, p = .049), and mean maximum distance errors were 37.5% higher (20.68mm vs 15.08mm, p = .036). Non-expert radiologists showed the largest benefit: for abnormal lesions without AI warnings, RMSE was 61.9% higher without AI (12.20mm vs 7.57mm, p = .010) and maximum distance error was 67.5% higher (15.76mm vs 9.47mm, p = .028). These reductions are clinically relevant given typical screen-detected breast tumor sizes (median, 13mm [IQR: 9-20]). ConclusionAI-assisted tissue matching significantly reduced DBT localization errors, particularly for non-experts handling challenging cases. By keeping errors below typical tumor dimensions, AI may improve diagnostic precision and reduce risks of missed or mischaracterized lesions. Summary StatementDynamic artificial intelligence assisted tissue matching in digital breast tomosynthesis improves localization accuracy for non-expert radiologists, with errors in abnormal cases significantly larger (67.5%, p [≤] 0.05) without assistance. Key PointsIn this multicenter retrospective study of 94 Regions of Interest (ROI) analyzed by 12 radiologists across 5 hospitals, manual tissue matching was found to have errors 32% higher in abnormal cases than AI-assisted tissue matching (p < 0.05). For non-expert radiologists interpreting abnormal cases (excluding cases with AI warnings) without AI assistance, the root mean squared distance errors (RMSE) were found to be 61.9% higher (12.20mm vs 7.57mm, p < 0.01) and the maximum distance errors (MDE) was 67.6% higher (15.76mm vs 9.47mm, p < 0.05) than when using AI assistance. For challenging cases, many non-expert readers MDE without AI assistance (75th percentile: 20.21mm) exceeded the largest tumor dimensions (75th percentile: 20mm), while AI-assisted errors (75th percentile: 11.94mm, p < 0.05) remained within median tumor sizes (12mm), potentially preventing correlation with non-lesion tissue.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Improved accuracy of breast volume calculation from 3D surface imaging data using statistical shape models 95%
- Classification performance bias between training and test sets in a limited mammography dataset 94%
- Development of an H&E on-block staining technique for collagen detection in cryo-fluorescence tomography imaging of frozen breast tissue samples 92%
Similar papers in this journal
- Model uncertainty estimates for deep learning mammographic density prediction using ordinal and classification approaches 93%
- Breast density prediction from low and standard dose mammograms using deep learning: effect of image resolution and model training approach on prediction quality 92%
- Mammographic density assessed using deep learning in women at high risk of developing breast cancer: the effect of weight change on density 91%
Similar papers in this journal
- A Machine Learning Ensemble Based on Radiomics to Predict BI-RADS Category and Reduce the Biopsy Rate of Ultrasound-Detected Suspicious Breast Masses 97%
- Auto-detection of motion artifacts on CT pulmonary angiograms with a physician-trained AI algorithm 93%
- The NILS study protocol - a retrospective validation study of a preoperative decision-making tool for non-invasive lymph node staging in women with primary breast cancer [ISRCTN14341750] 91%
Similar papers in this journal
- Automated and Manual Quantification of Tumour Cellularity in Digital Slides for Tumour Burden Assessment 93%
- Content-based image retrieval assists radiologists in diagnosing eye and orbital mass lesions in MRI 92%
- Reproducible And Clinically Translatable Deep Neural Networks For Cervical Screening 92%
Similar papers in this journal
- Impact of Non-Contrast Enhanced Imaging Input Sequences on the Generation of Virtual Contrast-Enhanced Breast MRI Scans using Neural Networks 96%
- Assessing GPT-4 Multimodal Performance in Radiological Image Analysis 91%
- First-generation clinical dual-source photon-counting CT: ultra-low dose quantitative spectral imaging 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.