Deep Learning Features Improve the Performance of a Radiomics Signature for Predicting KRAS Status in Patients with Colorectal Cancer

PEDRA-EFB0: colorectal cancer prognostication using deep learning with patch embeddings and dual residual attention

In computer-aided diagnosis systems, precise feature extraction from CT scans of colorectal cancer using deep learning is essential for effective prognosis. However, existing convolutional neural networks struggle to capture long-range dependencies and contextual information, resulting in incomplete CT feature extraction. To address this, the PEDRA-EFB0 architecture integrates patch embeddings and a dual residual attention mechanism for enhanced feature extraction and survival prediction in colorectal cancer CT scans. A patch embedding method processes CT scans into patches, creating positional features for global representation and guiding spatial attention computation. Additionally, a dual residual attention mechanism during the upsampling stage selectively combines local and global features, enhancing CT data utilization. Furthermore, this paper proposes a feature selection algorithm that combines autoencoders and entropy technology, encoding and compressing high-dimensional data to reduce redundant information and using entropy to assess the importance of features, thereby achieving precise feature selection. Experimental results indicate the PEDRA-EFB0 model outperforms traditional methods on colorectal cancer CT metrics, notably in C-index, BS, MCC, and AUC, enhancing survival prediction accuracy. Our code is freely available at https://github.com/smile0208z/PEDRA .

Computed tomography-based deep learning radiomics model for preoperative prediction of tumor immune microenvironment in colorectal cancer

BACKGROUND

Colorectal cancer (CRC) is a leading cause of cancer-related death globally, with the tumor immune microenvironment (TIME) influencing prognosis and immunotherapy response. Current TIME evaluation relies on invasive biopsies, limiting its clinical application. This study hypothesized that computed tomography (CT)-based deep learning (DL) radiomics models can non-invasively predict key TIME biomarkers: Tumor-stroma ratio (TSR), tumor-infiltrating lymphocytes (TILs), and immune score (IS).

AIM

To develop a non-invasive DL approach using preoperative CT radiomics to evaluate TIME components in CRC patients.

METHODS

In this retrospective study, preoperative CT images of 315 pathologically confirmed CRC patients (220 in training cohort and 95 in validation cohort) were analyzed. Manually delineated regions of interest were used to extract DL features. Predictive models (DenseNet-121/169) for TSR, TILs, IS, and TIME classification were constructed. Performance was evaluated via receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA).

RESULTS

The DL-DenseNet-169 model achieved area under the curve (AUC) values of 0.892 [95% confidence interval (CI): 0.828-0.957] for TSR and 0.772 (95%CI: 0.674-0.870) for TIME score. The DenseNet-121 model yielded AUC values of 0.851 (95%CI: 0.768-0.933) for TILs and 0.852 (95%CI: 0.775-0.928) for IS. Calibration curves demonstrated strong prediction-observation agreement, and DCA confirmed clinical utility across threshold probabilities (P < 0.05 for all models).

CONCLUSION

CT-based DL radiomics provides a reliable non-invasive method for preoperative TIME evaluation, enabling personalized immunotherapy strategies in CRC management.

Comparison of Intratumoral and Peritumoral Deep Learning, Radiomics, and Fusion Models for Predicting KRAS Gene Mutations in Rectal Cancer Based on Endorectal Ultrasound Imaging

MAIN OBJECTIVES

We aimed at comparing intratumoral and peritumoral deep learning, radiomics, and fusion models in predicting KRAS mutations in rectal cancer using endorectal ultrasound imaging.

METHODS

This study included 304 patients with rectal cancer from Fujian Medical University Union Hospital. The patients were randomly divided into a training group (213 patients) and a test group (91 patients) at a 7:3 ratio. Radiomics and deep learning models were established using primary tumor and peritumoral images. In the optimally performing regions-of-interest, two fusion strategies, a feature-based and a decision-based model, were employed to build the fusion models. The Shapley additive explanation (SHAP) method was used to evaluate the significance of features in the optimal radiomics, deep learning, and fusion models. The performance of each model was assessed using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA).

RESULTS

In the test cohort, both the radiomics and deep learning models exhibited optimal performance with a 10-pixel patch extension, yielding AUC values of 0.824 and 0.856, respectively. The feature-based DLRexpand10_FB model attained the highest AUC (0.896) across all study sets. In addition, the DLRexpand10_FB model demonstrated excellent sensitivity, specificity, and DCA. SHAP analysis underscored the deep learning feature (DL_1) as the most significant factor in the hybrid model.

CONCLUSION

The feature-based fusion model DLRexpand10_FB can be employed to predict KRAS gene mutations based on pretreatment endorectal ultrasound images of rectal cancer. The integration of peritumoral regions enhanced the predictive performance of both the radiomics and deep learning models.

Radiomics in precision medicine for colorectal cancer: a bibliometric analysis (2013-2023)

Background

The incidence and mortality of colorectal cancer (CRC) have been rising steadily. Early diagnosis and precise treatment are essential for improving patient survival outcomes. Over the past decade, the integration of artificial intelligence (AI) and medical imaging technologies has positioned radiomics as a critical area of research in the diagnosis, treatment, and prognosis of CRC.

Methods

We conducted a comprehensive review of CRC-related radiomics literature published between 1 January 2013 and 31 December 2023 using the Web of Science Core Collection database. Bibliometric tools such as Bibliometrix, VOSviewer, and CiteSpace were employed to perform an in-depth bibliometric analysis.

Results

Our search yielded 1,226 publications, revealing a consistent annual growth in CRC radiomics research, with a significant rise after 2019. China led in publication volume (406 papers), followed by the United States (263 papers), whereas the United States dominated in citation numbers. Notable institutions included General Electric, Harvard University, University of London, Maastricht University, and the Chinese Academy of Sciences. Prominent researchers in this field are Tian J from the Chinese Academy of Sciences, with the highest publication count, and Ganeshan B from the University of London, with the most citations. Journals leading in publication and citation counts are Frontiers in Oncology and Radiology. Keyword and citation analysis identified deep learning, texture analysis, rectal cancer, image analysis, and management as prevailing research themes. Additionally, recent trends indicate the growing importance of AI and multi-omics integration, with a focus on improving precision medicine applications in CRC. Emerging keywords such as deep learning and AI have shown rapid growth in citation bursts over the past 3 years, reflecting a shift toward more advanced technological applications.

Conclusions

Radiomics plays a crucial role in the clinical management of CRC, providing valuable insights for precision medicine. It significantly contributes to predicting molecular biomarkers, assessing tumor aggressiveness, and monitoring treatment efficacy. Future research should prioritize advancing AI algorithms, enhancing multi-omics data integration, and further expanding radiomics applications in CRC precision medicine.

CHNet: A multi-task global-local Collaborative Hybrid Network for KRAS mutation status prediction in colorectal cancer

Accurate prediction of Kirsten rat sarcoma (KRAS) mutation status is crucial for personalized treatment of advanced colorectal cancer patients. However, despite the excellent performance of deep learning models in certain aspects, they often overlook the synergistic promotion among multiple tasks and the consideration of both global and local information, which can significantly reduce prediction accuracy. To address these issues, this paper proposes an innovative method called the Multi-task Global-Local Collaborative Hybrid Network (CHNet) aimed at more accurately predicting patients' KRAS mutation status. CHNet consists of two branches that can extract global and local features from segmentation and classification tasks, respectively, and exchange complementary information to collaborate in executing these tasks. Within the two branches, we have designed a Channel-wise Hybrid Transformer (CHT) and a Spatial-wise Hybrid Transformer (SHT). These transformers integrate the advantages of both Transformer and CNN, employing cascaded hybrid attention and convolution to capture global and local information from the two tasks. Additionally, we have created an Adaptive Collaborative Attention (ACA) module to facilitate the collaborative fusion of segmentation and classification features through guidance. Furthermore, we introduce a novel Class Activation Map (CAM) loss to encourage CHNet to learn complementary information between the two tasks. We evaluate CHNet on the T2-weighted MRI dataset, and achieve an accuracy of 88.93% in KRAS mutation status prediction, which outperforms the performance of representative KRAS mutation status prediction methods. The results suggest that our CHNet can more accurately predict KRAS mutation status in patients via a multi-task collaborative facilitation and considering global-local information way, which can assist doctors in formulating more personalized treatment strategies for patients.

Using tumor habitat-derived radiomic analysis during pretreatment 18F-FDG PET for predicting KRAS/NRAS/BRAF mutations in colorectal cancer

BACKGROUND

To investigate the association between Kirsten rat sarcoma viral oncogene homolog (KRAS) / neuroblastoma rat sarcoma viral oncogene homolog (NRAS) /v-raf murine sarcoma viral oncogene homolog B (BRAF) mutations and the tumor habitat-derived radiomic features obtained during pretreatment 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) in patients with colorectal cancer (CRC).

METHODS

We retrospectively enrolled 62 patients with CRC who had undergone 18F-FDG PET/computed tomography from January 2017 to July 2022 before the initiation of therapy. The patients were randomly split into training and validation cohorts with a ratio of 6:4. The whole tumor region radiomic features, habitat-derived radiomic features, and metabolic parameters were extracted from 18F-FDG PET images. After reducing the feature dimension and selecting meaningful features, we constructed a hierarchical model of KRAS/NRAS/BRAF mutations by using the support vector machine. The convergence of the model was evaluated by using learning curve, and its performance was assessed based on the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis. The SHapley Additive exPlanation was used to interpret the contributions of various features to predictions of the model.

RESULTS

The model constructed by using habitat-derived radiomic features had adequate predictive power with respect to KRAS/NRAS/BRAF mutations, with an AUC of 0.759 (95% CI: 0.585-0.909) on the training cohort and that of 0.701 (95% CI: 0.468-0.916) on the validation cohort. The model exhibited good convergence, suitable calibration, and clinical application value. The results of the SHapley Additive explanation showed that the peritumoral habitat and a high_metabolism habitat had the greatest impact on predictions of the model. No meaningful whole tumor region radiomic features or metabolic parameters were retained during feature selection.

CONCLUSION

The habitat-derived radiomic features were found to be helpful in stratifying the status of KRAS/NRAS/BRAF in CRC patients. The approach proposed here has significant implications for adjuvant treatment decisions in patients with CRC, and needs to be further validated on a larger prospective cohort.

Detecting microsatellite instability in colorectal cancer using Transformer-based colonoscopy image classification and retrieval

Colorectal cancer (CRC) is a major global health concern, with microsatellite instability-high (MSI-H) being a defining characteristic of hereditary nonpolyposis colorectal cancer syndrome and affecting 15% of sporadic CRCs. Tumors with MSI-H have unique features and better prognosis compared to MSI-L and microsatellite stable (MSS) tumors. This study proposed establishing a MSI prediction model using more available and low-cost colonoscopy images instead of histopathology. The experiment utilized a database of 427 MSI-H and 1590 MSS colonoscopy images and vision Transformer (ViT) with different feature training approaches to establish the MSI prediction model. The accuracy of combining pre-trained ViT features was 84% with an area under the receiver operating characteristic curve of 0.86, which was better than that of DenseNet201 (80%, 0.80) in the experiment with support vector machine. The content-based image retrieval (CBIR) approach showed that ViT features can obtain a mean average precision of 0.81 compared to 0.79 of DenseNet201. ViT reduced the issues that occur in convolutional neural networks, including limited receptive field and gradient disappearance, and may be better at interpreting diagnostic information around tumors and surrounding tissues. By using CBIR, the presentation of similar images with the same MSI status would provide more convincing deep learning suggestions for clinical use.

Exploring non-invasive precision treatment in non-small cell lung cancer patients through deep learning radiomics across imaging features and molecular phenotypes

BACKGROUND

Accurate prediction of tumor molecular alterations is vital for optimizing cancer treatment. Traditional tissue-based approaches encounter limitations due to invasiveness, heterogeneity, and molecular dynamic changes. We aim to develop and validate a deep learning radiomics framework to obtain imaging features that reflect various molecular changes, aiding first-line treatment decisions for cancer patients.

METHODS

We conducted a retrospective study involving 508 NSCLC patients from three institutions, incorporating CT images and clinicopathologic data. Two radiomic scores and a deep network feature were constructed on three data sources in the 3D tumor region. Using these features, we developed and validated the 'Deep-RadScore,' a deep learning radiomics model to predict prognostic factors, gene mutations, and immune molecule expression levels.

FINDINGS

The Deep-RadScore exhibits strong discrimination for tumor molecular features. In the independent test cohort, it achieved impressive AUCs: 0.889 for lymphovascular invasion, 0.903 for pleural invasion, 0.894 for T staging; 0.884 for EGFR and ALK, 0.896 for KRAS and PIK3CA, 0.889 for TP53, 0.895 for ROS1; and 0.893 for PD-1/PD-L1. Fusing features yielded optimal predictive power, surpassing any single imaging feature. Correlation and interpretability analyses confirmed the effectiveness of customized deep network features in capturing additional imaging phenotypes beyond known radiomic features.

INTERPRETATION

This proof-of-concept framework demonstrates that new biomarkers across imaging features and molecular phenotypes can be provided by fusing radiomic features and deep network features from multiple data sources. This holds the potential to offer valuable insights for radiological phenotyping in characterizing diverse tumor molecular alterations, thereby advancing the pursuit of non-invasive personalized treatment for NSCLC patients.

CT-based intratumoral and peritumoral deep transfer learning features prediction of lymph node metastasis in non-small cell lung cancer

BACKGROUND

The main metastatic route for lung cancer is lymph node metastasis, and studies have shown that non-small cell lung cancer (NSCLC) has a high risk of lymph node infiltration.

OBJECTIVE

This study aimed to compare the performance of handcrafted radiomics (HR) features and deep transfer learning (DTL) features in Computed Tomography (CT) of intratumoral and peritumoral regions in predicting the metastatic status of NSCLC lymph nodes in different machine learning classifier models.

METHODS

We retrospectively collected data of 199 patients with pathologically confirmed NSCLC. All patients were divided into training (n = 159) and validation (n = 40) cohorts, respectively. The best HR and DTL features in the intratumoral and peritumoral regions were extracted and selected, respectively. Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Light Gradient Boosting Machine (Light GBM), Multilayer Perceptron (MLP), and Logistic Regression (LR) models were constructed, and the performance of the models was evaluated.

RESULTS

Among the five models in the training and validation cohorts, the LR classifier model performed best in terms of HR and DTL features. The AUCs of the training cohort were 0.841 (95% CI: 0.776-0.907) and 0.955 (95% CI: 0.926-0.983), and the AUCs of the validation cohort were 0.812 (95% CI: 0.677-0.948) and 0.893 (95% CI: 0.795-0.991), respectively. The DTL signature was superior to the handcrafted radiomics signature.

CONCLUSIONS

Compared with the radiomics signature, the DTL signature constructed based on intratumoral and peritumoral areas in CT can better predict NSCLC lymph node metastasis.

Deep Learning Radiomics of Preoperative Breast MRI for Prediction of Axillary Lymph Node Metastasis in Breast Cancer

The objective of this study is to develop a radiomic signature constructed from deep learning features and a nomogram for prediction of axillary lymph node metastasis (ALNM) in breast cancer patients. Preoperative magnetic resonance imaging data from 479 breast cancer patients with 488 lesions were studied. The included patients were divided into two cohorts by time (training/testing cohort, n = 366/122). Deep learning features were extracted from diffusion-weighted imaging-quantitatively measured apparent diffusion coefficient (DWI-ADC) imaging and dynamic contrast-enhanced MRI (DCE-MRI) by a pretrained neural network of DenseNet121. After the selection of both radiomic and clinicopathological features, deep learning signature and a nomogram were built for independent validation. Twenty-three deep learning features were automatically selected in the training cohort to establish the deep learning signature of ALNM. Three clinicopathological factors, including LN palpability (odds ratio (OR) = 6.04; 95% confidence interval (CI) = 3.06-12.54, P = 0.004), tumor size in MRI (OR = 1.45, 95% CI = 1.18-1.80, P = 0.104), and Ki-67 (OR = 1.01; 95% CI = 1.00-1.02, P = 0.099), were selected and combined with radiomic signature to build a combined nomogram. The nomogram showed excellent predictive ability for ALNM (AUC 0.80 and 0.71 in training and testing cohorts, respectively). The sensitivity, specificity, and accuracy were 65%, 80%, and 75%, respectively, in the testing cohort. MRI-based deep learning radiomics in patients with breast cancer could be used to predict ALNM, providing a noninvasive approach to structuring the treatment strategy.

Modeling the survival of colorectal cancer patients based on colonoscopic features in a feature ensemble vision transformer

The prognosis of patients with colorectal cancer (CRC) mostly relies on the classic tumor node metastasis (TNM) staging classification. A more accurate and convenient prediction model would provide a better prognosis and assist in treatment. From May 2014 to December 2017, patients who underwent an operation for CRC were enrolled. The proposed feature ensemble vision transformer (FEViT) used ensemble classifiers to benefit the combinations of relevant colonoscopy features from the pretrained vision transformer and clinical features, including sex, age, family history of CRC, and tumor location, to establish the prognostic model. A total of 1729 colonoscopy images were enrolled in the current retrospective study. For the prediction of patient survival, FEViT achieved an accuracy of 94 % with an area under the receiver operating characteristic curve of 0.93, which was better than the TNM staging classification (90 %, 0.83) in the experiment. FEViT reduced the limited receptive field and gradient disappearance in the conventional convolutional neural network and was a relatively effective and efficient procedure. The promising accuracy of FEViT in modeling survival makes the prognosis of CRC patients more predictable and practical.

Repeatability of radiomics studies in colorectal cancer: a systematic review

BACKGROUND

Recently, radiomics has been widely used in colorectal cancer, but many variable factors affect the repeatability of radiomics research. This review aims to analyze the repeatability of radiomics studies in colorectal cancer and to evaluate the current status of radiomics in the field of colorectal cancer.

METHODS

The included studies in this review by searching from the PubMed and Embase databases. Then each study in our review was evaluated using the Radiomics Quality Score (RQS). We analyzed the factors that may affect the repeatability in the radiomics workflow and discussed the repeatability of the included studies.

RESULTS

A total of 188 studies was included in this review, of which only two (2/188, 1.06%) studies controlled the influence of individual factors. In addition, the median score of RQS was 11 (out of 36), range-1 to 27.

CONCLUSIONS

The RQS score was moderately low, and most studies did not consider the repeatability of radiomics features, especially in terms of Intra-individual, scanners, and scanning parameters. To improve the generalization of the radiomics model, it is necessary to further control the variable factors of repeatability.

Radiomics approach with deep learning for predicting T4 obstructive colorectal cancer using CT image

OBJECTIVES

Patients with T4 obstructive colorectal cancer (OCC) have a high mortality rate. Therefore, an accurate distinction between T4 and T1-T3 (NT4) in OCC is an important part of preoperative evaluation, especially in the emergency setting. This paper introduces three models of radiomics, deep learning, and deep learning-based radiomics to identify T4 OCC.

METHODS

We established a dataset of computed tomography (CT) images of 164 patients with pathologically confirmed OCC, from which 2537 slides were extracted. First, since T4 tumors penetrate the bowel wall and involve adjacent organs, we explored whether the peritumoral region contributes to the assessment of T4 OCC. Furthermore, we visualized the radiomics and deep learning features using the t-distributed stochastic neighbor embedding technique (t-SNE). Finally, we built a merged model by fusing radiomic features with deep learning features. In this experiment, the performance of each model was evaluated by the area under the receiver operating characteristic curve (AUC).

RESULTS

In the test cohort, the AUC values predicted by the radiomics model in the dilated region of interest (dROI) was 0.770. And the AUC value of the deep learning model with the patches extended 20-pixel reached 0.936. Combining the characteristics of radiomics and deep learning, our method achieved an AUC value of 0.947 in the T4 and non-T4 (NT4) classification, and increased the AUC value to 0.950 after the addition of clinical features.

CONCLUSION

The prediction results of our merged model of deep learning radiomics outperformed the deep learning model and significantly outperformed the radiomics model. The experimental results demonstrate that combining the peritumoral region improves the prediction performance of the radiomics model and the deep learning model.

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.

A Deep Learning Model Based on MRI and Clinical Factors Facilitates Noninvasive Evaluation of KRAS Mutation in Rectal Cancer

BACKGROUND

Recent studies showed the potential of MRI-based deep learning (DL) for assessing treatment response in rectal cancer, but the role of MRI-based DL in evaluating Kirsten rat sarcoma viral oncogene homologue (KRAS) mutation remains unclear.

PURPOSE

To develop a DL method based on T2-weighted imaging (T2WI) and clinical factors for noninvasively evaluating KRAS mutation in rectal cancer.

STUDY TYPE

Retrospective.

SUBJECTS

A total of 376 patients (108 women [28.7%]) with histopathology-confirmed rectal adenocarcinoma and KRAS mutation status.

FIELD STRENGTH/SEQUENCE

A 3 T, turbo spin echo T2WI and single-shot echo-planar diffusion-weighted imaging (b = 0, 1000 sec/mm² ).

ASSESSMENT

A clinical model was constructed with clinical factors (age, gender, carcinoembryonic antigen level, and carbohydrate antigen 199 level) and MRI features (tumor length, tumor location, tumor stage, lymph node stage, and extramural vascular invasion), and two DL models based on modified MobileNetV2 architecture were evaluated for diagnosing KRAS mutation based on T2WI alone (image model) or both T2WI and clinical factors (combined model). The clinical usefulness of these models was evaluated through calibration analysis and decision curve analysis (DCA).

STATISTICAL TESTS

Mann-Whitney U test, Chi-squared test, Fisher's exact test, logistic regression analysis, receiver operating characteristic curve (ROC), Delong's test, Hosmer-Lemeshow test, interclass correlation coefficients, and Fleiss kappa coefficients (P < 0.05 was considered statistically significant).

RESULTS

All the nine clinical-MRI characteristics were included for clinical model development. The clinical model, image model, and combined model in the testing cohort demonstrated good calibration and achieved areas under the curve (AUCs) of 0.668, 0.765, and 0.841, respectively. The combined model showed improved performance compared to the clinical model and image model in two cohorts. DCA confirmed the higher net benefit of the combined model than the other two models when the threshold probability is between 0.05 and 0.85.

DATA CONCLUSION

The proposed combined DL model incorporating T2WI and clinical factors may show good diagnostic performance. Thus, it could potentially serve as a supplementary approach for noninvasively evaluating KRAS mutation in rectal cancer.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Predicting Kirsten Rat Sarcoma Virus Gene Mutation Status in Patients With Colorectal Cancer by Radiomics Models Based on Multiphasic CT

OBJECTIVE

To develop and validate radiomics models based on multiphasic CT in predicting Kirsten rat sarcoma virus (KRAS) gene mutation status in patients with colorectal cancer (CRC).

MATERIALS AND METHODS

A total of 231 patients with pathologically confirmed CRC were retrospectively enrolled and randomly divided into training(n=184) and test groups(n=47) in a ratio of 4:1. A total of 1316 quantitative radiomics features were extracted from non-contrast phase (NCP), arterial-phase (AP) and venous-phase (VP) CT for each patient. Four steps were applied for feature selection including Spearman correlation analysis, variance threshold, least absolute contraction and selection operator, and multivariate stepwise regression analysis. Clinical and pathological characteristics were also assessed. Subsequently, three classification methods, logistic regression (LR), support vector machine (SVM) and random tree (RT) algorithm, were applied to develop seven groups of prediction models (NCP, AP, VP, AP+VP, AP+VP+NCP, AP&VP, AP&VP&NCP) for KRAS mutation prediction. The performance of these models was evaluated by receiver operating characteristics curve (ROC) analysis.

RESULTS

Among the three groups of single-phase models, the AP model, developed by LR algorithm, showed the best prediction performance with an AUC value of 0.811 (95% CI:0.685-0.938) in the test cohort. Compared with the single-phase models, the dual-phase (AP+VP) model with the LR algorithm showed better prediction performance (AUC=0.826, 95% CI:0.700-0.952). The performance of multiphasic (AP+VP+NCP) model with the LR algorithm (AUC=0.811, 95%CI: 0.679-0.944) is comparable to the model with the SVM algorithm (AUC=0.811, 95%CI: 0.695-0.918) in the test cohort, but the sensitivity, specificity, and accuracy of the multiphasic (AP+VP+NCP) model with the LR algorithm were 0.810, 0.808, 0.809 respectively, which were highest among these seven groups of prediction models in the test cohort.

CONCLUSION

The CT radiomics models have the potential to predict KRAS mutation in patients with CRC; different phases may affect the predictive efficacy of radiomics model, of which arterial-phase CT is more informative. The combination of multiphasic CT images can further improve the performance of radiomics model.

Radiomics-guided radiation therapy: opportunities and challenges

Radiomics is an advanced image-processing framework, which extracts image features and considers them as biomarkers towards personalized medicine. Applications include disease detection, diagnosis, prognosis, and therapy response assessment/prediction. As radiation therapy aims for further individualized treatments, radiomics could play a critical role in various steps before, during and after treatment. Elucidation of the concept of radiomics-guided radiation therapy (RGRT) is the aim of this review, attempting to highlight opportunities and challenges underlying the use of radiomics to guide clinicians and physicists towards more effective radiation treatments. This work identifies the value of RGRT in various steps of radiotherapy from patient selection to follow-up, and subsequently provides recommendations to improve future radiotherapy using quantitative imaging features.

Preoperative prediction of KRAS mutation status in colorectal cancer using a CT-based radiomics nomogram

OBJECTIVE

This study aimed to develop a model to predict KRAS mutations in colorectal cancer according to radiomic signatures based on CT and clinical risk factors.

METHODS

This retrospective study included 172 patients with colorectal cancer. All patients were randomized at a 7:3 ratio into a training cohort (n = 121, 38.8% positive for KRAS mutation) and a validation cohort (n = 51, 39.2% positive for KRAS mutation). Radiomics features were extracted from single-slice and full-volume regions of interest on the portal-venous CT images. The least absolute shrinkage and selection operator (LASSO) algorithm was adopted to construct a radiomics signature, and logistic regression was applied to select the significant variables to develop the clinical-radiomics model. The predictive performance was evaluated by receiver operating characteristic curve (ROC) analysis, calibration curve analysis, and decision curve analysis (DCA).

RESULTS

1018 radiomics features were extracted from single-slice and full-volume ROIs. Eight features were retained to construct 2D (two-dimensional, 2D) radiomics model. Similarly, eight features were retained to construct 3D (three-dimensional, 3D) radiomics model. The area under the curve (AUC) values of the test cohort were 0.75 and 0.84, respectively. Delong test showed that the integrated nomogram (AUC = 0.92 in the test cohort) had better clinical predictive efficiency than 2D radiomics (p-value < 0.05) model and 3D radiomics model (p-value < 0.05).

CONCLUSION

The 2D and 3D radiomics models can both predict KRAS mutations. And, the integrated nomogram can be better applied to predict KRAS mutation status in colorectal cancer.

ADVANCES IN KNOWLEDGE

CT-based radiomics showed satisfactory diagnostic significance for the KRAS status in colorectal cancer, the clinical-combined model may be applied in the individual pre-operative prediction of KRAS mutation.

Development and validation of a radiomics-based nomogram for the preoperative prediction of microsatellite instability in colorectal cancer

BACKGROUND

Preoperative prediction of microsatellite instability (MSI) status in colorectal cancer (CRC) patients is of great significance for clinicians to perform further treatment strategies and prognostic evaluation. Our aims were to develop and validate a non-invasive, cost-effective reproducible and individualized clinic-radiomics nomogram method for preoperative MSI status prediction based on contrast-enhanced CT (CECT)images.

METHODS

A total of 76 MSI CRC patients and 200 microsatellite stability (MSS) CRC patients with pathologically confirmed (194 in the training set and 82 in the validation set) were identified and enrolled in our retrospective study. We included six significant clinical risk factors and four qualitative imaging data extracted from CECT images to build the clinics model. We applied the intra-and inter-class correlation coefficient (ICC), minimal-redundancy-maximal-relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) for feature reduction and selection. The selected independent prediction clinical risk factors, qualitative imaging data and radiomics features were performed to develop a predictive nomogram model for MSI status on the basis of multivariable logistic regression by tenfold cross-validation. The area under the receiver operating characteristic (ROC) curve (AUC), calibration plots and Hosmer-Lemeshow test were performed to assess the nomogram model. Finally, decision curve analysis (DCA) was performed to determine the clinical utility of the nomogram model by quantifying the net benefits of threshold probabilities.

RESULTS

Twelve top-ranked radiomics features, three clinical risk factors (location, WBC and histological grade) and CT-reported IFS were finally selected to construct the radiomics, clinics and combined clinic-radiomics nomogram model. The clinic-radiomics nomogram model with the highest AUC value of 0.87 (95% CI, 0.81-0.93) and 0.90 (95% CI, 0.83-0.96), as well as good calibration and clinical utility observed using the calibration plots and DCA in the training and validation sets respectively, was regarded as the candidate model for identification of MSI status in CRC patients.

CONCLUSION

The proposed clinic-radiomics nomogram model with a combination of clinical risk factors, qualitative imaging data and radiomics features can potentially be effective in the individualized preoperative prediction of MSI status in CRC patients and may help performing further treatment strategies.

Special issue "The advance of solid tumor research in China": Prognosis prediction for stage II colorectal cancer by fusing CT radiomics and deep-learning features of primary lesions and peripheral lymph nodes

Currently, the prognosis assessment of stage II colorectal cancer (CRC) remains a difficult clinical problem; therefore, more accurate prognostic predictors must be developed. In this study, we developed a prognostic prediction model for stage II CRC by fusing radiomics and deep-learning (DL) features of primary lesions and peripheral lymph nodes (LNs) in computed tomography (CT) scans. First, two CT radiomics models were built using primary lesion and LN image features. Subsequently, an information fusion method was used to build a fusion radiomics model by combining the tumor and LN image features. Furthermore, a transfer learning method was applied to build a deep convolutional neural network (CNN) model. Finally, the prediction scores generated by the radiomics and CNN models were fused to improve the prognosis prediction performance. The disease-free survival (DFS) and overall survival (OS) prediction areas under the curves (AUCs) generated by the fusion model improved to 0.76±0.08 and 0.91±0.05, respectively. These were significantly higher than the AUCs generated by the models using the individual CT radiomics and deep image features. Applying the survival analysis method, the DFS and OS fusion models yielded concordance index (C-index) values of 0.73 and 0.9, respectively. Hence, the combined model exhibited good predictive efficacy; therefore, it could be used for the accurate assessment of the prognosis of stage II CRC patients. Moreover, it could be used to screen out high-risk patients with poor prognoses, and assist in the formulation of clinical treatment decisions in a timely manner to achieve precision medicine. This article is protected by copyright. All rights reserved.

Preoperative Prediction of BRAF Mutation Status in Colorectal Cancer Using a Clinical-radiomics Model

RATIONALE AND OBJECTIVES

This study aimed to develop a clinically practical model to predict V-raf murine sarcoma viral oncogene homolog B1 (BRAF) mutation in colorectal cancer according to radiomic signatures based on computed tomography (CT) and clinical risk factors, and to determine the model's diagnostic accuracy for BRAF mutation status.

MATERIALS AND METHODS

This retrospective study included 140 patients with colorectal cancer. The significant clinical risk factors were used to build the clinical model; the least absolute shrinkage and selection operator algorithm was adopted to construct a radiomics signature according to imaging features of the tumor lesion, and stepwise logistic regression was applied to select the significant variables to develop the clinical-radiomics model. The predictive performance was evaluated by receiver operating characteristic curve analysis, calibration curve analysis, and decision curve analysis.

RESULTS

The radscore, generated by 5 selected radiomics features, demonstrated a favorable ability to predict BRAF mutation in both the training (area under the receiver operating characteristic curve [AUC] 0.93) and validation (AUC 0.87) cohorts. Subsequently, integrating two independent predictors (including the radscore and clinical risk factors) into a nomogram exhibited more favorable discriminatory performance, with the AUC improved to 0.95 and 0.88 in both cohorts. Moreover, the accuracy for predicting BRAF mutations was higher than that of the clinical model, ranging from 0.70 to 0.89.

CONCLUSION

The proposed CT-based radiomics signature is associated with BRAF mutations. The present study also proposes a combined model can potentially be applied in the individual preoperative prediction of BRAF mutation status in colorectal cancer.

ADVANCES IN KNOWLEDGE

CT-based radiomics showed satisfactory diagnostic significance for the BRAF status in colorectal cancer, the clinical-combined model may be applied in the individual preoperative prediction of BRAF mutation.

Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features

Objectives: To develop and validate the model for distinguishing brain abscess from cystic glioma by combining deep transfer learning (DTL) features and hand-crafted radiomics (HCR) features in conventional T1-weighted imaging (T1WI) and T2-weighted imaging (T2WI).

Methods: This single-center retrospective analysis involved 188 patients with pathologically proven brain abscess (102) or cystic glioma (86). One thousand DTL and 105 HCR features were extracted from the T1WI and T2WI of the patients. Three feature selection methods and four classifiers, such as k-nearest neighbors (KNN), random forest classifier (RFC), logistic regression (LR), and support vector machine (SVM), for distinguishing brain abscess from cystic glioma were compared. The best feature combination and classifier were chosen according to the quantitative metrics including area under the curve (AUC), Youden Index, and accuracy.

Results: In most cases, deep learning-based radiomics (DLR) features, i.e., DTL features combined with HCR features, contributed to a higher accuracy than HCR and DTL features alone for distinguishing brain abscesses from cystic gliomas. The AUC values of the model established, based on the DLR features in T2WI, were 0.86 (95% CI: 0.81, 0.91) in the training cohort and 0.85 (95% CI: 0.75, 0.95) in the test cohort, respectively.

Conclusions: The model established with the DLR features can distinguish brain abscess from cystic glioma efficiently, providing a useful, inexpensive, convenient, and non-invasive method for differential diagnosis. This is the first time that conventional MRI radiomics is applied to identify these diseases. Also, the combination of HCR and DTL features can lead to get impressive performance.

A multitask dual-stream attention network for the identification of KRAS mutation in colorectal cancer

PURPOSE

It is of great significance to accurately identify the KRAS gene mutation status for patients in tumor prognosis and personalized treatment. Although the computer-aided diagnosis system based on deep learning has gotten all-round development, its performance still cannot meet the current clinical application requirements due to the inherent limitations of small-scale medical image data set and inaccurate lesion feature extraction. Therefore, our aim is to propose a deep learning model based on T2 MRI of colorectal cancer (CRC) patients to identify whether KRAS gene is mutated.

METHODS

In this research, a multitask attentive model is proposed to identify KRAS gene mutations in patients, which is mainly composed of a segmentation subnetwork and an identification subnetwork. Specifically, at first, the features extracted by the encoder of segmentation model are used as guidance information to guide the two attention modules in the identification network for precise activation of the lesion area. Then the original image of the lesion and the segmentation result are concatenated for feature extraction. Finally, features extracted from the second step are combined with features activated by the attention modules to identify the gene mutation status. In this process, we introduce the interlayer loss function to encourage the similarity of the two subnetwork parameters and ensure that the key features are fully extracted to alleviate the overfitting problem caused by small data set to some extent.

RESULTS

The proposed identification model is benchmarked primarily using 15-fold cross validation. Three hundred and eighty-two images from 36 clinical cases were used to test the model. For the identification of KRAS mutation status, the average accuracy is 89.95 ± 1.23%, the average sensitivity is 89.29 ± 1.79%, the average specificity is 90.53 ± 2.45%, and the average area under the curve (AUC) is 95.73 ± 0.52%. For segmentation of lesions, the average dice is 88.11 ± 0.86%.

CONCLUSIONS

We developed a novel deep learning-based model to identify the KRAS status in CRC. We demonstrated the excellent properties of the proposed identification through comparison with ground truth gene mutation status of 36 clinical cases. And all these results show that the novel method has great potential for clinical application.

Spatial-Frequency dual-branch attention model for determining KRAS mutation status in colorectal cancer with T2-weighted MRI

BACKGROUND AND OBJECTIVE

Identifying the KRAS mutation status accurately in medical images is very important for the diagnosis and treatment of colorectal cancer. Despite the substantial progress achieved by existing methods, it remains challenging due to limited annotated dataset, large intra-class variances, and a high degree of inter-class similarities.

METHODS

To tackle these challenges, we propose a spatial-frequency dual-branch attention model (SF-DBAM) to determine the KRAS mutation status of colorectal cancer patients using a limited T2-weighted MRI dataset. The dataset contains 169 wild-type patients (2151 images) and 137 mutation-type patients (1666 images). The first branch utilizes part of the pre-trained Xception model to capture spatial-domain information and alleviate the small-scale dataset problem. The second branch builds frequency-domain information into cube columns using block-based discrete cosine transform and channel rearrangement. Then the cube columns are fed into convolutional long short-term memory (convLSTM) to explore the effective information between the reconstructed frequency-domain channels. Also, we design a channel enhanced attention module (CEAM) at the end of each branch to make them focus on the lesion areas. Finally, we concatenate the two branches and output the classified results through fully connected layers.

RESULTS

The proposed method achieves 88.03% overall accuracy with AUC of 94.27% and specificity of 90.75% in 10-fold cross-validation, which is better than the current non-invasive methods for determining KRAS mutation status.

CONCLUSIONS

We believe that the proposed method can assist physicians to diagnose the KRAS mutation status in patients with colorectal cancer, and other medical problems can benefit from the spatial and frequency domains information.

Radiomics and machine learning applications in rectal cancer: Current update and future perspectives

The high incidence of rectal cancer in both sexes makes it one of the most common tumors, with significant morbidity and mortality rates. To define the best treatment option and optimize patient outcome, several rectal cancer biological variables must be evaluated. Currently, medical imaging plays a crucial role in the characterization of this disease, and it often requires a multimodal approach. Magnetic resonance imaging is the first-choice imaging modality for local staging and restaging and can be used to detect high-risk prognostic factors. Computed tomography is widely adopted for the detection of distant metastases. However, conventional imaging has recognized limitations, and many rectal cancer characteristics remain assessable only after surgery and histopathology evaluation. There is a growing interest in artificial intelligence applications in medicine, and imaging is by no means an exception. The introduction of radiomics, which allows the extraction of quantitative features that reflect tumor heterogeneity, allows the mining of data in medical images and paved the way for the identification of potential new imaging biomarkers. To manage such a huge amount of data, the use of machine learning algorithms has been proposed. Indeed, without prior explicit programming, they can be employed to build prediction models to support clinical decision making. In this review, current applications and future perspectives of artificial intelligence in medical imaging of rectal cancer are presented, with an imaging modality-based approach and a keen eye on unsolved issues. The results are promising, but the road ahead for translation in clinical practice is rather long.

Prediction of recurrence after surgery in colorectal cancer patients using radiomics from diagnostic contrast-enhanced computed tomography: a two-center study

OBJECTIVES

To assess the value of contrast-enhanced (CE) diagnostic CT scans characterized through radiomics as predictors of recurrence for patients with stage II and III colorectal cancer in a two-center context.

MATERIALS AND METHODS

This study included 193 patients diagnosed with stage II and III colorectal adenocarcinoma from 1 July 2008 to 15 March 2017 in two different French University Hospitals. To compensate for the variability in two-center data, a statistical harmonization method Bootstrapped ComBat (B-ComBat) was used. Models predicting disease-free survival (DFS) were built using 3 different machine learning (ML): (1) multivariate regression (MR) with 10-fold cross-validation after feature selection based on least absolute shrinkage and selection operator (LASSO), (2) random forest (RF), and (3) support vector machine (SVM), both with embedded feature selection.

RESULTS

The performance for both balanced and 95% sensitivity models was systematically higher after our proposed B-ComBat harmonization compared to the use of the original untransformed data. The most clinically relevant performance was achieved by the multivariate regression model combining a clinical variable (postoperative chemotherapy) with two radiomics shape descriptors (compactness and least axis length) with a BAcc of 0.78 and an MCC of 0.6 associated with a required sensitivity of 95%. The resulting stratification in terms of DFS was significant (p = 0.00021), especially compared to the use of unharmonized original data (p = 0.17).

CONCLUSIONS

Radiomics models derived from contrast-enhanced CT could be trained and validated in a two-center cohort with a good predictive performance of recurrence in stage II et III colorectal cancer patients.

KEY POINTS

• Adjuvant therapy decision in colorectal cancer can be a challenge in medical oncology. • Radiomics models, derived from diagnostic CT, trained and validated in a two-center cohort, could predict recurrence in stage II and III colorectal cancer patients. • Identifying patients with a low risk of recurrence, these models could facilitate treatment optimization and avoid unnecessary treatment.

Serum Tumor Markers Combined With Clinicopathological Characteristics for Predicting MMR and KRAS Status in 2279 Chinese Colorectal Cancer Patients: A Retrospective Analysis

Although serum tumor markers (STMs), clinicopathological characteristics and the status of KRAS and MMR play an important role in optimizing the treatment and prognosis of colorectal cancer, their interrelationships remain largely unknown. A retrospective analysis of 2279 patients who tested for KRAS and MMR status, and STM measurements prior to treatment over the past four years was conducted. Of the 784 patients tested for KRAS and 2279 patients tested for MMR status, KRAS mutations and dMMR were identified in 276 patients (35.20%) and 177 patients (7.77%), respectively. Logistic regression analysis demonstrated that right colon, well and moderate differentiation and negative CA19-9 were independent predictors for KRAS mutations. The ROC curve yielded an AUC of 0.609 through the combination of these three factors. Age < 65 was an independent predictive factor for dMMR, along with tumor size > 4.6 cm, right colon, poor differentiation, harvested lymph nodes ≥ 22, no lymph node metastasis, no perineural invasion, negative CEA and positive CA72-4. When the nine criteria were used together, the AUC was 0.849. In summary, both STMs and clinicopathological characteristics were found to be significantly associated with the status of KRAS and MMR. The combination of these two factors possessed a strong predictive power for KRAS mutations and dMMR among CRC patients.

Systematic Review on the Association of Radiomics with Tumor Biological Endpoints

Radiomics supposes an alternative non-invasive tumor characterization tool, which has experienced increased interest with the advent of more powerful computers and more sophisticated machine learning algorithms. Nonetheless, the incorporation of radiomics in cancer clinical-decision support systems still necessitates a thorough analysis of its relationship with tumor biology. Herein, we present a systematic review focusing on the clinical evidence of radiomics as a surrogate method for tumor molecular profile characterization. An extensive literature review was conducted in PubMed, including papers on radiomics and a selected set of clinically relevant and commonly used tumor molecular markers. We summarized our findings based on different cancer entities, additionally evaluating the effect of different modalities for the prediction of biomarkers at each tumor site. Results suggest the existence of an association between the studied biomarkers and radiomics from different modalities and different tumor sites, even though a larger number of multi-center studies are required to further validate the reported outcomes.

Status quo and future prospects of artificial neural network from the perspective of gastroenterologists

Artificial neural networks (ANNs) are one of the primary types of artificial intelligence and have been rapidly developed and used in many fields. In recent years, there has been a sharp increase in research concerning ANNs in gastrointestinal (GI) diseases. This state-of-the-art technique exhibits excellent performance in diagnosis, prognostic prediction, and treatment. Competitions between ANNs and GI experts suggest that efficiency and accuracy might be compatible in virtue of technique advancements. However, the shortcomings of ANNs are not negligible and may induce alterations in many aspects of medical practice. In this review, we introduce basic knowledge about ANNs and summarize the current achievements of ANNs in GI diseases from the perspective of gastroenterologists. Existing limitations and future directions are also proposed to optimize ANN's clinical potential. In consideration of barriers to interdisciplinary knowledge, sophisticated concepts are discussed using plain words and metaphors to make this review more easily understood by medical practitioners and the general public.

Development and validation of MRI-based deep learning models for prediction of microsatellite instability in rectal cancer

BACKGROUND

Microsatellite instability (MSI) predetermines responses to adjuvant 5-fluorouracil and immunotherapy in rectal cancer and serves as a prognostic biomarker for clinical outcomes. Our objective was to develop and validate a deep learning model that could preoperatively predict the MSI status of rectal cancer based on magnetic resonance images.

METHODS

This single-center retrospective study included 491 rectal cancer patients with pathologically proven microsatellite status. Patients were randomly divided into the training/validation cohort (n = 395) and the testing cohort (n = 96). A clinical model using logistic regression was constructed to discriminate MSI status using only clinical factors. Based on a modified MobileNetV2 architecture, deep learning models were tested for the predictive ability of MSI status from magnetic resonance images, with or without integrating clinical factors.

RESULTS

The clinical model correctly classified 37.5% of MSI status in the testing cohort, with an AUC value of 0.573 (95% confidence interval [CI], 0.468 ~ 0.674). The pure imaging-based model and the combined model correctly classified 75.0% and 85.4% of MSI status in the testing cohort, with AUC values of 0.820 (95% CI, 0.718 ~ 0.884) and 0.868 (95% CI, 0.784 ~ 0.929), respectively. Both deep learning models performed better than the clinical model (p < 0.05). There was no statistically significant difference between the deep learning models with or without integrating clinical factors.

CONCLUSIONS

Deep learning based on high-resolution T2-weighted magnetic resonance images showed a good predictive performance for MSI status in rectal cancer patients. The proposed model may help to identify patients who would benefit from chemotherapy or immunotherapy and determine individualized therapeutic strategies for these patients.

Cancer genotypes prediction and associations analysis from imaging phenotypes: a survey on radiogenomics

In this paper, we present a survey on the progress of radiogenomics research, which predicts cancer genotypes from imaging phenotypes and investigates the associations between them. First, we present an overview of the popular technology modalities for obtaining diagnostic medical images. Second, we summarize recently used methodologies for radiogenomics analysis, including statistical analysis, radiomics and deep learning. And then, we give a survey on the recent research based on several types of cancers. Finally, we discuss these studies and propose possible future research directions. In conclusion, we have identified strong correlations between cancer genotypes and imaging phenotypes. In addition, with the rapid growth of medical data, deep learning models show great application potential for radiogenomics.

A low-cost texture-based pipeline for predicting myocardial tissue remodeling and fibrosis using cardiac ultrasound

Background

Maturation of ultrasound myocardial tissue characterization may have far-reaching implications as a widely available alternative to cardiac magnetic resonance (CMR) for risk stratification in left ventricular (LV) remodeling.

Methods

We extracted 328 texture-based features of myocardium from still ultrasound images. After we explored the phenotypes of myocardial textures using unsupervised similarity networks, global LV remodeling parameters were predicted using supervised machine learning models. Separately, we also developed supervised models for predicting the presence of myocardial fibrosis using another cohort who underwent cardiac magnetic resonance (CMR). For the prediction, patients were divided into a training and test set (80:20).

Findings

Texture-based tissue feature extraction was feasible in 97% of total 534 patients. Interpatient similarity analysis delineated two patient groups based on the texture features: one group had more advanced LV remodeling parameters compared to the other group. Furthermore, this group was associated with a higher incidence of cardiac deaths (p = 0.001) and major adverse cardiac events (p < 0.001). The supervised models predicted reduced LV ejection fraction (<50%) and global longitudinal strain (<16%) with area under the receiver-operator-characteristics curves (ROC AUC) of 0.83 and 0.87 in the hold-out test set, respectively. Furthermore, the presence of myocardial fibrosis was predicted from only ultrasound myocardial texture with an ROC AUC of 0.84 (sensitivity 86.4% and specificity 83.3%) in the test set.

Interpretation

Ultrasound texture-based myocardial tissue characterization identified phenotypic features of LV remodeling from still ultrasound images. Further clinical validation may address critical barriers in the adoption of ultrasound techniques for myocardial tissue characterization.

Funding

None.