Literature DB >> 34286371

Performance of automatic machine learning versus radiologists in the evaluation of endometrium on computed tomography.

Dan Li1, Rong Hu2, Huizhou Li3, Yeyu Cai3, Paul J Zhang4, Jing Wu3, Chengzhang Zhu5,6, Harrison X Bai7.   

Abstract

PURPOSE: In this study, we developed radiomic models that utilize 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 (95% CI 0.62-0.82), sensitivity of 0.64 (95% CI 0.45-0.79), and specificity of 0.78 (95% CI 0.65-0.87), while TPOT achieved a test ROC AUC of 0.79, accuracy of 0.80 (95% CI 0.70-0.87), sensitivity of 0.61 (95% CI 0.43-0.77), and specificity of 0.90 (95% 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.
© 2021. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Entities:  

Keywords:  Automatic machine learning; Computed tomography; Endometrial cancer; Radiomics

Year:  2021        PMID: 34286371     DOI: 10.1007/s00261-021-03210-9

Source DB:  PubMed          Journal:  Abdom Radiol (NY)


  4 in total

1.  Clinical and morphological correlations in early diagnosis of endometrial cancer.

Authors:  Adrian Neacşu; Mădălina Lucia Marcu; Cătălina Diana Stănică; Anca Daniela Brăila; Irina Pacu; Raluca Gabriela Ioan; Cicerone Cătălin Grigorescu; Crîngu Antoniu Ionescu
Journal:  Rom J Morphol Embryol       Date:  2018       Impact factor: 1.033

Review 2.  Diagnosis and Management of Endometrial Cancer.

Authors:  Michael M Braun; Erika A Overbeek-Wager; Robert J Grumbo
Journal:  Am Fam Physician       Date:  2016-03-15       Impact factor: 3.292

3.  Conservative treatment in early stage endometrial cancer: a review.

Authors:  Giuseppe Trojano; Claudiana Olivieri; Raffaele Tinelli; Gianluca Raffaello Damiani; Antonio Pellegrino; Ettore Cicinelli
Journal:  Acta Biomed       Date:  2019-12-23

4.  Considerations for automated machine learning in clinical metabolic profiling: Altered homocysteine plasma concentration associated with metformin exposure.

Authors:  Alena Orlenko; Jason H Moore; Patryk Orzechowski; Randal S Olson; Junmei Cairns; Pedro J Caraballo; Richard M Weinshilboum; Liewei Wang; Matthew K Breitenstein
Journal:  Pac Symp Biocomput       Date:  2018
  4 in total
  1 in total

1.  A model for predicting fall risks of hospitalized elderly in Taiwan-A machine learning approach based on both electronic health records and comprehensive geriatric assessment.

Authors:  Wei-Min Chu; Endah Kristiani; Yu-Chieh Wang; Yen-Ru Lin; Shih-Yi Lin; Wei-Cheng Chan; Chao-Tung Yang; Yu-Tse Tsan
Journal:  Front Med (Lausanne)       Date:  2022-08-09
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.