Search

Background: Cardiovascular management and risk stratification of patients is an important issue in clinics. Patients who have experienced an adverse cardiac event are concerned for their future and want to know the survival probability. Methods: We trained eight state-of-the-art CNN models using polar maps of myocardial perfusion imaging (MPI), gender, lung/heart ratio, and patient age for 5-year survival prediction after an adverse cardiac event based on a cohort of 862 patients who had experienced adverse cardiac events and stress/rest MPIs. The CNN model outcome is to predict a patient's survival 5 years after a cardiac event, i.e., two classes, either yes or no. Results: The best accuracy of all the CNN prediction models was 0.70 (median value), which resulted from ResNet-50V2, using image as the input in the baseline experiment. All the CNN models had better performance after using frequency spectra as the input. The accuracy increment was about 7~9%. Conclusions: This is the first trial to use pure rest/stress MPI polar maps and limited clinical data to predict patients' 5-year survival based on CNN models and deep learning. The study shows the feasibility of using frequency spectra rather than images, which might increase the performance of CNNs. [ABSTRACT FROM AUTHOR]

Objectives: To predict KRAS mutation in rectal cancer (RC) through computer vision of [18F]fluorodeoxyglucose (18F‐FDG) positron emission tomography (PET)/computed tomography (CT) by using metric learning (ML). Methods: This study included 160 patients with RC who had undergone preoperative PET/CT. KRAS mutation was identified through polymerase chain reaction analysis. This model combined ML with the deep‐learning framework to analyze PET data with or without CT images. The Batch Balance Wrapper framework and K‐fold cross‐validation were employed during the learning process. A receiver operating characteristic (ROC) curve analysis was performed to assess the model's predictive performance. Results: Genetic alterations in KRAS were identified in 82 (51%) tumors. Both PET and CT images were used, and the proposed model had an area under the ROC curve of 0.836 for its ability to predict a mutation status. The sensitivity, specificity, and accuracy were 75.3%, 79.3%, and 77.5%, respectively. When PET images alone were used, the area under the curve was 0.817, whereas the sensitivity, specificity, and accuracy were 73.2%, 79.6%, and 76.2%, respectively. Conclusions: The ML model presented herein revealed that baseline 18F‐FDG PET/CT images could provide supplemental information to determine KRAS mutation in RC. Additional studies are required to maximize the predictive accuracy. Advances in knowledge: The results of the ML model presented herein indicate that baseline 18F‐FDG PET/CT images could provide supplemental information for determining KRAS mutation in RC. The predictive accuracy of the model was 77.5% when both image types were used and 76.2% when PET images alone were used. Additional studies are required to maximize the predictive accuracy. [ABSTRACT FROM AUTHOR]

Abstract Background To define a suitable threshold setting for gross tumor volume (GTV) when using 18Fluoro-deoxyglucose positron emission tomography and computed tomogram (PET/CT) for radiotherapy planning in head and neck cancer (HNC). Methods Fifteen HNC patients prospectively received PET/CT simulation for their radiation treatment planning. Biological target volume (BTV) was derived from PET/CT-based GTV of the primary tumor. The BTVs were defined as the isodensity volumes when adjusting different percentage of the maximal standardized uptake value (SUVmax), excluding any artifact from surrounding normal tissues. CT-based primary GTV (C-pGTV) that had been previously defined by radiation oncologists was compared with the BTV. Suitable threshold level (sTL) could be determined when BTV value and its morphology using a certain threshold level was observed to be the best fitness of the C-pGTV. Suitable standardized uptake value (sSUV) was calculated as the sTL multiplied by the SUVmax. Results Our result demonstrated no single sTL or sSUV method could achieve an optimized volumetric match with the C-pGTV. The sTL was 13% to 27% (mean, 19%), whereas the sSUV was 1.64 to 3.98 (mean, 2.46). The sTL was inversely correlated with the SUVmax [sTL = -0.1004 Ln (SUVmax) + 0.4464; R2 = 0.81]. The sSUV showed a linear correlation with the SUVmax (sSUV = 0.0842 SUVmax + 1.248; R2 = 0.89). The sTL was not associated with the value of C-pGTVs. Conclusion In PET/CT-based BTV for HNC, a suitable threshold or SUV level can be established by correlating with SUVmax rather than using a fixed threshold.

Background: We designed a deep learning model for assessing 18F-FDG PET/CT for early prediction of local and distant failures for patients with locally advanced cervical cancer.Methods: All 142 patients with cervical cancer underwent 18F-FDG PET/CT for pretreatment staging and received allocated treatment. To augment the amount of image data, each tumor was represented as 11 slice sets each of which contains 3 2D orthogonal slices to acquire a total of 1562 slice sets. In each round of k-fold cross-validation, a well-trained proposed model and a slice-based optimal threshold were derived from a training set and used to classify each slice set in the test set into the categories of with or without local or distant failure. The classification results of each tumor were aggregated to summarize a tumor-based prediction result.Results: In total, 21 and 26 patients experienced local and distant failures, respectively. Regarding local recurrence, the tumor-based prediction result summarized from all test sets demonstrated that the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 71%, 93%, 63%, 95%, and 89%, respectively. The corresponding values for distant metastasis were 77%, 90%, 63%, 95%, and 87%, respectively.Conclusion: This is the first study to use deep learning model for assessing 18F-FDG PET/CT images which is capable of predicting treatment outcomes in cervical cancer patients.Key Points: • This is the first study to use deep learning model for assessing 18 F-FDG PET/CT images which is capable of predicting treatment outcomes in cervical cancer patients. • All 142 patients with cervical cancer underwent 18 F-FDG PET/CT for pretreatment staging and received allocated treatment. To augment the amount of image data, each tumor was represented as 11 slice sets each of which contains 3 2D orthogonal slices to acquire a total of 1562 slice sets. • For local recurrence, all test sets demonstrated that the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 71%, 93%, 63%, 95%, and 89%, respectively. The corresponding values for distant metastasis were 77%, 90%, 63%, 95%, and 87%, respectively. [ABSTRACT FROM AUTHOR]

Purpose: To understand the association between genetic mutations and radiomics of 2-deoxy-2-[18F]fluoro-D-glucose ([18F]FDG) positron emission tomography (PET)/x-ray computed tomography (CT) in patients with colorectal cancer (CRC).Procedures: This study included 74 CRC patients who had undergone preoperative [18F]FDG PET/CT. A total of 65 PET/CT-related features including intensity, volume-based, histogram, and textural features were calculated. High-resolution melting methods were used for genetic mutation analysis.Results: Genetic mutants were found in 21 KRAS tumors (28 %), 31 TP53 tumors (42 %), and 17 APC tumors (23 %). Tumors with a mutated KRAS had an increased value at the 25th percentile of maximal standardized uptake value (SUVmax) within their metabolic tumor volume (MTV) (P < .0001; odds ratio [OR] 1.99; 95 % confidence interval [CI] 1.37-2.90) and their contrast from the gray-level cooccurrence matrix (P = .005; OR 1.52; 95 % CI 1.14-2.04). A mutated TP53 was associated with an increased value of short-run low gray-level emphasis derived from the gray-level run length matrix (P = .001; OR 243006.0; 95 % CI 59.2-996,872,313). APC mutants exhibited lower low gray-level zone emphasis derived from the gray-level zone length matrix (P = .006; OR < .0001; 95 % CI 0.000-0.22).Conclusion: PET/CT-derived radiomics can provide supplemental information to determine KRAS, TP53, and APC genetic alterations in CRC. [ABSTRACT FROM AUTHOR]

Purpose: This study investigated the correlation of the matrix heterogeneity of tumors on F-fluorodeoxyglucose positron emission tomography-computed tomography (PET-CT) with gene-expression profiling in patients with pharyngeal cancer and determined the prognostic factors for radiotherapy-based treatment outcomes. Methods: We retrospectively reviewed the records of 57 patients with stage III-IV oropharyngeal or hypopharyngeal cancer who had completed definitive therapy. Four groups of the textural features as well as 31 indices were studied in addition to maximum standard uptake value, metastatic tumor volume, and total lesion glycolysis. Immunohistochemical data from pretreatment biopsy specimens ( Glut1, CAIX, VEGF, HIF-1α, EGFR, Ki-67, Bcl-2, CLAUDIN-4, YAP-1, c-Met, and p16) were analyzed. The relationships between the indices and genomic expression were studied, and the robustness of various textural features relative to cause-specific survival and primary relapse-free survival was analyzed. Results: The overexpression of VEGF was positively associated with the increased values of the matrix heterogeneity obtained using gray-level nonuniformity for zone (GLNUz) and run-length nonuniformity (RLNU). Advanced T stage ( p = 0.01, hazard ratio [HR] = 3.38), a VEGF immunoreactive score of >2 ( p = 0.03, HR = 2.79), and a higher GLNUz value ( p = 0.04, HR = 2.51) were prognostic factors for low cause-specific survival, whereas advanced T stage, a HIF-1α staining percentage of ≥80%, and a higher GLNUz value were prognostic factors for low primary-relapse free survival. Conclusions: The overexpression of VEGF was associated with the increased matrix index of GLNUz and RLNU. For patients with pharyngeal cancer requiring radiotherapy, the treatment outcome can be stratified according to the textural features, T stage, and biomarkers. [ABSTRACT FROM AUTHOR]

Background: This study examined genomic factors associated with a reduction in fluoro-2-deoxy- D-glucose (FDG) uptake during positron emission tomography-computed tomography (PET-CT) for definitive chemoradiotherapy (CRT) in patients with pharyngeal cancer. Methods: The pretreatment and interim PET-CT images of 25 patients with advanced pharyngeal cancers receiving definitive CRT were prospectively evaluated. The maximum standardized uptake value (SUV) of the interim PET-CT and the reduction ratio of the SUV (SRR) between the two images were measured. Genomic data from pretreatment incisional biopsy specimens ( SLC2A1, CAIX, VEGF, HIF1A, BCL2, Claudin-4, YAP1, MET, MKI67, and EGFR) were analyzed using tissue microarrays. Differences in FDG uptake and SRRs between tumors with low and high gene expression were examined using the Mann-Whitney test. Cox regression analysis was performed to examine the effects of variables on local control. Results: The SRR of the primary tumors (SRR-P) was 0.59 ± 0.31, whereas the SRR of metastatic lymph nodes (SRR-N) was 0.54 ± 0.32. Overexpression of HIF1A was associated with a high iSUV of the primary tumor ( P < 0.001) and neck lymph node ( P = 0.04) and a low SRR-P ( P = 0.02). Multivariate analysis revealed that patients who had tumors with low SRR-P or high HIF1A expression levels showed inferior local control. Conclusion: In patients with pharyngeal cancer requiring CRT, HIF1A overexpression was positively associated with high interim SUV or a slow reduction in FDG uptake. Prospective trials are needed to determine whether the local control rate can be stratified using the HIF1A level as a biomarker and SRR-P. [ABSTRACT FROM AUTHOR]

Hepatocellular carcinoma (HCC) is a disease usually diagnosed in its advanced-stage, and is frequently not amenable to curative surgical treatment. Also, HCC is resistant to chemotherapy and less vulnerable to radiation therapy compared to normal hepatic parenchyma. Both of these facts render the efficacy of adjuvant and palliative treatments problematic. Selective internal radiation therapy (SIRT) with Y-bearing microspheres is characterized by preferentially delivering substantially high doses of radiation to a liver tumor dose simultaneously limiting the damage to its non-tumorous cells, providing an opportunity for effective local tumor control and even tumor regression therapy. The current article reviews the specific characters, dosimetry, possible applications, and special considerations toward the pre-existing radiation therapy of Y microsphere SIRT in treating HCC. [ABSTRACT FROM AUTHOR]

Objectives/Hypothesis The study aimed to investigate the prognostic effects of interim 18fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (PET/CT) during definitive radiotherapy (RT) or chemoradiotherapy (CRT) in patients with head and neck cancer. Study Design This is a prospectively treatment study. Methods The pretreatment and interim PET/CT images of 51 patients with advanced pharyngeal cancers receiving definitive RT/CRT were evaluated prospectively. The interim PET/CT images were taken at a cumulative RT dose ranging from 41.4 to 46.8 Gy. The maximum standardized uptake value (SUVm) of the interim PET/CT and the reduction ratio of the SUVm (SRR) between the two images were measured. The differences between patients with or without local failures were examined using the Mann-Whitney test. Overall survival (OS), disease-free survival (DFS), and primary and nodal relapse-free survival rates were calculated using the Kaplan-Meier method. Independent prognosticators were identified using Cox regression analysis. Results After a median follow-up duration of 23 months, a higher interim SUVm was associated with local failures. Conducting a multivariate analysis revealed that a SUVmax reduction ratio of primary tumor (SRR-P) < 0.64 was associated with the inferior OS (hazard ratio 2.64; P =0.035) and DFS (hazard ratio 2.33; P = 0.045). Patients who had tumors with an SRR-P < 0.64 had a considerably lower 2-year OS and DFS compared with those who had SRR-P ≥ 0.64 (47% vs. 66%; 41% vs. 64%). Conclusion A higher interim SUVm was associated with local recurrence. In addition, patients with a lower SRR-P should be considered to be at risk of primary failure. Level of Evidence 4. Laryngoscope, 124:2732-2738, 2014 [ABSTRACT FROM AUTHOR]

Simple Summary: Neoadjuvant chemoradiotherapy (NCRT) before surgery is the mainstay of treatment for patients with locally advanced rectal cancer. Based on baseline 18F-fluorodeoxyglucose ([18F]-FDG)-positron emission tomography (PET)/computed tomography (CT), a new artificial intelligence model was introduced to predict responses to NCRT. The model employed metric learning combined with the Uniform Manifold Approximation and Projection for dimensionality reduction. The treatment response was scored by Dworak tumor regression grade (TRG); TRG3 and TRG4 indicated favorable responses. Using this model, the area under the receiver operating characteristic curve was 0.96 for predicting a favorable response. The sensitivity, specificity, and accuracy were 98.3%, 96.5%, and 97.5%, respectively. After further external validation, oncologists may use the proposed model to advise patients on the relative suitability of treatment options, including the therapeutic decision between NCRT and neoadjuvant chemotherapy. Integrating this approach would have a notable effect on counseling patients about treatment alternatives or prognoses. Objectives: Neoadjuvant chemoradiotherapy (NCRT) followed by surgery is the mainstay of treatment for patients with locally advanced rectal cancer. Based on baseline 18F-fluorodeoxyglucose ([18F]-FDG)-positron emission tomography (PET)/computed tomography (CT), a new artificial intelligence model using metric learning (ML) was introduced to predict responses to NCRT. Patients and Methods: This study used the data of 236 patients with newly diagnosed rectal cancer; the data of 202 and 34 patients were for training and validation, respectively. All patients received pretreatment [18F]FDG-PET/CT, NCRT, and surgery. The treatment response was scored by Dworak tumor regression grade (TRG); TRG3 and TRG4 indicated favorable responses. The model employed ML combined with the Uniform Manifold Approximation and Projection for dimensionality reduction. A receiver operating characteristic (ROC) curve analysis was performed to assess the model's predictive performance. Results: In the training cohort, 115 patients (57%) achieved TRG3 or TRG4 responses. The area under the ROC curve was 0.96 for the prediction of a favorable response. The sensitivity, specificity, and accuracy were 98.3%, 96.5%, and 97.5%, respectively. The sensitivity, specificity, and accuracy for the validation cohort were 95.0%, 100%, and 98.8%, respectively. Conclusions: The new ML model presented herein was used to determined that baseline 18F[FDG]-PET/CT images could predict a favorable response to NCRT in patients with rectal cancer. External validation is required to verify the model's predictive value. [ABSTRACT FROM AUTHOR]

Niemann-Pick type C disease (NPC) is a rare autosomal recessive lipid storage disorder caused by impaired cellular functions in processing and transporting low-density lipoprotein-cholesterol. In this report, we present magnetic resonance imaging (MRI), magnetic resonance spectrography (MRS) and 18-fluoro-2-deoxyglucose positron emission tomography (PET) imaging results for a 22-year-old male NPC patient. The patient''s two MRI studies (at age 19 years and 22 years) demonstrated progressive changes of brain atrophy that were more prominent at the frontal lobes, and hyperintense signals in bilateral parietal-occipital periventricular white matter. MRS (at age 19 years) revealed no significant decrease in N-acetyl aspartate/choline ratio in the left frontal central white matter. PET (at age 22 years) showed significant bilateral hypometabolism in the prefrontal cortex and dorsomedial thalamus, and hypermetabolism in the parietal-occipital white matter, lenticular nucleus of the basal ganglia, cerebellum and pons. The imaging findings noted by MRI, MRS and 18-fluoro-2-deoxyglucose PET offered a possible supplementary explanation for the clinical neurological symptoms of this NPC patient. [Copyright &y& Elsevier]

The aim of this study was to establish an early diagnostic system for the identification of the bone metastasis of prostate cancer in whole-body bone scan images by using a deep convolutional neural network (D-CNN). The developed system exhibited satisfactory performance for a small dataset containing 205 cases, 100 of which were of bone metastasis. The sensitivity and precision for bone metastasis detection and classification in the chest were 0.82 ± 0.08 and 0.70 ± 0.11, respectively. The sensitivity and specificity for bone metastasis classification in the pelvis were 0.87 ± 0.12 and 0.81 ± 0.11, respectively. We propose the use of hard example mining for increasing the sensitivity and precision of the chest D-CNN. The developed system has the potential to provide a prediagnostic report for physicians' final decisions. [ABSTRACT FROM AUTHOR]

This study aimed to explore efficient ways to diagnose bone metastasis early using bone scintigraphy images through negative mining, pre-training, the convolutional neural network, and deep learning. We studied 205 prostate cancer patients and 371 breast cancer patients and used bone scintigraphy data from breast cancer patients to pre-train a YOLO v4 with a false-positive reduction strategy. With the pre-trained model, transferred learning was applied to prostate cancer patients to build a model to detect and identify metastasis locations using bone scintigraphy. Ten-fold cross validation was conducted. The mean sensitivity and precision rates for bone metastasis location detection and classification (lesion-based) in the chests of prostate patients were 0.72 ± 0.04 and 0.90 ± 0.04, respectively. The mean sensitivity and specificity rates for bone metastasis classification (patient-based) in the chests of prostate patients were 0.94 ± 0.09 and 0.92 ± 0.09, respectively. The developed system has the potential to provide pre-diagnostic reports to aid in physicians' final decisions. [ABSTRACT FROM AUTHOR]

Abstract: Purpose: We found several cases with unexpected pulmonary abnormalities on the 18F-FDG PET scan after the gastrointestinal endoscopy with sedation during a compact health check-up course, interfering the interpretations of 18F-FDG PET scan for cancer screening. The current studies aimed to analyze the incidence and the clinical relevance of this pulmonary finding. Materials and methods: From June to December 2009, 127 subjects undergoing the sequential gastrointestinal endoscopy with sedation and 18F-FDG PET scan within 48h as part of routine health check-up were retrospectively enrolled in this study. The incidence of abnormal pulmonary findings and their SUVmax of FDG were calculated and correlated with the clinical manifestations. Results: Five subjects had abnormal 18F-FDG PET findings but pulmonary symptoms were only found in 2. The SUVmax did not seem to reflect the severity of pulmonary symptoms or the need of intervention. Although the incidence of unrecognized pulmonary aspiration featuring inflammation detected by the 18F-FDG PET scan was high (3.94%, 5/127), the incidence of events needed intervention remained low (0.79%, 1/127), similar to those previously reported literatures. Conclusions: Although higher incidence of pulmonary aspiration in this study, it probably reflects the better sensitivity of 18F-FDG PET for inflammation. The low incidence of clinical events needed intervention may still reflect the safety of sedation used for gastrointestinal endoscopy. Proper arrangement of the sequential examinations if subjects need both gastrointestinal endoscopy with sedation and 18F-FDG PET is important to reduce the interference degrading the performance of 18F-FDG PET in cancer screening, diagnosis or staging. [Copyright &y& Elsevier]

Objectives: A deep learning (DL) model using image data from pretreatment [ 18 F]fluorodeoxyglucose ([ 18 F] FDG)-PET or computed tomography (CT) augmented with a novel imaging augmentation approach was developed for the early prediction of distant metastases in patients with locally advanced uterine cervical cancer., Methods: This study used baseline [18F]FDG-PET/CT images of newly diagnosed uterine cervical cancer patients. Data from 186 to 25 patients were analyzed for training and validation cohort, respectively. All patients received chemoradiotherapy (CRT) and follow-up. PET and CT images were augmented by using three-dimensional techniques. The proposed model employed DL to predict distant metastases. Receiver operating characteristic (ROC) curve analysis was performed to measure the model's predictive performance., Results: The area under the ROC curves of the training and validation cohorts were 0.818 and 0.830 for predicting distant metastasis, respectively. In the training cohort, the sensitivity, specificity, and accuracy were 80.0%, 78.0%, and 78.5%, whereas, the sensitivity, specificity, and accuracy for distant failure were 73.3%, 75.5%, and 75.2% in the validation cohort, respectively., Conclusion: Through the use of baseline [ 18 F]FDG-PET/CT images, the proposed DL model can predict the development of distant metastases for patients with locally advanced uterine cervical cancer treatment by CRT. External validation must be conducted to determine the model's predictive performance., (Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.)

Objectives: To predict KRAS mutation in rectal cancer (RC) through computer vision of [18F]fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) by using metric learning (ML)., Methods: This study included 160 patients with RC who had undergone preoperative PET/CT. KRAS mutation was identified through polymerase chain reaction analysis. This model combined ML with the deep-learning framework to analyze PET data with or without CT images. The Batch Balance Wrapper framework and K-fold cross-validation were employed during the learning process. A receiver operating characteristic (ROC) curve analysis was performed to assess the model's predictive performance., Results: Genetic alterations in KRAS were identified in 82 (51%) tumors. Both PET and CT images were used, and the proposed model had an area under the ROC curve of 0.836 for its ability to predict a mutation status. The sensitivity, specificity, and accuracy were 75.3%, 79.3%, and 77.5%, respectively. When PET images alone were used, the area under the curve was 0.817, whereas the sensitivity, specificity, and accuracy were 73.2%, 79.6%, and 76.2%, respectively., Conclusions: The ML model presented herein revealed that baseline 18F-FDG PET/CT images could provide supplemental information to determine KRAS mutation in RC. Additional studies are required to maximize the predictive accuracy., Advances in Knowledge: The results of the ML model presented herein indicate that baseline 18F-FDG PET/CT images could provide supplemental information for determining KRAS mutation in RC.The predictive accuracy of the model was 77.5% when both image types were used and 76.2% when PET images alone were used. Additional studies are required to maximize the predictive accuracy.

Background: The investigation of incidental pulmonary nodules has rapidly become one of the main indications for 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET), currently combined with computed tomography (PET-CT). There is also a growing trend to use artificial Intelligence for optimization and interpretation of PET-CT Images. Therefore, we proposed a novel deep learning model that aided in the automatic differentiation between malignant and benign pulmonary nodules on FDG PET-CT., Methods: In total, 112 participants with pulmonary nodules who underwent FDG PET-CT before surgery were enrolled retrospectively. We designed a novel deep learning three-dimensional (3D) high-resolution representation learning (HRRL) model for the automated classification of pulmonary nodules based on FDG PET-CT images without manual annotation by experts. For the images to be localized more precisely, we defined the territories of the lungs through a novel artificial intelligence-driven image-processing algorithm, instead of the conventional segmentation method, without the aid of an expert; this algorithm is based on deep HRRL, which is used to perform high-resolution classification. In addition, the 2D model was converted to a 3D model., Results: All pulmonary lesions were confirmed through pathological studies (79 malignant and 33 benign). We evaluated its diagnostic performance in the differentiation of malignant and benign nodules. The area under the receiver operating characteristic curve (AUC) of the deep learning model was used to indicate classification performance in an evaluation using fivefold cross-validation. The nodule-based prediction performance of the model had an AUC, sensitivity, specificity, and accuracy of 78.1, 89.9, 54.5, and 79.4%, respectively., Conclusion: Our results suggest that a deep learning algorithm using HRRL without manual annotation from experts might aid in the classification of pulmonary nodules discovered through clinical FDG PET-CT images., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Lai, Wu, Tseng, Chen, Chang, Yen and Kao.)

Background: Neoadjuvant chemoradiotherapy (NCRT) followed by surgery is the standard treatment for patients with locally advanced rectal cancer. This study developed a random forest (RF) model to predict pathological complete response (pCR) based on radiomics derived from baseline 18 F-fluorodeoxyglucose ([ 18 F]FDG)-positron emission tomography (PET)/computed tomography (CT)., Methods: This study included 169 patients with newly diagnosed rectal cancer. All patients received 18 F[FDG]-PET/CT, NCRT, and surgery. In total, 68 radiomic features were extracted from the metabolic tumor volume. The numbers of splits in a decision tree and trees in an RF were determined based on their effects on predictive performance. Receiver operating characteristic curve analysis was performed to evaluate predictive performance and ascertain the optimal threshold for maximizing prediction accuracy., Results: After NCRT, 22 patients (13%) achieved pCR, and 42 features that could differentiate tumors with pCR were used to construct the RF model. Six decision trees and seven splits were suitable. Accordingly, the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 81.8%, 97.3%, 81.8%, 97.3%, and 95.3%, respectively., Conclusions: By using an RF, we determined that radiomics derived from baseline 18 F[FDG]-PET/CT could accurately predict pCR in patients with rectal cancer. Highly accurate and predictive values can be achieved but should be externally validated., Competing Interests: Conflicts of Interest: The authors have no conflicts of interest to declare., (2020 Annals of Translational Medicine. All rights reserved.)