Magnetic resonance imaging for clinical management of rectal cancer: Updated recommendations from the 2016 European Society of Gastrointestinal and Abdominal Radiology (ESGAR) consensus meeting. Eur Radiol. 2018;28:1465-1475. [PMID: 29043428 PMCID: PMC5834554 DOI: 10.1007/s00330-017-5026-2]

Rectal MR Imaging

MR imaging comprising high-resolution T2-weighted imaging and high b value diffusion-weighted imaging has proven effective in guiding treatment selection and preoperative planning for rectal cancer. In addition to staging, it enables the noninvasive assessment of key bioimaging markers such as extramural vascular invasion, tumor deposits, and the presence and location of mesorectal fascia and anal sphincter involvement. After neoadjuvant therapy, MR imaging offers noninvasive treatment response, complementing endoscopic and digital rectal evaluations. This assessment plays a crucial role in determining the feasibility of organ preservation or watch-and-wait strategy in patients who achieve complete clinical response.

Stage pT0-T1 rectal cancers: emphasis on submucosal high intensity on high-resolution T2-weighted imaging and other morphological features

BackgroundIdentification and staging of rectal cancer are mainly based on the difference in signal intensity (SI) between the tumor and normal structures of the intestinal wall on T2-weighted imaging. However, differentiating stage pT0-T1 from pT2 rectal tumors is difficult using routine magnetic resonance imaging (MRI) sequences.PurposeTo summarize and explore whether MRI findings from routine imaging can help differentiate pT0-T1 from pT2 rectal tumors.Material and MethodsA total of 110 patients with pT0-T2 rectal cancer underwent preoperative pelvic MRI examinations and tumor resection without preoperative chemoradiotherapy. MRI findings of rectal lesions (including tumor location, shape, longitudinal length, maximum cross-section, submucosal high intensity [SHI], extramural fibrotic scarring, wall shrinkage, lesion-to-wall signal intensity ratio, and presence of lymph node with short axis over 3 mm) and clinical characteristics were analyzed by univariate and multivariate analyses to screen the independent factors associated with pathological results.ResultsOf all the lesions, 32 tumors were proved to be pT0-T1 and 78 tumors were pT2. Univariate and multivariate logistic regression analyses revealed that tumor shape (odds ratio [OR] = 24.607, P < 0.001), SHI (OR = 6.129, P = 0.002), and extramural fibrotic scarring (OR = 0.110, P = 0.007) were independent factors distinguishing pT0-T1 tumors from pT2 tumors. If the rectal lesion has a cauliflower-like shape with SHI and no extramural fibrotic scarring, it is more likely to be a pT0-T1 tumor.ConclusionThe imaging features obtained from the routine MRI sequence showed potential value for differentiating pT0-T1 from pT2 rectal tumors.

Approvers, Disapprovers, and Strugglers: a Q-methodology study of rectal cancer MRI proforma use

OBJECTIVES

Rectal cancer MRI (rcMRI) allows accurate staging and informs treatment decisions in rectal cancer. There is variability in reporting completeness; however, template proforma reports can significantly increase the inclusion of key tumour descriptors. We aimed to identify socially shared viewpoints of radiologists relating to barriers to implementing proforma reporting. Measuring the subjectivity of opinions relative to other radiologists will allow identification of common patterns preventing implementation.

METHODS

Specialist gastrointestinal radiologists from 16 hospital trusts were invited to a Q-methodology study. Participants ranked 56 statements on barriers to using proforma reports (the Q-set) in a normal distribution (Q-grid). Factor analyses were undertaken to identify independent accounts, and additional survey data were used to support interpretation.

RESULTS

Twenty-seven radiologists participated; 11 (41%) had more than 10 years reporting rcMRIs. Three distinct accounts of radiologist attitudes to proforma-use were identified: Approvers, Disapprovers, and Struggling champions. The highest ranked barriers related to proforma format, individual radiologists' preferences and beliefs about efficacy and factors relating to wider multidisciplinary teams and health system-level implementation.

CONCLUSIONS

Radiologists that disapprove of proformas are unlikely to use them unless external influences are applied, such as a requirement by treating clinicians. Increased internal and organizational support would also increase use. Targeted implementation strategies focusing on these barriers has the potential to increase uptake of similar interventions.

ADVANCES IN KNOWLEDGE

Specialist radiologists require a multi-level adaptive implementation strategy, tailored to proforma characteristics as well as individual and organizational barriers to increase proforma reporting for rcMRI to support accurate treatment decision making.

Node-RADS: a systematic review and meta-analysis of diagnostic performance, category-wise malignancy rates, and inter-observer reliability

OBJECTIVE

To perform a systematic review and meta-analysis to estimate diagnostic performance, category-wise malignancy rates, and inter-observer reliability of Node Reporting and Data System 1.0 (Node-RADS).

METHODS

Five electronic databases were systematically searched for primary studies on the use of Node-RADS to report the possibility of cancer involvement of lymph nodes on CT and MRI from January 1, 2021, until April 15, 2024. The study quality was assessed by modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and Quality Appraisal of Diagnostic Reliability (QAREL) tools. The diagnostic accuracy was estimated with bivariate random-effects model, while the pooled category-wise malignancy rates were obtained with random-effects model.

RESULTS

Six Node-RADS-CT studies and three Node-RADS-MRI studies covering nine types of cancer were included. The study quality was mainly damaged by inappropriate index test and unknown timing according to QUADAS-2, and unclear blindness during the rating process according to QAREL. The area under hierarchical summary receiver operating characteristic curve (95% conventional interval) was 0.92 (0.89-0.94) for Node-RADS ≥ 3 as positive and 0.91 (0.88-0.93) for Node-RADS ≥ 4 as positive, respectively. The pooled malignancy rates (95% CIs) of Node-RADS 1 to 5 were 4% (0-10%), 31% (9-58%), 55% (34-75%), 89% (73-99%), and 100% (97-100%), respectively. The inter-observer reliability of five studies was interpreted as fair to substantial.

CONCLUSION

Node-RADS presented a promising diagnostic performance with an increasing probability of malignancy along higher category. However, the evidence for inter-observer reliability of Node-RADS is insufficient, and may hinder its implementation in clinical practice for lymph node assessment.

KEY POINTS

Question Node-RADS is designed for structured reporting of the possibility of cancer involvement of lymph nodes, but the evidence supporting its application has not been summarized. Findings Node-RADS presented diagnostic performance with AUC of 0.92, and malignancy rates for categories 1-5 ranged from 4% to 100%, while the inter-observer reliability was unclear. Clinical relevance Node-RADS is a useful tool for structured reporting of the possibility of cancer involvement of lymph nodes with high diagnostic performance and appropriate malignancy rate for each category, but unclear inter-observer reliability may hinder its implementation in clinical practice.

"Sigmoid take-off" to define recto-sigmoid junction and its impact on rectal cancer classification, staging, and management

AIM

The primary objective of this study was to determine the clinical impact of using sigmoid take-off (STO) in the management of rectal cancer. We also evaluated the inter-observer reliability in the identification of STO.

MATERIAL AND METHODS

This retrospective study reviewed staging MRI of patients with mid and high-rectal cancers performed between January 2019 and December 2022. The location of the tumour was reclassified based on STO as defined by D'Souza et al. (2018) and compared with the location determined based on distance from the anal verge. The proportions of cases that show a change in tumour location from rectal cancer to sigmoid cancer and the potential change in treatment were noted. The interobserver agreement for the location of STO and the location of tumours from STO was studied among four subspecialised abdominal radiologists.

RESULTS

Out of 134 rectal cancer patients included, STO-based assessment resulted in the reclassification of 13.4% (n=18) cases into sigmoid cancer. There was, however, no change in the stage of cancer. Among these 18 patients, there would have been a change in management in 5 patients had the initial assessment been a sigmoid cancer. There was excellent agreement among the radiologists for measuring the distance of STO from the anal verge (ICC = 0.883, p<0.001) and determining the location of the tumour based on STO (K = 0.82, p<0.001).

CONCLUSIONS

Using STO changed the location of tumours in 13.4% of high- and mid-rectal cancers. There was excellent agreement among radiologists regarding determining STO and identifying tumour locations using STO.

Diagnostic performance of node-RADS classification for primary lymph node assessment in rectal cancer: a modality benchmarking study

PURPOSE

To evaluate how well the Node Reporting and Data System (Node-RADS) diagnoses lymph node involvement (LNI) in the initial stages of rectal cancer, utilizing contrast-enhanced CT (CE-CT), T2-weighted MRI (T2WI) and contrast-enhanced T1-weighted MRI (T1CE).

METHODS

This retrospective study included 113 rectal cancer patients who underwent radical surgery without neoadjuvant therapy. Two radiologists independently assessed regional lymph nodes using the highest NODE-RADS classification and histopathology as reference criteria. Diagnostic performance was evaluated using receiver operating characteristic (ROC) curve analysis. Statistical analysis was performed using the McNemar test with Bonferroni correction for multiple comparisons.

RESULTS

Node-RADS showed improved diagnostic performance over short-axis diameter (SAD) in all modalities (AUC: 0.838 vs. 0.744 for CE-CT, 0.845 vs. 0.747 for T2WI, 0.853 vs. 0.786 for T1CE; all P < 0.05). The sensitivity and specificity of Node-RADS across three modalities ranged from 76.19 - 78.57% and 91.55 - 92.96%, respectively. Pairwise comparisons of sensitivity and specificity among the three modalities showed no significant differences after Bonferroni correction (all McNemar test P = 1.0). There was no significant difference in Node-RADS performance among the three modalities (all P > 0.05). The weighted kappa values were 0.742-0.798.

CONCLUSION

Node-RADS demonstrated superior diagnostic performance over SAD measurements and similar diagnostic effectiveness in assessing LNI for primary rectal cancer stages across CE-CT, T2WI, and T1CE.

Novel deep learning algorithm based MRI radiomics for predicting lymph node metastases in rectal cancer

To explore the value of applying the MRI-based radiomic nomogram for predicting lymph node metastasis (LNM) in rectal cancer (RC). This retrospective analysis used data from 430 patients with RC from two medical centers. The patients were categorized into the LNM negative (LNM-) and LNM positive (LNM+) according to their surgical pathology results. We developed a physician model by selecting clinical independent predictors through physician assessments. Additionally, we developed deep learning radscore (DLRS) models by extracting deep features from multiparametric MRI (mpMRI) images. A nomogram model was constructed by combining the physician model and DLRS models. Among the patients, 192 (44.65%, 192/430) experienced LNM+. Six prediction models were developed, namely the physician model, three sequence models, the DLRS, and the nomogram. The physician model achieved AUC of the receiver operating characteristic (ROC) values of 0.78, 0.79, and 0.7, whereas the sequence models, DLRS model, and nomogram model achieved AUC values ranging from 0.83 to 0.99. The predictive performance of the DLRS and nomogram models was superior to that of the physician model. DLRS and nomogram models based on mpMRI provided higher accuracy in predicting LNM status in patients with RC than the other models.

Feasibility of Three-Dimension Chemical Exchange Saturation Transfer MRI for Predicting Tumor and Node Staging in Rectal Adenocarcinoma: An Exploration of Optimal ROI Measurement

To investigate the feasibility of predicting rectal adenocarcinoma (RA) tumor (T) and node (N) staging from an optimal ROI measurement using amide proton transfer weighted-signal intensity (APTw-SI) and magnetization transfer (MT) derived from three-dimensional chemical exchange saturation transfer(3D-CEST). Fifty-eight RA patients with pathological TN staging underwent 3D-CEST and DWI. APTw-SI, MT, and ADC values were measured using three ROI approaches (ss-ROI, ts-ROI, and wt-ROI) to analyze the TN staging (T staging, T1-2 vs T3-4; N staging, N - vs N +); the reproducibility of APTw-SI and MT was also evaluated. The AUC was used to assess the staging performance and determine the optimal ROI strategy. MT and APTw-SI yielded good excellent reproducibility with three ROIs, respectively. Significant differences in MT were observed (all P < 0.05) from various ROIs but not in APTw-SI and ADC (all P > 0.05) in the TN stage. AUCs of MT from ss-ROI were 0.860 (95% CI, 0.743-0.937) and 0.852 (95% CI, 0.735-0.932) for predicting T and N staging, which is similar to ts-ROI (T staging, 0.856 [95% CI, 0.739-0.934]; N staging, 0.831 [95% CI, 0.710-0.917]) and wt-ROI (T staging, 0.833 [95% CI, 0.712-0.918]; N staging, 0.848 [95% CI, 0.729-0.929]) (all P > 0.05). MT value of 3D-CEST has excellent TN staging predictive performance in RA patients with all three kinds of ROI methods. The ss-ROI is easy to operate and could be served as the preferred ROI approach for clinical and research applications of 3D-CEST imaging.

What is the predictive value of pretreatment MRI characteristics for achieving a complete response after total neoadjuvant treatment in locally advanced rectal cancer?

OBJECTIVES

To investigate the value of pretreatment magnetic resonance imaging (MRI) features in predicting a complete response to total neoadjuvant treatment (TNT) in locally advanced rectal cancer (LARC).

METHODS

The data of patients who received TNT were analyzed retrospectively. MRI features, including T stage, morphology, length, and volume; the presence of MR-detected extramural venous invasion (mrEMVI), the number of mrEMVI, and the diameter of the largest invaded vein; main vein mrEMVI; presence of MR-detected tumor deposits (mrTDs), the number of mrTDs, and the size of the largest mrTD; MR-detected lymph node status (mrLN); tumor distance from the anal verge; mesorectal fascia involvement (mrMRF + ); and mean apparent diffusion coefficient (ADC) values were recorded. Patients were classified as complete (CRs) or noncomplete responders (non-CRs) according to the pathological/clinical outcomes. For patients managed nonoperatively, a sustained clinical complete response for > 2 years was deemed a surrogate endpoint for complete response. The MRI parameters were categorized into three distinct groups: baseline, advanced, and quantitative features, and were analyzed using multivariable stepwise logistic regression. The ability to predict complete response was evaluated by comparing different combinations of MRI parameters, and performance on an "independent" dataset was estimated using bootstrapped leave-one-out cross-validation (LOOCV).

RESULTS

The data of 84 patients were evaluated (CRs, n = 44; non-CRs, n = 40). The optimal model, which included baseline and quantitative MRI features, achieved an area under the curve of 0.837 for predicting complete response. Selected predictors were T stage and ADC mean value. Advanced MRI features did not improve the performance of the model.

CONCLUSION

A multivariable model combining T stage and the ADC mean value can help identify LARC patients who are likely to a achieve complete response before the initiation of TNT.

[Rectal Cancer: Optimal Preoperative Diagnostics]

Preoperative diagnostics for rectal cancer aim to determine the extent of local and systemic spread. Local staging includes rectoscopy with accurate height localisation, histological confirmation, MRI of the pelvis and, particularly in the case of localised tumours, endosonography. In addition to tumour height and possible infiltration of adjacent organs, MRI findings should include minimum tumour distance from the mesorectal fascia and MR morphological criteria for extramural vascular invasion. In the case of lower rectal cancer, the relationship to the various components of the sphincter muscle is important in planning the surgical strategy; in the case of upper rectal cancer, the MRI findings should include possible infiltration of the peritoneal fold. As outlined in the German guidelines, the basic diagnostic tests required to detect or exclude distant metastases are a chest X-ray and an abdominal ultrasound. If unclear findings are observed, these should be supplemented by a chest and abdominal CT. In addition to the carcinoembryonic antigen (CEA) test, which is primarily used for follow-up, a complete colonoscopy should be performed to rule out a second malignancy in the colon. If this is not possible due to an obstructive tumour, the colonoscopy should be performed three months postoperatively. Additionally, a preoperative CT or MR colonoscopy can reliably detect larger polyps and carcinomas.

[Postsurgical follow-up and long-term monitoring of colorectal cancer : Radiology as a key component]

CLINICAL/METHODOLOGICAL ISSUE

Colorectal cancer is one of the most common malignant tumors worldwide. Postsurgical follow-up and long-term monitoring are essential to detect local recurrence, metastases, or secondary tumors at an early stage.

STANDARD RADIOLOGICAL METHODS

According to the current guideline on colorectal cancer, radiologic follow-up is primarily performed using a single computed tomography (CT) scan 3 months after completion of therapy. Annual chest X‑ray examinations within the first 5 years after completion of treatment can be employed, and, due to cost-effective availability, regular abdominal ultrasound is recommended.

METHODOLOGICAL INNOVATIONS

The German guideline on colorectal cancer is currently being revised. As the sensitivity of ultrasound is inferior to CT and magnetic resonance imaging (MRI), thoracoabdominal CT will probably become crucial in follow-up care with the revised guideline, which would align with international recommendations.

PERFORMANCE

CT is well suited for detecting local recurrence, as well as lung or liver metastases. MRI is used in assessing local cancer grades for treatment planning and monitoring. Structured reporting, stage- and guideline-based recommendations including follow-up intervals as well as interdisciplinary tumor conferences ensure high-quality follow-up care.

ACHIEVEMENTS

Radiology is essential to interdisciplinary follow-up care for colorectal cancer.

PRACTICAL RECOMMENDATIONS

Structured reporting and clear recommendations on follow-up intervals should be standard in radiological reports. The importance of radiological follow-up for patients with colorectal cancer is likely to increase further with the guideline that is currently being revised.

MRI radiomic study on prediction of nonenlarged lymph node metastasis of rectal cancer: reduced field-of-view versus conventional DWI

BACKGROUND

Nonenlarged lymph node metastasis (NELNM) of rectal cancer is easily overlooked because these apparently normal lymph nodes are sometimes too small to measure directly using imaging techniques. Radiomic-based multiparametric imaging sequences could predict NELNM based on the primary lesion of rectal cancer. We aimed to study the performance of magnetic resonance imaging (MRI) radiomics derived from reduced field-of-view diffusion-weighted imaging (rDWI) and conventional DWI (cDWI) for the prediction of NELNM.

METHODS

A total of 86 rectal cancer patients (60 and 26 patients in training and test cohorts, respectively), underwent multiparametric MRI. Radiomic features were extracted from the whole primary lesion of rectal cancer segmented on T2-weighted imaging (T2WI), rDWI, and cDWI, both with b-value of 800 s/mm2 and apparent diffusion coefficient (ADC) maps from both DWI sequences (rADC and cADC). The radiomic models based on the above imaging methods were built for the assessment of NELNM status. Their diagnostic performances were evaluated in comparison with subjective evaluation by radiologists.

RESULTS

rADC demonstrated a significant advantage over subjective assessment in predicting NELNM in both training and test cohorts (p ≤ 0.002). In the test cohort, rADC exhibited a significantly higher area under the receiver operating characteristics curve than cADC, cDWIb800, and T2WI (p ≤ 0.020) in assessing NELNM for region-of-interest (ROI) delineation while excelling over rDWIb800 for prediction of NELNM (p = 0.0498).

CONCLUSION

Radiomic features based on rADC outperformed those derived from T2WI and fDWI in predicting the NELNM status of rectal cancer, rADC was more advantageous than rDWIb800 in assessing NELNM.

RELEVANCE STATEMENT

Advanced rDWI excelled over cDWI in radiomic assessment of NELNM of rectal cancer, with the best performance observed for rADC, in contrast to rDWIb800, cADC, cDWIb800, and T2WI.

KEY POINTS

rDWI, cDWI, and T2WI radiomics could help assess NELNM of rectal cancer. Radiomic features based on rADC outperformed those based on rDWIb800, cADC, cDWIb800, and T2WI in predicting NELNM. For rDWI radiomics, the ADC map was more accurate and reliable than DWI to assess NELNM for region of interest delineation.

Why did we encounter a pCRM-positive specimen whose preoperative MRI indicates negative mesorectal fascia involvement in middle to low rectal cancer?

BACKGROUND

This study aims to examine why we encounter a pathological circumferential resection margin (pCRM)-positive specimen whose preoperative MRI indicates negative mesorectal fascia involvement in middle to low rectal cancer.

METHODS

Forty-four consecutive patients included in this study had c(yc)T1-3 primary rectal adenocarcinoma without mesorectal fascia involvement and underwent laparoscopic total mesorectal excision (TME) with curative intent in the Department of Gastrointestinal Surgery of Kansai Medical University Hospital from January 2014 to April 2018. We adopted three checkpoints to investigate the misleading point causing positive pCRM (≤ 1 mm). (1) c(yc)CRM diagnosis by two radiologists with more than 20 and 15 years of experience in rectal cancer MRI diagnosis. (2) The specimen was assessed using the TME score presented by Nagtegaal. (3) We compared the standard sectioning according to UK guidelines (group A; n = 26) with the specimen MRI image navigation-based section (group B; n = 18) in terms of estimation of pCRM by c(yc)CRM.

RESULTS

We achieved a "complete" resection specimen in all cases. A simple correlation coefficient in group B revealed a significant correlation between c(yc)CRM and pCRM (r = 0.663, p = 0.00513); this correlation was not significant in group A (r = 0.261, p = 0.19824). However, tests for differences between linear regression coefficients in groups A and B showed no significant differences (p = 0.12596). There were five cases of pCRM ≤ 1 mm: three in group A and two in group B. An anterior lesion caused pCRM ≤ 1 mm in three cases; the tumor deposits or extramural vascular invasion caused the other cases.

CONCLUSION

The cause of misleading pCRM was the inaccurate preoperative MRI diagnosis of c(yc)CRM.

A method of matching nodes between MRI and pathology with MRI-based 3D node map in rectal cancer

PURPOSE

To propose a node-by-node matching method between MRI and pathology with 3D node maps based on preoperative MRI for rectal cancer patients to improve the yet unsatisfactory diagnostic performance of nodal status in rectal cancer.

METHODS

This methodological study prospectively enrolled consecutive participants with rectal cancer who underwent preoperative MRI and radical surgery from December 2021 to August 2023. All nodes with short-axis diameters of ≥ 3 mm within the mesorectum were regarded as target nodes and were localized in three directions based on the positional relationship on MRI and drawn on a node map with the primary tumor as the main reference, which was used as a template for node-by-node matching with pathological evaluation. Patient and nodal-level analyses were performed to investigate factors affecting the matching accuracy.

RESULTS

545 participants were included, of whom 253 received direct surgery and 292 received surgery after neoadjuvant therapy (NAT). In participants who underwent direct surgery, 1782 target nodes were identified on MRI, of which 1302 nodes (73%) achieved matching with pathology, with 1018 benign and 284 metastatic. In participants who underwent surgery after NAT, 1277 target nodes were identified and 918 nodes (72%) achieved matching, of which 689 were benign and 229 were metastatic. Advanced disease and proximity to primary tumor resulted in matching difficulties.

CONCLUSION

An easy-to-use and reliable method of node-by-node matching between MRI and pathology with 3D node map based on preoperative MRI was constructed for rectal cancer, which provided reliable node-based ground-truth labels for further radiological studies.

Enhancing the role of MRI in rectal cancer: advances from staging to prognosis prediction

Rectal cancer (RC) is one of the major health challenges worldwide. Accurate staging, restaging, invasiveness assessment, and treatment efficacy evaluation are crucial for its clinical management. Magnetic resonance imaging (MRI) plays a significant role in these processes. However, standard MRI techniques, including T2-weighted and diffusion-weighted imaging, have uncertainties in identifying early-stage tumors, high-risk nodules, extramural vascular invasion, and treatment efficacy, potentially leading to inappropriate treatment. Recent advances suggest that the integration of traditional MRI methods, including diffusion-weighted imaging, opposed-phase or contrast-enhanced T1-weighted imaging, as well as emerging synthetic MRI, could address these challenges. Additionally, improvements in imaging technology have spurred research into advanced functional MRI techniques such as diffusion kurtosis imaging and amide proton transfer weighted MRI, yielding promising results in RC assessment. Total neoadjuvant therapy has emerged as a new treatment paradigm for locally advanced RC, with neoadjuvant immunotherapy and chemotherapy offering viable alternatives to neoadjuvant chemoradiotherapy. However, the lack of standards for the early prediction of patient survival and tumor response to neoadjuvant therapy highlights a critical unmet need in matching therapies to suitable patients. Furthermore, organ preservation strategies after neoadjuvant therapy provide personalized options based on tumor response and patient preferences, yet traditional MRI assessments show significant variability. Radiomics and artificial intelligence hold promise for revealing complex patterns in MRI images associated with patient prognosis and treatment response. This review provides an overview of current MRI advancements in RC assessment and emphasizes how future research can refine tailored treatment strategies to improve patient outcomes. KEY POINTS: Question The accurate diagnosis of early-stage rectal tumors, high-risk nodules, treatment responses, and the early prediction of patient survival and therapeutic outcomes remain an unmet need. Findings Visual MRI has improved staging, restaging, and invasiveness evaluation. Advanced MRI, radiomics and artificial intelligence provide significant potential for tumor characterization and outcome prediction. Clinical relevance Advances in visual MRI are improving routine imaging protocols and radiomics and artificial intelligence show promise in enhancing treatment decisions through precise tumor characterization and outcome prediction.

Can MRI radiomics distinguish residual adenocarcinoma from acellular mucin in treated rectal cancer?

BACKGROUND

We explored the use of MRI T2-weighted imaging (T2WI) radiomics to help distinguish acellular mucin from cellular mucin (residual tumor) to inform patient management.

METHODS

This retrospective, multi-institutional study included consecutive patients with rectal adenocarcinoma containing mucin on restaging MRI from March 2012-January 2020. Radiologists segmented 3-mm-thick T2WI. Data were split into training (n = 122), validation (n = 40), and test (n = 42) sets. Sensitivity, specificity, PPV, NPV, and AUC of the developed radiomic models were investigated on the test set. Histopathology was the reference standard. Two radiologists independently reviewed 42 patients using a unique five-point Likert scale for the probability of cellular mucin. DeLong-Delong or McNemar's test was used to compare the AUC and diagnostic performance, respectively, of the radiomics model to that of the human readers.

RESULTS

Of 204 patients (mean age, 56.6 ± 13.3 years; 129 men and 75 women), 39/204 (19 %) had acellular mucin whereas 165/204 (81 %) had cellular mucin. The radiomics model demonstrated a sensitivity of 90 % (27/30, 95 % CI: 74-97 %), specificity of 83 % (10/12, 95 % CI: 55-95 %), PPV of 93 % (27/29, 95 % CI: 78-98 %), NPV of 77 % (10/13, 95 % CI: 50-92 %), and AUC of 0.84 (95 % CI: 0.65-0.99), whereas the human readers showed inferior sensitivities of 47 % (14/30) (95 % CI: 28-66 %) and 50 % (15/30) (95 % CI: 31-69 %) and AUCs of 0.58 (95 % CI: 0.41-0.74) (DeLong's p = 0.06 [95 % CI: -0.55, 0.01]) and 0.73 (95 % CI: 0.57-0.88) (DeLong's p = 0.43 [95 % CI: -0.39, 0.16]).

CONCLUSION

The developed MRI radiomics model predicts cellular mucin post neoadjuvant chemoradiation with higher sensitivity than human readers.

Diagnosing Complete Response to Preoperative Chemoradiation in Esophageal Cancer Using Dynamic Contrast-Enhanced MRI Response Criteria

OBJECTIVE

To assess the performance of novel qualitative diagnostic criteria using dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) to identify the pathologic complete response (pCR) of primary tumors in esophageal cancer after neoadjuvant chemoradiation (nCRT).

MATERIALS AND METHODS

Patients who underwent nCRT, subsequent MRI, positron emission tomography/computed tomography (PET/CT), endoscopy, or esophagectomy for esophageal cancer between October 2021 and October 2023 were retrospectively analyzed. The DCE-MRI response of primary tumors was interpreted using five grades by thoracic radiologists as follows: G1 (compatible with CR), G2 (probable CR), G3 (probable partial response [PR]), G4 (compatible with PR), and G5 (stable or progressive disease). The performances of MRI, PET/CT, endoscopy, and their combinations in diagnosing pCR in primary tumors were calculated.

RESULTS

A total of 52 patients (male:female, 46:6; age, 61.2 ± 8.0 years) were included. Surgical specimens revealed pCR (ypT0) in 34 patients. G1 as the MRI criterion for pCR of primary tumors yielded a positive predictive value (PPV), specificity of 100% (18/18), and low sensitivity (23.5% [8/34]). Combining G1 and G2 as the MRI criteria increased the sensitivity to 73.5% (25/34), with a specificity of 88.9% (16/18), accuracy of 78.8% (41/52), and PPV of 92.6% (25/27). Adding the DCE-MRI results (G1-2) significantly improved accuracy for both PET/CT (from 65.4% [34/52] to 80.8% [42/52], P = 0.03) and endoscopy (from 55.8% [29/52] to 76.9% [40/52], P = 0.005), with increase in sensitivity (from 55.9% [19/34] to 82.4% [28/34] for PET/CT-based evaluation [P = 0.008] and from 47.1% [16/34] to 82.4% [28/34] for endoscopy-based evaluation [P = 0.001]).

CONCLUSION

DCE-MRI-based grading shows high diagnostic performance for identifying pCR in primary tumors, particularly in terms of PPV and specificity, and enhances response evaluation when combined with PET/CT and endoscopy.

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.

Improving radiology reporting locally and globally: who, how, and why?

The radiology report is the communication from radiologist to referrer, used to inform prognosis and guide patient management. The report is the final step in a process which is influenced by the information on the referral, image quality, the reporting environment, and appropriate detection and interpretation of findings by the radiologist. It should present accurate, complete information in a way that can be easily understood. Even small improvements in any of these areas can have a significant impact on the average quality of radiology reports, with potential impact on vast numbers of patients across the globe. How do we train our future referrers to understand the complexities of imaging and write better referrals? How do we improve image quality as close to source as possible by engaging with equipment vendors? How can we make it easier for all radiologists to have access to the latest guidelines and use reporting templates where appropriate? Every radiologist has a role to play, with possible actions ranging from individual choice to departmental policies and global collaboration. The diseases we diagnose are the same, the equipment similar and knowledge freely available. All our patients deserve the best report we can provide.

Beyond the tumor region: Peritumoral radiomics enhances prognostic accuracy in locally advanced rectal cancer

BACKGROUND

The peritumoral region possesses attributes that promote cancer growth and progression. However, the potential prognostic biomarkers in this region remain relatively underexplored in radiomics.

AIM

To investigate the prognostic value and importance of peritumoral radiomics in locally advanced rectal cancer (LARC).

METHODS

This retrospective study included 409 patients with biopsy-confirmed LARC treated with neoadjuvant chemoradiotherapy and surgically. Patients were divided into training (n = 273) and validation (n = 136) sets. Based on intratumoral and peritumoral radiomic features extracted from pretreatment axial high-resolution small-field-of-view T2-weighted images, multivariate Cox models for progression-free survival (PFS) prediction were developed with or without clinicoradiological features and evaluated with Harrell’s concordance index (C-index), calibration curve, and decision curve analyses. Risk stratification, Kaplan-Meier analysis, and permutation feature importance analysis were performed.

RESULTS

The comprehensive integrated clinical-radiological-omics model (Model_ICRO) integrating seven peritumoral, three intratumoral, and four clinicoradiological features achieved the highest C-indices (0.836 and 0.801 in the training and validation sets, respectively). This model showed robust calibration and better clinical net benefits, effectively distinguished high-risk from low-risk patients (PFS: 97.2% vs 67.6% and 95.4% vs 64.8% in the training and validation sets, respectively; both P < 0.001). Three most influential predictors in the comprehensive Model_ICRO were, in order, a peritumoral, an intratumoral, and a clinicoradiological feature. Notably, the peritumoral model outperformed the intratumoral model (C-index: 0.754 vs 0.670; P = 0.015); peritumoral features significantly enhanced the performance of models based on clinicoradiological or intratumoral features or their combinations.

CONCLUSION

Peritumoral radiomics holds greater prognostic value than intratumoral radiomics for predicting PFS in LARC. The comprehensive model may serve as a reliable tool for better stratification and management postoperatively.

Multi-parametric MRI Habitat Radiomics Based on Interpretable Machine Learning for Preoperative Assessment of Microsatellite Instability in Rectal Cancer

RATIONALE AND OBJECTIVES

This study constructed an interpretable machine learning model based on multi-parameter MRI sub-region habitat radiomics and clinicopathological features, aiming to preoperatively evaluate the microsatellite instability (MSI) status of rectal cancer (RC) patients.

MATERIALS AND METHODS

This retrospective study recruited 291 rectal cancer patients with pathologically confirmed MSI status and randomly divided them into a training cohort and a testing cohort at a ratio of 8:2. First, the K-means method was used for cluster analysis of tumor voxels, and sub-region radiomics features and classical radiomics features were respectively extracted from multi-parameter MRI sequences. Then, the synthetic minority over-sampling technique method was used to balance the sample size, and finally, the features were screened. Prediction models were established using logistic regression based on clinicopathological variables, classical radiomics features, and MSI-related sub-region radiomics features, and the contribution of each feature to the model decision was quantified by the Shapley-Additive-Explanations (SHAP) algorithm.

RESULTS

The area under the curve (AUC) of the sub-region radiomics model in the training and testing groups was 0.848 and 0.8, respectively, both better than that of the classical radiomics and clinical models. The combined model performed the best, with AUCs of 0.908 and 0.863 in the training and testing groups, respectively.

CONCLUSION

We developed and validated a robust combined model that integrates clinical variables, classical radiomics features, and sub-region radiomics features to accurately determine the MSI status of RC patients. We visualized the prediction process using SHAP, enabling more effective personalized treatment plans and ultimately improving RC patient survival rates.

The Avocado Sign: A novel imaging marker for nodal staging in rectal cancer

OBJECTIVES

To evaluate the diagnostic performance of the Avocado Sign, a novel contrast-enhancement-based MR imaging marker, for prognostication of mesorectal lymph node spread in rectal cancer.

METHODS

This retrospective study included 106 patients with rectal cancer who underwent MRI examination. The Avocado Sign, defined as a hypointense core within an otherwise homogeneously hyperintense lymph node on contrast-enhanced T1-weighted images, was assessed. Of the cohort, 77 patients received neoadjuvant chemoradiotherapy followed by restaging MRI. Histopathological examination served as the reference standard. Diagnostic metrics were calculated and compared between subgroups using chi-square tests. Interobserver agreement was evaluated using Cohen's kappa.

RESULTS

The Avocado Sign demonstrated high diagnostic accuracy for predicting lymph node involvement, with an overall sensitivity of 88.7%, specificity of 84.9%, PPV of 85.5%, NPV of 88.2%, and accuracy of 86.8%. The area under the ROC curve was 0.87. Subgroup analysis revealed excellent performance in both patients undergoing surgery alone (sensitivity 100%, specificity 83.3%) and those receiving neoadjuvant therapy (sensitivity 84.2%, specificity 85.4%). Interobserver agreement was almost perfect (κ = 0.92).

CONCLUSION

The Avocado Sign is a promising imaging predictor for mesorectal lymph node status in rectal cancer. Its straightforward application, high reproducibility, and remarkable diagnostic accuracy underline its potential to refine MRI staging. However, further validation in larger, prospective multicenter studies is warranted to confirm these findings and assess their impact on clinical decision-making.

KEY POINTS

Question Can the Avocado Sign on contrast-enhanced MRI improve mesorectal lymph node staging in rectal cancer independently of classical morphological criteria? Findings The Avocado Sign demonstrated high sensitivity (88.7%) and specificity (84.9%) as a standalone marker for predicting mesorectal lymph node involvement. Clinical relevance Incorporating contrast-enhanced sequences and the Avocado Sign into MRI protocols enhances nodal staging accuracy in rectal cancer, potentially informing treatment decisions. Further validation is required to confirm its effectiveness and compare it with existing criteria.

Development and evaluation of the mrTE scoring system for MRI-detected tumor deposits and extramural venous invasion in rectal cancer

PURPOSE

Tumor deposits (TDs) and extramural venous invasion (EMVI) in locally advanced rectal cancer (LARC) are MRI-detectable markers that reflect the invasive and metastatic potential of tumors. However, both mrTDs and mrEMVI are closely associated with peritumoral vascular signals, and they show a high degree of statistical correlation. We developed a novel scoring system that integrates mrTDs and mrEMVI into a single parameter, simplifying the assessment process and capturing the prognostic value of both factors simultaneously.

METHODS

We retrospectively included LARC patients who received neoadjuvant chemoradiotherapy at five centers and proposed a novel MRI-based scoring system, mrTE (derived from mrTDs and mrEMVI), to integrate the prognostic significance of mrEMVI and mrTDs in rectal cancer. The prognostic value of different mrTE scores was evaluated using Kaplan-Meier curves and the Cox model. The predictive accuracy of the new scoring system was evaluated using the integrated area under the ROC curve (iAUC).

RESULTS

A total of 1188 patients with LARC were included in the evaluation cohort to assess the reliability of the novel imaging scoring system. Based on the mrTE scores ranging from 0 to 2, the patients were categorized into three groups. The 3-year disease-free survival rates for the groups were 88.1%, 78.1%, and 51.9% (score 1 vs 0: HR 2.00, 95% CI 1.36-2.93, p < 0.001; score 2 vs 0: HR 4.75, 95% CI 3.61-6.26, p < 0.001). The mrTE scoring system demonstrated superior performance in predicting DFS compared to other clinical and imaging markers, with a higher predictive accuracy (iAUC = 0.707).

CONCLUSIONS

The mrTE scoring system simplifies the clinical assessment of relevant MR markers and has proven to be an effective tool for predicting the prognosis of LARC patients.

Defining the tumor location in rectal cancer - Practice variations and impact on treatment decision making

OBJECTIVE

To summarize differences in current guideline recommendations for rectal tumor localization and generate an overview of published MRI measurement methods and their correlation with endoscopy.

SUMMARYOF BACKGROUND DATA

Rectal tumor location is a well-known factor that impacts treatment planning, but there is currently no consensus on the optimal method to define it.

METHODS

A literature search was conducted to retrieve clinical and radiological rectal cancer guidelines as well as original research studies on MRI-based measurements. Guidelines were assessed for definitions, landmarks, modalities and measurement methods to define tumor location, and how these impact treatment planning. Research studies were evaluated to compare MRI-methods and their correlation with endoscopy.

RESULTS

18 clinical and 6 radiological guidelines were retrieved. In 83 % of clinical guidelines tumor location (low/middle/high) is included in the treatment algorithm as a factor impacting surgical and/or neoadjuvant treatment. Measurement cut-offs and landmarks vary significantly with the anal verge being the most commonly used landmark (28 %). Thirty-nine percent of clinical guidelines offer no definitions to define rectal tumor location. The majority of research studies (67 %) reported good-excellent agreement between MRI and endoscopy, though measurement differences of up to 2.5 cm were reported.

CONCLUSION

There is substantial variation in definitions and landmarks recommended in current guidelines to measure and classify rectal tumor location. This may affect treatment planning as well as trial inclusions, highlighting the need for standardized methods that better align between clinical and radiological guidelines.

Early Rectal Cancer: Advances in Diagnosis and Management Strategies

Colorectal cancer (CRC) is the second most prevalent cause of cancer-related death and the third most common cancer globally. Early-stage rectal cancer is defined by lesions confined to the bowel wall, without extension beyond the submucosa in T1 or the muscularis propria in T2, with no indication of lymph node involvement or distant metastasis. The gold standard for managing rectal cancer is total mesorectal excision (TME); however, it is linked to considerable morbidities and impaired quality of life. There is a growing interest in local resection and non-operative treatment of early RC for organ preservation. Local resection options include three types of transanal endoscopic surgery (TES): transanal endoscopic microsurgery (TEM), transanal endoscopic operations (TEO), and transanal minimally invasive surgery (TAMIS), while endoscopic resection includes endoscopic mucosal resection (EMR), underwater endoscopic mucosal resection (UEMR), and endoscopic submucosal dissection (ESD). Although the oncological outcome of local resection of early rectal cancer is debated in the current literature, some studies have shown comparable outcomes with radical surgery in selected patients. The use of adjuvant and neoadjuvant chemoradiotherapy in early rectal cancer management is also controversial in the literature, but a number of studies have reported promising outcomes. This review focuses on the available literature regarding diagnosis, staging, and management strategies of early rectal cancer and provides possible recommendations.

Dual-energy CT quantitative parameters for prediction of prognosis in patients with resectable rectal cancer

OBJECTIVE

To determine whether quantitative parameters derived from dual-energy CT (DECT) could predict prognosis in patients with resectable rectal cancer (RC).

MATERIALS AND METHODS

One hundred and thirty-four patients (recurrence/distant metastasis group, n = 36; non-metastasis/non-recurrence group, n = 98) with RC who underwent radical resection and DECT were retrospectively included. DECT quantitative parameters, including iodine concentration (IC), normalized iodine concentration (NIC), electron density (Rho), effective atomic number (Zeff), dual-energy index (DEI), the slope of the spectral Hounsfield unit curve (λHU) on arterial and venous phase images. Univariate and multivariate Cox proportional hazards models were employed to identify independent risk factors of prognosis. The area under the receiver operating characteristic curve (AUC) was used to assess the performance. Disease-free survival (DFS) curves were constructed using the Kaplan-Meier method.

RESULTS

Patients in the metastasis/recurrence group had higher Rho in arterial phase (A-Rho), NIC in venous phase (V-NIC), Rho in venous phase (V-Rho), Zeff in venous phase (V-Zeff), λHU in venous phase (V-λHU), pT stage, pN stage, serum carcinoembryonic antigen (CEA), carbohydrate antigen-199 levels and more frequent in extramural venous invasion than those in non-metastasis/non-recurrence group (all p < 0.05). V-NIC, V-λHU, and CEA were independent risk factors of recurrence/distant metastasis (all p < 0.05). The AUC of combined indicator integrating three independent risk factors achieved the best diagnostic performance (AUC = 0.900). In stratified survival analysis, patients with high V-NIC, V-λHU, and CEA had lower 3-year DFS than those with low V-NIC, V-λHU, and CEA.

CONCLUSION

Combining V-NIC, V-λHU, and CEA could be used to noninvasively predict prognosis in resectable RC.

KEY POINTS

Question TNM staging fails to accurately prognosticate; can quantitative parameters derived from dual-energy CT predict prognosis in patients with resectable rectal cancer? Findings Normalized iodine concentration (V-NIC) and the slope of the spectral Hounsfield unit curve in venous phase (V-λHU), and carcinoembryonic antigen (CEA) are independent risk factors for recurrence/metastasis. Clinical relevance The combined indicator integrating V-NIC, V-λHU, and CEA could predict 3-year disease-free survival in patients with resectable rectal cancer and could aid in postoperative survival risk stratification to guide personalized treatment.

Inclusion of tumor periphery in radiomics analysis of magnetic resonance images does not improve predictions of preoperative therapy response in patients with rectal cancer

BACKGROUND/PURPOSE

To evaluate the advantages of including versus excluding the tumor periphery and combining diffusion-weighted imaging (DWI) with T2-weighted imaging (T2w) for outcome predictions of preoperative radio(chemo)therapy in rectal cancer.

METHODS

Four analysis strategies, based on two segmentation methods and two magnetic resonance imaging (MRI) sequences, were evaluated in 106 patients examined with pretreatment MRI. One segmentation method included the tumor periphery in the region of interest (ROI) encompassing the whole tumor (wROI), considered as the reference segmentation approach, and one included only the central part (cROI). Relevant radiomics imaging features were extracted from either T2w alone or from both T2w and DWI and used by a machine learning algorithm for the prediction of pathologic complete response (pCR), neoadjuvant rectal (NAR) score, and disease recurrence. The area under the curve (AUC) was the performance measure. AUCs were compared with a bootstrapping method based on 104 bootstraps.

RESULTS

cROI applied to both T2w and DWI provided the highest numerical prediction of pCR (AUC 0.76), however, not significantly superior to the other strategies (p ≥ 0.138). cROI applied to both T2w and DWI also yielded the highest numerical prediction of NAR score (AUC 0.84), showing advantages over wROI-based analysis strategies (AUC 0.66 and 0.69; p ≤ 0.008). When compared to cROI applied to T2w alone (AUC 0.73), the benefit was borderline statistically significant (p = 0.053). For prediction of disease recurrence, no differences were found between the analysis strategies.

CONCLUSIONS

Inclusion of the tumor periphery in radiomic analysis of magnetic resonance images does not improve predictions of the preoperative therapy response in patients with rectal cancer. Excluding tumor periphery while adding DWI to T2w improves prediction of the NAR score, although it does not affect pCR or recurrence prediction.

Assessment of prognostic indicators and KRAS mutations in rectal cancer using a fractional-order calculus MR diffusion model: whole tumor histogram analysis

PURPOSE

This study aims to explore the relationship between apparent diffusion coefficient (ADC) and fractional-order calculus (FROC)-specific parameters with prognostic indicators and Kirsten rat sarcoma viral oncogene homologue (KRAS) mutation status in rectal cancer.

METHODS

One hundred fifty-eight patients with rectal cancer were retrospectively enrolled. Histogram measurements of ADC, diffusion coefficient (D), intravoxel diffusion heterogeneity (β), and a microstructural quantity (μ) were estimated for the whole-tumor volume. The relationships between histogram measurements and prognostic indicators were evaluated. The efficacy of histogram measurements, both conducted singly and in conjunction, for evaluating different KRAS mutation statuses was also assessed. The performance of mean and median histogram measurements in evaluating various KRAS mutation statuses was assessed using Receiver Operating Characteristic (ROC) curve analysis. A p-value of less than 0.05 was considered statistically significant.

RESULTS

The histogram measurements of ADC, D, β, and μ differed significantly between well-moderately differentiated groups and poorly differentiated groups, T1-2 and T3-4 subgroups, lymph node metastasis (LNM)-negative and LNM-positive subgroups, extranodal extension (ENE)-negative and ENE-positive subgroups, tumor deposit (TD)-negative and TD-positive subgroups, and lymphovascular invasion (LVI)-negative and LVI-positive subgroups. The combination of Dmean, βmean, and μmean achieved the highest performance [The area under the ROC curve (AUC) = 0.904] in evaluating the KRAS mutation status.

CONCLUSION

When assessing parameters from the FROC model as potential biomarkers through histograms, they surpass traditional ADC values in distinguishing prognostic indicators and determining KRAS mutation status in rectal cancer.

Selection of rectal cancer patients for organ preservation after neoadjuvant therapy: value of T2W-MRI signal intensity

BackgroundOrgan preservation strategies have been widely implemented for rectal cancer (RC) patients with a good response after neoadjuvant chemoradiation (nCRT). However, to accurately select eligible patients remains one of the key diagnostic challenges.PurposeTo identify eligible candidates for organ preservation after nCRT in RC, by identifying luminal response and lymph node metastases, based on T2W-MRI signal intensities.Material and MethodsA total of 171 RC patients underwent MRI before and after nCRT. The primary tumor (pre-nCRT-MRI) and tumor remnant (post-nCRT-MRI) were manually delineated. Ten signal intensity features were extracted and delta features were calculated by subtraction. Histopathological evaluation classified patients as lymph node negative (ypN0) or positive (ypN+), and as good responders (GR) or partial/poor responders (PR). Five models were constructed based on the timing of imaging.Results42/170 (25%) patients had ypN+, and 72/152 (47%) patients were considered GR. Univariate analysis showed 13/40 signal intensity features were significantly different between luminal response groups and 4/40 between nodal response groups. In multivariate analysis, the Baseline + Restaging-model yielded the best results for both luminal and nodal response with AUCs in the test set of 0.81 (95% CI=0.67-0.95) and 0.74 (95% CI=0.59-0.90), respectively. To identify PR, the Delta-model yielded an AUC of 0.72 (95% CI=0.56-0.89) and the Delta + Restaging-model an AUC of 0.81 (95% CI=0.67-0.95), both were not able to differentiate nodal response. The models including solely baseline or restaging features were not predictive.ConclusionT2W-MRI signal intensities of the primary rectal tumor are related to the luminal and nodal response after nCRT and hold promise to identify patients eligible for organ preservation.

A robust auto-contouring and data augmentation pipeline for adaptive MRI-guided radiotherapy of pancreatic cancer with a limited dataset

Objective.This study aims to develop and evaluate a fast and robust deep learning-based auto-segmentation approach for organs at risk in MRI-guided radiotherapy of pancreatic cancer to overcome the problems of time-intensive manual contouring in online adaptive workflows. The research focuses on implementing novel data augmentation techniques to address the challenges posed by limited datasets.Approach.This study was conducted in two phases. In phase I, we selected and customized the best-performing segmentation model among ResU-Net, SegResNet, and nnU-Net, using 43 balanced 3DVane images from 10 patients with 5-fold cross-validation. Phase II focused on optimizing the chosen model through two advanced data augmentation approaches to improve performance and generalizability by increasing the effective input dataset: (1) a novel structure-guided deformation-based augmentation approach (sgDefAug) and (2) a generative adversarial network-based method using a cycleGAN (GANAug). These were compared with comprehensive conventional augmentations (ConvAug). The approaches were evaluated using geometric (Dice score, average surface distance (ASD)) and dosimetric (D2% and D50% from dose-volume histograms) criteria.Main results.The nnU-Net framework demonstrated superior performance (mean Dice: 0.78 ± 0.10, mean ASD: 3.92 ± 1.94 mm) compared to other models. The sgDefAug and GANAug approaches significantly improved model performance over ConvAug, with sgDefAug demonstrating slightly superior results (mean Dice: 0.84 ± 0.09, mean ASD: 3.14 ± 1.79 mm). The proposed methodology produced auto-contours in under 30 s, with 75% of organs showing less than 1% difference in D2% and D50% dose criteria compared to ground truth.Significance.The integration of the nnU-Net framework with our proposed novel augmentation technique effectively addresses the challenges of limited datasets and stringent time constraints in online adaptive radiotherapy for pancreatic cancer. Our approach offers a promising solution for streamlining online adaptive workflows and represents a substantial step forward in the practical application of auto-segmentation techniques in clinical radiotherapy settings.

Evaluation of MRI characterisation of histopathologically matched lymph nodes and other mesorectal nodal structures in rectal cancer

PURPOSE

To evaluate current MRI-based criteria for malignancy in mesorectal nodal structures in rectal cancer.

METHOD

Mesorectal nodal structures identified on baseline MRI as lymph nodes were anatomically compared to their corresponding structures histopathologically, reported as lymph nodes, tumour deposits or extramural venous invasion. All anatomically matched nodal structures from patients with primary surgery and all malignant nodal structures from patients with neoadjuvant treatment were included. Mixed-effects logistic regression models were used to evaluate the morphological criteria irregular margin, round shape, heterogeneous signal and nodal size, as well as the combined 2016 European Society of Gastrointestinal and Abdominal Radiology (ESGAR) consensus criteria, with histopathological nodal status as the gold standard.

RESULTS

In total, 458 matched nodal structures were included from 46 patients (mean age, 67.7 years ± 1.5 [SD], 27 men), of which 19 received neoadjuvant treatment. The strongest associations in the univariable model were found for short-axis diameter ≥ 5 mm (OR 21.43; 95% CI: 4.13-111.29, p < 0.001) and heterogeneous signal (OR 9.02; 95% CI: 1.33-61.08, p = 0.024). Only size remained significant in multivariable analysis (OR 12.32; 95% CI: 2.03-74.57, p = 0.006). When applying the ESGAR consensus criteria to create a binary classification of nodal status, the OR of malignant outcome for nodes with positive ESGAR was 8.23 (95% CI: 2.15-31.50, p = 0.002), with corresponding sensitivity and specificity of 54% and 85%, respectively.

CONCLUSION

The results confirm the role of morphological and size criteria in predicting lymph node metastases. However, the current criteria might not be accurate enough for nodal staging.

KEY POINTS

Question Pretreatment lymph node staging in rectal cancer is challenging, and the ESGAR consensus criteria are not fully validated. Findings Although the ESGAR criteria correlated with malignant outcomes, diagnostic performance in terms of particular sensitivity, but also specificity, was not high. Clinical relevance Accurate nodal staging in rectal cancer is crucial for individual treatment planning. However, this validation of the current ESGAR consensus criteria suggests that these should be used with caution.

A Comprehensive Approach to Neoadjuvant Treatment of Locally Advanced Rectal Cancer

At the end of the past century, the introduction of Total Mesorectal Excision (TME), preceded by either short-course radiotherapy (SCRT) or chemoradiation (CRT), established the new standard of care for locally advanced rectal cancer (LARC). Recently, significant advancements were achieved for both dMMR/MSI and pMMR/MSS LARC patients. For the 2-3% of dMMR/MSI LARCs, ablative immunotherapy emerged as a curative approach, offering the possibility of avoiding chemotherapy (CT), radiotherapy, and surgery altogether. In pMMR/MSS LARCs, the intensification of preoperative treatments with Total Neoadjuvant Treatment (TNT) afforded three outcomes: (a) a reduction of distant metastases, positively impacting on survival endpoints, (b) a significant increase of complete clinical response (cCR) rate, paving the way for non-operative management (NOM), and (c) the selective omission of radiotherapy following induction CT. The choice of the most appropriate therapeutic strategy can only be made through the shared decision-making process between physician and patient based on risk stratification and patient preferences.

A novel MRI-based radiomics for preoperative prediction of lymphovascular invasion in rectal cancer

BACKGROUND

To develop and validate a clinical-radiomics model for preoperative prediction of lymphovascular invasion (LVI) in rectal cancer.

METHODS

This retrospective study included data from 239 patients with pathologically confirmed rectal adenocarcinoma from two centers, all of whom underwent MRI examinations. Cases from the first center (n = 189) were randomly divided into a training set and an internal validation set at a 7:3 ratio, while cases from the second center (n = 50) constituted the external validation set. The clinical features and MRI imaging characteristics of the patients in the training set were analyzed. Univariate and multivariate logistic regression analyses were used to identify independent risk factors for LVI in rectal cancer, and these risk factors were then used to construct a clinical model. Regions of interest (ROIs) were delineated on T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) sequences for feature extraction. After feature reduction and selection, the most strongly correlated features were identified, and their respective regression coefficients were calculated to construct the radiomics model. Finally, a combined clinical-radiomics model was built using a weighted linear combination of features and was visualized as a nomogram. The predictive performance of each model was quantified using receiver operating characteristics (ROC) curves and the area under the curve (AUC) in both training and validation sets, with DeLong analysis being used to compare model performance. Decision curve analysis (DCA) was used to evaluate the clinical utility of each model in the validation sets.

RESULTS

In the 239 patients, the combined model outperformed the clinical and radiomics models in predicting LVI in rectal cancer. The combined model showed excellent predictive performance in the training, internal validation, and external validation sets, with AUCs of 0.90 (0.88-0.97), 0.88 (0.78-0.99), and 0.88 (0.78-0.95), respectively. The sensitivity values were 75.9%, 68.8%, and 80.0%, respectively, and the specificity values were 90.3%, 92.7%, and 88.6%. DCA results indicated that the nomogram of the combined model had superior clinical utility compared with the clinical and radiomics models.

CONCLUSIONS

The clinical-radiomics nomogram serves as a valuable tool for non-invasive preoperative prediction of LVI status in patients with rectal cancer.

Node Reporting and Data System 1.0 (Node-RADS) for the Assessment of Oncological Patients' Lymph Nodes in Clinical Imaging

The assessment of lymph node (LN) involvement with clinical imaging is a key factor in cancer staging. Node Reporting and Data System 1.0 (Node-RADS) was introduced in 2021 as a new system specifically tailored for classifying and reporting LNs on computed tomography (CT) and magnetic resonance imaging scans. The aim of this review is to compile the scientific evidence that has emerged since the introduction of Node-RADS, with a specific focus on its diagnostic performance and reliability. Node-RADS's performance has been evaluated in various cancer types and anatomical sites, revealing a trend where higher Node-RADS scores correspond to a greater probability of metastatic LN with better diagnostic performances compared to using short axis diameter alone. Moreover, Node-RADS exhibits encouraging diagnostic value for both Node-RADS ≥ 3 and Node-RADS ≥ 4 cutoffs in predicting metastatic LN. In terms of Node-RADS scoring reliability, preliminary studies show promising but partially conflicting results, with agreement levels, mostly between two readers, ranging from fair to almost perfect. This review highlights a wide variation in methodologies across different studies. Thus, to fully realize the potential of Node-RADS in clinical practice, future studies should comprehensively evaluate its diagnostic accuracy, category-specific malignancy rates, and inter-observer agreement. Finally, although limited, promising evidence has suggested the following: a potential prognostic role for Node-RADS; the possible value of diffusion-weighted imaging for LNs classified as Node-RADS ≥ 3; a correlation between Node-RADS and certain texture features in CT; and improved diagnostic performance when Node-RADS is integrated into radiomics or clinical models.

Ultra-high b-value DWI in rectal cancer: image quality assessment and regional lymph node prediction based on radiomics

OBJECTIVES

This study aims to evaluate image quality and regional lymph node metastasis (LNM) in patients with rectal cancer (RC) on multi-b-value diffusion-weighted imaging (DWI).

METHODS

This retrospective study included 199 patients with RC who had undergone multi-b-value DWI. Subjective (five-point Likert scale) and objective assessments of quality images were performed on DWIb1000, DWIb2000, and DWIb3000. Patients were randomly divided into a training (n = 140) or validation cohort (n = 59). Radiomics features were extracted within the whole volume tumor on ADC maps (b = 0, 1000 s/mm2), DWIb1000, DWIb2000, and DWIb3000, respectively. Five prediction models based on selected features were developed using logistic regression analysis. The performance of radiomics models was evaluated with a receiver operating characteristic curve, calibration, and decision curve analysis (DCA).

RESULTS

The mean signal intensity of the tumor (SItumor), signal-to-noise ratio (SNR), and artifact and anatomic differentiability score gradually were decreased as the b-value increased. However, the contrast-to-noise (CNR) on DWIb2000 was superior to those of DWIb1000 and DWIb3000 (4.58 ± 0.86, 3.82 ± 0.77, 4.18 ± 0.84, p < 0.001, respectively). The overall image quality score of DWIb2000 was higher than that of DWIb3000 (p < 0.001) and showed no significant difference between DWIb1000 and DWIb2000 (p = 0.059). The area under curve (AUC) value of the radiomics model based on DWIb2000 (0.728) was higher than conventional ADC maps (0.690), DWIb1000 (0.699), and DWIb3000 (0.707), but inferior to multi-b-value DWI (0.739) in predicting LNM.

CONCLUSION

DWIb2000 provides better lesion conspicuity and LNM prediction than DWIb1000 and DWIb3000 in RC.

CLINICAL RELEVANCE STATEMENT

DWIb2000 offers satisfactory visualization of lesions. Radiomics features based on DWIb2000 can be applied for preoperatively predicting regional lymph node metastasis in rectal cancer, thereby benefiting the stratified treatment strategy.

KEY POINTS

Lymph node staging is required to determine the best treatment plan for rectal cancer. DWIb2000 provides superior contrast-to-noise ratio and lesion conspicuity and its derived radiomics best predict lymph node metastasis. DWIb2000 may be recommended as the optimal b-value in rectal MRI protocol.

Pretreatment MRI Parameters and Neutrophil-to-Lymphocyte Ratio Could Predict the Long-Term Prognosis of Locally Advanced Rectal Cancer Patients With Pathological Complete Response after Neoadjuvant Chemoradiotherapy

BackgroundLocal advanced rectal cancer (LARC) patients who achieved pathological complete response (pCR) after neoadjuvant chemoradiotherapy (NCRT) generally have a favorable prognosis. This retrospective study aimed to evaluate the prognostic value of magnetic resonance imaging (MRI) parameters and neutrophil-to-lymphocyte ratio (NLR) in LARC patients with pCR.MethodsBetween 2015 and 2019, 180 LARC patients who achieved pCR after NCRT and surgery were included. MRI parameters and NLR were evaluated as potential predictors for 5-year overall survival (OS) and disease-free survival (DFS) using the Kaplan-Meier and COX regression analysis.ResultsWith a median follow-up time of 68.3 months, the 5-year OS and DFS rates were 94.2% and 91.4%, respectively. Thirteen patients (7.2%) died, 2 (1.1%) experienced local recurrence, and 15 (8.3%) experienced distant metastases. Pretreatment MRI parameters and NLR were correlated with 5-year OS and DFS in pCR patients in the univariate analysis. The multivariate analysis identified baseline EMVI and NLR as independent predictors for 5-year OS and DFS (all P < .05). Patients in the low-risk group (EMVI-negative and/or NLR ≤ 2.8, n = 159, 88.3%) had a more favorable 5-year DFS compared to those in the high-risk group (EMVI-positive and NLR > 2.8, n = 21, 11.7%) (95.6% vs 59.4%, P < .001), with similar findings for 5-year OS (97.4% vs 70.6%, P < .001).ConclusionsThis study showed that MRI parameters and NLR were associated with long-term prognosis in patients with pCR. These findings could aid in stratifying pCR patients and guide subsequent treatment and follow-up strategies.

MRI of the Rectum: A Decade into DISTANCE, Moving to DISTANCED

Over the past decade, advancements in rectal cancer research have reshaped treatment paradigms. Historically, treatment for locally advanced rectal cancer has focused on neoadjuvant long-course chemoradiotherapy, followed by total mesorectal excision. Interest in organ preservation strategies has been strengthened by the introduction of total neoadjuvant therapy with improved rates of complete clinical response. The administration of systemic induction chemotherapy and consolidation chemoradiotherapy in the neoadjuvant setting has introduced a new dimension to the treatment landscape and patients now face a more intricate decision-making process, given the expanded therapeutic options. This complexity underlines the importance of shared decision-making and brings to light the crucial role of radiologists. MRI, especially high-spatial-resolution T2-weighted imaging, is heralded as the reference standard for rectal cancer management because of its exceptional ability to provide staging and prognostic insights. A key evolution in MRI interpretation for rectal cancer is the transition from the DISTANCE mnemonic to the more encompassing DISTANCED-DIS, distal tumor boundary; T, T stage; A, anal sphincter complex; N, nodal status; C, circumferential resection margin; E, extramural venous invasion; D, tumor deposits. This nuanced shift in the mnemonic captures a wider range of diagnostic indicators. It also emphasizes the escalating role of radiologists in steering well-informed decisions in the realm of rectal cancer care.

Radiographs are of limited use and low cost-effectiveness when combined with ultrasound for abdominal restaging in dogs with solid, soft tissue tumours

OBJECTIVE

The purposes of this study were to assess the frequency of detection of clinically relevant findings by abdominal radiographs and abdominal ultrasound during restaging of solid, soft tissue tumours in dogs and to determine the cost per clinically relevant finding for both modalities.

MATERIALS AND METHODS

The medical records of 159 dogs which underwent a total of 223 restaging episodes following a diagnosis of a solid, soft tissue tumour within, or with potential for metastasis to, the abdomen were reviewed. Data collected from the sample dogs were reviewed for clinically relevant findings, including local recurrence, lymph node or intra-abdominal metastasis, and other changes that would influence prognosis or management. The clinically relevant findings were compared between abdominal radiographs and abdominal ultrasound. The cost per clinically relevant finding was calculated per modality based on current hospital costs.

RESULTS

Clinically relevant findings were observed in 158 restaging episodes. Ninety-two clinically relevant findings were detected with ultrasound alone, and 65 clinically relevant findings were detected with a combination of both modalities. Only one dog had a clinically relevant finding detected with radiographs alone. Findings were identified significantly more frequently with ultrasound than radiographs. Cost per clinically relevant finding was 495 USD (approx. 373 GBP/448 EUR) for abdominal radiographs and 323 USD (approx. 242 GBP/292 EUR) for abdominal ultrasound.

CLINICAL SIGNIFICANCE

Abdominal radiographs were of minimal use beyond abdominal ultrasound for restaging in this study, despite a higher cost per clinically relevant finding than abdominal ultrasound. This study does not support routine use of abdominal radiographs during routine restaging of solid, soft tissue tumours.

Diagnostic performance of Node-RADS score for mesorectal lymph node metastasis in rectal cancer

PURPOSE

To explore the diagnostic performance of the Node-RADS scoring system on preoperative assessment of mesorectal lymph node metastasis (LNM) status in rectal cancer, in comparison with the ESGAR category and size of lymph node (LN).

METHODS

Preoperative clinical and MRI data of 154 rectal adenocarcinoma patients treated with radical resection surgery were retrospectively analyzed. The differences in the clinical, pathological and imaging characteristics between the pN- and pN + groups were surveyed. The correlations of Node-RADS score and ESGAR category to pN stage, LNM number and lymph node ratio (LNR) were investigated. The performances on assessing pathological LNM were compared among individual approaches. A nomogram combined the imaging and clinical features was also established and evaluated.

RESULTS

Significant differences in CEA, tumor maximum diameter, tumor location, LN short-axis diameter, Node-RADS score and ESGAR category were found between the pN- and pN + groups. Node-RADS correlated significantly with pN stage, LNM number, and LNR (r = 0.665, 0.685, and 0.675, p < 0.001). Node-RADS had the highest AUC (0.862) for predicting pN + status, surpassing ESGAR (AUC = 0.797, p = 0.040) and LN size (AUC = 0.762, p = 0.015). The nomogram had the best diagnostic performance (AUC = 0.901), significantly outperforming Node-RADS alone (p = 0.037).

CONCLUSIONS

The Node-RADS scoring system is comparable to the ESGAR category and surpasses short-axis diameter in preoperatively predicting LNM in rectal cancer. Integrating imaging and clinical features will lead to an enhancement in diagnostic performance. Moreover, a clear relationship was demonstrated between the Node-RADS score and the quantity-dependent pathological characteristics of LNM.

Deep learning for segmentation of colorectal carcinomas on endoscopic ultrasound

BACKGROUND

Bowel-preserving local resection of early rectal cancer is less successful if the tumor infiltrates the muscularis propria as opposed to submucosal infiltration only. Magnetic resonance imaging currently lacks the spatial resolution to provide a reliable estimation of the infiltration depth. Endoscopic ultrasound (EUS) has better resolution, but its interpretation is investigator dependent. We hypothesize that automated image segmentation of EUS could be a way to standardize EUS interpretation.

METHODS

EUS media and outcome data were collected prospectively. Based on 373 expert manual segmentations, a convolutional neural network was developed to perform segmentation of the submucosa, muscularis propria, and tumors. The mean surface distance (MSD), maximal distance between segmentations (Hausdorff distance; HDD), and overlap (Dice similarity index; DSI) were calculated.

RESULTS

The median MSD and HDD values were 3.2 and 17.7 pixels for the tumor, 3.4 and 24.7 pixels for the submucosa, and 2.6 and 20.0 pixels for the muscularis propria, respectively. The median DSI values for the tumor, submucosa, and muscularis propria were 0.82, 0.57, and 0.59, respectively. These values reflect good agreement between manual and deep learning segmentation.

CONCLUSIONS

This study found encouraging results of using automated analysis of EUS images of early rectal cancer, supporting further exploration in clinical practice.

Accelerated T2W Imaging with Deep Learning Reconstruction in Staging Rectal Cancer: A Preliminary Study

Deep learning reconstruction (DLR) has exhibited potential in saving scan time. There is limited research on the evaluation of accelerated acquisition with DLR in staging rectal cancers. Our first objective was to explore the best DLR level in saving time through phantom experiments. Resolution and number of excitations (NEX) adjusted for different scan time, image quality of conventionally reconstructed T2W images were measured and compared with images reconstructed with different DLR level. The second objective was to explore the feasibility of accelerated T2W imaging with DLR in image quality and diagnostic performance for rectal cancer patients. 52 patients were prospectively enrolled to undergo accelerated acquisition reconstructed with highly-denoised DLR (DLR_H40sec) and conventional reconstruction (ConR2min). The image quality and diagnostic performance were evaluated by observers with varying experience and compared between protocols using κ statistics and area under the receiver operating characteristic curve (AUC). The phantom experiments demonstrated that DLR_H could achieve superior signal-to-noise ratio (SNR), detail conspicuity, sharpness, and less distortion within the least scan time. The DLR_H40sec images exhibited higher sharpness and SNR than ConR2min. The agreements with pathological TN-stages were improved using DLR_H40sec images compared to ConR2min (T: 0.846vs. 0.771, 0.825vs. 0.700, and 0.697vs. 0.512; N: 0.527vs. 0.521, 0.421vs. 0.348 and 0.517vs. 0.363 for junior, intermediate, and senior observes, respectively). Comparable AUCs to identify T3-4 and N1-2 tumors were achieved using DLR_H40sec and ConR2min images (P > 0.05). Consequently, with 2/3-time reduction, DLR_H40sec images showed improved image quality and comparable TN-staging performance to conventional T2W imaging for rectal cancer patients.

Effects of mesenteric artery ligation level on patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy: a retrospective cohort study

BACKGROUND

There is currently limited research on the optimal level of inferior mesenteric artery (IMA) ligation during surgery for patients with locally advanced rectal cancer (LARC) undergoing neoadjuvant chemoradiotherapy (nCRT). We carried out a retrospective cohort study to analyze the impact of IMA ligation level on surgical outcomes and long-term patient prognosis.

METHODS

The data originated from a multicenter randomized controlled trial conducted across six tertiary referral hospitals in Beijing, involving patients with LARC undergoing nCRT followed by radical surgery. Patients were divided into high ligation (HL) and low ligation (LL) groups on the basis of the ligation level of IMA. Evaluation parameters included surgical outcomes, complications, long-term survival, and quality of life questionnaires.

RESULTS

From August 2017 to April 2022, a total of 337 patients were included in the analysis. The number of lymph nodes retrieved was higher in the LL group compared with the HL group. Patients in both groups experienced a significant decrease in quality-of-life scores, but no difference in the extent of this decline was observed between the two groups. There were no significant differences between the two groups in terms of operation time, intraoperative blood loss, and other factors. There was also no significant difference in DFS (p = 0.818) and OS (p = 0.945) between the two groups.

CONCLUSIONS

For patients with LARC undergoing nCRT, the level of IMA ligation during radical surgery does not significantly impact complications or long-term prognosis. The selection of ligation pattern should be on the basis of a comprehensive assessment of factors including metastatic risk, vascular anatomy, comorbidity (such as atherosclerosis), and surgical skills of the surgeons.

MRI of early rectal cancer; bisacodyl micro-enema increases submucosal width, reader confidence, and tumor conspicuity

PURPOSE

To investigate the influence of a micro-enema on diagnostic performance, submucosal width, reader confidence, and tumor conspicuity using MRI to stage early rectal cancers (ERC).

METHODS

In this single-center study, we consecutively included 50 participants with assumed ERC who all completed MRI with (MRin) and without (MRex) a micro-enema. The diagnostic performance was recorded for two experienced radiologists using histopathology as the gold standard. In addition, the width of the submucosa in the tumor-bearing wall, reader confidence for T-staging, and tumor conspicuity were assessed. Significance levels were calculated using McNemar's test (diagnostic performance) and Wilcoxon's signed-rank test (reader confidence, submucosal width, and conspicuity). Interreader agreement was assessed using kappa statistics.

RESULTS

Sensitivity/specificity were for Reader1 91%/87% for both MRex and MRin and for Reader2 74%/87% and 89%/87%, both readers p > 0.05. The micro-enema induced a significant widening of the submucosa, p < 0.001, with a mean increase of 2.2/2.8 mm measured by Reader1/Reader2. Reader confidence in T-staging and tumor conspicuity increased for both readers, p < 0.005. The proportion of tumors with both correct staging and high reader confidence increased from 58% (29/50) to 80% (40/50) (p = 0.04) for Reader1 and from 42% (21/50) to 72% (36/50) (p = 0.002) for Reader2. Interreader agreement increased from moderate (kappa 0.58) to good (kappa 0.68).

CONCLUSION

The micro-enema significantly increased the submucosal width in the tumor-bearing wall, reader confidence, and tumor conspicuity and improved interreader agreement from moderate to good. Sensitivity and specificity in T-staging did not improve, but there was a significant increase in the proportion of tumors staged with both high confidence and correct T-stage.

Comparative effectiveness of two abbreviated rectal MRI protocols in assessing tumor response to neoadjuvant chemoradiotherapy in patients with rectal cancer

The present study aimed to compare the effectiveness of two abbreviated magnetic resonance imaging (MRI) protocols in assessing the response to neoadjuvant chemoradiotherapy (CRT) in patients with rectal cancer. Data from the examinations of 62 patients with rectal cancer who underwent neoadjuvant CRT and standard contrast-enhanced rectal MRI were retrospectively evaluated. Standard contrast-enhanced T2-weighted imaging (T2-WI), post-contrast T1-weighted imaging (T1-WI) and diffusion-weighted imaging (DWI) MRI, as well as two abbreviated protocols derived from these images, namely protocol AB1 (T2-WI and DWI) and protocol AB2 (post-contrast fat-suppressed (FS) T1-WI and DWI), were assessed. Measurements of lesion length and width, lymph node short-axis length, tumor staging, circumferential resection margin (CRM), presence of extramural venous invasion (EMVI), luminal mucin accumulation (MAIN), mucinous response, mesorectal fascia (MRF) involvement, and MRI-based tumor regression grade (mrTRG) were obtained. The reliability and compatibility of the AB1 and AB2 protocols in the evaluation of tumor response were analyzed. The imaging performed according to the AB1 and AB2 protocols revealed significant decreases in lesion length, width and lymph node size after CRT. These protocols also showed reductions in lymph node positivity, CRM, MRF, EMVI.Furthermore, both protocols were found to be reliable in determining lesion length and width. Additionally, compliance was observed between the protocols in determining lymph node size and positivity, CRM involvement, and EMVI after CRT. In conclusion, the use of abbreviated MRI protocols, specifically T2-WI with DWI sequences or post-contrast FS T1-WI with DWI sequences, is effective for evaluating tumor response in patients with rectal cancer following neoadjuvant CRT. The AB protocols examined in this study yielded similar results in terms of lesion length and width, lymph node positivity, CRM involvement, EMVI, MAIN, and MRF involvement.

Fractional order calculus model-derived histogram metrics for assessing pathological complete response to neoadjuvant chemotherapy in locally advanced rectal cancer

AIM

This study evaluates the value of diffusion fractional order calculus (FROC) model for the assessment of pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) for locally advanced rectal cancer (LARC) by using histogram analysis derived from whole-tumor volumes.

MATERIALS AND METHODS

Ninety-eight patients were prospectively included. Every patient received MRI scans before and after nCRT using a 3.0-Tesla MRI machine. Parameters of the FROC model, including the anomalous diffusion coefficient (D), intravoxel diffusion heterogeneity (β), spatial parameter (μ), and the standard apparent diffusion coefficient (ADC), were calculated. Changes in median values (ΔX-median) and ratio (rΔX-median) were calculated. Receiver operating characteristic (ROC) curves were used for evaluating the diagnostic performance.

RESULTS

Pre-treatmentβ-10th percentile values were significantly lower in the pCR group compared to the non-pCR group (p < 0.001). The Δβ-median showed higher diagnostic accuracy (AUC = 0.870) and sensitivity (76.67 %) for predicting tumor response compared to MRI tumor regression grading (mrTRG) scores (AUC = 0.722; sensitivity = 90.0 %).

DISCUSSION

The use of FROC alongside comprehensive tumor histogram analysis was found to be practical and effective in evaluating the tumor response to nCRT in LARC patients.

Localized Rectal Cancer: Indian Consensus and Guidelines

The rising incidence of colorectal cancer (CRC) in India, particularly the prevalence of rectal cancer over colon cancer (0.7:1), has been a growing concern in recent decades; especially notable is the trend of increasing cases among young CRC patients. Given the diverse treatment approaches for rectal cancer globally and the varying economic capacities of patients in low to middle-income countries (LMICs) like India, it is essential to establish consensus guidelines that are specifically tailored to meet the needs of these patients. To achieve this, a panel comprising 30 eminent rectal cancer experts convened to conduct a comprehensive and impartial evaluation of existing practices and recent advancements in the field. Through meticulous scrutiny of published literature and a consensus-building process that involved voting on pertinent questions, the panel formulated management strategies. These recommendations are the result of a rigorous, evidence-based process and encapsulate the collective wisdom and judgment of leading authorities in the field.

A Machine Learning Model Based on MRI Radiomics to Predict Response to Chemoradiation Among Patients with Rectal Cancer

BACKGROUND

With rectum-sparing protocols becoming more common for rectal cancer treatment, this study aimed to predict the pathological complete response (pCR) to preoperative chemoradiotherapy (pCRT) in rectal cancer patients using pre-treatment MRI and a radiomics-based machine learning approach.

METHODS

We divided MRI-data from 102 patients into a training cohort (n = 72) and a validation cohort (n = 30). In the training cohort, 52 patients were classified as non-responders and 20 as pCR based on histological results from total mesorectal excision.

RESULTS

We trained various machine learning models using radiomic features to capture disease heterogeneity between responders and non-responders. The best-performing model achieved a receiver operating characteristic area under the curve (ROC-AUC) of 73% and an accuracy of 70%, with a sensitivity of 78% and a positive predictive value (PPV) of 80%. In the validation cohort, the model showed a sensitivity of 81%, specificity of 75%, and accuracy of 80%.

CONCLUSIONS

These results highlight the potential of radiomics and machine learning in predicting treatment response and support the integration of advanced imaging and computational methods for personalized rectal cancer management.