Predicting Rectal Cancer Response to Neoadjuvant Chemoradiotherapy Using Deep Learning of Diffusion Kurtosis MRI

Deep learning algorithms for predicting pathological complete response in MRI of rectal cancer patients undergoing neoadjuvant chemoradiotherapy: a systematic review

PURPOSE

This systematic review examines the utility of deep learning algorithms in predicting pathological complete response (pCR) in rectal cancer patients undergoing neoadjuvant chemoradiotherapy (nCRT). The primary goal is to evaluate the performance of MRI-based artificial intelligence (AI) models and explore factors affecting their diagnostic accuracy.

METHODS

The review followed PRISMA guidelines and is registered with PROSPERO (CRD42024628017). Literature searches were conducted in PubMed, Embase, and Cochrane Library using keywords such as "artificial intelligence," "rectal cancer," "MRI," and "pathological complete response." Articles involving deep learning models applied to MRI for predicting pCR were included, excluding non-MRI data and studies without AI applications. Data on study characteristics, MRI sequences, AI model details, and performance metrics were extracted. Quality assessment was performed using the PROBAST tool.

RESULTS

Out of 512 initial records, 26 studies met the inclusion criteria. Most studies demonstrated promising diagnostic performance, with AUC values for external validation typically exceeding 0.8. The use of T2W and diffusion-weighted imaging (DWI) MRI phases enhanced model accuracy compared to T2W alone. Larger datasets generally correlated with improved model performance. However, heterogeneity in model designs, MRI protocols, and the limited integration of clinical data were noted as challenges.

CONCLUSION

AI-enhanced MRI demonstrates significant potential in predicting pCR in rectal cancer, particularly with T2W + DWI sequences and larger datasets. While integrating clinical data remains controversial, standardizing methodologies and expanding datasets will further enhance model robustness and clinical utility.

ResNet-Vision Transformer based MRI-endoscopy fusion model for predicting treatment response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer: A multicenter study

Background:

Neoadjuvant chemoradiotherapy followed by radical surgery has been a common practice for patients with locally advanced rectal cancer, but the response rate varies among patients. This study aimed to develop a ResNet-Vision Transformer based magnetic resonance imaging (MRI)-endoscopy fusion model to precisely predict treatment response and provide personalized treatment.

Methods:

In this multicenter study, 366 eligible patients who had undergone neoadjuvant chemoradiotherapy followed by radical surgery at eight Chinese tertiary hospitals between January 2017 and June 2024 were recruited, with 2928 pretreatment colonic endoscopic images and 366 pelvic MRI images. An MRI-endoscopy fusion model was constructed based on the ResNet backbone and Transformer network using pretreatment MRI and endoscopic images. Treatment response was defined as good response or non-good response based on the tumor regression grade. The Delong test and the Hanley–McNeil test were utilized to compare prediction performance among different models and different subgroups, respectively. The predictive performance of the MRI-endoscopy fusion model was comprehensively validated in the test sets and was further compared to that of the single-modal MRI model and single-modal endoscopy model.

Results:

The MRI-endoscopy fusion model demonstrated favorable prediction performance. In the internal validation set, the area under the curve (AUC) and accuracy were 0.852 (95% confidence interval [CI]: 0.744–0.940) and 0.737 (95% CI: 0.712–0.844), respectively. Moreover, the AUC and accuracy reached 0.769 (95% CI: 0.678–0.861) and 0.729 (95% CI: 0.628–0.821), respectively, in the external test set. In addition, the MRI-endoscopy fusion model outperformed the single-modal MRI model (AUC: 0.692 [95% CI: 0.609–0.783], accuracy: 0.659 [95% CI: 0.565–0.775]) and the single-modal endoscopy model (AUC: 0.720 [95% CI: 0.617–0.823], accuracy: 0.713 [95% CI: 0.612–0.809]) in the external test set.

Conclusion:

The MRI-endoscopy fusion model based on ResNet-Vision Transformer achieved favorable performance in predicting treatment response to neoadjuvant chemoradiotherapy and holds tremendous potential for enabling personalized treatment regimens for locally advanced rectal cancer patients.

Prediction and validation of pathologic complete response for locally advanced rectal cancer under neoadjuvant chemoradiotherapy based on a novel predictor using interpretable machine learning

BACKGROUND

Precise evaluation of pathological complete response (pCR) is essential for determining the prognosis of patients with locally advanced rectal cancer (LARC) undergoing neoadjuvant chemoradiotherapy (NCRT) and can offer clues for the selection of subsequent treatment strategies. Most current predictive models for pCR focus primarily on pre-treatment factors, neglecting the dynamic systemic changes that occur during neoadjuvant chemoradiotherapy, and are constrained by low accuracy and lack of integrity.

PURPOSE

This study devised a novel predictor of pCR using dynamic alterations in systemic inflammation-nutritional marker indexes (SINI) during neoadjuvant therapy and developed a machine-learning model to predict pCR.

METHODS

Two cohorts of patients with LARC from center one from 2012 to 2017 and from center two from 2020 to 2023 were integrated for analysis. This study compared dynamic changes in blood indexes before and after neoadjuvant therapy and surgical operation. A least absolute shrinkage and selection operator (LASSO) regression analysis was conducted to mitigate collinearity and identify key indexes, constructing the SINI. Univariate and multiple logistic regression analyses were used to identify the independent risk factors associated with pCR. Additionally, 10 machine learning algorithms were employed to develop predictive models to assess risk. The hyperparameters of the machine learning models were optimized using a random search and 10-fold cross-validation. The models were assessed by examining various metrics, including the area under the receiver operating characteristic curves (AUC), the area under the precision-recall curve (AUPRC), decision curve analysis, calibration curves, and the precision and accuracy of the internal and external validation cohorts. Additionally, Shapley's additive explanations (SHAP) were employed to interpret the machine learning models.

RESULTS

The study cohort comprised 677 patients from the center one and 224 patients from the center two. Six key indexes were identified, and a predictive index, SINI, was constructed. Univariate and multiple logistic regression analyses revealed that SINI, clinical T-stage, clinical N-stage, tumor size, and the distance from the anal verge were independent risk factors for pCR in patients with LARC following NCRT. The mean AUC value of the extreme gradient boosting (XGB) model in the 10-fold cross-validation of the training set was 0.877. The XGB model demonstrated superior performance in the internal and external validation sets. Specifically, in the internal test set, the XGB model achieved an AUC of 0.86, AUPRC of 0.707, accuracy of 0.82, and precision of 0.80. In the external validation set, the XGB model exhibited an AUC of 0.83, AUPRC of 0.702, accuracy of 0.81, and precision of 0.81. Additionally, the predictions generated by the XGB model were analyzed using SHAP.

CONCLUSION

This study involved developing and validating an XGB model using SINI to predict pCR in patients with LARC. Besides, a SINI-based machine learning model shows promise in accurately predicting pCR following NCRT in patients with resectable LARC, offering valuable insights for personalized treatment approaches.

Visualization analysis of research hotspots and trends in MRI-based artificial intelligence in rectal cancer

Background

Rectal cancer (RC) is one of the most common types of cancer worldwide. With the development of artificial intelligence (AI), the application of AI in preoperative evaluation and follow-up treatment of RC based on magnetic resonance imaging (MRI) has been the focus of research in this field. This review was conducted to develop comprehensive insight into the current research progress, hotspots, and future trends in AI based on MRI in RC, which remains to be studied.

Methods

Literature related to AI based on MRI and RC, as of November 2023, was obtained from the Web of Science Core Collection database. Visualization and bibliometric analyses of publication quantity and content were conducted to explore temporal trends, spatial distribution, collaborative networks, influential articles, keyword co-occurrence, and research directions.

Results

A total of 177 papers (152 original articles and 25 reviews) were identified from 24 countries/regions, 351 institutions, and 81 journals. Since 2019, the number of studies on this topic has rapidly increased. China and the United States have contributed the highest number of publications and institutions, cultivating the most intimate collaborative relationship. The highest number of articles derive from Sun Yat-sen University, while Frontiers in Oncology has published the highest number of relevant articles. Research on MRI-based AI in this field has mainly focused on preoperative diagnosis and prediction of treatment efficacy and prognosis.

Conclusions

This study provides an objective and comprehensive overview of the publications on MRI-based AI in RC and identifies the present research landscape, hotspots, and prospective trends in this field, which can provide valuable guidance for scholars worldwide.

Predicting pathological complete response following neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer using merged model integrating MRI-based radiomics and deep learning data

BACKGROUND

To construct and compare merged models integrating clinical factors, MRI-based radiomics features and deep learning (DL) models for predicting pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC).

METHODS

Totally 197 patients with LARC administered surgical resection after nCRT were assigned to cohort 1 (training and test sets); meanwhile, 52 cases were assigned to cohort 2 as a validation set. Radscore and DL models were established for predicting pCR applying pre- and post-nCRT MRI data, respectively. Different merged models integrating clinical factors, Radscore and DL model were constituted. Their predictive performances were validated and compared by receiver operating characteristic (ROC) and decision curve analyses (DCA).

RESULTS

Merged models were established integrating selected clinical factors, Radscore and DL model for pCR prediction. The areas under the ROC curves (AUCs) of the pre-nCRT merged model were 0.834 (95% CI: 0.737-0.931) and 0.742 (95% CI: 0.650-0.834) in test and validation sets, respectively. The AUCs of the post-nCRT merged model were 0.746 (95% CI: 0.636-0.856) and 0.737 (95% CI: 0.646-0.828) in test and validation sets, respectively. DCA showed that the pretreatment algorithm could yield enhanced clinically benefit than the post-nCRT approach.

CONCLUSIONS

The pre-nCRT merged model including clinical factors, Radscore and DL model constitutes an effective non-invasive tool for pCR prediction in LARC.

Advancements and Challenges in the Image-Based Diagnosis of Lung and Colon Cancer: A Comprehensive Review

Image-based diagnosis has become a crucial tool in the identification and management of various cancers, particularly lung and colon cancer. This review delves into the latest advancements and ongoing challenges in the field, with a focus on deep learning, machine learning, and image processing techniques applied to X-rays, CT scans, and histopathological images. Significant progress has been made in imaging technologies like computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET), which, when combined with machine learning and artificial intelligence (AI) methodologies, have greatly enhanced the accuracy of cancer detection and characterization. These advances have enabled early detection, more precise tumor localization, personalized treatment plans, and overall improved patient outcomes. However, despite these improvements, challenges persist. Variability in image interpretation, the lack of standardized diagnostic protocols, unequal access to advanced imaging technologies, and concerns over data privacy and security within AI-based systems remain major obstacles. Furthermore, integrating imaging data with broader clinical information is crucial to achieving a more comprehensive approach to cancer diagnosis and treatment. This review provides valuable insights into the recent developments and challenges in image-based diagnosis for lung and colon cancers, underscoring both the remarkable progress and the hurdles that still need to be overcome to optimize cancer care.

Added value of histogram analysis of intravoxel incoherent motion and diffusion kurtosis imaging for the evaluation of complete response to neoadjuvant therapy in locally advanced rectal cancer

OBJECTIVE

To evaluate how intravoxel incoherent motion (IVIM) and diffusion kurtosis imaging (DKI) histogram analysis contribute to assessing complete response (CR) to neoadjuvant therapy (NAT) in locally advanced rectal cancer (LARC).

MATERIAL AND METHODS

In this prospective study, participants with LARC, who underwent NAT and subsequent surgery, with adequate MR image quality, were enrolled from November 2021 to March 2023. Conventional MRI (T2WI and DWI), IVIM, and DKI were performed before NAT (pre-NAT) and within two weeks before surgery (post-NAT). Image evaluation was independently performed by two experienced radiologists. Pathological complete response (pCR) was used as the reference standard. An IVIM-DKI-added model (a combination of IVIM and DKI histogram parameters with T2WI and DWI) was constructed. Receiver operating characteristic (ROC) curves were generated to evaluate the diagnostic performance of conventional MRI and the IVIM-DKI-added model.

RESULTS

A total of 59 participants (median age: 58.00 years [IQR: 52.00, 62.00]; 38 [64%] men) were evaluated, including 21 pCR and 38 non-pCR cases. The histogram parameters of DKI, including skewness of kurtosis post-NAT (post-KSkewness) and root mean squared of change ratio of diffusivity (Δ%DDKI-root mean squared), were entered into the IVIM-DKI-added model. The area under the ROC curve (AUC) of the IVIM-DKI-added model for assessing CR to NAT was significantly higher than that of conventional MRI (0.855 [95% CI: 0.749-0.960] vs 0.685 [95% CI: 0.565-0.806], p < 0.001).

CONCLUSION

IVIM and DKI provide added value in the evaluation of CR to NAT in LARC.

KEY POINTS

Question The current conventional imaging evaluation system lacks adequacy for assessing CR to NAT in LARC. Findings Significantly improved diagnostic performance was observed with the histogram analysis of IVIM and DKI in conjunction with conventional MRI. Clinical relevance IVIM and DKI provide significant value in evaluating CR to NAT in LARC, which bears significant implications for reducing surgical complications and facilitating organ preservation.

Utilization of diffusion-weighted derived mathematical models to predict prognostic factors of resectable rectal cancer

PURPOSE

This study explored models of monoexponential diffusion-weighted imaging (DWI), diffusion kurtosis imaging (DKI), stretched exponential (SEM), fractional-order calculus (FROC), and continuous-time random-walk (CTRW) as diagnostic tools for assessing pathological prognostic factors in patients with resectable rectal cancer (RRC).

METHODS

RRC patients who underwent radical surgery were included. The apparent diffusion coefficient (ADC), the mean kurtosis (MK) and mean diffusion (MD) from the DKI model, the distributed diffusion coefficient (DDC) and α from the SEM model, D, β and u from the FROC model, and D, α and β from the CTRW model were assessed.

RESULTS

There were a total of 181 patients. The area under the receiver operating characteristic (ROC) curve (AUC) of CTRW-α for predicting histology type was significantly higher than that of FROC-u (0.780 vs. 0.671, p = 0.043). The AUC of CTRW-α for predicting pT stage was significantly higher than that of FROC-u and ADC (0.786 vs.0.683, p = 0.043; 0.786 vs. 0.682, p = 0.030), the difference in predictive efficacy of FROC-u between ADC and MK was not statistically significant [0.683 vs. 0.682, p = 0.981; 0.683 vs. 0.703, p = 0.720]; the difference between the predictive efficacy of MK and ADC was not statistically significant (p = 0.696). The AUC of CTRW (α + β) (0.781) was significantly higher than that of FROC-u (0.781 vs. 0.625, p = 0.003) in predicting pN stage but not significantly different from that of MK (p = 0.108).

CONCLUSION

The CTRW and DKI models may serve as imaging biomarkers to predict pathological prognostic factors in RRC patients before surgery.

Deep learning model based on endoscopic images predicting treatment response in locally advanced rectal cancer undergo neoadjuvant chemoradiotherapy: a multicenter study

PURPOSE

Neoadjuvant chemoradiotherapy has been the standard practice for patients with locally advanced rectal cancer. However, the treatment response varies greatly among individuals, how to select the optimal candidates for neoadjuvant chemoradiotherapy is crucial. This study aimed to develop an endoscopic image-based deep learning model for predicting the response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer.

METHODS

In this multicenter observational study, pre-treatment endoscopic images of patients from two Chinese medical centers were retrospectively obtained and a deep learning-based tumor regression model was constructed. Treatment response was evaluated based on the tumor regression grade and was defined as good response and non-good response. The prediction performance of the deep learning model was evaluated in the internal and external test sets. The main outcome was the accuracy of the treatment prediction model, measured by the AUC and accuracy.

RESULTS

This deep learning model achieved favorable prediction performance. In the internal test set, the AUC and accuracy were 0.867 (95% CI: 0.847-0.941) and 0.836 (95% CI: 0.818-0.896), respectively. The prediction performance was fully validated in the external test set, and the model had an AUC of 0.758 (95% CI: 0.724-0.834) and an accuracy of 0.807 (95% CI: 0.774-0.843).

CONCLUSION

The deep learning model based on endoscopic images demonstrated exceptional predictive power for neoadjuvant treatment response, highlighting its potential for guiding personalized therapy.

Machine learning in predicting pathological complete response to neoadjuvant chemoradiotherapy in rectal cancer using MRI: a systematic review and meta-analysis

OBJECTIVES

To evaluate the performance of machine learning models in predicting pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) in patients with rectal cancer using magnetic resonance imaging.

METHODS

We searched PubMed, Embase, Cochrane Library, and Web of Science for studies published before March 2024. The Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) was used to assess the methodological quality of the included studies, random-effects models were used to calculate sensitivity and specificity, I2 values were used for heterogeneity measurements, and subgroup analyses were carried out to detect potential sources of heterogeneity.

RESULTS

A total of 1699 patients from 24 studies were included. For machine learning models in predicting pCR to nCRT, the meta-analysis calculated a pooled area under the curve (AUC) of 0.91 (95% CI, 0.88-0.93), pooled sensitivity of 0.83 (95% CI, 0.74-0.89), and pooled specificity of 0.86 (95% CI, 0.80-0.91). We investigated 6 studies that mainly contributed to heterogeneity. After performing meta-analysis again excluding these 6 studies, the heterogeneity was significantly reduced. In subgroup analysis, the pooled AUC of the deep-learning model was 0.93 and 0.89 for the traditional statistical model; the pooled AUC of studies that used diffusion-weighted imaging (DWI) was 0.90 and 0.92 in studies that did not use DWI; the pooled AUC of studies conducted in China was 0.93, and was 0.83 in studies conducted in other countries.

CONCLUSIONS

This systematic study showed that machine learning has promising potential in predicting pCR to nCRT in patients with locally advanced rectal cancer. Compared to traditional machine learning models, although deep-learning-based studies are less predominant and more heterogeneous, they are able to obtain higher AUC.

ADVANCES IN KNOWLEDGE

Compared to traditional machine learning models, deep-learning-based studies are able to obtain higher AUC, although they are less predominant and more heterogeneous. Together with clinical information, machine learning-based models may bring us closer towards precision medicine.

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Can rectal MRI and endorectal ultrasound accurately predict the complete response to neoadjuvant immunotherapy for rectal cancer?

Background

Standardized assessments of clinical complete response (cCR) to neoadjuvant chemoradiotherapy (nCRT) for rectal cancer have been established, but their utility and accuracy remain unclear. This study aimed to evaluate the clinical diagnostic value of rectal magnetic resonance imaging (MRI) and endorectal ultrasonography (ERUS) for the determination of cCRs after neoadjuvant immunotherapy and to investigate the concordance between cCR and pathological complete response (pCR).

Methods

Ninety-four patients with rectal cancer treated with neoadjuvant radiotherapy with or without immunotherapy were included. The sensitivity, specificity, and accuracy of each evaluation method were calculated.

Results

Combined MRI and ERUS assessments found cCR in seven of the 94 patients in our cohort. In the non-immunotherapy group, the sensitivity, specificity, and accuracy of MRI for diagnosing cCR were 50.0%, 85.2%, and 77.1%, respectively, whereas those of ERUS were 50.0%, 92.6%, and 82.9%, respectively; those of combined MRI and ERUS were 25.0%, 96.3%, and 87.5%, respectively. In the immunotherapy group, the sensitivity, specificity, and accuracy with which MRI identified CR were 51.7%, 76.7%, and 64.4%, respectively; those of ERUS were 13.8%, 90.0%, and 52.5%, respectively, and those of combined MRI and ERUS were 10.3%, 96.7%, and 54.2%, respectively. We also found that 32 of 37 patients with pCR did not meet the cCR evaluation criteria. Of these pCR patients, 78.4% (29/37) received immunotherapy. In the entire cohort, there were five pCRs among the seven cCRs. Of the four cCRs that occurred in the immunotherapy group, three were pCRs.

Conclusions

Rectal MRI and/or ERUS did not provide sufficiently accurate assessments of cCR in patients with rectal cancer receiving neoadjuvant therapy, especially immunotherapy, and cCR did not predict pCR.

Image-based artificial intelligence for the prediction of pathological complete response to neoadjuvant chemoradiotherapy in patients with rectal cancer: a systematic review and meta-analysis

OBJECTIVE

Artificial intelligence (AI) holds enormous potential for noninvasively identifying patients with rectal cancer who could achieve pathological complete response (pCR) following neoadjuvant chemoradiotherapy (nCRT). We aimed to conduct a meta-analysis to summarize the diagnostic performance of image-based AI models for predicting pCR to nCRT in patients with rectal cancer.

METHODS

This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. A literature search of PubMed, Embase, Cochrane Library, and Web of Science was performed from inception to July 29, 2023. Studies that developed or utilized AI models for predicting pCR to nCRT in rectal cancer from medical images were included. The Quality Assessment of Diagnostic Accuracy Studies-AI was used to appraise the methodological quality of the studies. The bivariate random-effects model was used to summarize the individual sensitivities, specificities, and areas-under-the-curve (AUCs). Subgroup and meta-regression analyses were conducted to identify potential sources of heterogeneity. Protocol for this study was registered with PROSPERO (CRD42022382374).

RESULTS

Thirty-four studies (9933 patients) were identified. Pooled estimates of sensitivity, specificity, and AUC of AI models for pCR prediction were 82% (95% CI: 76-87%), 84% (95% CI: 79-88%), and 90% (95% CI: 87-92%), respectively. Higher specificity was seen for the Asian population, low risk of bias, and deep-learning, compared with the non-Asian population, high risk of bias, and radiomics (all P < 0.05). Single-center had a higher sensitivity than multi-center (P = 0.001). The retrospective design had lower sensitivity (P = 0.012) but higher specificity (P < 0.001) than the prospective design. MRI showed higher sensitivity (P = 0.001) but lower specificity (P = 0.044) than non-MRI. The sensitivity and specificity of internal validation were higher than those of external validation (both P = 0.005).

CONCLUSIONS

Image-based AI models exhibited favorable performance for predicting pCR to nCRT in rectal cancer. However, further clinical trials are warranted to verify the findings.

Fully semantic segmentation for rectal cancer based on post-nCRT MRl modality and deep learning framework

PURPOSE

Rectal tumor segmentation on post neoadjuvant chemoradiotherapy (nCRT) magnetic resonance imaging (MRI) has great significance for tumor measurement, radiomics analysis, treatment planning, and operative strategy. In this study, we developed and evaluated segmentation potential exclusively on post-chemoradiation T2-weighted MRI using convolutional neural networks, with the aim of reducing the detection workload for radiologists and clinicians.

METHODS

A total of 372 consecutive patients with LARC were retrospectively enrolled from October 2015 to December 2017. The standard-of-care neoadjuvant process included 22-fraction intensity-modulated radiation therapy and oral capecitabine. Further, 243 patients (3061 slices) were grouped into training and validation datasets with a random 80:20 split, and 41 patients (408 slices) were used as the test dataset. A symmetric eight-layer deep network was developed using the nnU-Net Framework, which outputs the segmentation result with the same size. The trained deep learning (DL) network was examined using fivefold cross-validation and tumor lesions with different TRGs.

RESULTS

At the stage of testing, the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and mean surface distance (MSD) were applied to quantitatively evaluate the performance of generalization. Considering the test dataset (41 patients, 408 slices), the average DSC, HD95, and MSD were 0.700 (95% CI: 0.680-0.720), 17.73 mm (95% CI: 16.08-19.39), and 3.11 mm (95% CI: 2.67-3.56), respectively. Eighty-two percent of the MSD values were less than 5 mm, and fifty-five percent were less than 2 mm (median 1.62 mm, minimum 0.07 mm).

CONCLUSIONS

The experimental results indicated that the constructed pipeline could achieve relatively high accuracy. Future work will focus on assessing the performances with multicentre external validation.

Prediction of Pathologic Complete Response for Rectal Cancer Based on Pretreatment Factors Using Machine Learning

BACKGROUND

Pathologic complete response after neoadjuvant therapy is an important prognostic indicator for locally advanced rectal cancer and may give insights into which patients might be treated nonoperatively in the future. Existing models for predicting pathologic complete response in the pretreatment setting are limited by small data sets and low accuracy.

OBJECTIVE

We sought to use machine learning to develop a more generalizable predictive model for pathologic complete response for locally advanced rectal cancer.

DESIGN

Patients with locally advanced rectal cancer who underwent neoadjuvant therapy followed by surgical resection were identified in the National Cancer Database from years 2010 to 2019 and were split into training, validation, and test sets. Machine learning techniques included random forest, gradient boosting, and artificial neural network. A logistic regression model was also created. Model performance was assessed using an area under the receiver operating characteristic curve.

SETTINGS

This study used a national, multicenter data set.

PATIENTS

Patients with locally advanced rectal cancer who underwent neoadjuvant therapy and proctectomy.

MAIN OUTCOME MEASURES

Pathologic complete response defined as T0/xN0/x.

RESULTS

The data set included 53,684 patients. Pathologic complete response was experienced by 22.9% of patients. Gradient boosting showed the best performance with an area under the receiver operating characteristic curve of 0.777 (95% CI, 0.773-0.781), compared with 0.684 (95% CI, 0.68-0.688) for logistic regression. The strongest predictors of pathologic complete response were no lymphovascular invasion, no perineural invasion, lower CEA, smaller size of tumor, and microsatellite stability. A concise model including the top 5 variables showed preserved performance.

LIMITATIONS

The models were not externally validated.

CONCLUSIONS

Machine learning techniques can be used to accurately predict pathologic complete response for locally advanced rectal cancer in the pretreatment setting. After fine-tuning a data set including patients treated nonoperatively, these models could help clinicians identify the appropriate candidates for a watch-and-wait strategy. See Video Abstract .

EL CNCER DE RECTO BASADA EN FACTORES PREVIOS AL TRATAMIENTO MEDIANTE EL APRENDIZAJE AUTOMTICO

ANTECEDENTES:La respuesta patológica completa después de la terapia neoadyuvante es un indicador pronóstico importante para el cáncer de recto localmente avanzado y puede dar información sobre qué pacientes podrían ser tratados de forma no quirúrgica en el futuro. Los modelos existentes para predecir la respuesta patológica completa en el entorno previo al tratamiento están limitados por conjuntos de datos pequeños y baja precisión.OBJETIVO:Intentamos utilizar el aprendizaje automático para desarrollar un modelo predictivo más generalizable para la respuesta patológica completa para el cáncer de recto localmente avanzado.DISEÑO:Los pacientes con cáncer de recto localmente avanzado que se sometieron a terapia neoadyuvante seguida de resección quirúrgica se identificaron en la Base de Datos Nacional del Cáncer de los años 2010 a 2019 y se dividieron en conjuntos de capacitación, validación y prueba. Las técnicas de aprendizaje automático incluyeron bosque aleatorio, aumento de gradiente y red neuronal artificial. También se creó un modelo de regresión logística. El rendimiento del modelo se evaluó utilizando el área bajo la curva característica operativa del receptor.ÁMBITO:Este estudio utilizó un conjunto de datos nacional multicéntrico.PACIENTES:Pacientes con cáncer de recto localmente avanzado sometidos a terapia neoadyuvante y proctectomía.PRINCIPALES MEDIDAS DE VALORACIÓN:Respuesta patológica completa definida como T0/xN0/x.RESULTADOS:El conjunto de datos incluyó 53.684 pacientes. El 22,9% de los pacientes experimentaron una respuesta patológica completa. El refuerzo de gradiente mostró el mejor rendimiento con un área bajo la curva característica operativa del receptor de 0,777 (IC del 95%: 0,773 - 0,781), en comparación con 0,684 (IC del 95%: 0,68 - 0,688) para la regresión logística. Los predictores más fuertes de respuesta patológica completa fueron la ausencia de invasión linfovascular, la ausencia de invasión perineural, un CEA más bajo, un tamaño más pequeño del tumor y la estabilidad de los microsatélites. Un modelo conciso que incluye las cinco variables principales mostró un rendimiento preservado.LIMITACIONES:Los modelos no fueron validados externamente.CONCLUSIONES:Las técnicas de aprendizaje automático se pueden utilizar para predecir con precisión la respuesta patológica completa para el cáncer de recto localmente avanzado en el entorno previo al tratamiento. Después de realizar ajustes en un conjunto de datos que incluye pacientes tratados de forma no quirúrgica, estos modelos podrían ayudar a los médicos a identificar a los candidatos adecuados para una estrategia de observar y esperar. (Traducción-Dr. Ingrid Melo ).

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.

Preoperative detection of lymphovascular invasion in rectal cancer using intravoxel incoherent motion imaging based on radiomics

BACKGROUND

Lymphovascular invasion (LVI) status plays an important role in treatment decision-making in rectal cancer (RC). Intravoxel incoherent motion (IVIM) imaging has been shown to detect LVI; however, making better use of IVIM data remains an important issue that needs to be discussed.

PURPOSE

We proposed to explore the best way to use IVIM quantitative parameters and images to construct radiomics models for the noninvasive detection of LVI in RC.

METHODS

A total of 83 patients (LVI negative (LVI-): LVI positive (LVI+) = 51:32) with postoperative pathology-confirmed LVI status in RC were divided into a training group (n = 58) and a validation group (n = 25). Images were acquired from a 3.0 Tesla machine, including oblique axial T2 weighted imaging (T2WI) and IVIM with 11 b values. The ADC, D, D* and f values were measured on IVIM maps. The ROIs of tumors were delineated on T2WI, DWI, ADCmap , and Dmap images, and three mapping methods were used: ROIs_mapping from DWI, ROIs_mapping from ADCmap , and ROIs_mapping from Dmap . Three-dimensional radiomics features were extracted from the delineated ROIs. Multivariate logistic regression was used for radiomics feature selection. Radiomics models based on different mapping methods were developed. Receiver operating characteristic (ROC) curves, calibration, and decision curve analyses (DCA) were used to evaluate the performance of the models.

RESULTS

Model B, which was constructed with radiomics features from ADCmap , Dmap and fmap by "ROIs_mapping from DWI" and T2WI (AUC 0.894), performed better than other models based on single sequence (AUC 0.600-0.806) and even better than Model A, which was based on "ROIs_mapping from ADC" and T2WI (AUC 0.838). Furthermore, an integrated model was constructed with Model B and the IVIM parameter (f value) with an AUC of 0.920 (95% CI: 0.820-1.000), which was higher than that of Model B, in the validation group.

CONCLUSIONS

The integrated model incorporating the radiomics features and IVIM parameters accurately detected LVI of RC. The "ROIs_mapping from DWI" method provided the best results.

Computed Diffusion-Weighted Images of Rectal Cancer: Image Quality, Restaging, and Treatment Response after Neoadjuvant Therapy

BACKGROUND

Computed diffusion-weighted images (cDWI) of random b value could be derived from acquired DWI (aDWI) with at least two different b values. However, its comparison between aDWI and cDWI images in locally advanced rectal cancer (LARC) patients after neoadjuvant therapy (NT) is needed.

PURPOSE

To compare the cDWI and aDWI in image quality, restaging, and treatment response of LARC after NT.

STUDY TYPE

Retrospective.

POPULATION

Eighty-seven consecutive patients.

FIELD STRENGTH/SEQUENCE

3.0 T/DWI.

ASSESSMENT

All patients underwent two DWI sequences, including conventional acquisition with b = 0 and 1000 s/mm2 (aDWIb1000 ) and another with b = 0 and 700 s/mm2 on a 3.0-T MR scanner. The images of the latter were used to compute the diffusion images with b = 1000 s/mm2 (cDWIb1000 ). Four radiologists with 3, 4, 14, and 25 years of experience evaluated the images to compare the image quality, TN restaging performance, and treatment response between aDWIb1000 and cDWIb1000 .

STATISTICAL TESTS

Interclass correlation coefficients, weighted κ coefficient, paired Wilcoxon, and McNemar or Fisher test were used. A significance level of 0.05 was used.

RESULTS

The cDWIb1000 images were superior to the aDWIb1000 ones in both subjective and objective image quality. In T restaging, the overall diagnostic accuracy of cDWIb1000 images was higher than that of aDWIb1000 images (57.47% vs. 49.43%, P = 0.289 for the inexperienced radiologist; 77.01% vs. 63.22%, significant for the experienced radiologist), with better sensitivity in determining ypT0-Tis tumors. Additionally, it increased the sensitivity in detecting ypT2 tumors for the inexperienced radiologist and ypT3 tumors for the experienced radiologist. N restaging and treatment response were found to be similar between two sequences for both radiologists.

DATA CONCLUSION

Compared to aDWIb1000 images, the computed ones might serve as a wise approach, providing comparable or better image quality, restaging performance, and treatment response assessment for LARC after NT.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY STAGE: 2.

Multiparametric MRI for evaluation of pathological response to the neoadjuvant chemo-immunotherapy in resectable non-small-cell lung cancer

OBJECTIVES

This study aimed to explore the predictive value of intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) and diffusion kurtosis imaging (DKI) quantitative parameters for the response to neoadjuvant chemo-immunotherapy (NCIT) in resectable non-small-cell lung cancer (NSCLC) patients, so as to provide a basis for clinical individualized precision treatment.

METHODS

Treatment naive locally advanced NSCLC patients who enrolled in 3 prospective, open-label, and single-arm clinical trials and received NCIT were retrospectively analyzed in this study. Functional MRI imaging was performed at baseline and following 3 weeks of treatment as an exploratory endpoint to evaluate treatment efficacy. Univariate and multivariate logistic regressions were used to identify independent predictive parameters for NCIT response. Prediction models were built with statistically significant quantitative parameters and their combinations.

RESULTS

In total of 32 patients, 13 were classified as complete pathological response (pCR) and 19 were non-pCR. Post-NCIT ADC, ΔADC, and ΔD values in the pCR group were significantly higher than those in the non-pCR group, while the pre-NCIT D, post-NCIT Kapp, and ΔKapp were significantly lower than those in non-pCR group. Multivariate logistic regression analysis demonstrated that pre-NCIT D and post-NCIT Kapp values were independent predictors for NCIT response. The combined predictive model, which consisted of IVIM-DWI and DKI, showed the best prediction performance with AUC of 0.889.

CONCLUSIONS

The pre-NCIT D, post-NCIT parameters (ADC and Kapp) and Δ parameters (ΔADC, ΔD, and ΔKapp) were effective biomarkers for predicting pathologic response, and pre-NCIT D and post-NCIT Kapp values were independent predictors of NCIT response for NSCLC patients.

CLINICAL RELEVANCE STATEMENT

This exploratory study indicated that IVIM-DWI and DKI MRI imaging would predict pathologic response of neoadjuvant chemo-immunotherapy in locally advanced NSCLC patients at initial state and early treatment, which could help make clinical individualized treatment strategies.

KEY POINTS

• Effective NCIT treatment resulted in increased ADC and D values for NSCLC patients. • The residual tumors in non-pCR group tend to have higher microstructural complexity and heterogeneity, as measured by Kapp. • Pre-NCIT D and post-NCIT Kapp values were independent predictors of NCIT response.

Attention mechanism based multi-sequence MRI fusion improves prediction of response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer

BACKGROUND

Accurate prediction of response to neoadjuvant chemoradiotherapy (nCRT) is very important for treatment plan decision in locally advanced rectal cancer (LARC). The aim of this study was to investigate whether self-attention mechanism based multi-sequence fusion strategy applied to multiparametric magnetic resonance imaging (MRI) based deep learning or hand-crafted radiomics model construction can improve prediction of response to nCRT in LARC.

METHODS

This retrospective analysis enrolled 422 consecutive patients with LARC who received nCRT before surgery at two hospitals. All patients underwent multiparametric MRI scans with three imaging sequences. Tumor regression grade (TRG) was used to assess the response of nCRT based on the resected specimen. Patients were separated into 2 groups: poor responders (TRG 2, 3) versus good responders (TRG 0, 1). A self-attention mechanism, namely channel attention, was applied to fuse the three sequence information for deep learning and radiomics models construction. For comparison, other two models without channel attention were also constructed. All models were developed in the same hospital and validated in the other hospital.

RESULTS

The deep learning model with channel attention mechanism achieved area under the curves (AUCs) of 0.898 in the internal validation cohort and 0.873 in the external validation cohort, which was the best performed model in all cohorts. More importantly, both the deep learning and radiomics model that applied channel attention mechanism performed better than those without channel attention mechanism.

CONCLUSIONS

The self-attention mechanism based multi-sequence fusion strategy can improve prediction of response to nCRT in LARC.

Artificial intelligence based system for predicting permanent stoma after sphincter saving operations

Although the goal of rectal cancer treatment is to restore gastrointestinal continuity, some patients with rectal cancer develop a permanent stoma (PS) after sphincter-saving operations. Although many studies have identified the risk factors and causes of PS, few have precisely predicted the probability of PS formation before surgery. To validate whether an artificial intelligence model can accurately predict PS formation in patients with rectal cancer after sphincter-saving operations. Patients with rectal cancer who underwent a sphincter-saving operation at Taipei Medical University Hospital between January 1, 2012, and December 31, 2021, were retrospectively included in this study. A machine learning technique was used to predict whether a PS would form after a sphincter-saving operation. We included 19 routinely available preoperative variables in the artificial intelligence analysis. To evaluate the efficiency of the model, 6 performance metrics were utilized: accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiving operating characteristic curve. In our classification pipeline, the data were randomly divided into a training set (80% of the data) and a validation set (20% of the data). The artificial intelligence models were trained using the training dataset, and their performance was evaluated using the validation dataset. Synthetic minority oversampling was used to solve the data imbalance. A total of 428 patients were included, and the PS rate was 13.6% (58/428) in the training set. The logistic regression (LR), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), random forest, decision tree and light gradient boosting machine (LightGBM) algorithms were employed. The accuracies of the logistic regression (LR), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), random forest (RF), decision tree (DT) and light gradient boosting machine (LightGBM) models were 70%, 76%, 89%, 93%, 95%, 79% and 93%, respectively. The area under the receiving operating characteristic curve values were 0.79 for the LR model, 0.84 for the GNB, 0.95 for the XGB, 0.95 for the GB, 0.99 for the RF model, 0.79 for the DT model and 0.98 for the LightGBM model. The key predictors that were identified were the distance of the lesion from the anal verge, clinical N stage, age, sex, American Society of Anesthesiologists score, and preoperative albumin and carcinoembryonic antigen levels. Integration of artificial intelligence with available preoperative data can potentially predict stoma outcomes after sphincter-saving operations. Our model exhibited excellent predictive ability and can improve the process of obtaining informed consent.

Deep learning of endoscopic features for the assessment of neoadjuvant therapy response in locally advanced rectal cancer

BACKGROUND

For locally advanced rectal cancer (LARC), accurate response evaluation is necessary to select complete responders after neoadjuvant therapy (NAT) for a watch-and-wait (W&W) strategy. Algorithms based on deep learning have shown great value in medical image analyses. Here we used deep learning algorithms of endoscopic images for the assessment of NAT response in LARC.

METHOD

214 LARC patients were retrospectively included in the study. After NAT, these patients underwent total mesorectal excision (TME) surgery. Among them, 51 (23.8%) of the patients achieved a pathological complete response (pCR). 160 patients from Shanghai Changzheng Hospital were regarded as primary dataset, and the other 54 patients from Zhejiang Cancer Hospital were regarded as validation dataset. ResNet-18 and DenseNet-121 were applied to train the models based on endoscopic images after NAT. Deep learning models were valid in the validation dataset and compared to manual method.

RESULTS

The performances were comparable in AUC between deep learning models and manual method. For mean metrics, sensitivity (0.750 vs. 0.417) and AUC (0.716 vs. 0.601) in ResNet-18 deep learning model were higher than those in the manual method. The deep learning models were able to identify the endoscopic features associated with NAT response by the heatmaps. A diagnostic flow diagram which integrated the deep learning model to assist the clinicians in making decisions for W&W strategy was constructed.

CONCLUSIONS

We created deep learning models using endoscopic features for assessment of NAT in LARC. The deep learning models achieved modest accuracies and performed comparably to manual method.

Accuracy of deep neural learning models in the imaging prediction of pathological complete response after neoadjuvant chemoradiotherapy for locally advanced rectal cancer: a systematic review

PURPOSE

Up to 15-27% of patients achieve pathologic complete response (pCR) following neoadjuvant chemoradiotherapy (CRT) for locally advanced rectal cancer (LARC). Deep neural learning (DL) algorithms have been suggested to be a useful adjunct to allow accurate prediction of pCR and to identify patients who could potentially avoid surgery. This systematic review aims to interrogate the accuracy of DL algorithms at predicting pCR.

METHODS

Embase (PubMed, MEDLINE) databases and Google Scholar were searched to identify eligible English-language studies, with the search concluding in July 2022. Studies reporting on the accuracy of DL models in predicting pCR were selected for review and information pertaining to study characteristics and diagnostic measures was extracted from relevant studies. Risk of bias was evaluated using the Newcastle-Ottawa scale (NOS).

RESULTS

Our search yielded 85 potential publications. Nineteen full texts were reviewed, and a total of 12 articles were included in this systematic review. There were six retrospective and six prospective cohort studies. The most common DL algorithm used was the Convolutional Neural Network (CNN). Performance comparison was carried out via single modality comparison. The median performance for each best-performing algorithm was an AUC of 0.845 (range 0.71-0.99) and Accuracy of 0.85 (0.83-0.98).

CONCLUSIONS

There is a promising role for DL models in the prediction of pCR following neoadjuvant-CRT for LARC. Further studies are needed to provide a standardised comparison in order to allow for large-scale clinical application.

PROPERO REGISTRATION

PROSPERO 2021 CRD42021269904 Available from: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021269904 .

Pretreatment ultrasound-based deep learning radiomics model for the early prediction of pathologic response to neoadjuvant chemotherapy in breast cancer

OBJECTIVES

To investigate the predictive performance of the deep learning radiomics (DLR) model integrating pretreatment ultrasound imaging features and clinical characteristics for evaluating therapeutic response after neoadjuvant chemotherapy (NAC) in patients with breast cancer.

METHODS

A total of 603 patients who underwent NAC were retrospectively included between January 2018 and June 2021 from three different institutions. Four different deep convolutional neural networks (DCNNs) were trained by pretreatment ultrasound images using annotated training dataset (n = 420) and validated in a testing cohort (n = 183). Comparing the predictive performance of these models, the best one was selected for image-only model structure. Furthermore, the integrated DLR model was constructed based on the image-only model combined with independent clinical-pathologic variables. Areas under the curve (AUCs) of these models and two radiologists were compared by using the DeLong method.

RESULTS

As the optimal basic model, Resnet50 achieved an AUC and accuracy of 0.879 and 82.5% in the validation set. The integrated DLR model, yielding the highest classification performance in predicting response to NAC (AUC 0.962 and 0.939 in the training and validation cohort), outperformed the image-only model and the clinical model and also performed better than two radiologists' prediction (all p < 0.05). In addition, predictive efficacy of the radiologists was improved under the assistance of the DLR model significantly.

CONCLUSION

The pretreatment US-based DLR model could hold promise as a clinical guidance for predicting NAC response of patients with breast cancer, thereby providing benefit of timely treatment strategy adjustment to potential poor NAC responders.

KEY POINTS

• Multicenter retrospective study showed that deep learning radiomics (DLR) model based on pretreatment ultrasound image and clinical parameter achieved satisfactory prediction of tumor response to neoadjuvant chemotherapy (NAC) in breast cancer. • The integrated DLR model could become an effective tool to guide clinicians in identifying potential poor pathological responders before chemotherapy. • The predictive efficacy of the radiologists was improved under the assistance of the DLR model.

Imaging of colon and rectal cancer

Colon and rectal cancer imaging has traditionally been performed to assess for distant disease (typically lung and liver metastases) and to assess the resectability of the primary tumor. With technological and scientific advances in imaging and the evolution of treatment options, the role of imaging has expanded. Radiologists are now expected to provide a precise description of primary tumor invasion extent, including adjacent organ invasion, involvement of the surgical resection plane, extramural vascular invasion, lymphadenopathy, and response to neoadjuvant treatment, and to monitor for recurrence after clinical complete response.

Prediction of lymph node metastasis in stage T1-2 rectal cancers with MRI-based deep learning

OBJECTIVES

This study aimed to investigate whether a deep learning (DL) model based on preoperative MR images of primary tumors can predict lymph node metastasis (LNM) in patients with stage T1-2 rectal cancer.

METHODS

In this retrospective study, patients with stage T1-2 rectal cancer who underwent preoperative MRI between October 2013 and March 2021 were included and assigned to the training, validation, and test sets. Four two-dimensional and three-dimensional (3D) residual networks (ResNet18, ResNet50, ResNet101, and ResNet152) were trained and tested on T2-weighted images to identify patients with LNM. Three radiologists independently assessed LN status on MRI, and diagnostic outcomes were compared with the DL model. Predictive performance was assessed with AUC and compared using the Delong method.

RESULTS

In total, 611 patients were evaluated (444 training, 81 validation, and 86 test). The AUCs of the eight DL models ranged from 0.80 (95% confidence interval [CI]: 0.75, 0.85) to 0.89 (95% CI: 0.85, 0.92) in the training set and from 0.77 (95% CI: 0.62, 0.92) to 0.89 (95% CI: 0.76, 1.00) in the validation set. The ResNet101 model based on 3D network architecture achieved the best performance in predicting LNM in the test set, with an AUC of 0.79 (95% CI: 0.70, 0.89) that was significantly greater than that of the pooled readers (AUC, 0.54 [95% CI: 0.48, 0.60]; p < 0.001).

CONCLUSION

The DL model based on preoperative MR images of primary tumors outperformed radiologists in predicting LNM in patients with stage T1-2 rectal cancer.

KEY POINTS

• Deep learning (DL) models with different network frameworks showed different diagnostic performance for predicting lymph node metastasis (LNM) in patients with stage T1-2 rectal cancer. • The ResNet101 model based on 3D network architecture achieved the best performance in predicting LNM in the test set. • The DL model based on preoperative MR images outperformed radiologists in predicting LNM in patients with stage T1-2 rectal cancer.

Application of artificial intelligence in diagnosis and treatment of colorectal cancer: A novel Prospect

In the past few decades, according to the rapid development of information technology, artificial intelligence (AI) has also made significant progress in the medical field. Colorectal cancer (CRC) is the third most diagnosed cancer worldwide, and its incidence and mortality rates are increasing yearly, especially in developing countries. This article reviews the latest progress in AI in diagnosing and treating CRC based on a systematic collection of previous literature. Most CRCs transform from polyp mutations. The computer-aided detection systems can significantly improve the polyp and adenoma detection rate by early colonoscopy screening, thereby lowering the possibility of mutating into CRC. Machine learning and bioinformatics analysis can help screen and identify more CRC biomarkers to provide the basis for non-invasive screening. The Convolutional neural networks can assist in reading histopathologic tissue images, reducing the experience difference among doctors. Various studies have shown that AI-based high-level auxiliary diagnostic systems can significantly improve the readability of medical images and help clinicians make more accurate diagnostic and therapeutic decisions. Moreover, Robotic surgery systems such as da Vinci have been more and more commonly used to treat CRC patients, according to their precise operating performance. The application of AI in neoadjuvant chemoradiotherapy has further improved the treatment and efficacy evaluation of CRC. In addition, AI represented by deep learning in gene sequencing research offers a new treatment option. All of these things have seen that AI has a promising prospect in the era of precision medicine.

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.

Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer

Neoadjuvant systemic treatment before surgery is a prevalent regimen in the patients with advanced-stage or high-risk tumor, which has shaped the treatment strategies and cancer survival in the past decades. However, some patients present with poor response to the neoadjuvant treatment. Therefore, it is of great significance to develop tools to help distinguish the patients that could achieve pathological complete response before surgery to avoid inappropriate treatment. Here, this study demonstrated a multi-task deep learning tool called DeepInteg. In the DeepInteg framework, the segmentation module was constructed based on the CE-Net with a context extractor to achieve end-to-end delineation of region of interest (ROI) from radiological images, then the features of segmented Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) images of each case were fused and input to the classification module based on a convolution neural network for treatment outcome prediction. The dataset with 1700 MRI and CT slices collected from the prospectively randomized clinical trial (NCT01211210) on systemic treatment for rectal cancer was used to develop and systematically optimize DeepInteg. As a result, DeepInteg achieved automatic segmentation of tumoral ROI with Dices of 0.766 and 0.719 and mIoUs of 0.788 and 0.756 in CT and MRI images, respectively. In addition, DeepInteg achieved AUC of 0.833, accuracy of 0.826 and specificity of 0.856 in the prediction for pathological complete response after treatment, which showed better performance compared with the model based on CT or MRI alone. This study provide a robust framework to develop disease-specific tools for automatic delineation of ROI and clinical outcome prediction. The well-trained DeepInteg could be readily applied in clinic to predict pathological complete response after neoadjuvant therapy in rectal cancer patients.

Predicting Rectal Cancer Response to Total Neoadjuvant Treatment Using an Artificial Intelligence Model Based on Magnetic Resonance Imaging and Clinical Data

PURPOSE

To develop a model for predicting response to total neoadjuvant treatment (TNT) for patients with locally advanced rectal cancer (LARC) based on baseline magnetic resonance imaging (MRI) and clinical data using artificial intelligence methods.

METHODS

Baseline MRI and clinical data were curated from patients with LARC and analyzed using logistic regression (LR) and deep learning (DL) methods to predict TNT response retrospectively. We defined two groups of response to TNT as pathological complete response (pCR) versus non-pCR (Group 1), and high sensitivity [tumor regression grade (TRG) 0 and TRG 1] versus moderate sensitivity (TRG 2 or patients with TRG 3 and a reduction in tumor volume of at least 20% compared to baseline) versus low sensitivity (TRG 3 and a reduction in tumor volume <20% compared to baseline) (Group 2). We extracted and selected clinical and radiomic features on baseline T2WI. Then we built LR models and DL models. Receiver operating characteristic (ROC) curves analysis was performed to assess predictive performance of models.

RESULTS

Eighty-nine patients were assigned to the training cohort, and 29 patients were assigned to the testing cohort. The area under receiver operating characteristics curve (AUC) of LR models, which were predictive of high sensitivity and pCR, were 0.853 and 0.866, respectively. Whereas the AUCs of DL models were 0.829 and 0.838, respectively. After 10 rounds of cross validation, the accuracy of the models in Group 1 is higher than in Group 2.

CONCLUSION

There was no significant difference between LR model and DL model. Artificial Intelligence-based radiomics biomarkers may have potential clinical implications for adaptive and personalized therapy.

Machine learning–based multiparametric magnetic resonance imaging radiomics model for distinguishing central neurocytoma from glioma of lateral ventricle

OBJECTIVES

To develop a machine learning-based radiomics model based on multiparametric magnetic resonance imaging (MRI) for preoperative discrimination between central neurocytomas (CNs) and gliomas of lateral ventricles.

METHODS

A total of 132 patients from two medical centers were enrolled in this retrospective study. Patients from the first medical center were divided into a training cohort (n = 74) and an internal validation cohort (n = 30). Patients from the second medical center were used as the external validation cohort (n = 28). Features were extracted from contrast-enhanced T1-weighted and T2-weighted images. A support vector machine was used for radiomics model investigation. Performance was evaluated using the sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). The model's performance was also compared with those of three radiologists.

RESULTS

The radiomics model achieved an AUC of 0.986 in the training cohort, 0.933 in the internal validation cohort, and 0.903 in the external validation cohort. In the three cohorts, the AUC values were 0.657, 0.786, and 0.708 for radiologist 1; 0.838, 0.799, and 0.790 for radiologist 2; and 0.827, 0.871, and 0.862 for radiologist 3. When assisted by the radiomics model, two radiologists improved their performance in the training cohort (p < 0.05) but not in the internal or external validation cohorts.

CONCLUSIONS

The machine learning radiomics model based on multiparametric MRI showed better performance for distinguishing CNs from lateral ventricular gliomas than did experienced radiologists, and it showed the potential to improve radiologist performance.

KEY POINTS

• The machine learning radiomics model shows excellent performance in distinguishing CNs from gliomas. • The radiomics model outweighs two experienced radiologists (area under the receiver operating characteristic curve, 0.90 vs 0.79 and 0.86, respectively). • The radiomics model has the potential to enhance radiologist performance.

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.

Application of Radiomics in Predicting Treatment Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer: Strategies and Challenges

Neoadjuvant chemoradiotherapy (nCRT) followed by total mesorectal excision is the standard treatment for locally advanced rectal cancer (LARC). A noninvasive preoperative prediction method should greatly assist in the evaluation of response to nCRT and for the development of a personalized strategy for patients with LARC. Assessment of nCRT relies on imaging and radiomics can extract valuable quantitative data from medical images. In this review, we examined the status of radiomic application for assessing response to nCRT in patients with LARC and indicated a potential direction for future research.

Artificial intelligence with magnetic resonance imaging for prediction of pathological complete response to neoadjuvant chemoradiotherapy in rectal cancer: A systematic review and meta-analysis

Purpose

The purpose of this study was to evaluate the diagnostic accuracy of artificial intelligence (AI) models with magnetic resonance imaging(MRI) in predicting pathological complete response(pCR) to neoadjuvant chemoradiotherapy (nCRT) in patients with rectal cancer. Furthermore, assessed the methodological quality of the models.

Methods

We searched PubMed, Embase, Cochrane Library, and Web of science for studies published before 21 June 2022, without any language restrictions. The Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) and Radiomics Quality Score (RQS) tools were used to assess the methodological quality of the included studies. We calculated pooled sensitivity and specificity using random-effects models, I² values were used to measure heterogeneity, and subgroup analyses to explore potential sources of heterogeneity.

Results

We selected 21 papers for inclusion in the meta-analysis from 1562 retrieved publications, with a total of 1873 people in the validation groups. The meta-analysis showed that AI models based on MRI predicted pCR to nCRT in patients with rectal cancer: a pooled area under the curve (AUC) 0.91 (95% CI, 0.88-0.93), sensitivity of 0.82(95% CI,0.71-0.90), pooled specificity 0.86(95% CI,0.80-0.91). In the subgroup analysis, the pooled AUC of the deep learning(DL) model was 0.97, the pooled AUC of the radiomics model was 0.85; the pooled AUC of the combined model with clinical factors was 0.92, and the pooled AUC of the radiomics model alone was 0.87. The mean RQS score of the included studies was 10.95, accounting for 30.4% of the total score.

Conclusions

Radiomics is a promising noninvasive method with high value in predicting pathological response to nCRT in patients with rectal cancer. DL models have higher predictive accuracy than radiomics models, and combined models incorporating clinical factors have higher diagnostic accuracy than radiomics models alone. In the future, prospective, large-scale, multicenter investigations using radiomics approaches will strengthen the diagnostic power of pCR.

Systematic Review Registration

https://www.crd.york.ac.uk/prospero/, identifier CRD42021285630.

Prospective clinical research of radiomics and deep learning in oncology: A translational review

Radiomics and deep learning (DL) hold transformative promise and substantial and significant advances in oncology; however, most methods have been tested in retrospective or simulated settings. There is considerable interest in the biomarker validation, clinical utility, and methodological robustness of these studies and their deployment in real-world settings. This review summarizes the characteristics of studies, the level of prospective validation, and the overview of research on different clinical endpoints. The discussion of methodological robustness shows the potential for independent external replication of prospectively reported results. These in-depth analyses further describe the barriers limiting the translation of radiomics and DL into primary care options and provide specific recommendations regarding clinical deployment. Finally, we propose solutions for integrating novel approaches into the treatment environment to unravel the critical process of translating AI models into the clinical routine and explore strategies to improve personalized medicine.

Magnetic Resonance Imaging and Diffusion Weighted Imaging-Based Histogram in Predicting Mesenchymal Transition High-Grade Serous Ovarian Cancer

RATIONALE AND OBJECTIVES

To investigate the value of magnetic resonance imaging (MRI) including diffusion-weighted imaging (DWI) findings in predicting mesenchymal transition (MT) high-grade serous ovarian cancer (HGSOC).

MATERIALS AND METHODS

Patients with HGSOC were enrolled from May 2017 to December 2020, who underwent pelvic MRI including DWI (b = 0,1000 s/mm²) before surgery, and were assigned to the MT HGSOC or non-MT HGSOC group according to histopathology results. Clinical characteristics and MRI features including DWI-based histogram metrics were assessed and compared between the two groups. Univariate and multivariate analyses were performed to identify the significant variables associated with MT HGSOC - these variables were then incorporated into a predictive nomogram, and ROC curve analysis was subsequently carried out to evaluate diagnostic performance.

RESULTS

A total of 81 consecutive patients were recruited for pelvic MRI before surgery, including 37 (45.7%) MT patients and 44 (54.3%) non-MT patients. At univariate analysis, the features significantly related to MT HGSOC were identified as absence of discrete primary ovarian mass, pouch of Douglas implants, ovarian mass size, tumor volume, mean, SD, median, and 95th percentile apparent diffusion coefficient (ADC) values (all p < 0.05). At multivariate analysis, the absence of discrete primary ovarian mass {odds ratio (OR): 46.477; p = 0.025}, mean ADC value ≤ 1.105 (OR: 1.023; p = 0.009), and median ADC value ≤ 1.038 (OR: 0.982; p = 0.034) were found to be independent risk factors associated with MT HGSOC. The combination of all independent criteria yielded the largest AUC of 0.82 with a sensitivity of 83.87% and specificity of 66.67%, superior to any of the single predictor alone (p ≤ 0.012). The predictive C-index nomogram performance of the combination was 0.82.

CONCLUSION

The combination of absence of discrete primary ovarian mass, lower mean ADC value, and median ADC value may be helpful for preoperatively predicting MT HGSOC.

Are We There Yet? The Value of Deep Learning in a Multicenter Setting for Response Prediction of Locally Advanced Rectal Cancer to Neoadjuvant Chemoradiotherapy

This retrospective study aims to evaluate the generalizability of a promising state-of-the-art multitask deep learning (DL) model for predicting the response of locally advanced rectal cancer (LARC) to neoadjuvant chemoradiotherapy (nCRT) using a multicenter dataset. To this end, we retrained and validated a Siamese network with two U-Nets joined at multiple layers using pre- and post-therapeutic T2-weighted (T2w), diffusion-weighted (DW) images and apparent diffusion coefficient (ADC) maps of 83 LARC patients acquired under study conditions at four different medical centers. To assess the predictive performance of the model, the trained network was then applied to an external clinical routine dataset of 46 LARC patients imaged without study conditions. The training and test datasets differed significantly in terms of their composition, e.g., T-/N-staging, the time interval between initial staging/nCRT/re-staging and surgery, as well as with respect to acquisition parameters, such as resolution, echo/repetition time, flip angle and field strength. We found that even after dedicated data pre-processing, the predictive performance dropped significantly in this multicenter setting compared to a previously published single- or two-center setting. Testing the network on the external clinical routine dataset yielded an area under the receiver operating characteristic curve of 0.54 (95% confidence interval [CI]: 0.41, 0.65), when using only pre- and post-therapeutic T2w images as input, and 0.60 (95% CI: 0.48, 0.71), when using the combination of pre- and post-therapeutic T2w, DW images, and ADC maps as input. Our study highlights the importance of data quality and harmonization in clinical trials using machine learning. Only in a joint, cross-center effort, involving a multidisciplinary team can we generate large enough curated and annotated datasets and develop the necessary pre-processing pipelines for data harmonization to successfully apply DL models clinically.

Deep Learning Model for Predicting the Pathological Complete Response to Neoadjuvant Chemoradiotherapy of Locally Advanced Rectal Cancer

Objective

This study aimed to develop an artificial intelligence model for predicting the pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) of locally advanced rectal cancer (LARC) using digital pathological images.

Background

nCRT followed by total mesorectal excision (TME) is a standard treatment strategy for patients with LARC. Predicting the PCR to nCRT of LARC remine difficulty.

Methods

842 LARC patients treated with standard nCRT from three medical centers were retrospectively recruited and subgrouped into the training, testing and external validation sets. Treatment response was classified as pCR and non-pCR based on the pathological diagnosis after surgery as the ground truth. The hematoxylin & eosin (H&E)-stained biopsy slides were manually annotated and used to develop a deep pathological complete response (DeepPCR) prediction model by deep learning.

Results

The proposed DeepPCR model achieved an AUC-ROC of 0.710 (95% CI: 0.595, 0.808) in the testing cohort. Similarly, in the external validation cohort, the DeepPCR model achieved an AUC-ROC of 0.723 (95% CI: 0.591, 0.844). The sensitivity and specificity of the DeepPCR model were 72.6% and 46.9% in the testing set and 72.5% and 62.7% in the external validation cohort, respectively. Multivariate logistic regression analysis showed that the DeepPCR model was an independent predictive factor of nCRT (P=0.008 and P=0.004 for the testing set and external validation set, respectively).

Conclusions

The DeepPCR model showed high accuracy in predicting pCR and served as an independent predictive factor for pCR. The model can be used to assist in clinical treatment decision making before surgery.

Evaluation of cancer outcome assessment using MRI: A review of deep-learning methods

Accurate evaluation of tumor response to treatment is critical to allow personalized treatment regimens according to the predicted response and to support clinical trials investigating new therapeutic agents by providing them with an accurate response indicator. Recent advances in medical imaging, computer hardware, and machine-learning algorithms have resulted in the increased use of these tools in the field of medicine as a whole and specifically in cancer imaging for detection and characterization of malignant lesions, prognosis, and assessment of treatment response. Among the currently available imaging techniques, magnetic resonance imaging (MRI) plays an important role in the evaluation of treatment assessment of many cancers, given its superior soft-tissue contrast and its ability to allow multiplanar imaging and functional evaluation. In recent years, deep learning (DL) has become an active area of research, paving the way for computer-assisted clinical and radiological decision support. DL can uncover associations between imaging features that cannot be visually identified by the naked eye and pertinent clinical outcomes. The aim of this review is to highlight the use of DL in the evaluation of tumor response assessed on MRI. In this review, we will first provide an overview of common DL architectures used in medical imaging research in general. Then, we will review the studies to date that have applied DL to magnetic resonance imaging for the task of treatment response assessment. Finally, we will discuss the challenges and opportunities of using DL within the clinical workflow.

A Survey on Deep Learning for Precision Oncology

Precision oncology, which ensures optimized cancer treatment tailored to the unique biology of a patient’s disease, has rapidly developed and is of great clinical importance. Deep learning has become the main method for precision oncology. This paper summarizes the recent deep-learning approaches relevant to precision oncology and reviews over 150 articles within the last six years. First, we survey the deep-learning approaches categorized by various precision oncology tasks, including the estimation of dose distribution for treatment planning, survival analysis and risk estimation after treatment, prediction of treatment response, and patient selection for treatment planning. Secondly, we provide an overview of the studies per anatomical area, including the brain, bladder, breast, bone, cervix, esophagus, gastric, head and neck, kidneys, liver, lung, pancreas, pelvis, prostate, and rectum. Finally, we highlight the challenges and discuss potential solutions for future research directions.

Endoscopy-Based Deep Convolutional Neural Network Predicts Response to Neoadjuvant Treatment for Locally Advanced Rectal Cancer

Background and Aims: Although the wait and watch (W&W) strategy is a treatment choice for locally advanced rectal cancer (LARC) patients who achieve clinical complete response (cCR) after neoadjuvant therapy (NT), the issue on consistency between cCR and pathological CR (pCR) remains unsettled. Herein, we aimed to develop a deep convolutional neural network (DCNN) model using endoscopic images of LARC patients after NT to distinguish tumor regression grade (TRG) 0 from non-TRG0, thus providing strength in identifying surgery candidates. Methods: A total of 1000 LARC patients (6,939 endoscopic images) who underwent radical surgery after NT from April 2013 to April 2021 at the Sixth Affiliated Hospital, Sun Yat-sen University were retrospectively included in our study. Patients were divided into three cohorts in chronological order: the training set for constructing the model, the validation set, and the independent test set for validating its predictive capability. Besides, we compared the model's performance with that of three endoscopists on a class-balanced, randomly selected subset of 20 patients' LARC images (10 TRG0 patients with 70 images and 10 non-TRG0 patients with 72 images). The measures used to evaluate the efficacy for identifying TRG0 included overall accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUROC). Results: There were 219 (21.9%) cases of TRG0 in the included patients. The constructed DCNN model in the training set obtained an excellent performance with good accuracy of 94.21%, specificity of 94.39%, NPV of 98.11%, and AUROC of 0.94. The validation set showed accuracy, specificity, NPV, and AUROC of 92.13%, 93.04%, 96.69%, and 0.95, respectively; the corresponding values in the independent set were 87.14%, 92.98%, 91.37%, and 0.77, respectively. In the reader study, the model outperformed the three experienced endoscopists with an AUROC of 0.85. Conclusions: The proposed DCNN model achieved high specificity and NPV in detecting TRG0 LARC tumors after NT, with a better performance than experienced endoscopists. As a supplement to radiological images, this model may serve as a useful tool for identifying surgery candidates in LARC patients after NT.

The Need for Medical Artificial Intelligence That Incorporates Prior Images

The use of artificial intelligence (AI) has grown dramatically in the past few years in the United States and worldwide, with more than 300 AI-enabled devices approved by the U.S. Food and Drug Administration (FDA). Most of these AI-enabled applications focus on helping radiologists with detection, triage, and prioritization of tasks by using data from a single point, but clinical practice often encompasses a dynamic scenario wherein physicians make decisions on the basis of longitudinal information. Unfortunately, benchmark data sets incorporating clinical and radiologic data from several points are scarce, and, therefore, the machine learning community has not focused on developing methods and architectures suitable for these tasks. Current AI algorithms are not suited to tackle key image interpretation tasks that require comparisons to previous examinations. Focusing on the curation of data sets and algorithm development that allow for comparisons at different points will be required to advance the range of relevant tasks covered by future AI-enabled FDA-cleared devices.

MRI radiomics features of mesorectal fat can predict response to neoadjuvant chemoradiation therapy and tumor recurrence in patients with locally advanced rectal cancer

OBJECTIVE

To interrogate the mesorectal fat using MRI radiomics feature analysis in order to predict clinical outcomes in patients with locally advanced rectal cancer.

METHODS

This retrospective study included patients who underwent neoadjuvant chemoradiotherapy for locally advanced rectal cancer from 2009 to 2015. Three radiologists independently segmented mesorectal fat on baseline T2-weighted axial MRI. Radiomics features were extracted from segmented volumes and calculated using CERR software, with adaptive synthetic sampling being employed to combat large class imbalances. Outcome variables included pathologic complete response (pCR), local recurrence, distant recurrence, clinical T-category (cT), post-treatment T category (ypT), and post-treatment N category (ypN). A maximum of eight most important features were selected for model development using support vector machines and fivefold cross-validation to predict each outcome parameter via elastic net regularization. Diagnostic metrics of the final models were calculated, including sensitivity, specificity, PPV, NPV, accuracy, and AUC.

RESULTS

The study included 236 patients (54 ± 12 years, 135 men). The AUC, sensitivity, specificity, PPV, NPV, and accuracy for each clinical outcome were as follows: for pCR, 0.89, 78.0%, 85.1%, 52.5%, 94.9%, 83.9%; for local recurrence, 0.79, 68.3%, 80.7%, 46.7%, 91.2%, 78.3%; for distant recurrence, 0.87, 80.0%, 88.4%, 58.3%, 95.6%, 87.0%; for cT, 0.80, 85.8%, 56.5%, 89.1%, 49.1%, 80.1%; for ypN, 0.74, 65.0%, 80.1%, 52.7%, 87.0%, 76.3%; and for ypT, 0.86, 81.3%, 84.2%, 96.4%, 46.4%, 81.8%.

CONCLUSION

Radiomics features of mesorectal fat can predict pathological complete response and local and distant recurrence, as well as post-treatment T and N categories.

KEY POINTS

• Mesorectal fat contains important prognostic information in patients with locally advanced rectal cancer (LARC). • Radiomics features of mesorectal fat were significantly different between those who achieved complete vs incomplete pathologic response (accuracy 83.9%, 95% CI: 78.6-88.4%). • Radiomics features of mesorectal fat were significantly different between those who did vs did not develop local or distant recurrence (accuracy 78.3%, 95% CI: 72.0-83.7% and 87.0%, 95% CI: 81.6-91.2% respectively).

T2*-weighted imaging and diffusion kurtosis imaging (DKI) of rectal cancer: correlation with clinical histopathologic prognostic factors

PURPOSE

Histopathologic prognostic factors of rectal cancer are closely associated with local recurrence and distant metastasis. We aim to investigate the feasibility of T2*WI in assessment of clinical prognostic factors of rectal cancer, and compare with DKI.

METHODS

This retrospective study enrolled 50 out of 205 patients with rectal cancer according to the inclusion criteria. The following parameters were obtained: R2* from T2*WI, mean diffusivity (MD_k), mean kurtosis (MK), and mean diffusivity (MD_t) from DKI using tensor method. Above parameters were compared by Mann-Whitney U-test or students' t test. Spearman correlations between different parameters and histopathological prognostic factors were determined. The diagnostic performances of R2* and DKI-derived parameters were analyzed by receiver operating characteristic curves (ROC), separately and jointly.

RESULTS

There were positive correlations between R2* and multiple prognostic factors of rectal cancer such as T category, N category, tumor grade, CEA level, and LVI (P < 0.004). MD_k and MD_t showed negative correlations with almost all the histopathological prognostic factors except CRM and TIL involvement (P < 0.003). MK correlated positively with the prognostic factors except CA19-9 level and CRM involvement (P < 0.006). The AUC ranges were 0.724-0.950 for R2* and 0.755-0.913 for DKI-derived parameters for differentiation of prognostic factors. However, no significant differences of diagnostic performance were found between T2*WI, DKI, or the combined imaging methods in characterizing rectal cancer.

CONCLUSION

R2* and DKI-derived parameters were associated with different histopathological prognostic factors, and might act as noninvasive biomarkers for histopathological characterization of rectal cancer.

The feasibility of MRI-based radiomics model in presurgical evaluation of tumor budding in locally advanced rectal cancer

PURPOSE

To build and validate a magnetic resonance imaging-based radiomics model to preoperatively evaluate tumor budding (TB) in locally advanced rectal cancer (LARC).

METHODS

Pathologically confirmed LARC cases submitted to preoperative rectal MRI in two distinct hospitals were enrolled in this retrospective study and assigned to cohort 1 (training set, n = 77; test set, n = 51) and cohort 2 (validation set, n = 96). Radiomics features were obtained from multiple sequences, comprising high-resolution T2, contrast-enhanced T1, and diffusion-weighted imaging (T2WI, CE-T1WI, and DWI, respectively). The least absolute shrinkage and selection operator (LASSO) was utilized to select the optimal features from T2WI, CE-T1WI, DWI, and the combination of multi-sequences, respectively. A support vector machine (SVM) classifier was utilized to construct various radiomics models for discriminating the TB grades. Receiver operating characteristic curve analysis and decision curve analysis (DCA) were carried out to determine the diagnostic value.

RESULTS

Five optimal features associated with TB grade were determined from combined multi-sequence data. Accordingly, a radiomics model based on combined multi-sequences had an area under the curve of 0.796, with an accuracy of 81.2% in the validation set, showing a better performance in comparison with other models in both cohorts (p < 0.05). DCA exhibited a clinical benefit for this radiomics model.

CONCLUSION

The novel MRI-based radiomics model combining multiple sequences is an effective and non-invasive approach for evaluating TB grade preoperatively in patients with LARC.

Prediction of Neoadjuvant Chemoradiotherapy Response in Rectal Cancer with Metric Learning Using Pretreatment 18F-Fluorodeoxyglucose Positron Emission Tomography

OBJECTIVES

Neoadjuvant chemoradiotherapy (NCRT) followed by surgery is the mainstay of treatment for patients with locally advanced rectal cancer. Based on baseline 18F-fluorodeoxyglucose ([18F]-FDG)-positron emission tomography (PET)/computed tomography (CT), a new artificial intelligence model using metric learning (ML) was introduced to predict responses to NCRT.

PATIENTS AND METHODS

This study used the data of 236 patients with newly diagnosed rectal cancer; the data of 202 and 34 patients were for training and validation, respectively. All patients received pretreatment [18F]FDG-PET/CT, NCRT, and surgery. The treatment response was scored by Dworak tumor regression grade (TRG); TRG3 and TRG4 indicated favorable responses. The model employed ML combined with the Uniform Manifold Approximation and Projection for dimensionality reduction. A receiver operating characteristic (ROC) curve analysis was performed to assess the model's predictive performance.

RESULTS

In the training cohort, 115 patients (57%) achieved TRG3 or TRG4 responses. The area under the ROC curve was 0.96 for the prediction of a favorable response. The sensitivity, specificity, and accuracy were 98.3%, 96.5%, and 97.5%, respectively. The sensitivity, specificity, and accuracy for the validation cohort were 95.0%, 100%, and 98.8%, respectively.

CONCLUSIONS

The new ML model presented herein was used to determined that baseline 18F[FDG]-PET/CT images could predict a favorable response to NCRT in patients with rectal cancer. External validation is required to verify the model's predictive value.

The Conversion of MRI Data With Multiple b-Values into Signature-Like Pictures to Predict Treatment Response for Rectal Cancer

BACKGROUND

Diffusion weighted imaging (DWI) at multiple b-values has been used to predict the pathological complete response (pCR) to neoadjuvant chemoradiotherapy for locally advanced rectal cancer. Non-Gaussian models fit the signal decay of diffusion by several physical values from different approaches of approximation.

PURPOSE

To develop a deep learning method to analyze DWI data scanned at multiple b-values independent on Gaussian or non-Gaussian models and to apply to a rectal cancer neoadjuvant chemoradiotherapy model.

STUDY TYPE

Retrospective.

POPULATION

A total of 472 participants (age: 56.6 ± 10.5 years; 298 males and 174 females) with locally advanced adenocarcinoma were enrolled and chronologically divided into a training group (n = 200; 42 pCR/158 non-pCR), a validation group (n = 72; 11 pCR/61 non-pCR) and a test group (n = 200; 44 pCR/156 non-pCR).

FIELD STRENGTH/SEQUENCE

A 3.0 T MRI scanner. DWI with a single-shot spin echo-planar imaging pulse sequence at 12 b-values (0, 20, 50, 100, 200, 400, 600, 800, 1000, 1200, 1400, and 1600 sec/mm² ).

ASSESSMENT

DWI signals from manually delineated tumor region were converted into a signature-like picture by concatenating all histograms from different b-values. Pathological results (pCR/non-pCR) were used as the ground truth for deep learning. Gaussian and non-Gaussian methods were used for comparison.

STATISTICAL TESTS

Analysis of variance for age; Chi-square for gender and pCR/non-pCR; area under the receiver operating characteristic (ROC) curve (AUC); DeLong test for AUC. P < 0.05 for significant difference.

RESULTS

The AUC in the test group is 0.924 (95% CI: 0.866-0.983) for the signature-like pictures converted from 35 bins, and it is 0.931 (95% CI: 0.884-0.979) for the signature-like pictures converted from 70 bins, which is significantly (Z = 3.258, P < 0.05) larger than D_app , the best predictor in non-Gaussian methods with AUC = 0.773 (95% CI: 0.682-0.865).

DATA CONCLUSION

The proposed signature-like pictures provide more accurate pretreatment prediction of the response to neoadjuvant chemoradiotherapy than the fitted methods for locally advanced rectal cancer.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Toward Generalizability in the Deployment of Artificial Intelligence in Radiology: Role of Computation Stress Testing to Overcome Underspecification

The clinical deployment of artificial intelligence (AI) applications in medical imaging is perhaps the greatest challenge facing radiology in the next decade. One of the main obstacles to the incorporation of automated AI-based decision-making tools in medicine is the failure of models to generalize when deployed across institutions with heterogeneous populations and imaging protocols. The most well-understood pitfall in developing these AI models is overfitting, which has, in part, been overcome by optimizing training protocols. However, overfitting is not the only obstacle to the success and generalizability of AI. Underspecification is also a serious impediment that requires conceptual understanding and correction. It is well known that a single AI pipeline, with prescribed training and testing sets, can produce several models with various levels of generalizability. Underspecification defines the inability of the pipeline to identify whether these models have embedded the structure of the underlying system by using a test set independent of, but distributed identically, to the training set. An underspecified pipeline is unable to assess the degree to which the models will be generalizable. Stress testing is a known tool in AI that can limit underspecification and, importantly, assure broad generalizability of AI models. However, the application of stress tests is new in radiologic applications. This report describes the concept of underspecification from a radiologist perspective, discusses stress testing as a specific strategy to overcome underspecification, and explains how stress tests could be designed in radiology-by modifying medical images or stratifying testing datasets. In the upcoming years, stress tests should become in radiology the standard that crash tests have become in the automotive industry. Keywords: Computer Applications-General, Informatics, Computer-aided Diagnosis © RSNA, 2021.

A systematic review on application of deep learning in digestive system image processing

With the advent of the big data era, the application of artificial intelligence represented by deep learning in medicine has become a hot topic. In gastroenterology, deep learning has accomplished remarkable accomplishments in endoscopy, imageology, and pathology. Artificial intelligence has been applied to benign gastrointestinal tract lesions, early cancer, tumors, inflammatory bowel diseases, livers, pancreas, and other diseases. Computer-aided diagnosis significantly improve diagnostic accuracy and reduce physicians' workload and provide a shred of evidence for clinical diagnosis and treatment. In the near future, artificial intelligence will have high application value in the field of medicine. This paper mainly summarizes the latest research on artificial intelligence in diagnosing and treating digestive system diseases and discussing artificial intelligence's future in digestive system diseases. We sincerely hope that our work can become a stepping stone for gastroenterologists and computer experts in artificial intelligence research and facilitate the application and development of computer-aided image processing technology in gastroenterology.