Comparable Performance of Deep Learning-Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer

Improved deep learning for automatic localisation and segmentation of rectal cancer on T2-weighted MRI

INTRODUCTION

The automatic segmentation approaches of rectal cancer from magnetic resonance imaging (MRI) are very valuable to relieve physicians from heavy workloads and enhance working efficiency. This study aimed to compare the segmentation accuracy of a proposed model with the other three models and the inter-observer consistency.

METHODS

A total of 65 patients with rectal cancer who underwent MRI examination were enrolled in our cohort and were randomly divided into a training cohort (n = 45) and a validation cohort (n = 20). Two experienced radiologists independently segmented rectal cancer lesions. A novel segmentation model (AttSEResUNet) was trained on T2WI based on ResUNet and attention mechanisms. The segmentation performance of the AttSEResUNet, U-Net, ResUNet and U-Net with Attention Gate (AttUNet) was compared, using Dice similarity coefficient (DSC), Hausdorff distance (HD), mean distance to agreement (MDA) and Jaccard index. The segmentation variability of automatic segmentation models and inter-observer was also evaluated.

RESULTS

The AttSEResUNet with post-processing showed perfect lesion recognition rate (100%) and false recognition rate (0), and its evaluation metrics outperformed other three models for two independent readers (observer 1: DSC = 0.839 ± 0.112, HD = 9.55 ± 6.68, MDA = 0.556 ± 0.722, Jaccard index = 0.736 ± 0.150; observer 2: DSC = 0.856 ± 0.099, HD = 11.0 ± 10.1, MDA = 0.789 ± 1.07, Jaccard index = 0.673 ± 0.130). The segmentation performance of AttSEResUNet was comparable and similar to manual variability (DSC = 0.857 ± 0.115, HD = 10.0 ± 10.0, MDA = 0.704 ± 1.17, Jaccard index = 0.666 ± 0.139).

CONCLUSION

Comparing with other three models, the proposed AttSEResUNet model was demonstrated as a more accurate model for contouring the rectal tumours in axial T2WI images, whose variability was similar to that of inter-observer.

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.

Performance reporting design in artificial intelligence studies using image-based TNM staging and prognostic parameters in rectal cancer: a systematic review

PURPOSE

The integration of artificial intelligence (AI) and magnetic resonance imaging in rectal cancer has the potential to enhance diagnostic accuracy by identifying subtle patterns and aiding tumor delineation and lymph node assessment. According to our systematic review focusing on convolutional neural networks, AI-driven tumor staging and the prediction of treatment response facilitate tailored treat-ment strategies for patients with rectal cancer.

METHODS

This paper summarizes the current landscape of AI in the imaging field of rectal cancer, emphasizing the performance reporting design based on the quality of the dataset, model performance, and external validation.

RESULTS

AI-driven tumor segmentation has demonstrated promising results using various convolutional neural network models. AI-based predictions of staging and treatment response have exhibited potential as auxiliary tools for personalized treatment strategies. Some studies have indicated superior performance than conventional models in predicting microsatellite instability and KRAS status, offer-ing noninvasive and cost-effective alternatives for identifying genetic mutations.

CONCLUSION

Image-based AI studies for rectal can-cer have shown acceptable diagnostic performance but face several challenges, including limited dataset sizes with standardized data, the need for multicenter studies, and the absence of oncologic relevance and external validation for clinical implantation. Overcoming these pitfalls and hurdles is essential for the feasible integration of AI models in clinical settings for rectal cancer, warranting further research.

KRAS status predicted by pretreatment MRI radiomics was associated with lung metastasis in locally advanced rectal cancer patients

BACKGROUND

Mutated KRAS may indicate an invasive nature and predict prognosis in locally advanced rectal cancer (LARC). We aimed to establish a radiomic model using pretreatment T2W MRIs to predict KRAS status and explore the association between the KRAS status or model predictions and lung metastasis.

METHODS

In this retrospective multicentre study, LARC patients from two institutions between January 2012 and January 2019 were randomly divided into training and testing cohorts. Least absolute shrinkage and selection operator (LASSO) regression and the support vector machine (SVM) classifier were utilized to select significant radiomic features and establish a prediction model, which was validated by radiomic score distribution and decision curve analysis. The association between the model stratification and lung metastasis was investigated by Cox regression and Kaplan‒Meier survival analysis; the results were compared by the log-rank test.

RESULTS

Overall, 103 patients were enrolled (73 and 30 in the training and testing cohorts, respectively). The median follow-up was 38.1 months (interquartile range: 26.9, 49.4). The radiomic model had an area under the curve (AUC) of 0.983 in the training cohort and 0.814 in the testing cohort. Using a cut-off of 0.679 defined by the receiver operating characteristic (ROC) curve, patients with a high radiomic score (RS) had a higher risk for lung metastasis (HR 3.565, 95% CI 1.337, 9.505, p = 0.011), showing similar predictive performances for the mutant and wild-type KRAS groups (HR 3.225, 95% CI 1.249, 8.323, p = 0.016, IDI: 1.08%, p = 0.687; NRI 2.23%, p = 0.766).

CONCLUSIONS

We established and validated a radiomic model for predicting KRAS status in LARC. Patients with high RS experienced more lung metastases. The model could noninvasively detect KRAS status and may help individualize clinical decision-making.

Radiogenomics: Contemporary Applications in the Management of Rectal Cancer

Radiogenomics, a sub-domain of radiomics, refers to the prediction of underlying tumour biology using non-invasive imaging markers. This novel technology intends to reduce the high costs, workload and invasiveness associated with traditional genetic testing via the development of 'imaging biomarkers' that have the potential to serve as an alternative 'liquid-biopsy' in the determination of tumour biological characteristics. Radiogenomics also harnesses the potential to unlock aspects of tumour biology which are not possible to assess by conventional biopsy-based methods, such as full tumour burden, intra-/inter-lesion heterogeneity and the possibility of providing the information of tumour biology longitudinally. Several studies have shown the feasibility of developing a radiogenomic-based signature to predict treatment outcomes and tumour characteristics; however, many lack prospective, external validation. We performed a systematic review of the current literature surrounding the use of radiogenomics in rectal cancer to predict underlying tumour biology.

Artificial intelligence and radiomics in magnetic resonance imaging of rectal cancer: a review

Rectal cancer (RC) is one of the most common tumours worldwide in both males and females, with significant morbidity and mortality rates, and it accounts for approximately one-third of colorectal cancers (CRCs). Magnetic resonance imaging (MRI) has been demonstrated to be accurate in evaluating the tumour location and stage, mucin content, invasion depth, lymph node (LN) metastasis, extramural vascular invasion (EMVI), and involvement of the mesorectal fascia (MRF). However, these features alone remain insufficient to precisely guide treatment decisions. Therefore, new imaging biomarkers are necessary to define tumour characteristics for staging and restaging patients with RC. During the last decades, RC evaluation via MRI-based radiomics and artificial intelligence (AI) tools has been a research hotspot. The aim of this review was to summarise the achievement of MRI-based radiomics and AI for the evaluation of staging, response to therapy, genotyping, prediction of high-risk factors, and prognosis in the field of RC. Moreover, future challenges and limitations of these tools that need to be solved to favour the transition from academic research to the clinical setting will be discussed.

Prognostic value of multi b-value DWI in patients with locally advanced rectal cancer

OBJECTIVES

To evaluate the potential of multi b-value DWI in predicting the prognosis of patients with locally advanced rectal cancer (LARC).

METHODS

From 2015 to 2019, a total of 161 patients with LARC were enrolled and randomly sampled into a training set (n = 113) and validation set (n = 48). Multi b-value DWI (b = 0~1500 s/mm²) scans were postprocessed to generate functional parameters, including apparent diffusion coefficient (ADC), Dt, Dp, f, distributed diffusion coefficient (DDC), and α. Histogram features of each functional parameter were submitted into Least absolute shrinkage and selection operator (LASSO) and stepwise multivariate COX analysis to generate DWI_score based on the training set. The prognostic model was constructed with functional parameter, DWI_score, and clinicopathologic factors by using univariate and multivariate COX analysis on the training set and verified on the validation set.

RESULTS

Multivariate COX analysis revealed that DWI_score was an independent indicator for 5-year progression-free survival (PFS, HR = 5.573, p < 0.001), but not for overall survival (OS, HR = 2.177, p = 0.051). No mean value of functional parameters was correlated with PFS or OS. Prognostic model for 5-year PFS based on DWI_score, TNM-stage, mesorectal fascia (MRF), and extramural venous invasion (EMVI) showed good performance both in the training set (AUC = 0.819) and validation set (AUC = 0.815).

CONCLUSIONS

The DWI_score based on histogram features of multi b-value DWI functional parameters was an independent factor for PFS of LARC and the prognostic model with a combination of DWI_score and clinicopathologic factors could indicate the progression risk before treatment.

KEY POINTS

• Mean value of functional parameters obtained from multi b-value DWI might not be useful to assess the prognosis of LARC. • The DWI_score based on histogram features of multi b-value DWI functional parameters was an independent prognosis factor for PFS of LARC. • Prognostic model based on DWI_score and clinicopathologic factors could indicate the progression risk of LARC before treatment.

MRI-Based Artificial Intelligence in Rectal Cancer

Rectal cancer (RC) accounts for approximately one-third of colorectal cancer (CRC), with death rates increasing in patients younger than 50 years old. Magnetic resonance imaging (MRI) is routinely performed for tumor evaluation. However, the semantic features from images alone remain insufficient to guide treatment decisions. Functional MRIs are useful for revealing microstructural and functional abnormalities and nevertheless have low or modest repeatability and reproducibility. Therefore, during the preoperative evaluation and follow-up treatment of patients with RC, novel noninvasive imaging markers are needed to describe tumor characteristics to guide treatment strategies and achieve individualized diagnosis and treatment. In recent years, the development of artificial intelligence (AI) has created new tools for RC evaluation based on MRI. In this review, we summarize the research progress of AI in the evaluation of staging, prediction of high-risk factors, genotyping, response to therapy, recurrence, metastasis, prognosis, and segmentation with RC. We further discuss the challenges of clinical application, including improvement in imaging, model performance, and the biological meaning of features, which may also be major development directions in the future. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 2.

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.

Role of radiomics in the diagnosis and treatment of gastrointestinal cancer

Gastrointestinal cancer (GIC) has high morbidity and mortality as one of the main causes of cancer death. Preoperative risk stratification is critical to guide patient management, but traditional imaging studies have difficulty predicting its biological behavior. The emerging field of radiomics allows the conversion of potential pathophysiological information in existing medical images that cannot be visually recognized into high-dimensional quantitative image features. Tumor lesion characterization, therapeutic response evaluation, and survival prediction can be achieved by analyzing the relationships between these features and clinical and genetic data. In recent years, the clinical application of radiomics to GIC has increased dramatically. In this editorial, we describe the latest progress in the application of radiomics to GIC and discuss the value of its potential clinical applications, as well as its limitations and future directions.

Cleaning Radiotherapy Contours for Radiomics Studies, is it Worth it? A Head and Neck Cancer Study

•

PET images features are more stable across different delineation of the same target.

•

Shape family features are more stable.

•

The survival model based on Dedicated contours achieved better performance for predicting PFS.

A vast majority of studies in the radiomics field are based on contours originating from radiotherapy planning. This kind of delineation (e.g. Gross Tumor Volume, GTV) is often larger than the true tumoral volume, sometimes including parts of other organs (e.g. trachea in Head and Neck, H&N studies) and the impact of such over-segmentation was little investigated so far. In this paper, we propose to evaluate and compare the performance between models using two contour types: those from radiotherapy planning, and those specifically delineated for radiomics studies. For the latter, we modified the radiotherapy contours to fit the true tumoral volume. The two contour types were compared when predicting Progression-Free Survival (PFS) using Cox models based on radiomics features extracted from FluoroDeoxyGlucose-Positron Emission Tomography (FDG-PET) and CT images of 239 patients with oropharyngeal H&N cancer collected from five centers, the data from the 2020 HECKTOR challenge. Using Dedicated contours demonstrated better performance for predicting PFS, where Harell’s concordance indices of 0.61 and 0.69 were achieved for Radiotherapy and Dedicated contours, respectively. Using automatically Resegmented contours based on a fixed intensity range was associated with a C-index of 0.63. These results illustrate the importance of using clean dedicated contours that are close to the true tumoral volume in radiomics studies, even when tumor contours are already available from radiotherapy treatment planning