Artificial Intelligence in the Imaging of Gastric Cancer: Current Applications and Future Direction

Application of Photoactive Compounds in Cancer Theranostics: Review on Recent Trends from Photoactive Chemistry to Artificial Intelligence

According to the World Health Organization (WHO) and the International Agency for Research on Cancer (IARC), the number of cancer cases and deaths worldwide is predicted to nearly double by 2030, reaching 21.7 million cases and 13 million fatalities. The increase in cancer mortality is due to limitations in the diagnosis and treatment options that are currently available. The close relationship between diagnostics and medicine has made it possible for cancer patients to receive precise diagnoses and individualized care. This article discusses newly developed compounds with potential for photodynamic therapy and diagnostic applications, as well as those already in use. In addition, it discusses the use of artificial intelligence in the analysis of diagnostic images obtained using, among other things, theranostic agents.

Deep learning-based clinical-radiomics nomogram for preoperative prediction of lymph node metastasis in patients with rectal cancer: a two-center study

Background

Precise preoperative evaluation of lymph node metastasis (LNM) is crucial for ensuring effective treatment for rectal cancer (RC). This research aims to develop a clinical-radiomics nomogram based on deep learning techniques, preoperative magnetic resonance imaging (MRI) and clinical characteristics, enabling the accurate prediction of LNM in RC.

Materials and methods

Between January 2017 and May 2023, a total of 519 rectal cancer cases confirmed by pathological examination were retrospectively recruited from two tertiary hospitals. A total of 253 consecutive individuals were selected from Center I to create an automated MRI segmentation technique utilizing deep learning algorithms. The performance of the model was evaluated using the dice similarity coefficient (DSC), the 95th percentile Hausdorff distance (HD95), and the average surface distance (ASD). Subsequently, two external validation cohorts were established: one comprising 178 patients from center I (EVC1) and another consisting of 88 patients from center II (EVC2). The automatic segmentation provided radiomics features, which were then used to create a Radscore. A predictive nomogram integrating the Radscore and clinical parameters was constructed using multivariate logistic regression. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were employed to evaluate the discrimination capabilities of the Radscore, nomogram, and subjective evaluation model, respectively.

Results

The mean DSC, HD95 and ASD were 0.857 ± 0.041, 2.186 ± 0.956, and 0.562 ± 0.194 mm, respectively. The nomogram, which incorporates MR T-stage, CEA, CA19-9, and Radscore, exhibited a higher area under the ROC curve (AUC) compared to the Radscore and subjective evaluation in the training set (0.921 vs. 0.903 vs. 0.662). Similarly, in both external validation sets, the nomogram demonstrated a higher AUC than the Radscore and subjective evaluation (0.908 vs. 0.735 vs. 0.640, and 0.884 vs. 0.802 vs. 0.734).

Conclusion

The application of the deep learning method enables efficient automatic segmentation. The clinical-radiomics nomogram, utilizing preoperative MRI and automatic segmentation, proves to be an accurate method for assessing LNM in RC. This approach has the potential to enhance clinical decision-making and improve patient care.

Research registration unique identifying number UIN

Research registry, identifier 9158, https://www.researchregistry.com/browse-the-registry#home/registrationdetails/648e813efffa4e0028022796/.

Deep learning models for preoperative T-stage assessment in rectal cancer using MRI: exploring the impact of rectal filling

Background

The objective of this study was twofold: firstly, to develop a convolutional neural network (CNN) for automatic segmentation of rectal cancer (RC) lesions, and secondly, to construct classification models to differentiate between different T-stages of RC. Additionally, it was attempted to investigate the potential benefits of rectal filling in improving the performance of deep learning (DL) models.

Methods

A retrospective study was conducted, including 317 consecutive patients with RC who underwent MRI scans. The datasets were randomly divided into a training set (n = 265) and a test set (n = 52). Initially, an automatic segmentation model based on T2-weighted imaging (T2WI) was constructed using nn-UNet. The performance of the model was evaluated using the dice similarity coefficient (DSC), the 95th percentile Hausdorff distance (HD95), and the average surface distance (ASD). Subsequently, three types of DL-models were constructed: Model 1 trained on the total training dataset, Model 2 trained on the rectal-filling dataset, and Model 3 trained on the non-filling dataset. The diagnostic values were evaluated and compared using receiver operating characteristic (ROC) curve analysis, confusion matrix, net reclassification index (NRI), and decision curve analysis (DCA).

Results

The automatic segmentation showed excellent performance. The rectal-filling dataset exhibited superior results in terms of DSC and ASD (p = 0.006 and 0.017). The DL-models demonstrated significantly superior classification performance to the subjective evaluation in predicting T-stages for all test datasets (all p < 0.05). Among the models, Model 1 showcased the highest overall performance, with an area under the curve (AUC) of 0.958 and an accuracy of 0.962 in the filling test dataset.

Conclusion

This study highlighted the utility of DL-based automatic segmentation and classification models for preoperative T-stage assessment of RC on T2WI, particularly in the rectal-filling dataset. Compared with subjective evaluation, the models exhibited superior performance, suggesting their noticeable potential for enhancing clinical diagnosis and treatment practices.

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.

Deciphering gastric inflammation-induced tumorigenesis through multi-omics data and AI methods

Gastric cancer (GC), the fifth most common cancer globally, remains the leading cause of cancer deaths worldwide. Inflammation-induced tumorigenesis is the predominant process in GC development; therefore, systematic research in this area should improve understanding of the biological mechanisms that initiate GC development and promote cancer hallmarks. Here, we summarize biological knowledge regarding gastric inflammation-induced tumorigenesis, and characterize the multi-omics data and systems biology methods for investigating GC development. Of note, we highlight pioneering studies in multi-omics data and state-of-the-art network-based algorithms used for dissecting the features of gastric inflammation-induced tumorigenesis, and we propose translational applications in early GC warning biomarkers and precise treatment strategies. This review offers integrative insights for GC research, with the goal of paving the way to novel paradigms for GC precision oncology and prevention.

Assessing synchronous ovarian metastasis in gastric cancer patients using a clinical-radiomics nomogram based on baseline abdominal contrast-enhanced CT: a two-center study

BACKGROUND

To build and validate a radiomics nomogram based on preoperative CT scans and clinical data for detecting synchronous ovarian metastasis (SOM) in female gastric cancer (GC) cases.

METHODS

Pathologically confirmed GC cases in 2 cohorts were retrospectively enrolled. All cases had presurgical abdominal contrast-enhanced CT and pelvis contrast-enhanced MRI and pathological examinations for any suspicious ovarian lesions detected by MRI. Cohort 1 cases (n = 101) were included as the training set. Radiomics features were obtained to develop a radscore. A nomogram combining the radscore and clinical factors was built to detect SOM. The bootstrap method was carried out in cohort 1 as internal validation. External validation was carried out in cohort 2 (n = 46). Receiver operating characteristic (ROC) curve analysis, decision curve analysis (DCA) and the confusion matrix were utilized to assess the performances of the radscore, nomogram and subjective evaluation model.

RESULTS

The nomogram, which combined age and the radscore, displayed a higher AUC than the radscore and subjective evaluation (0.910 vs 0.827 vs 0.773) in the training cohort. In the external validation cohort, the nomogram also had a higher AUC than the radscore and subjective evaluation (0.850 vs 0.790 vs 0.675). DCA and the confusion matrix confirmed the nomogram was superior to the radscore in both cohorts.

CONCLUSIONS

This pilot study showed that a nomogram model combining the radscore and clinical characteristics is useful in detecting SOM in female GC cases. It may be applied to improve clinical treatment and is superior to subjective evaluation or the radscore alone.

Artificial Intelligence-Aided Optical Imaging for Cancer Theranostics

The use of artificial intelligence (AI) to assist biomedical imaging have demonstrated its high accuracy and high efficiency in medical decision-making for individualized cancer medicine. In particular, optical imaging methods are able to visualize both the structural and functional information of tumors tissues with high contrast, low cost, and noninvasive property. However, no systematic work has been performed to inspect the recent advances on AI-aided optical imaging for cancer theranostics. In this review, we demonstrated how AI can guide optical imaging methods to improve the accuracy on tumor detection, automated analysis and prediction of its histopathological section, its monitoring during treatment, and its prognosis by using computer vision, deep learning and natural language processing. By contrast, the optical imaging techniques involved mainly consisted of various tomography and microscopy imaging methods such as optical endoscopy imaging, optical coherence tomography, photoacoustic imaging, diffuse optical tomography, optical microscopy imaging, Raman imaging, and fluorescent imaging. Meanwhile, existing problems, possible challenges and future prospects for AI-aided optical imaging protocol for cancer theranostics were also discussed. It is expected that the present work can open a new avenue for precision oncology by using AI and optical imaging tools.

A CT-based radiomics signature for prediction of HER2 overexpression and treatment efficacy of trastuzumab in advanced gastric cancer

Background

Accurate evaluation of human epidermal growth factor receptor 2 (HER2) status is very important for appropriate management of advanced gastric cancer (AGC) patients. In this study, we aimed to develop and validate a computed tomography (CT)-based radiomics signature for preoperative prediction of HER2 overexpression and treatment efficacy of trastuzumab in AGC.

Methods

We retrospectively enrolled 536 consecutive AGC patients (median age, 59 years; interquartile range, 52-65 years; 377 male, 159 female) and separated them into a training set (n=357) and a testing set (n=179). Radiomic features were extracted from 3 different phase images of contrast-enhanced CT scans, and a radiomics signature was built based on highly reproducible features using the least absolute shrinkage and selection operator (LASSO) method. The predictive performance of the radiomics signature was assessed in the training and testing sets. Univariable and multivariable logistical regression analyses were used to identify independent risk factors of HER2 overexpression. Univariable and multivariable Cox regression analyses were used to identify the risk factors of overall survival (OS) and progression-free survival (PFS). The predictive value of the radiomics signature for treatment efficacy of trastuzumab was also evaluated.

Results

The radiomics signature comprised eight robust features that demonstrated good discrimination ability for HER2 overexpression in the training set [area under the curve (AUC) =0.85] and the testing set (AUC =0.81). Multivariable Cox regression analysis revealed that the radiomics signature was an independent risk factor for OS [hazard ratio (HR) =2.01, P=0.001] and PFS (HR =1.32, P=0.01). The radiomics score of patients who achieved disease control was significantly lower than that of patients with progressive disease (P=0.023).

Conclusions

The proposed radiomics signature showed favorable accuracy for prediction of HER2 overexpression and prognosis in AGC. It has promising potential as a noninvasive approach for selecting patients for target therapy.

Enhanced CT-based radiomics predicts pathological complete response after neoadjuvant chemotherapy for advanced adenocarcinoma of the esophagogastric junction: a two-center study

Purpose

This study aimed to develop and validate CT-based models to predict pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) for advanced adenocarcinoma of the esophagogastric junction (AEG).

Methods

Pre-NAC clinical and imaging data of AEG patients who underwent surgical resection after preoperative-NAC at two centers were retrospectively collected from November 2014 to September 2020. The dataset included training (n = 60) and external validation groups (n = 32). Three models, including CT-based radiomics, clinical and radiomics–clinical combined models, were established to differentiate pCR (tumor regression grade (TRG) = grade 0) and nonpCR (TRG = grade 1–3) patients. For the radiomics model, tumor-region-based radiomics features in the arterial and venous phases were extracted and selected. The naïve Bayes classifier was used to establish arterial- and venous-phase radiomics models. The selected candidate clinical factors were used to establish a clinical model, which was further incorporated into the radiomics–clinical combined model. ROC analysis, calibration and decision curves were used to assess the model performance.

Results

For the radiomics model, the AUC values obtained using the venous data were higher than those obtained using the arterial data (training: 0.751 vs. 0.736; validation: 0.768 vs. 0.750). Borrmann typing, tumor thickness and degree of differentiation were utilized to establish the clinical model (AUC-training: 0.753; AUC-validation: 0.848). The combination of arterial- and venous-phase radiomics and clinical factors further improved the discriminatory performance of the model (AUC-training: 0.838; AUC-validation: 0.902). The decision curve reflects the higher net benefit of the combined model.

Conclusion

The combination of CT imaging and clinical factors pre-NAC for advanced AEG could help stratify potential responsiveness to NAC.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-022-01273-w.

Establishing a cancer driver gene signature-based risk model for predicting the prognoses of gastric cancer patients

Despite the high prevalence of gastric cancer (GC), molecular biomarkers that can reliably detect GC are yet to be discovered. The present study aimed to establish a robust gene signature based on cancer driver genes (CDGs) that can predict GC prognosis. Transcriptional profiles and clinical data from GC patients were analyzed using univariate Cox regression analysis and the least absolute shrinkage and selection (LASSO)-penalized Cox regression analysis to select optimal prognosis-related genes for modeling. Time-dependent receiver operating characteristic (ROC) and Kaplan-Meier analyses were done to assess the predictive power of this gene signature. A nomogram model for prediction of survival of GC patients was established using the CDG signature and clinical information, and a seven-CDG signature was identified. Risk scores were calculated using this signature, and patients were subsequently divided into high- and low-risk groups; high-risk patients in the training and validation datasets had poorer prognoses than low-risk patients. Cox regression analysis revealed that the CDG signature is an independent prognostic factor for GC. The signature and other clinical features were used to construct a nomogram for predicting overall GC patient survival. Calibration and decision curve analysis showed that the nomogram accurately predicted survival, highlighting its clinical utility. Thus, we established a novel CDG signature and nomogram for predicting GC prognosis, which may facilitate personalized treatment of GC.