PMID- 37064402
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20230418
IS  - 2223-4292 (Print)
IS  - 2223-4306 (Electronic)
IS  - 2223-4306 (Linking)
VI  - 13
IP  - 4
DP  - 2023 Apr 1
TI  - Ultrasound-based prediction of preoperative core biopsy categories in solid 
      breast tumor using machine learning.
PG  - 2634-2646
LID - 10.21037/qims-22-877 [doi]
AB  - BACKGROUND: The American College of Radiology Breast Imaging Reporting and Data 
      System (ACR BI-RADS) used with ultrasonography cannot guide the individual 
      management of solid breast tumors, but preoperative core biopsy categories (CBCs) 
      can. We aimed to use machine learning to analyze clinical and ultrasonic features 
      for predicting CBCs and to aid in the development of a new ultrasound (US) 
      imaging reporting system for solid tumors of the breast. METHODS: This 
      retrospective study included women with solid breast tumors who underwent 
      US-guided core needle biopsy from March 1, 2019, to December 31, 2019. All 
      patients were randomly assigned to a training or validation cohort (7:3 ratio). 
      CBC was predicted using 5 machine learning models: random forest (RF), support 
      vector machine (SVM), k-nearest-neighbor (KNN), multilayer perceptron (MLP), and 
      ridge regression (RR). In the validation cohort, the area under the curve (AUC) 
      and accuracy were ascertained for every algorithm. Based on AUC values, the 
      optimal algorithm was determined, and the features' importance was depicted. 
      RESULTS: A total of 1,082 female patients were included (age range, 12-96 years; 
      mean age +/- standard deviation, 42.22+/-13.37 years). The proportion of the 4 CBCs 
      was 4% (44/1,185) for the B1 group, 60% (714/1,185) for the B2 group, 5% 
      (57/1,185) for the B3 group, and 31% (370/1,185) for the B5 group. In the 
      validation cohort, AUCs of the optimal algorithm constructed RF were 0.78, 0.88, 
      0.64, and 0.92 for B1, B2, B3, and B5, respectively, with an accuracy of 0.82. 
      CONCLUSIONS: Machine learning could strongly predict CBC, particularly in B2 and 
      B5 categories of solid breast tumors, with RF being the optimal machine learning 
      model.
CI  - 2023 Quantitative Imaging in Medicine and Surgery. All rights reserved.
FAU - Liang, Ting
AU  - Liang T
AD  - Department of Ultrasound, The First Affiliated Hospital of Guangzhou University 
      of Chinese Medicine, Guangzhou University of Chinese Medicine, Guangzhou, China.
AD  - Department of Ultrasound, Guangdong Provincial People's Hospital (Guangdong 
      Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
FAU - Shen, Junhui
AU  - Shen J
AD  - Department of Rehabilitation Medicine, Guangdong Provincial People's Hospital 
      (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, 
      China.
FAU - Wang, Jiexin
AU  - Wang J
AD  - Department of Ultrasound, Affiliated Hospital of Guangdong Medical University, 
      Zhanjiang, China.
FAU - Liao, Weilin
AU  - Liao W
AD  - School of Geography and Planning, Sun Yat-sen University, Guangzhou, China.
FAU - Zhang, Zhi
AU  - Zhang Z
AD  - School of Geography and Planning, Sun Yat-sen University, Guangzhou, China.
FAU - Liu, Juanjuan
AU  - Liu J
AD  - Department of Ultrasound, Guangdong Provincial People's Hospital (Guangdong 
      Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
FAU - Feng, Zhanwu
AU  - Feng Z
AD  - Department of Ultrasound, Guangdong Provincial People's Hospital (Guangdong 
      Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
FAU - Pei, Shufang
AU  - Pei S
AD  - Department of Ultrasound, Guangdong Provincial People's Hospital (Guangdong 
      Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
FAU - Liu, Kebing
AU  - Liu K
AD  - Department of Ultrasound, The First Affiliated Hospital of Guangzhou University 
      of Chinese Medicine, Guangzhou University of Chinese Medicine, Guangzhou, China.
LA  - eng
PT  - Journal Article
DEP - 20230303
PL  - China
TA  - Quant Imaging Med Surg
JT  - Quantitative imaging in medicine and surgery
JID - 101577942
PMC - PMC10102795
OTO - NOTNLM
OT  - Ultrasound (US)
OT  - core biopsy categories (CBCs)
OT  - machine learning
OT  - prediction
OT  - solid breast tumor
COIS- Conflicts of Interest: All authors have completed the ICMJE uniform disclosure 
      form (available at 
      https://qims.amegroups.com/article/view/10.21037/qims-22-877/coif). The authors 
      have no conflicts of interest to declare.
EDAT- 2023/04/18 06:00
MHDA- 2023/04/18 06:01
PMCR- 2023/04/01
CRDT- 2023/04/17 03:42
PHST- 2022/08/21 00:00 [received]
PHST- 2023/02/23 00:00 [accepted]
PHST- 2023/04/18 06:01 [medline]
PHST- 2023/04/17 03:42 [entrez]
PHST- 2023/04/18 06:00 [pubmed]
PHST- 2023/04/01 00:00 [pmc-release]
AID - qims-13-04-2634 [pii]
AID - 10.21037/qims-22-877 [doi]
PST - ppublish
SO  - Quant Imaging Med Surg. 2023 Apr 1;13(4):2634-2646. doi: 10.21037/qims-22-877. 
      Epub 2023 Mar 3.