- author = "Dan Li and Rong Hu and Huizhou Li and Yeyu Cai and Paul J Zhang and Jing Wu and Chengzhang Zhu and Harrison X Bai",
- title = "Performance of automatic machine learning versus radiologists in the evaluation of endometrium on computed tomography",
- journal = "Abdominal radiology",
- year = "2021",
- volume = "46",
- number = "11",
- pages = "5316--5324",
- month = nov,
- keywords = "genetic algorithms, genetic programming, TPOT, Endometrium, Female, Humans, Machine Learning, Radiologists, Retrospective Studies, Tomography, X-Ray Computed, Automatic machine learning, Computed tomography, Endometrial cancer, Radiomics, Pelvis",
- ISSN = "2366-0058",
-
DOI = "
doi:10.1007/s00261-021-03210-9",
-
abstract = "PURPOSE: In this study, we developed radiomic models
that use a combination of imaging features and clinical
variables to distinguish endometrial cancer (EC) from
normal endometrium on routine computed tomography (CT).
METHODS: A total of 926 patients consisting of 416
endometrial cancer (EC) and 510 normal endometrium were
included. The CT images of these patients were
segmented manually, and divided into training,
validation, testing and external testing sets.
Non-texture and texture features of these images with
endometrium or uterus as region of interest were
extracted. The clinical feature age was also included
in the feature set. Feature selection and machine
learning classifier were applied to normalized feature
set. This manual optimized combination was then
compared with the best pipeline exported by Tree-Based
Pipeline Optimization Tool (TPOT) on testing and
external testing set. The performances of these machine
learning pipelines were compared to that of
radiologists. RESULTS: The manual expert optimized
pipeline using the reliefF feature selection method and
Bagging classifier on the external testing set achieved
a test ROC AUC of 0.73, accuracy of 0.73 (95percent CI
0.62-0.82), sensitivity of 0.64 (95percent CI
0.45-0.79), and specificity of 0.78 (95percent CI
0.65-0.87), while TPOT achieved a test ROC AUC of 0.79,
accuracy of 0.80 (95percent CI 0.70-0.87), sensitivity
of 0.61 (95percent CI 0.43-0.77), and specificity of
0.90 (95percent CI 0.78-0.96). When compared to average
radiologist performance, the TPOT achieved higher test
accuracy (0.80 vs. 0.49, p < 0.001) and specificity
(0.90 vs. 0.51, p < 0.001), with comparable
sensitivity (0.61 vs. 0.46, p = 0.130).
CONCLUSION: Our results demonstrate that automatic machine learning can distinguish EC from normal endometrium on routine CT imaging with higher accuracy and specificity than radiologists.",
- notes = "PMID: 34286371",
