Prediction of histologic grade and type of small (< 4 cm) papillary renal cell carcinomas using texture and neural network analysis: a feasibility study.
Objective: To predict the histologic grade and type of small papillary renal cell carcinomas (pRCCs) using texture analysis and machine learning algorithms. Methods: This was a retrospective HIPAA-compliant study. 24 noncontrast (NC), 22 corticomedullary (CM) phase, and 24 nephrographic (NG) phase C...
| Publicado en: | Abdominal Radiology Vol. 46; no. 9; pp. 4266 - 4278 |
|---|---|
| Autores principales: | , , , , , , , |
| Formato: | Journal Article |
| Publicado: |
Springer Nature
Sep2021
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=151776192&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 151776192 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 2366004X JT14 jtl: Abdominal Radiology issn: 2366004X maglogo: N pubinfo: dt: Sep2021 vid: 46 iid: 9 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 151776192 149628252 10.1007/s00261-021-03044-5 151776192 ppf: 4266 ppct: 12 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Prediction of histologic grade and type of small (< 4 cm) papillary renal cell carcinomas using texture and neural network analysis: a feasibility study. aug: au: Haji-Momenian, Shawn Ricker, RyeAnne Chen, Zirong Houser, Margaret Adusumilli, Nagasai Yang, Myung Toubaji, Antoun Loew, Murray affil: Department of Radiology, George Washington University Hospital, 900 23rd St NW, 20037, Washington, DC, USA sug: ab: Objective: To predict the histologic grade and type of small papillary renal cell carcinomas (pRCCs) using texture analysis and machine learning algorithms. Methods: This was a retrospective HIPAA-compliant study. 24 noncontrast (NC), 22 corticomedullary (CM) phase, and 24 nephrographic (NG) phase CTs of small (< 4 cm) surgically resected pRCCs were identified. Surgical pathology classified the tumors as low- or high-Fuhrman histologic grade and type 1 or 2. The axial image with the largest cross-sectional tumor area was exported and segmented. Six histogram and 31 texture (20 gray-level co-occurrences and 11 gray-level run-lengths) features were calculated for each tumor in each phase. Feature values in low- versus high-grade and type 1 versus 2 pRCCs were compared. Area under the receiver operating curve (AUC) was calculated for each feature to assess prediction of histologic grade and type of pRCCs in each phase. Histogram, texture, and combined histogram and texture feature sets were used to train and test three classification algorithms (support vector machine (SVM), random forest, and histogram-based gradient boosting decision tree (HGBDT)) with stratified shuffle splits and threefold cross-validation; AUCs were calculated for each algorithm in each phase to assess prediction of histologic grade and type of pRCCs. Results: Individual histogram and texture features did not have statistically significant differences between low- and high-grade or type 1 and type 2 pRCCs across all phases. Individual features had low predictive power for tumor grade or type in all phases (AUC < 0.70). HGBDT was highly accurate at predicting pRCC histologic grade and type using histogram, texture or combined histogram and texture feature data from the CM phase (AUCs = 0.97–1.0). All algorithms had highest AUCs using CM phase feature data sets; AUCs decreased using feature sets from NC or NG phases. Conclusions: The histologic grade and type of small pRCCs can be predicted with classification algorithms using CM histogram and texture features, which outperform NC and NG phase image data. The accurate prediction of pRCC histologic grade and type may be able to further guide management of patients with small (< 4 cm) pRCCs being considered for active surveillance. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|