Using computer‐extracted image features for modeling of error‐making patterns in detection of mammographic masses among radiology residents
Authors:
- 20 August 2014
- journal article
- research article
- Published by Wiley in Medical Physics
- Vol. 41 (9) , 091907
Abstract
Purpose:: Mammography is the most widely accepted and utilized screening modality for early breast cancer detection. Providing high quality mammography education to radiology trainees is essential, since excellent interpretation skills are needed to ensure the highest benefit of screening mammography for patients. The authors have previously proposed a computer‐aided education system based on trainee models. Those models relate human‐assessed image characteristics to trainee error. In this study, the authors propose to build trainee models that utilize features automatically extracted from images using computer vision algorithms to predict likelihood of missing each mass by the trainee. This computer vision‐based approach to trainee modeling will allow for automatically searching large databases of mammograms in order to identify challenging cases for each trainee.Methods:: The authors’ algorithm for predicting the likelihood of missing a mass consists of three steps. First, a mammogram is segmented into air, pectoral muscle, fatty tissue, dense tissue, and mass using automated segmentation algorithms. Second, 43 features are extracted using computer vision algorithms for each abnormality identified by experts. Third, error‐making models (classifiers) are applied to predict the likelihood of trainees missing the abnormality based on the extracted features. The models are developed individually for each trainee using his/her previous reading data. The authors evaluated the predictive performance of the proposed algorithm using data from a reader study in which 10 subjects (7 residents and 3 novices) and 3 experts read 100 mammographic cases. Receiver operating characteristic (ROC) methodology was applied for the evaluation.Results:: The average area under the ROC curve (AUC) of the error‐making models for the task of predicting which masses will be detected and which will be missed was 0.607 (95% CI,0.564‐0.650). This value was statistically significantly different from 0.5 (p < 0.0001). For the 7 residents only, the AUC performance of the models was 0.590 (95% CI,0.537‐0.642) and was also significantly higher than 0.5 (p = 0.0009). Therefore, generally the authors’ models were able to predict which masses were detected and which were missed better than chance.Conclusions:: The authors proposed an algorithm that was able to predict which masses will be detected and which will be missed by each individual trainee. This confirms existence of error‐making patterns in the detection of masses among radiology trainees. Furthermore, the proposed methodology will allow for the optimized selection of difficult cases for the trainees in an automatic and efficient manner.Keywords
This publication has 24 references indexed in Scilit:
- Cancer statistics, 2013CA: A Cancer Journal for Clinicians, 2013
- Identifying Error-making Patterns in Assessment of Mammographic BI-RADS Descriptors among Radiology Residents Using Statistical Pattern RecognitionAcademic Radiology, 2012
- A review of automatic mass detection and segmentation in mammographic imagesMedical Image Analysis, 2010
- Performance Parameters for Screening and Diagnostic Mammography in a Community Practice: Are There Differences Between Specialists and General Radiologists?American Journal of Roentgenology, 2007
- Approaches for automated detection and classification of masses in mammogramsPattern Recognition, 2006
- The Perception of Breast Cancer: What Differentiates Missed from Reported Cancers in Mammography?Academic Radiology, 2002
- Multiscale vessel enhancement filtering1998
- Variability in Radiologists' Interpretations of MammogramsNew England Journal of Medicine, 1994
- Seeded region growingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- The role of the Hessian matrix in fitting models to measurementsJournal of Geophysical Research: Oceans, 1989