Application of Machine Learning Analyses Using Clinical and [18F]-FDG-PET/CT Radiomic Characteristics to Predict Recurrence in Patients with Breast Cancer

Kodai Kawaji; Masatoyo Nakajo; Yoshiaki Shinden; Megumi Jinguji; Atsushi Tani; Daisuke Hirahara; Ikumi Kitazono; Takao Ohtsuka; Takashi Yoshiura

doi:10.1007/s11307-023-01823-8

Application of Machine Learning Analyses Using Clinical and [¹⁸F]-FDG-PET/CT Radiomic Characteristics to Predict Recurrence in Patients with Breast Cancer

Mol Imaging Biol. 2023 Oct;25(5):923-934. doi: 10.1007/s11307-023-01823-8. Epub 2023 May 16.

Authors

Kodai Kawaji¹, Masatoyo Nakajo², Yoshiaki Shinden³, Megumi Jinguji¹, Atsushi Tani¹, Daisuke Hirahara⁴, Ikumi Kitazono⁵, Takao Ohtsuka³, Takashi Yoshiura¹

Affiliations

¹ Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.
² Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan. toyo.nakajo@dolphin.ocn.ne.jp.
³ Department of Digestive Surgery, Breast and Thyroid Surgery, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.
⁴ Department of Management Planning Division, Harada Academy, 2-54-4 Higashitaniyama, Kagoshima, 890-0113, Japan.
⁵ Department of Pathology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.

PMID: 37193804
DOI: 10.1007/s11307-023-01823-8

Abstract

Purpose: To develop and identify machine learning (ML) models using pretreatment clinical and 2-deoxy-2-[¹⁸F]fluoro-D-glucose positron emission tomography ([¹⁸F]-FDG-PET)-based radiomic characteristics to predict disease recurrences in patients with breast cancers who underwent surgery.

Procedures: This retrospective study included 112 patients with 118 breast cancer lesions who underwent [¹⁸F]-FDG-PET/ X-ray computed tomography (CT) preoperatively, and these lesions were assigned to training (n=95) and testing (n=23) cohorts. A total of 12 clinical and 40 [¹⁸F]-FDG-PET-based radiomic characteristics were used to predict recurrences using 7 different ML algorithms, namely, decision tree, random forest (RF), neural network, k-nearest neighbors, naive Bayes, logistic regression, and support vector machine (SVM) with a 10-fold cross-validation and synthetic minority over-sampling technique. Three different ML models were created using clinical characteristics (clinical ML models), radiomic characteristics (radiomic ML models), and both clinical and radiomic characteristics (combined ML models). Each ML model was constructed using the top ten characteristics ranked by the decrease in Gini impurity. The areas under ROC curves (AUCs) and accuracies were used to compare predictive performances.

Results: In training cohorts, all 7 ML algorithms except for logistic regression algorithm in the radiomics ML model (AUC = 0.760) achieved AUC values of >0.80 for predicting recurrences with clinical (range, 0.892-0.999), radiomic (range, 0.809-0.984), and combined (range, 0.897-0.999) ML models. In testing cohorts, the RF algorithm of combined ML model achieved the highest AUC and accuracy (95.7% (22/23)) with similar classification performance between training and testing cohorts (AUC: training cohort, 0.999; testing cohort, 0.992). The important characteristics for modeling process of this RF algorithm were radiomic GLZLM_ZLNU and AJCC stage.

Conclusions: ML analyses using both clinical and [¹⁸F]-FDG-PET-based radiomic characteristics may be useful for predicting recurrence in patients with breast cancers who underwent surgery.

Keywords: Breast cancer; Machine learning; PET/CT; Prognosis; [18F]-FDG.