A Comprehensive Prediction Model Based on MRI Radiomics and Clinical Factors to Predict Tumor Response After Neoadjuvant Chemoradiotherapy in Rectal Cancer

CLIP-based multimodal endorectal ultrasound enhances prediction of neoadjuvant chemoradiotherapy response in locally advanced rectal cancer

BACKGROUND

Forecasting the patient's response to neoadjuvant chemoradiotherapy (nCRT) is crucial for managing locally advanced rectal cancer (LARC). This study investigates whether a predictive model using image-text features extracted from endorectal ultrasound (ERUS) via Contrastive Language-Image Pretraining (CLIP) can predict tumor regression grade (TRG) before nCRT.

METHODS

A retrospective analysis of 577 LARC patients who received nCRT followed by surgery was conducted from January 2018 to December 2023. ERUS scans and TRG were used to assess nCRT response, categorizing patients into good (TRG 0) and poor (TRG 1-3) responders. Image and text features were extracted using the ResNet50+RBT3 (RN50) and ViT-B/16+RoBERTa-wwm (VB16) components of the Chinese-CLIP model. LightGBM was used for model construction and comparison. A subset of 100 patients from each responder group was used to compare the CLIP method with manual radiomics methods (logistic regression, support vector machines, and random forest). SHapley Additive exPlanations (SHAP) technique was used to analyze feature contributions.

RESULTS

The RN50 and VB16 models achieved AUROC scores of 0.928 (95% CI: 0.90-0.96) and 0.900 (95% CI: 0.86-0.93), respectively, outperforming manual radiomics methods. SHAP analysis indicated that image features dominated the RN50 model, while both image and text features were significant in the VB16 model.

CONCLUSIONS

The CLIP-based predictive model using ERUS image-text features and LightGBM showed potential for improving personalized treatment strategies. However, this study is limited by its retrospective design and single-center data.

Enhancing biomedical imaging: the role of nanoparticle-based contrast agents

Biomedical imaging plays a critical role in early detection, precise diagnosis, treatment planning, and monitoring responses, but traditional methods encounter challenges such as limited sensitivity, specificity, and inability to monitor therapeutic responses due to factors like short circulation half-life and potential toxicity. Nanoparticles are revolutionizing biomedical imaging as contrast agents across modalities like computed tomography (CT), optical, magnetic resonance imaging (MRI), and ultrasound, exploiting unique attributes such as those of metal-based, polymeric, and lipid nanoparticles. They shield imaging agents from immune clearance, extending circulation time, and enhancing bioavailability at tumor sites. This results in improved imaging sensitivity. The study highlights advancements in multifunctional nanoparticles for targeted imaging, tackling concerns regarding toxicity and biocompatibility. Critically evaluating conventional contrast agents, emphasizes the shortcomings that nanoparticles aim to overcome. This review provides insight into the current status of nanoparticle-based contrast agents, illuminating their potential to reshape therapeutic monitoring and precision diagnostics.

Predicting disease recurrence in breast cancer patients using machine learning models with clinical and radiomic characteristics: a retrospective study

BACKGROUND

The goal is to use three different machine learning models to predict the recurrence of breast cancer across a very heterogeneous sample of patients with varying disease kinds and stages.

METHODS

A heterogeneous group of patients with varying cancer kinds and stages, including both triple-negative breast cancer (TNBC) and non-triple-negative breast cancer (non-TNBC), was examined. Three distinct models were created using the following five machine learning techniques: Adaptive Boosting (AdaBoost), Random Under-sampling Boosting (RUSBoost), Extreme Gradient Boosting (XGBoost), support vector machines (SVM), and Logistic Regression. The clinical model used both clinical and pathology data in conjunction with the machine learning algorithms. The machine learning algorithms were combined with dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) imaging characteristics in the radiomic model, and the merged model combined the two types of data. Each technique was evaluated using several criteria, including the receiver operating characteristic (ROC) curve, precision, recall, and F1 score.

RESULTS

The results suggest that the integration of clinical and radiomic data improves the predictive accuracy in identifying instances of breast cancer recurrence. The XGBoost algorithm is widely recognized as the most effective algorithm in terms of performance.

CONCLUSION

The findings presented in this study offer significant contributions to the field of breast cancer research, particularly in relation to the prediction of cancer recurrence. These insights hold great potential for informing future investigations and clinical interventions that seek to enhance the accuracy and effectiveness of recurrence prediction in breast cancer patients.

Multi-task reconstruction network for synthetic diffusion kurtosis imaging: Predicting neoadjuvant chemoradiotherapy response in locally advanced rectal cancer

PURPOSE

To assess the feasibility and clinical value of synthetic diffusion kurtosis imaging (DKI) generated from diffusion weighted imaging (DWI) through multi-task reconstruction network (MTR-Net) for tumor response prediction in patients with locally advanced rectal cancer (LARC).

METHODS

In this retrospective study, 120 eligible patients with LARC were enrolled and randomly divided into training and testing datasets with a 7:3 ratio. The MTR-Net was developed for reconstructing Dapp and Kapp images from apparent diffusion coefficient (ADC) images. Tumor regions were manually segmented on both true and synthetic DKI images. The synthetic image quality and manual segmentation agreement were quantitatively assessed. The support vector machine (SVM) classifier was used to construct radiomics models based on the true and synthetic DKI images for pathological complete response (pCR) prediction. The prediction performance for the models was evaluated by the receiver operating characteristic (ROC) curve analysis.

RESULTS

The mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) for tumor regions were 0.212, 24.278, and 0.853, respectively, for the synthetic Dapp images and 0.516, 24.883, and 0.804, respectively, for the synthetic Kapp images. The Dice similarity coefficient (DSC), positive predictive value (PPV), sensitivity (SEN), and Hausdorff distance (HD) for the manually segmented tumor regions were 0.786, 0.844, 0.755, and 0.582, respectively. For predicting pCR, the true and synthetic DKI-based radiomics models achieved area under the curve (AUC) values of 0.825 and 0.807 in the testing datasets, respectively.

CONCLUSIONS

Generating synthetic DKI images from DWI images using MTR-Net is feasible, and the efficiency of synthetic DKI images in predicting pCR is comparable to that of true DKI images.

Development and validation of a multi-modal ultrasomics model to predict response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer

OBJECTIVES

To assess the performance of multi-modal ultrasomics model to predict efficacy to neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC) and compare with the clinical model.

MATERIALS AND METHODS

This study retrospectively included 106 patients with LARC who underwent total mesorectal excision after nCRT between April 2018 and April 2023 at our hospital, randomly divided into a training set of 74 and a validation set of 32 in a 7: 3 ratios. Ultrasomics features were extracted from the tumors' region of interest of B-mode ultrasound (BUS) and contrast-enhanced ultrasound (CEUS) images based on PyRadiomics. Mann-Whitney U test, spearman, and least absolute shrinkage and selection operator algorithms were utilized to reduce features dimension. Five models were built with ultrasomics and clinical analysis using multilayer perceptron neural network classifier based on python. Including BUS, CEUS, Combined_1, Combined_2 and Clinical models. The diagnostic performance of models was assessed with the area under the curve (AUC) of the receiver operating characteristic. The DeLong testing algorithm was utilized to compare the models' overall performance.

RESULTS

The AUC (95% confidence interval [CI]) of the five models in the validation cohort were as follows: BUS 0.675 (95%CI: 0.481-0.868), CEUS 0.821 (95%CI: 0.660-0.983), Combined_1 0.829 (95%CI: 0.673-0.985), Combined_2 0.893 (95%CI: 0.780-1.000), and Clinical 0.690 (95%CI: 0.509-0.872). The Combined_2 model was the best in the overall prediction performance, showed significantly better compared to the Clinical model after DeLong testing (P < 0.01). Both univariate and multivariate logistic regression analyses showed that age (P < 0.01) and clinical stage (P < 0.01) could be an independent predictor of efficacy after nCRT in patients with LARC.

CONCLUSION

The ultrasomics model had better diagnostic performance to predict efficacy to nCRT in patients with LARC than the Clinical model.

Performance and Dimensionality of Pretreatment MRI Radiomics in Rectal Carcinoma Chemoradiotherapy Prediction

(1) Background: This study aimed to develop a machine learning model based on radiomics of pretreatment magnetic resonance imaging (MRI) 3D T2W contrast sequence scans combined with clinical parameters (CP) to predict neoadjuvant chemoradiotherapy (nCRT) response in patients with locally advanced rectal carcinoma (LARC). The study also assessed the impact of radiomics dimensionality on predictive performance. (2) Methods: Seventy-five patients were prospectively enrolled with clinicopathologically confirmed LARC and nCRT before surgery. Tumor properties were assessed by calculating 2141 radiomics features. Least absolute shrinkage selection operator (LASSO) and multivariate regression were used for feature selection. (3) Results: Two predictive models were constructed, one starting from 72 CP and 107 radiomics features, and the other from 72 CP and 1862 radiomics features. The models revealed moderately advantageous impact of increased dimensionality, with their predictive respective AUCs of 0.86 and 0.90 in the entire cohort and 0.84 within validation folds. Both models outperformed the CP-only model (AUC = 0.80) which served as the benchmark for predictive performance without radiomics. (4) Conclusions: Predictive models developed in this study combining pretreatment MRI radiomics and clinicopathological features may potentially provide a routine clinical predictor of chemoradiotherapy responders, enabling clinicians to personalize treatment strategies for rectal carcinoma.

Development of a deep learning model for early gastric cancer diagnosis using preoperative computed tomography images

Background

Gastric cancer is a highly prevalent and fatal disease. Accurate differentiation between early gastric cancer (EGC) and advanced gastric cancer (AGC) is essential for personalized treatment. Currently, the diagnostic accuracy of computerized tomography (CT) for gastric cancer staging is insufficient to meet clinical requirements. Many studies rely on manual marking of lesion areas, which is not suitable for clinical diagnosis.

Methods

In this study, we retrospectively collected data from 341 patients with gastric cancer at the First Affiliated Hospital of Wenzhou Medical University. The dataset was randomly divided into a training set (n=273) and a validation set (n=68) using an 8:2 ratio. We developed a two-stage deep learning model that enables fully automated EGC screening based on CT images. In the first stage, an unsupervised domain adaptive segmentation model was employed to automatically segment the stomach on unlabeled portal phase CT images. Subsequently, based on the results of the stomach segmentation model, the image was cropped out of the stomach area and scaled to a uniform size, and then the EGC and AGC classification models were built based on these images. The segmentation accuracy of the model was evaluated using the dice index, while the classification performance was assessed using metrics such as the area under the curve (AUC) of the receiver operating characteristic (ROC), accuracy, sensitivity, specificity, and F1 score.

Results

The segmentation model achieved an average dice accuracy of 0.94 on the hand-segmented validation set. On the training set, the EGC screening model demonstrated an AUC, accuracy, sensitivity, specificity, and F1 score of 0.98, 0.93, 0.92, 0.92, and 0.93, respectively. On the validation set, these metrics were 0.96, 0.92, 0.90, 0.89, and 0.93, respectively. After three rounds of data regrouping, the model consistently achieved an AUC above 0.9 on both the validation set and the validation set.

Conclusion

The results of this study demonstrate that the proposed method can effectively screen for EGC in portal venous CT images. Furthermore, the model exhibits stability and holds promise for future clinical applications.