CT-based deep learning radiomics analysis for evaluation of serosa invasion in advanced gastric cancer

A Clinical-Radiomic Combined Model based on Dual-Layer Spectral CT for Predicting Pathological T4 in Gastric Cancer

RATIONALE AND OBJECTIVES

This study aimed to develop and validate a dual-layer spectral CT based clinical-radiomic model for pre-treatment prediction of pathological T4 (pT4) in gastric cancer (GC) patients.

MATERIALS AND METHODS

This retrospective study included 148 surgically confirmed GC patients who underwent dual-layer spectral CT scanning before surgery and were divided into a training (n=104) and test (n=44) cohorts. Subjective assessments were performed based on conventional 120-kV CT images by two readers. Clinical models were developed using patient demographics, serum tumor markers, and image features from CT scans. Radiomics model included features extracted from conventional 120-kV CT and dual-layer CT-derived spectral base image (SBI), such as virtual monoenergetic images (40 keV, 70 keV, 100 keV), iodine density (ID), effective atomic number (Zeff), and electron density (ED) images for both the arterial phase (AP) and portal venous phase (PVP). A clinical-radiomic combined model was developed and visualized using a nomogram.

RESULTS

Tumor thickness on CT and serum level of CA19-9 levels were identified as independent predictors. The clinical-radiomic combined model demonstrated superior performance compared to subjective image interpretation and other models, with an AUC of 0.906 (95% CI, 0.848-0.963) in the training cohort and 0.873 in the test cohort. The nomogram was significantly associated with pT4 status, supporting its potential utility in clinical prediction.

CONCLUSION

The integration of clinical characteristics with radiomic features from conventional CT and dual-layer CT-derived SBI achieved a high diagnostic accuracy for predicting pT4 in GC patients. This combined approach could assist in treatment planning and patient management in GC.

Radiomics analysis of dual-energy CT-derived iodine maps for differentiating between T1/2 and T3/4a in gastric cancer: A multicenter study

OBJECTIVE

To investigate the value of radiomic analysis of dual-energy CT (DECT)-derived iodine maps (IMs) for the differentiation between T1/2 and T3/4a stage tumors in gastric cancer (GC).

METHODS

A total of 263 patients who received upfront surgery and were pathologically confirmed with gastric adenocarcinoma were enrolled in this study. Dual-phase enhanced CT scans with gemstone spectral imaging (GSI) mode were performed within two weeks before surgery. 151 patients were retrospectively collected for the training (n = 105) and validation (n = 46) cohorts, and 112 patients were prospectively collected for the external test1 (n = 68) and external test2 (n = 44) cohorts. According to the postoperative pathological T stage, patients were classified into T1/2 and T3/4a stage groups. Clinical characteristics were recorded and quantitative iodine concentration (IC) of tumors was measured. Radiomics features were extracted from the venous phase (VP) IMs by three-dimensional region of interest (3D-ROI) segmentation. Feature selection was performed using the least absolute shrinkage and selection operator. Four machine learning algorithms, including random forest, logistic regression, naive Bayes, and support vector machine, were used to construct radiomics models. Finally, the most valuable clinical characteristics, DECT parameters, and the best radiomics model were combined to build a nomogram. The diagnostic performance of nomogram was evaluated by the area under receiver operating characteristic curve (AUC), calibration curve, and decision curve.

RESULTS

The nomogram combined tumor clinical T stage (cT), tumor thickness, venous-phase iodine concentration (ICVP), normalized arterial-phase iodine concentration (nICAP), and Radscore (derived from logistic regression model). This integrated model demonstrated favorable performance in the differentiation between T1/2 and T3/4a stage tumors in GC, with AUCs of 0.892 (95 %CI: 0.829-0.956), 0.846 (95 %CI: 0.734-0.958), 0.894 (95 %CI: 0.818-0.970) and 0.821 (95 %CI: 0.689-0.952) observed for the training, validation, external test 1, and external test 2 cohorts, respectively. Hosmer-Lemeshow test showed a good fit (all P > 0.05). Decision curves confirmed that the nomogram provided more net clinical benefit than the default simple strategy over a wide range of threshold probabilities.

CONCLUSION

We have developed and validated a multidimensional personalized nomogram that integrates a radiomics model based on DECT-derived IMs, DECT quantitative parameters, and traditional clinical features. The proposed model demonstrated favorable performance in preoperative identification of T3/4a stage tumors in GC.

The value of deep learning and radiomics models in predicting preoperative serosal invasion in gastric cancer: a dual-center study

PURPOSE

To establish and validate a model based on deep learning (DL), integrating radiomic features with relevant clinical features to generate nomogram, for predicting preoperative serosal invasion in gastric cancer (GC).

METHODS

This retrospective study included 335 patients from dual centers. T staging (T1-3 or T4) was used to assess serosal invasion. Radiomic features were extracted from primary GC lesions in the venous phase CT, and DL features from 8 transfer learning models were combined to create the Hand-crafted Radiomics and Deep Learning Radiomics (HCR-DLR) model. The Clinical (CL) model was built using clinical features, and both were combined into the Clinical and Radiomics Combined (CRC) model. In total, 15 predictive models were developed using 5 machine learning algorithms. The best-performing models were visualized as nomograms.

RESULTS

The total of 14 radiomic features, 13 DL features, and 2 clinical features were considered valuable through dimensionality reduction and selection. Among the constructed models: CRC model (AUC, training cohort: 0.9212; internal test cohort: 0.8743; external test cohort: 0.8853) than HCR-DLR model (AUC, training cohort: 0.8607; internal test cohort: 0.8543; external test cohort: 0.8824) and CL model (AUC, training cohort: 0.7632; internal test cohort: 0.7219; external test cohort: 0.7294) showed better performance. A nomogram based on the logistic CL model was drawn to facilitate the usage and showed its excellent predictive performance.

CONCLUSION

The predictive performance of the CRC Model, which integrates clinical features, radiomic features, and DL features, exhibits robust predictive capability and can serve as a simple, non-invasive, and practical tool for predicting the serosal invasion status of GC.

A Transfer Learning Radiomics Nomogram to Predict the Postoperative Recurrence of Advanced Gastric Cancer

BACKGROUND AND AIM

In this study, a transfer learning (TL) algorithm was used to predict postoperative recurrence of advanced gastric cancer (AGC) and to evaluate its value in a small-sample clinical study.

METHODS

A total of 431 cases of AGC from three centers were included in this retrospective study. First, TL signatures (TLSs) were constructed based on different source domains, including whole slide images (TLS-WSIs) and natural images (TLS-ImageNet). Clinical model and non-TLS based on CT images were constructed simultaneously. Second, TL radiomic model (TLRM) was constructed by combining optimal TLS and clinical factors. Finally, the performance of the models was evaluated by ROC analysis. The clinical utility of the models was assessed using integrated discriminant improvement (IDI) and decision curve analysis (DCA).

RESULTS

TLS-WSI significantly outperformed TLS-ImageNet, non-TLS, and clinical models (p < 0.05). The AUC value of TLS-WSI in training cohort was 0.9459 (95CI%: 0.9054, 0.9863) and ranged from 0.8050 (95CI%: 0.7130, 0.8969) to 0.8984 (95CI%: 0.8420, 0.9547) in validation cohorts. TLS-WSI and the nodular or irregular outer layer of gastric wall were screened to construct TLRM. The AUC value of TLRM in training cohort was 0.9643 (95CI%: 0.9349, 0.9936) and ranged from 0.8561 (95CI%: 0.7571, 0.9552) to 0.9195 (95CI%: 0.8670, 0.9721) in validation cohorts. The IDI and DCA showed that the performance of TLRM outperformed the other models.

CONCLUSION

TLS-WSI can be used to predict postoperative recurrence in AGC, whereas TLRM is more effective. TL can effectively improve the performance of clinical research models with a small sample size.

The application of artificial intelligence in upper gastrointestinal cancers

Upper gastrointestinal cancers, mainly comprising esophageal and gastric cancers, are among the most prevalent cancers worldwide. There are many new cases of upper gastrointestinal cancers annually, and the survival rate tends to be low. Therefore, timely screening, precise diagnosis, appropriate treatment strategies, and effective prognosis are crucial for patients with upper gastrointestinal cancers. In recent years, an increasing number of studies suggest that artificial intelligence (AI) technology can effectively address clinical tasks related to upper gastrointestinal cancers. These studies mainly focus on four aspects: screening, diagnosis, treatment, and prognosis. In this review, we focus on the application of AI technology in clinical tasks related to upper gastrointestinal cancers. Firstly, the basic application pipelines of radiomics and deep learning in medical image analysis were introduced. Furthermore, we separately reviewed the application of AI technology in the aforementioned aspects for both esophageal and gastric cancers. Finally, the current limitations and challenges faced in the field of upper gastrointestinal cancers were summarized, and explorations were conducted on the selection of AI algorithms in various scenarios, the popularization of early screening, the clinical applications of AI, and large multimodal models.

Transformative artificial intelligence in gastric cancer: Advancements in diagnostic techniques

Gastric cancer represents a significant global health challenge with elevated incidence and mortality rates, highlighting the need for advancements in diagnostic and therapeutic strategies. This review paper addresses the critical need for a thorough synthesis of the role of artificial intelligence (AI) in the management of gastric cancer. It provides an in-depth analysis of current AI applications, focusing on their contributions to early diagnosis, treatment planning, and outcome prediction. The review identifies key gaps and limitations in the existing literature by examining recent studies and technological developments. It aims to clarify the evolution of AI-driven methods and their impact on enhancing diagnostic accuracy, personalizing treatment strategies, and improving patient outcomes. The paper emphasizes the transformative potential of AI in overcoming the challenges associated with gastric cancer management and proposes future research directions to further harness AI's capabilities. Through this synthesis, the review underscores the importance of integrating AI technologies into clinical practice to revolutionize gastric cancer management.

Deep learning nomogram for predicting neoadjuvant chemotherapy response in locally advanced gastric cancer patients

PURPOSE

Developed and validated a deep learning radiomics nomogram using multi-phase contrast-enhanced computed tomography (CECT) images to predict neoadjuvant chemotherapy (NAC) response in locally advanced gastric cancer (LAGC) patients.

METHODS

This multi-center study retrospectively included 322 patients diagnosed with gastric cancer from January 2013 to June 2023 at two hospitals. Handcrafted radiomics technique and the EfficientNet V2 neural network were applied to arterial, portal venous, and delayed phase CT images to extract two-dimensional handcrafted and deep learning features. A nomogram model was built by integrating the handcrafted signature, the deep learning signature, with clinical features. Discriminative ability was assessed using the receiver operating characteristics (ROC) curve and the precision-recall (P-R) curve. Model fitting was evaluated using calibration curves, and clinical utility was assessed through decision curve analysis (DCA).

RESULTS

The nomogram exhibited excellent performance. The area under the ROC curve (AUC) was 0.848 [95% confidence interval (CI), 0.793-0.893)], 0.802 (95% CI 0.688-0.889), and 0.751 (95% CI 0.652-0.833) for the training, internal validation, and external validation sets, respectively. The AUCs of the P-R curves were 0.838 (95% CI 0.756-0.895), 0.541 (95% CI 0.329-0.740), and 0.556 (95% CI 0.376-0.722) for the corresponding sets. The nomogram outperformed the clinical model and handcrafted signature across all sets (all P < 0.05). The nomogram model demonstrated good calibration and provided greater net benefit within the relevant threshold range compared to other models.

CONCLUSION

This study created a deep learning nomogram using CECT images and clinical data to predict NAC response in LAGC patients undergoing surgical resection, offering personalized treatment insights.

Development and Validation of a Computed Tomography-Based Model for Noninvasive Prediction of the T Stage in Gastric Cancer: Multicenter Retrospective Study

BACKGROUND

As part of the TNM (tumor-node-metastasis) staging system, T staging based on tumor depth is crucial for developing treatment plans. Previous studies have constructed a deep learning model based on computed tomographic (CT) radiomic signatures to predict the number of lymph node metastases and survival in patients with resected gastric cancer (GC). However, few studies have reported the combination of deep learning and radiomics in predicting T staging in GC.

OBJECTIVE

This study aimed to develop a CT-based model for automatic prediction of the T stage of GC via radiomics and deep learning.

METHODS

A total of 771 GC patients from 3 centers were retrospectively enrolled and divided into training, validation, and testing cohorts. Patients with GC were classified into mild (stage T1 and T2), moderate (stage T3), and severe (stage T4) groups. Three predictive models based on the labeled CT images were constructed using the radiomics features (radiomics model), deep features (deep learning model), and a combination of both (hybrid model).

RESULTS

The overall classification accuracy of the radiomics model was 64.3% in the internal testing data set. The deep learning model and hybrid model showed better performance than the radiomics model, with overall classification accuracies of 75.7% (P=.04) and 81.4% (P=.001), respectively. On the subtasks of binary classification of tumor severity, the areas under the curve of the radiomics, deep learning, and hybrid models were 0.875, 0.866, and 0.886 in the internal testing data set and 0.820, 0.818, and 0.972 in the external testing data set, respectively, for differentiating mild (stage T1~T2) from nonmild (stage T3~T4) patients, and were 0.815, 0.892, and 0.894 in the internal testing data set and 0.685, 0.808, and 0.897 in the external testing data set, respectively, for differentiating nonsevere (stage T1~T3) from severe (stage T4) patients.

CONCLUSIONS

The hybrid model integrating radiomics features and deep features showed favorable performance in diagnosing the pathological stage of GC.

Research Progress of Artificial Intelligence in the Grading and Classification of Meningiomas

A meningioma is a common primary central nervous system tumor. The histological features of meningiomas vary significantly depending on the grade and subtype, leading to differences in treatment and prognosis. Therefore, early diagnosis, grading, and typing of meningiomas are crucial for developing comprehensive and individualized diagnosis and treatment plans. The advancement of artificial intelligence (AI) in medical imaging, particularly radiomics and deep learning (DL), has contributed to the increasing research on meningioma grading and classification. These techniques are fast and accurate, involve fully automated learning, are non-invasive and objective, enable the efficient and non-invasive prediction of meningioma grades and classifications, and provide valuable assistance in clinical treatment and prognosis. This article provides a summary and analysis of the research progress in radiomics and DL for meningioma grading and classification. It also highlights the existing research findings, limitations, and suggestions for future improvement, aiming to facilitate the future application of AI in the diagnosis and treatment of meningioma.

Intratumoral and peritumoral radiomics predict pathological response after neoadjuvant chemotherapy against advanced gastric cancer

BACKGROUND

To investigate whether intratumoral and peritumoral radiomics may predict pathological responses after neoadjuvant chemotherapy against advanced gastric cancer.

METHODS

Clinical, pathological, and CT data from 231 patients with advanced gastric cancer who underwent neoadjuvant chemotherapy at our hospital between July 2014 and February 2022 were retrospectively collected. Patients were randomly divided into a training group (n = 161) and a validation group (n = 70). The support vector machine classifier was used to establish radiomics models. A clinical model was established based on the selected clinical indicators. Finally, the radiomics and clinical models were combined to generate a radiomics-clinical model. ROC analyses were used to evaluate the prediction efficiency for each model. Calibration curves and decision curves were used to evaluate the optimal model.

RESULTS

A total of 91 cases were recorded with good response and 140 with poor response. The radiomics model demonstrated that the AUC was higher in the combined model than in the intratumoral and peritumoral models (training group: 0.949, 0.943, and 0.846, respectively; validation group: 0.815, 0.778, and 0.701, respectively). Age, Borrmann classification, and Lauren classification were used to construct the clinical model. Among the radiomics-clinical models, the combined-clinical model showed the highest AUC (training group: 0.960; validation group: 0.843), which significantly improved prediction efficiency.

CONCLUSION

The peritumoral model provided additional value in the evaluation of pathological response after neoadjuvant chemotherapy against advanced gastric cancer, and the combined-clinical model showed the highest predictive efficiency.

CRITICAL RELEVANCE STATEMENT

Intratumoral and peritumoral radiomics can noninvasively predict the pathological response against advanced gastric cancer after neoadjuvant chemotherapy to guide early treatment decision and provide individual treatment for patients.

KEY POINTS

1. Radiomics can predict pathological responses after neoadjuvant chemotherapy against advanced gastric cancer. 2. Peritumoral radiomics has additional predictive value. 3. Radiomics-clinical models can guide early treatment decisions and improve patient prognosis.

Deep learning-based radiomics model can predict extranodal soft tissue metastasis in gastric cancer

BACKGROUND

The potential prognostic value of extranodal soft tissue metastasis (ESTM) has been confirmed by increasing studies about gastric cancer (GC). However, the gold standard of ESTM is determined by pathologic examination after surgery, and there are no preoperative methods for assessment of ESTM yet.

PURPOSE

This multicenter study aimed to develop a deep learning-based radiomics model to preoperatively identify ESTM and evaluate its prognostic value.

METHODS

A total of 959 GC patients were enrolled from two centers and split into a training cohort (N = 551) and a test cohort (N = 236) for ESTM evaluation. Additionally, an external survival cohort (N = 172) was included for prognostic analysis. Four models were established based on clinical characteristics and multiphase computed tomography (CT) images for preoperative identification of ESTM, including a deep learning model, a hand-crafted radiomic model, a clinical model, and a combined model. C-index, decision curve, and calibration curve were utilized to assess the model performances. Survival analysis was conducted to explore the ability of stratifying overall survival (OS).

RESULTS

The combined model showed good discrimination of the ESTM [C-indices (95% confidence interval, CI): 0.770 (0.729-0.812) and 0.761 (0.718-0.805) in training and test cohorts respectively], which outperformed deep learning model, radiomics model, and clinical model. The stratified analysis showed this model was not affected by patient's tumor size, the presence of lymphovascular invasion, and Lauren classification (p < 0.05). Moreover, the model score showed strong consistency with the OS [C-indices (95%CI): 0.723 (0.658-0.789, p < 0.0001) in the internal survival cohort and 0.715 (0.650-0.779, p < 0.0001) in the external survival cohort]. More interestingly, univariate analysis showed the model score was significantly associated with occult distant metastasis (p < 0.05) that was missed by preoperative diagnosis.

CONCLUSIONS

The model combining CT images and clinical characteristics had an impressive predictive ability of both ESTM and prognosis, which has the potential to serve as an effective complement to the preoperative TNM staging system.

Multiparametric MRI-based model for prediction of local progression of hepatocellular carcinoma after thermal ablation

PURPOSE

To develop a deep learning radiomics of multiparametric magnetic resonance imaging (DLRMM)-based model that incorporates preoperative and postoperative signatures for prediction of local tumor progression (LTP) after thermal ablation (TA) in hepatocellular carcinoma (HCC).

METHODS

From May 2017 to October 2021, 417 eligible patients with HCC were retrospectively enrolled from three hospitals (one primary cohort [PC, n = 189] and two external test cohorts [ETCs][n = 135, 93]). DLRMM features were extracted from T1WI + C, T2WI, and DWI using ResNet18 model. An integrative model incorporating the DLRMM signature with clinicopathologic variables were further built to LTP risk stratification. The performance of these models were compared by areas under receiver operating characteristic curve (AUC) using DeLong test.

RESULTS

A total of 1668 subsequences and 31,536 multiparametric MRI slice including T1WI, T2WI, and DWI were collected simultaneously. The DLRMM signatures were extracted from tumor and ablation zone, respectively. Ablative margin, multiple tumors, and tumor abutting major vessels were regarded as risk factors for LTP in clinical model. The AUC of DLRMM model were 0.864 in PC, 0.843 in ETC1, and 0.858 in ETC2, which was higher significantly than those in clinical model (p < 0.001). After integrating clinical variable, DLRMM model obtained significant improvement with AUC of 0.870-0.869 in three cohorts (all, p < 0.001), which can provide the risk stratification for overall survival of HCC patients.

CONCLUSIONS

The DLRMM model is essential to identify LTP risk of HCC patients who underwent TA and may potentially benefit personalized decision-making.

Combined Cerebrospinal Fluid Hydrodynamics and Fourth Ventricle Outlet Morphology to Improve Predictive Efficiency of Prognosis for Chiari Malformation Type I Decompression

OBJECTIVE

To identify the morphological characteristics together with cerebrospinal fluid (CSF) hydrodynamics on preoperative magnetic resonance imaging that improve the prediction of foramen magnum decompression (FMD) treatment outcome for Chiari malformations type I (CM-I) patients compared with the CSF hydrodynamics-based model.

METHODS

This retrospective study included CM-I patients who underwent FMD, phase-contrast cine magnetic resonance, and static MR between January 2018 and March 2022. The relationships of the preoperative CSF hydrodynamic quantifications derived from phase-contrast cine magnetic resonance and morphological measurements from static magnetic resonance imaging, clinical indicators with different outcomes, were analyzed with logistic regression analysis. The outcomes were determined using the Chicago Chiari Outcome Scale. The predictive performance was evaluated with receiver operating characteristic, calibration, decision curves and area under the receiver operating characteristic curve, net reclassification index, and integrated discrimination improvement and was compared with CSF hydrodynamics-based model.

RESULTS

A total of 27 patients were included. 17 (63%) had improved outcomes and 10 (37%) had poor outcomes. The peak diastolic velocity of the aqueduct midportion (odd ratio, 5.17; 95% confidence interval: 1.08, 24.70; P = 0.039) and the fourth ventricle outlet diameter (odd ratio, 7.17; 95% confidence interval: 1.07, 48.16; P = 0.043) were predictors of different prognoses. The predictive performance improved significantly than the CSF hydrodynamics-based model.

CONCLUSIONS

Combined CSF hydrodynamic and static morphologic MR measurements can better predict the response to FMD. A higher peak diastolic velocity of the aqueduct midportion and broader fourth ventricle outlet were associated with satisfying outcomes after decompression in CM-I patients.

Artificial Intelligence in Gastric Cancer Imaging With Emphasis on Diagnostic Imaging and Body Morphometry

Gastric cancer remains a significant global health concern, coercing the need for advancements in imaging techniques for ensuring accurate diagnosis and effective treatment planning. Artificial intelligence (AI) has emerged as a potent tool for gastric-cancer imaging, particularly for diagnostic imaging and body morphometry. This review article offers a comprehensive overview of the recent developments and applications of AI in gastric cancer imaging. We investigated the role of AI imaging in gastric cancer diagnosis and staging, showcasing its potential to enhance the accuracy and efficiency of these crucial aspects of patient management. Additionally, we explored the application of AI body morphometry specifically for assessing the clinical impact of gastrectomy. This aspect of AI utilization holds significant promise for understanding postoperative changes and optimizing patient outcomes. Furthermore, we examine the current state of AI techniques for the prognosis of patients with gastric cancer. These prognostic models leverage AI algorithms to predict long-term survival outcomes and assist clinicians in making informed treatment decisions. However, the implementation of AI techniques for gastric cancer imaging has several limitations. As AI continues to evolve, we hope to witness the translation of cutting-edge technologies into routine clinical practice, ultimately improving patient care and outcomes in the fight against gastric cancer.

Deep learning for diagnosis of malign pleural effusion on computed tomography images

BACKGROUND

The pleura is a serous membrane that surrounds the lungs. The visceral surface secretes fluid into the serous cavity and the parietal surface ensures a regular absorption of this fluid. If this balance is disturbed, fluid accumulation occurs in the pleural space called "Pleural Effusion". Today, accurate diagnosis of pleural diseases is becoming more critical, as advances in treatment protocols have contributed positively to prognosis. Our aim is to perform computer-aided numerical analysis of Computed Tomography (CT) images from patients showing pleural effusion images on CT and to examine the prediction of malignant/benign distinction using deep learning by comparing with the cytology results.

METHODS

The authors classified 408 CT images from 64 patients whose etiology of pleural effusion was investigated using the deep learning method. 378 of the images were used for the training of the system; 15 malignant and 15 benign CT images, which were not included in the training group, were used as the test.

RESULTS

Among the 30 test images evaluated in the system; 14 of 15 malignant patients and 13 of 15 benign patients were estimated with correct diagnosis (PPD: 93.3%, NPD: 86.67%, Sensitivity: 87.5%, Specificity: 92.86%).

CONCLUSION

Advances in computer-aided diagnostic analysis of CT images and obtaining a pre-diagnosis of pleural fluid may reduce the need for interventional procedures by guiding physicians about which patients may have malignancies. Thus, it is cost and time-saving in patient management, allowing earlier diagnosis and treatment.

The Applications of Artificial Intelligence in Digestive System Neoplasms: A Review

Importance

Digestive system neoplasms (DSNs) are the leading cause of cancer-related mortality with a 5-year survival rate of less than 20%. Subjective evaluation of medical images including endoscopic images, whole slide images, computed tomography images, and magnetic resonance images plays a vital role in the clinical practice of DSNs, but with limited performance and increased workload of radiologists or pathologists. The application of artificial intelligence (AI) in medical image analysis holds promise to augment the visual interpretation of medical images, which could not only automate the complicated evaluation process but also convert medical images into quantitative imaging features that associated with tumor heterogeneity.

Highlights

We briefly introduce the methodology of AI for medical image analysis and then review its clinical applications including clinical auxiliary diagnosis, assessment of treatment response, and prognosis prediction on 4 typical DSNs including esophageal cancer, gastric cancer, colorectal cancer, and hepatocellular carcinoma.

Conclusion

AI technology has great potential in supporting the clinical diagnosis and treatment decision-making of DSNs. Several technical issues should be overcome before its application into clinical practice of DSNs.

Does radiomics play a role in the diagnosis, staging and re-staging of gastroesophageal junction adenocarcinoma?

Radiomics is an emerging field of investigation in medicine consisting in the extraction of quantitative features from conventional medical images and exploring their potentials in improving diagnosis, prognosis and outcome prediction after therapy. Clinical applications are still limited, mostly due to reproducibility and repeatability issues as well as to limited interpretability of predictive radiomic-based features/signatures. In the specific case of gastroesophageal junction (GEJ) adenocarcinoma, the expectancies are particularly high, mainly due to its increasing incidence and to the limited performance of conventional imaging techniques in assessing correct diagnosis and accurate pre-surgical tumor characterization. Accordingly, current literature was reviewed, emphasizing the methodological quality. In addition, papers were scored according to the Radiomic Quality Score (RQS), weighting more the clinical applicability and generalizability of the resulting models. According to the criteria of the search, only two papers were retained: the resulting technical quality was relatively high for both, while the corresponding RQS were 15 and 19 (on a scale of 31). Although the potentials of radiomics in the setting of GEJ adenocarcinoma are relevant, they remain largely unexplored, warranting an urgent need of high-quality, possibly prospective, multicenter studies.

The clinical value of dual-energy CT imaging in preoperative evaluation of pathological types of gastric cancer

BACKGROUND

Gastric cancer (GC) is the fifth most common cancer worldwide and the third leading cause of cancer death. Due to the low rate of early diagnosis, most patients are already in the advanced stage and lose the chance of radical surgery.

OBJECTIVE

To investigate the clinical value of computed tomography (CT) dual-energy imaging in preoperative evaluation of pathological types of gastric cancer patients.

METHODS

121 patients with gastric cancer were selected. Dual-energy CT imaging was performed on the patients. The CT values of virtual noncontrast (VNC) images and iodine concentration of the lesion were measured, and the standardized iodine concentration ratio was calculated. The iodine concentration, iodine concentration ratio and CT values of VNC images of different pathological types were analyzed and compared.

RESULTS

The iodine concentration and iodine concentration ratio of gastric mucinous carcinoma patients in venous phase and parenchymal phase were lower than those of gastric non-mucinous carcinoma patients, and the differences were statistically significant (P< 0.05). The iodine concentration and iodine concentration ratio of patients with mucinous adenocarcinoma in venous phase and parenchymal phase were lower than those of patients with choriocarcinoma, and the differences were statistically significant (P< 0.05). The iodine concentration and iodine concentration ratio of middle and high differentiated adenocarcinoma patients in venous phase and parenchymal phase were lower than those of low differentiated adenocarcinoma patients, and the differences were statistically significant (P< 0.05). However, there was no significant difference in CT values of VNC images among venous, arterial, and parenchymal phases in all pathological types of gastric cancer patients (P> 0.05).

CONCLUSION

Dual-energy CT imaging plays an important role in the preoperative evaluation of patients with gastric cancer. The pathological types of gastric cancer are different, and the iodine concentration will change accordingly. Dual-energy CT imaging can effectively evaluate the pathological types of gastric cancer and has high clinical application value.

Are radiomic spleen features useful for assessing the differentiation status of advanced gastric cancer?

Background

The differentiation status of gastric cancer is related to clinical stage, treatment and prognosis. It is expected to establish a radiomic model based on the combination of gastric cancer and spleen to predict the differentiation degree of gastric cancer. Thus, we aim to determine whether radiomic spleen features can be used to distinguish advanced gastric cancer with varying states of differentiation.

Materials and methods

January 2019 to January 2021, we retrospectively analyzed 147 patients with advanced gastric cancer confirmed by pathology. The clinical data were reviewed and analyzed. Three radiomics predictive models were built from radiomics features based on gastric cancer (GC), spleen (SP) and combination of two organ position (GC+SP) images. Then, three Radscores (GC, SP and GC+SP) were obtained. A nomogram was developed to predict differentiation statue by incorporating GC+SP Radscore and clinical risk factors. The area under the curve (AUC) of operating characteristics (ROC) and calibration curves were assessed to evaluate the differential performance of radiomic models based on gastric cancer and spleen for advanced gastric cancer with different states of differentiation (poorly differentiated group and non- poorly differentiated group).

Results

There were 147 patients evaluated (mean age, 60 years ± 11SD, 111 men). Univariate and multivariate logistic analysis identified three clinical features (age, cTNM stage and CT attenuation of spleen arterial phase) were independent risk factors for the degree of differentiation of GC (p =0.004,0.000,0.020, respectively). The clinical radiomics (namely, GC+SP+Clin) model showed powerful prognostic ability in the training and test cohorts with AUCs of 0.97 and 0.91, respectively. The established model has the best clinical benefit in diagnosing GC differentiation.

Conclusion

By combining radiomic features (GC and spleen) with clinical risk factors, we develop a radiomic nomogram to predict differentiation status in patients with AGC, which can be used to guide treatment decisions.

Deep learning based radiomics for gastrointestinal cancer diagnosis and treatment: A minireview

Gastrointestinal (GI) cancers are the major cause of cancer-related mortality globally. Medical imaging is an important auxiliary means for the diagnosis, assessment and prognostic prediction of GI cancers. Radiomics is an emerging and effective technology to decipher the encoded information within medical images, and traditional machine learning is the most commonly used tool. Recent advances in deep learning technology have further promoted the development of radiomics. In the field of GI cancer, although there are several surveys on radiomics, there is no specific review on the application of deep-learning-based radiomics (DLR). In this review, a search was conducted on Web of Science, PubMed, and Google Scholar with an emphasis on the application of DLR for GI cancers, including esophageal, gastric, liver, pancreatic, and colorectal cancers. Besides, the challenges and recommendations based on the findings of the review are comprehensively analyzed to advance DLR.

Clinical-Radiomics Nomogram from T1W, T1CE, and T2FS MRI for Improving Diagnosis of Soft-Tissue Sarcoma

PURPOSE

To compare values of multiparametric magnetic resonance imaging (MRI) sequences and propose clinical-radiomics nomogram for diagnosis of soft-tissue sarcoma (STS).

PROCEDURES

This study enrolled 148 patients from Dec. 2017 to Feb. 2021. All patients underwent T1-weighted (T1W), contrast-enhanced T1-weighted (T1CE), and T2-weighted fat-suppressed (T2FS) MRI scans. A total of 1967 radiomic features were extracted from the segmented regions of interest (ROIs) in each MRI sequence. Highly diagnostic radiomic features were selected with Mann-Whitney U test, elastic net, and Akaike's information criterion (AIC) based on MRI images. Logistical regression was used to build Rad scores. Clinical factors were analyzed using the chi-square test or Mann-Whitney U test. The performance of the Rad scores was judged using the area under the receiver operating characteristic area under the curve (ROC AUC), sensitivity, specificity, and accuracy. The nomogram was developed by integrating the Rad score and the most important clinical factor.

RESULTS

By combining the three MRI sequences, the Rad-Com was developed consisting of twelve features selected by with Mann-Whitney U test, elastic net, and AIC: four from T1W, three from TICE, and five from T2FS MRI. The margin (P < 0.05) demonstrated a statistically significant difference between patients with benign and malignant soft-tissue tumors (STT). The nomogram was constructed by integrating the Rad-Com and margin, which yielded favorable diagnostic AUCs of 0.919 (sensitivity (Sen) = 0.784, specificity (Spe) = 0.936) and 0.913 (Sen = 0.923, Spe = 0.792) in the training and validation cohort.

CONCLUSION

The proposed nomogram may have potential as a noninvasive marker for STS diagnosis.

Artificial intelligence in gastric cancer: applications and challenges

Gastric cancer (GC) is one of the most common malignant tumors with high mortality. Accurate diagnosis and treatment decisions for GC rely heavily on human experts' careful judgments on medical images. However, the improvement of the accuracy is hindered by imaging conditions, limited experience, objective criteria, and inter-observer discrepancies. Recently, the developments of machine learning, especially deep-learning algorithms, have been facilitating computers to extract more information from data automatically. Researchers are exploring the far-reaching applications of artificial intelligence (AI) in various clinical practices, including GC. Herein, we aim to provide a broad framework to summarize current research on AI in GC. In the screening of GC, AI can identify precancerous diseases and assist in early cancer detection with endoscopic examination and pathological confirmation. In the diagnosis of GC, AI can support tumor-node-metastasis (TNM) staging and subtype classification. For treatment decisions, AI can help with surgical margin determination and prognosis prediction. Meanwhile, current approaches are challenged by data scarcity and poor interpretability. To tackle these problems, more regulated data, unified processing procedures, and advanced algorithms are urgently needed to build more accurate and robust AI models for GC.

Deep learning magnetic resonance imaging predicts platinum sensitivity in patients with epithelial ovarian cancer

OBJECTIVE

The aim of the study is to develop and validate a deep learning model to predict the platinum sensitivity of patients with epithelial ovarian cancer (EOC) based on contrast-enhanced magnetic resonance imaging (MRI).

METHODS

In this retrospective study, 93 patients with EOC who received platinum-based chemotherapy (≥4 cycles) and debulking surgery at the Sun Yat-sen Memorial Hospital from January 2011 to January 2020 were enrolled and randomly assigned to the training and validation cohorts (2:1). Two different models were built based on either the primary tumor or whole volume of the abdomen as the volume of interest (VOI) within the same cohorts, and then a pre-trained convolutional neural network Med3D (Resnet 10 version) was transferred to automatically extract 1,024 features from two MRI sequences (CE-T1WI and T2WI) of each patient to predict platinum sensitivity. The performance of the two models was compared.

RESULTS

A total of 93 women (mean age, 50.5 years ± 10.5 [standard deviation]) were evaluated (62 in the training cohort and 31 in the validation cohort). The AUCs of the whole abdomen model were 0.97 and 0.98 for the training and validation cohorts, respectively, which was better than the primary tumor model (AUCs of 0.88 and 0.81 in the training and validation cohorts, respectively). In k-fold cross-validation and stratified analysis, the whole abdomen model maintained a stable performance, and the decision function value generated by the model was a prognostic indicator that successfully discriminates high- and low-risk recurrence patients.

CONCLUSION

The non-manually segmented whole-abdomen deep learning model based on MRI exhibited satisfactory predictive performance for platinum sensitivity and may assist gynecologists in making optimal treatment decisions.

Deep learning radiomics of ultrasonography for differentiating sclerosing adenosis from breast cancer

OBJECTIVES: The purpose of our study is to present a method combining radiomics with deep learning and clinical data for improved differential diagnosis of sclerosing adenosis (SA)and breast cancer (BC). METHODS: A total of 97 patients with SA and 100 patients with BC were included in this study. The best model for classification was selected from among four different convolutional neural network (CNN) models, including Vgg16, Resnet18, Resnet50, and Desenet121. The intra-/inter-class correlation coefficient and least absolute shrinkage and selection operator method were used for radiomics feature selection. The clinical features selected were patient age and nodule size. The overall accuracy, sensitivity, specificity, Youden index, positive predictive value, negative predictive value, and area under curve (AUC) value were calculated for comparison of diagnostic efficacy. RESULTS: All the CNN models combined with radiomics and clinical data were significantly superior to CNN models only. The Desenet121+radiomics+clinical data model showed the best classification performance with an accuracy of 86.80%, sensitivity of 87.60%, specificity of 86.20% and AUC of 0.915, which was better than that of the CNN model only, which had an accuracy of 85.23%, sensitivity of 85.48%, specificity of 85.02%, and AUC of 0.870. In comparison, the diagnostic accuracy, sensitivity, specificity, and AUC value for breast radiologists were 72.08%, 100%, 43.30%, and 0.716, respectively. CONCLUSIONS: A combination of the CNN-radiomics model and clinical data could be a helpful auxiliary diagnostic tool for distinguishing between SA and BC.

Evaluation of the Design of "Shape" and "Meaning" of Book Binding from the Perspective of Deep Learning

Book binding is the procedure of manually accumulating a book in codex format from a well-ordered pile of paper sheets, which are folded together into sections or occasionally left as a stack of individual sheets. The books undergo binding into different shapes and sizes. Numerous kinds of book bindings are available, each of which comes with its own merits and demerits. Some of them are highly durable, some of them are light-weight, and some of them are attractive. Therefore, it is needed to effectively identify and classify the shape and type of book bindings. With this motivation, this paper develops a butterfly optimization algorithm with a deep learning-enabled book binding classification (BOADL-BBC) model. The major intention of the BOADL-BBC technique is to identify and categorise three different types of book bindings from the input images, namely, hard binding, soft binding, and long-stitch binding. The proposed BOADL-BBC technique initially employs a DL-based Inception v3 model to derive useful feature vectors from the images. For effective classification of book bindings, the BOA with wavelet kernel extreme learning machine (WKELM) model can be applied. The weight and bias values involved in the WKELM model can be effectively adjusted by the use of BOA for book binding classification shows the novelty of the work. To ensure the enhanced performance of the BOADL-BBC technique, a series of simulations were carried out using a set of images that people collected on their own. The experimental results stated that the BOADL-BBC technique has obtained a maximum book binding classification accuracy of 95.56%.

Diagnosis of Serosal Invasion in Gastric Adenocarcinoma by Dual-Energy CT Radiomics: Focusing on Localized Gastric Wall and Peritumoral Radiomics Features

Objectives

To build a radiomics model and combined model based on dual-energy CT (DECT) for diagnosing serosal invasion in gastric adenocarcinoma.

Materials and methods

231 gastric adenocarcinoma patients were enrolled and randomly divided into a training (n = 132), testing (n = 58), and independent validation (n = 41) cohort. Radiomics features were extracted from the rectangular ROI of the 120-kV equivalent mixed images and iodine map (IM) images in the venous phase of DECT, which was manually delineated perpendicularly to the gastric wall in the deepest location of tumor infiltration, including the peritumoral adipose tissue within 5 mm outside the serosa. The random forest algorithm was used for radiomics model construction. Traditional features were collected by two radiologists. Univariate and multivariate logistic regression was used to construct the clinical model and combined model. The diagnostic efficacy of the models was evaluated using ROC curve analysis and compared using the Delong's test. The calibration curves were used to evaluate the calibration performance of the combined model.

Results

Both the radiomics model and combined model showed high efficacy in diagnosing serosal invasion in the training, testing and independent validation cohort, with AUC of 0.90, 0.90, and 0.85 for radiomics model; 0.93, 0.93, and 0.89 for combined model. The combined model outperformed the clinical model (AUC: 0.76, 0.76 and 0.81).

Conclusion

The radiomics model and combined model constructed based on tumoral and peritumoral radiomics features derived from DECT showed high diagnostic efficacy for serosal invasion in gastric adenocarcinoma.

Development and Validation of Multivariate Models Integrating Preoperative Clinicopathological Parameters and Radiographic Findings Based on Late Arterial Phase CT Images for Predicting Lymph Node Metastasis in Gastric Cancer

RATIONALE AND OBJECTIVES

To develop and validate multivariate models integrating endoscopic biopsy, tumor markers, computed tomography (CT) morphological characteristics based on late arterial phase (LAP), and CT value-related and texture parameters to predict lymph node (LN) metastasis in gastric cancers (GCs).

MATERIALS AND METHODS

The preoperative differentiation degree based on biopsy, 6 tumor markers, 8 CT morphological characteristics based on LAP, 18 CT value-related parameters, and 35 CT texture parameters of 163 patients (111 men and 52 women) with GC were analyzed retrospectively. The differences in parameters between N (-) and N (+) GCs were analyzed by the Mann-Whitney U test. Diagnostic performance was obtained by receiver operating characteristic (ROC) curve analysis. Multivariate models based on regression analysis and machine learning algorithms were performed to improve diagnostic efficacy.

RESULTS

The differentiation degree, carbohydrate antigen (CA) 199 and CA242, 5 CT morphological characteristics, and 22 CT texture parameters showed significant differences between N (-) and N (+) GCs in the primary cohort (all p < 0.05). The multivariate model integrating clinicopathological parameters and radiographic findings based on regression analysis achieved areas under the ROC curve (AUCs) of 0.936 and 0.912 in the primary and validation cohorts, respectively. The model generated by the support vector machine algorithm achieved AUCs of 0.914 and 0.948, respectively.

CONCLUSION

We developed and validated multivariate models integrating endoscopic biopsy, tumor markers, CT morphological characteristics based on LAP, and CT texture parameters to predict LN metastasis in GCs and achieved satisfactory performance.

Machine Learning for Future Subtyping of the Tumor Microenvironment of Gastro-Esophageal Adenocarcinomas

Tumor progression involves an intricate interplay between malignant cells and their surrounding tumor microenvironment (TME) at specific sites. The TME is dynamic and is composed of stromal, parenchymal, and immune cells, which mediate cancer progression and therapy resistance. Evidence from preclinical and clinical studies revealed that TME targeting and reprogramming can be a promising approach to achieve anti-tumor effects in several cancers, including in GEA. Thus, it is of great interest to use modern technology to understand the relevant components of programming the TME. Here, we discuss the approach of machine learning, which recently gained increasing interest recently because of its ability to measure tumor parameters at the cellular level, reveal global features of relevance, and generate prognostic models. In this review, we discuss the relevant stromal composition of the TME in GEAs and discuss how they could be integrated. We also review the current progress in the application of machine learning in different medical disciplines that are relevant for the management and study of GEA.

Radiomics as a New Frontier of Imaging for Cancer Prognosis: A Narrative Review

The evaluation of the efficacy of different therapies is of paramount importance for the patients and the clinicians in oncology, and it is usually possible by performing imaging investigations that are interpreted, taking in consideration different response evaluation criteria. In the last decade, texture analysis (TA) has been developed in order to help the radiologist to quantify and identify parameters related to tumor heterogeneity, which cannot be appreciated by the naked eye, that can be correlated with different endpoints, including cancer prognosis. The aim of this work is to analyze the impact of texture in the prediction of response and in prognosis stratification in oncology, taking into consideration different pathologies (lung cancer, breast cancer, gastric cancer, hepatic cancer, rectal cancer). Key references were derived from a PubMed query. Hand searching and clinicaltrials.gov were also used. This paper contains a narrative report and a critical discussion of radiomics approaches related to cancer prognosis in different fields of diseases.

Prediction of serosal invasion in gastric cancer: development and validation of multivariate models integrating preoperative clinicopathological features and radiographic findings based on late arterial phase CT images

BACKGROUND

To develop and validate multivariate models integrating endoscopic biopsy, tumor markers, and CT findings based on late arterial phase (LAP) to predict serosal invasion in gastric cancer (GC).

METHODS

The preoperative differentiation degree, tumor markers, CT morphological characteristics, and CT value-related and texture parameters of 154 patients with GC were analyzed retrospectively. Multivariate models based on regression analysis and machine learning algorithms were performed to improve the diagnostic efficacy.

RESULTS

The differentiation degree, carbohydrate antigen (CA) 199, CA724, CA242, and multiple CT findings based on LAP differed significantly between T1-3 and T4 GCs in the primary cohort (all P < 0.05). Multivariate models based on regression analysis and random forest achieved AUCs of 0.849 and 0.865 in the primary cohort, respectively.

CONCLUSION

We developed and validated multivariate models integrating endoscopic biopsy, tumor markers, CT morphological characteristics, and CT value-related and texture parameters to predict serosal invasion in GCs and achieved favorable performance.

Establishment of the Radiologic Tumor Invasion Index Based on Radiomics Splenic Features and Clinical Factors to Predict Serous Invasion of Gastric Cancer

Background

Currently, there are shortcomings in diagnosing gastric cancer with or without serous invasion, making it difficult for patients to receive appropriate treatment. Therefore, we aimed to develop a radiomic nomogram for preoperative identification of serosal invasion.

Methods

We selected 315 patients with gastric cancer, confirmed by pathology, and randomly divided them into two groups: the training group (189 patients) and the verification group (126 patients). We obtained patient splenic imaging data for the training group. A p-value of <0.05 was considered significant for features that were selected for lasso regression. Eight features were chosen to construct a serous invasion prediction model. Patients were divided into high- and low-risk groups according to the radiologic tumor invasion risk score. Subsequently, univariate and multivariate regression analyses were performed with other invasion-related factors to establish a visual combined prediction model.

Results

The diagnostic accuracy of the radiologic tumor invasion score was consistent in the training and verification groups (p<0.001 and p=0.009, respectively). Univariate and multivariate analyses of invasion risk factors revealed that the radiologic tumor invasion index (p=0.002), preoperative hemoglobin <100 (p=0.042), and the platelet and lymphocyte ratio <92.8 (p=0.031) were independent risk factors for serosal invasion in the training cohort. The prediction model based on the three indexes accurately predicted the serosal invasion risk with an area under the curve of 0.884 in the training cohort and 0.837 in the testing cohort.

Conclusions

Radiological tumor invasion index based on splenic imaging combined with other factors accurately predicts serosal invasion of gastric cancer, increases diagnostic precision for the most effective treatment, and is time-efficient.

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

Gastric cancer (GC) is one of the most common cancers and one of the leading causes of cancer-related death worldwide. Precise diagnosis and evaluation of GC, especially using noninvasive methods, are fundamental to optimal therapeutic decision-making. Despite the recent rapid advancements in technology, pretreatment diagnostic accuracy varies between modalities, and correlations between imaging and histological features are far from perfect. Artificial intelligence (AI) techniques, particularly hand-crafted radiomics and deep learning, have offered hope in addressing these issues. AI has been used widely in GC research, because of its ability to convert medical images into minable data and to detect invisible textures. In this article, we systematically reviewed the methodological processes (data acquisition, lesion segmentation, feature extraction, feature selection, and model construction) involved in AI. We also summarized the current clinical applications of AI in GC research, which include characterization, differential diagnosis, treatment response monitoring, and prognosis prediction. Challenges and opportunities in AI-based GC research are highlighted for consideration in future studies.

Potential Value of Radiomics in the Identification of Stage T3 and T4a Esophagogastric Junction Adenocarcinoma Based on Contrast-Enhanced CT Images

Purpose

This study was designed to evaluate the predictive performance of contrast-enhanced CT-based radiomic features for the personalized, differential diagnosis of esophagogastric junction (EGJ) adenocarcinoma at stages T3 and T4a.

Methods

Two hundred patients with T3 (n = 44) and T4a (n = 156) EGJ adenocarcinoma lesions were enrolled in this study. Traditional computed tomography (CT) features were obtained from contrast-enhanced CT images, and the traditional model was constructed using a multivariate logistic regression analysis. A radiomic model was established based on radiomic features from venous CT images, and the radiomic score (Radscore) of each patient was calculated. A combined nomogram diagnostic model was constructed based on Radscores and traditional features. The diagnostic performances of these three models (traditional model, radiomic model, and nomogram) were assessed with receiver operating characteristics curves. Sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and areas under the curve (AUC) of models were calculated, and the performances of the models were evaluated and compared. Finally, the clinical effectiveness of the three models was evaluated by conducting a decision curve analysis (DCA).

Results

An eleven-feature combined radiomic signature and two traditional CT features were constructed as the radiomic and traditional feature models, respectively. The Radscore was significantly different between patients with stage T3 and T4a EGJ adenocarcinoma. The combined nomogram performed the best and has potential clinical usefulness.

Conclusions

The developed combined nomogram might be useful in differentiating T3 and T4a stages of EGJ adenocarcinoma and may facilitate the decision-making process for the treatment of T3 and T4a EGJ adenocarcinoma.