Search

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]