FDG PET/CT in colorectal cancer

Applying machine learning techniques to predict the risk of distant metastasis from gastric cancer: a real world retrospective study

Background

Distant metastasis of gastric cancer can seriously affect the treatment strategy of gastric cancer patients, so it is essential to identify patients at high risk of distant metastasis of gastric cancer earlier.

Method

In this study, we retrospectively collected research data from 18,472 gastric cancer patients from the SEER database. We applied six machine learning algorithms to construct a model that can predict distant metastasis of gastric cancer. We constructed the machine learning model using 10-fold cross-validation. We evaluated the model using the area under the receiver operating characteristic curves (AUC), the area under the precision-recall curve (AUPRC), decision curve analysis, and calibration curves. In addition, we used Shapley's addition interpretation (SHAP) to interpret the machine learning model. We used data from 1595 gastric cancer patients in the First Hospital of Jilin University for external validation. We plotted the correlation heat maps of the predictor variables. We selected an optimal model and constructed a web-based online calculator for predicting the risk of distant metastasis of gastric cancer.

Result

The study included 18,472 patients with gastric cancer from the SEER database, including 4,202 (22.75%) patients with distant metastases. The results of multivariate logistic regression analysis showed that age, race, grade of differentiation, tumor size, T stage, radiotherapy, and chemotherapy were independent risk factors for distant metastasis of gastric cancer. In the ten-fold cross-validation of the training set, the average AUC value of the random forest (RF) model was 0.80. The RF model performed best in the internal test set and external validation set. The RF model had an AUC of 0.80, an AUPRC of 0.555, an accuracy of 0.81, and a precision of 0.78 in the internal test set. The RF model had a metric AUC of 0.76 in the external validation set, an AUPRC of 0.496, an accuracy of 0.82, and a precision of 0.81. Finally, we constructed a network calculator for distant metastasis of gastric cancer using the RF model.

Conclusion

With the help of pathological and clinical indicators, we constructed a well-performing RF model for predicting the risk of distant metastasis in gastric cancer patients to help clinicians make clinical decisions.

Clinical significance of 18F-FDG-PET/CT for detection of incidental pre-malignant and malignant colonic lesions: correlation with colonoscopic and histopathological results

BACKGROUND

Incidental colorectal fluorodeoxyglucose (FDG) uptake, observed during positron emission tomography/computed tomography (PET/CT) scans, attracts particular attention due to its potential to represent both benign and pre-malignant/malignant lesions. Early detection and excision of these lesions are crucial for preventing cancer development and reducing mortality. This research aims to evaluate the correlation between incidental colorectal FDG uptake on PET/CT with colonoscopic and histopathological results.

METHODS

Retrospective analysis was performed on data from all patients who underwent PET/CT between December 2019 and December 2023 in our hospital. The study included 79 patients with incidental colonic FDG uptake who underwent endoscopy. Patient characteristics, imaging parameters, and the corresponding colonoscopy and histopathological results were studied. A comparative analysis was performed among the findings from each of these modalities. The optimal cut-off value of SUVmax for 18F-FDG PET/CT diagnosis of premalignant and malignant lesions was determined by receiver operating characteristic (ROC) curves. The area under the curve (AUC) of SUVmax and the combined parameters of SUVmax and colonic wall thickening (CWT) were analyzed.

RESULTS

Among the 79 patients with incidental colorectal FDG uptake, histopathology revealed malignancy in 22 (27.9%) patients and premalignant polyps in 22 (27.9%) patients. Compared to patients with benign lesions, patients with premalignant and malignant lesions were more likely to undergo a PET/CT scan for primary evaluation (p = 0.013), and more likely to have focal GIT uptake (p = 0.001) and CWT (p = 0.001). A ROC curve analysis was made and assesed a cut-off value of 7.66 SUVmax (sensitivity: 64.9% and specificity: 82.4%) to distinguish premalignant and malignant lesions from benign lesions. The AUCs of the SUVmax and the combined parameters of SUVmax and CWT were 0.758 and 0.832 respectively.

CONCLUSION

For patients undergo PET/CT for primary evaluation, imaging features of colorectal focal FDG uptake and CWT were more closely associated with premalignant and malignant lesions. The SUVmax helps determine benign and premalignant/malignant lesions of the colorectum. Moreover, the combination of SUVmax and CWT parameters have higher accuracy in estimating premalignant and malignant lesions than SUVmax.

Recommendations for the management of yttrium-90 radioembolization in the treatment of patients with colorectal cancer liver metastases: a multidisciplinary review

PURPOSE

Strategies for the treatment of liver metastases from colon cancer (lmCRC) are constantly evolving. Radioembolization with yttrium 90 (Y-90 TARE) has made significant advancements in treating liver tumors and is now considered a potential option allowing for future resection. This study reviewed the scientific evidence and developed recommendations for using Y-90 TARE as a treatment strategy for patients with unresectable lmCRC.

METHODS

A multidisciplinary scientific committee, consisting of experts in medical oncology, hepatobiliary surgery, radiology, and nuclear medicine, all with extensive experience in treating patients with ImCRC with Y-90 TARE, led this project. The committee established the criteria for conducting a comprehensive literature review on Y-90 TARE in the treatment of lmCRC. The data extraction process involved addressing initial preliminary inquiries, which were consolidated into a final set of questions.

RESULTS

This review offers recommendations for treating patients with lmCRC using Y-90 TARE, addressing four areas covering ten common questions: 1) General issues (multidisciplinary tumor committee, indications for treatment, contraindications); 2) Previous process (predictive biomarkers for patient selection, preintervention tests, published evidence); 3) Procedure (standard procedure); and 4) Post-intervention follow-up (potential toxicity and its management, parameters for evaluation, quality of life).

CONCLUSIONS

Based on the insights of the multidisciplinary committee, this document offers a comprehensive overview of the technical aspects involved in the management of Y-90 TARE. It synthesizes recommendations for applying Y-90 TARE across various phases of the treatment process.

Role of PET/Computed Tomography in Gastric and Colorectal Malignancies

This article focuses on the role of PET/computed tomography in evaluating and managing gastric cancer and colorectal cancer. The authors start with describing the common aspects of imaging with 2-deoxy-2-18F-d-glucose, followed by tumor-specific discussions of gastric and colorectal malignancies. Finally, the authors provide a brief overview of non-FDG tracers including their potential clinical applications, and describe future directions in imaging these malignancies.

A machine learning-based model for predicting distant metastasis in patients with rectal cancer

Background

Distant metastasis from rectal cancer usually results in poorer survival and quality of life, so early identification of patients at high risk of distant metastasis from rectal cancer is essential.

Method

The study used eight machine-learning algorithms to construct a machine-learning model for the risk of distant metastasis from rectal cancer. We developed the models using 23867 patients with rectal cancer from the Surveillance, Epidemiology, and End Results (SEER) database between 2010 and 2017. Meanwhile, 1178 rectal cancer patients from Chinese hospitals were selected to validate the model performance and extrapolation. We tuned the hyperparameters by random search and tenfold cross-validation to construct the machine-learning models. We evaluated the models using the area under the receiver operating characteristic curves (AUC), the area under the precision-recall curve (AUPRC), decision curve analysis, calibration curves, and the precision and accuracy of the internal test set and external validation cohorts. In addition, Shapley's Additive explanations (SHAP) were used to interpret the machine-learning models. Finally, the best model was applied to develop a web calculator for predicting the risk of distant metastasis in rectal cancer.

Result

The study included 23,867 rectal cancer patients and 2,840 patients with distant metastasis. Multiple logistic regression analysis showed that age, differentiation grade, T-stage, N-stage, preoperative carcinoembryonic antigen (CEA), tumor deposits, perineural invasion, tumor size, radiation, and chemotherapy were-independent risk factors for distant metastasis in rectal cancer. The mean AUC value of the extreme gradient boosting (XGB) model in ten-fold cross-validation in the training set was 0.859. The XGB model performed best in the internal test set and external validation set. The XGB model in the internal test set had an AUC was 0.855, AUPRC was 0.510, accuracy was 0.900, and precision was 0.880. The metric AUC for the external validation set of the XGB model was 0.814, AUPRC was 0.609, accuracy was 0.800, and precision was 0.810. Finally, we constructed a web calculator using the XGB model for distant metastasis of rectal cancer.

Conclusion

The study developed and validated an XGB model based on clinicopathological information for predicting the risk of distant metastasis in patients with rectal cancer, which may help physicians make clinical decisions. rectal cancer, distant metastasis, web calculator, machine learning algorithm, external validation.

Tailoring the clinical management of colorectal cancer by 18F-FDG PET/CT

Colorectal cancer (CRC) is among the most commonly diagnosed gastrointestinal malignancies worldwide. It is inadequate to handle in terms of staging and restaging only based on morphological imaging modalities and serum surrogate markers. And the correct and timely staging of CRC is imperative to prognosis and management. When compared to established sequential, multimodal conventional diagnostic methods, the molecular and functional imaging ¹⁸F-FDG PET/CT shows superiorities for tailoring appropriate treatment maneuvers to each patient. This review aims to summarize the utilities of ¹⁸F-FDG PET/CT in CRC, focusing on primary staging, follow-up assessment of tumor responses and diagnostic of recurrence. In addition, we also summarize the technical considerations of PET/CT and the conventional imaging modalities in those patients who are either newly diagnosed with CRC or has already been treated from this cancer.

Variants and Pitfalls in PET/CT Imaging of Gastrointestinal Cancers

In the past two decades, PET/CT has become an essential modality in oncology increasingly used in the management of gastrointestinal (GI) cancers. Most PET/CT tracers used in clinical practice show some degree of GI uptake. This uptake is quite variable and knowledge of common patterns of biodistribution of various radiotracers is helpful in clinical practice. 18F-Fluoro-Deoxy-Glucose (FDG) is the most commonly used radiotracer and has quite a variable uptake within the bowel. 68Ga-Prostate specific membrane antigen (PSMA) shows intense uptake within the proximal small bowel loops. 11C-methyl-L-methionine (MET) shows high accumulation within the bowels, which makes it difficult to assess bowel or pelvic diseases. One must also be aware of technical artifacts causing difficulties in interpretations, such as high attenuation oral contrast material within the bowel lumen or misregistration artifact due to patient movements. It is imperative to know the common variants and benign diseases that can mimic malignant pathologies. Intense FDG uptake within the esophagus and stomach may be a normal variant or may be associated with benign conditions such as esophagitis, reflux disease, or gastritis. Metformin can cause diffuse intense uptake throughout the bowel loops. Intense physiologic uptake can also be seen within the anal canal. Segmental bowel uptake can be seen in inflammatory bowel disease, radiation, or medication induced enteritis/colitis or infection. Diagnosis of appendicitis or diverticular disease requires CT correlation, as normal appendix or diverticulum can show intense uptake. Certain malignant pathologies are known to have only low FDG uptake, such as early-stage esophageal adenocarcinoma, mucinous tumors, indolent lymphomas, and multicystic mesotheliomas. Response assessment, particularly in the neoadjuvant setting, can be limited by post-treatment inflammatory changes. Post-operative complications such as abscess or fistula formation can also show intense uptake and may obscure underlying malignant pathology. In the absence of clinical suspicion or rising tumor marker, the role of FDG PET/CT in routine surveillance of patients with GI malignancy is not clear.

Investigating ultra-low-dose total-body [18F]-FDG PET/CT in colorectal cancer: initial experience

PURPOSE

This study was to evaluate the effects of an ultra-low dose of [18F]-FDG on the image quality of total-body PET/CT and its lesion detectability in colorectal cancer (CRC).

METHODS

Sixty-two CRC patients who underwent total-body PET/CT (uEXPLORER, United Imaging Healthcare, Shanghai, China) with an ultra-low dose (0.37 MBq/kg) of [18F]-FDG were enrolled in this retrospective study. The PET images were reconstructed with the entire 15-min dataset first and then split into 13-, 8-, 5-, 4-, 3-, 2-, and 1-min duration groups to simulate fast scanning images. For simplicity, the images reconstructed with the data from 15 to 1 min were referred to as G15, G13, and so on until G1. Subjective image quality was assessed with 5-point Likert scales. The objective image quality parameters included the SUVmax, SUVmean, and signal-to-noise ratio (SNR) of the liver and blood pool and the SUVmax and tumor-to-background ratio (TBR) of the lesions. G15 served as the control to evaluate lesion detectability.

RESULTS

A total of 62 patients (43 men, 19 women; age 41-88, mean ± SD 64.0 ± 10.9 years) with 64 CRC primary tumor lesions and 10 low-grade intraepithelial neoplasia (LGIN) lesions were enrolled in this study. The subjective scores were highest for G15 (4.5 ± 0.5) and then decreased from G13 (4.3 ± 0.4) to G8 (3.7 ± 0.5). The liver SNR increased with the extension of acquisition time from G8 (17.2 ± 2.8) to G13 (20.6 ± 3.4) and G15 (21.9 ± 3.4). The liver SNR of G8 was not significantly different from that of G13 (p = 0.15) and was significantly different from that of G15 (p = 0.001). All 64 CRC lesions could be identified in all image groups, even on G1. One of ten LGINs was missed on G1, G2, and G3, and one LGIN was missed on G1, G2, G3, and G4. G15 served as the control, and 100% (48/48) lymph nodes could be found on G13 and G8 compared to 93.8% (45/48) lymph nodes on G5 and G4, 85.4% (41/48) lymph nodes on G3, 81.3% (39/48) lymph nodes on G2, and 77.1% (37/48) lymph nodes on G1. For liver metastases, there were no missed liver lesions on G13 and G8 and 3, 4, 6, 7, and 9 missed liver lesions on G5, G4, G3, G2, and G1, respectively. For other areas of metastasis, including the lung, peritoneum, and ovaries, there were no missed lesions in any group.

CONCLUSIONS

Total-body PET/CT with an ultra-low dose of [18F]-FDG can maintain satisfactory image quality and lesion detectability in CRC.