Do MRI reports contain adequate preoperative staging information for end users to make appropriate treatment decisions for rectal cancer?

Clinical development of MRI-based multi-sequence multi-regional radiomics model to predict lymph node metastasis in rectal cancer

OBJECTIVE

We aim to construct a magnetic resonance imaging (MRI)-based multi-sequence multi-regional radiomics model that will improve the preoperative prediction ability of lymph node metastasis (LNM) in T3 rectal cancer.

METHODS

Multi-sequence MRI data from 190 patients with T3 rectal cancer were retrospectively analyzed, with 94 patients in the LNM group and 96 patients in the non-LNM group. The clinical factors, subjective imaging features, and the radiomic features of tumor and peritumoral mesorectum region of patients were extracted from T2WI and ADC images. Spearman's rank correlation coefficient, Mann-Whitney's U test, and the least absolute shrinkage and selection operator were used for feature selection and dimensionality reduction. Logistic regression was used to construct six models. The predictive performance of each model was evaluated by the receiver operating characteristic curve (ROC). The differences of each model were characterized by area under the curve (AUC) via the DeLong test.

RESULTS

The AUCs of T2WI, ADC single-sequence radiomics model and multi-sequence radiomics model were 0.73, 0.75, and 0.78, respectively. The multi-sequence multi-regional radiomics model with improved performance was created by combining the radiomics characteristics of the peritumoral mesorectum region with the multi-sequence radiomics model (AUC, 0.87; p < 0.01). The AUC of the clinical model was 0.68, and the MRI-clinical composite evaluation model was obtained by incorporating the clinical data with the multi-sequence multi-regional radiomics features, with an AUC of 0.89.

CONCLUSION

The MRI-based multi-sequence multi-regional radiomics model significantly improved the prediction ability of LNM for T3 rectal cancer and could be applied to guide surgical decision-making in patients with T3 rectal cancer.

Neuromuscular imaging in clinical practice: an ESNR survey of 30 centers

PURPOSE

We assessed the current clinical imaging practice in the primary evaluation of neuromuscular disorders (NMD), with respect to standardized imaging, evaluation and reporting through a European and extra-European-wide survey.

METHODS

An online questionnaire was emailed to all European Society of Neuroradiology (ESNR) members (n = 1662) who had expressed their interest in NMD. The questionnaire featured 40 individual items. Information was gathered on the context of the practices, available and preferred imaging modalities, applied imaging protocols and standards for interpretation, reporting and communication.

RESULTS

A total of 30 unique entries from European and extra-European academic and non-academic institutions were received. Of these, 70% were neuroradiologists, 23% general radiologists and 7% musculoskeletal radiologists. Of the 30 responding institutes, 40% performed from 20 to 50 neuromuscular scans per year for suspected NMD. The principal modality used for a suspected myopathy was magnetic resonance imaging (MRI) (50%) or "mainly MRI" (47%). The primary imaging modality used for the evaluation of patients suspected of a neuropathy was MRI in 63% of all institutions and "mainly MRI" in 37%. For both muscle and nerve pathology, pelvic girdle and inferior limbs are the most scanned parts of the body (28%), followed by the thigh and leg (24%), whole body MR (24%), scapular girdle (16%), and the thigh in just 8% of institutions. Multiplanar acquisitions were performed in 50% of institutions. Convectional sequences used for muscle MRI included T2-STIR (88%), 2D T1weighted (w) (68%), T1 Dixon or equivalent (52%), T2 Dixon (40%), DWI (36%), 2D T2w (28%), T1 3D and T2 3D (20% respectively). For nerve MRI conventional sequences included T2-STIR (80%), DWI (56%), T2 3D (48%), 2D T2w (48%), T1 3D (44%), T1 Dixon or equivalent (44%), 2D T1 (36%), T2 Dixon (28%). Quantitative sequences were used regularly by 40% respondents. While only 28% of institutions utilized structured reports, a notable 88% of respondents expressed a desire for a standardized consensus structured report. Most of the respondents (93%) would be interested in a common MRI neuromuscular protocol and would like to be trained (87%) by the ESNR society with specific neuromuscular sessions in European annual meetings.

CONCLUSIONS

Based on the survey findings, we can conclude that the current approach to neuromuscular imaging varies considerably among European and extra-European countries, both in terms of image acquisition and post-processing. Some of the challenges identified include the translation of research achievements (related to advanced imaging) into practical applications in a clinical setting, implementation of quantitative imaging post-processing techniques, adoption of structured reporting methods, and communication with referring physicians.

Advances in MRI-Based Assessment of Rectal Cancer Post-Neoadjuvant Therapy: A Comprehensive Review

Rectal cancer presents significant diagnostic and therapeutic challenges, with neoadjuvant therapy playing a pivotal role in improving resectability and patient outcomes. MRI serves as a critical tool in assessing treatment response. However, differentiating viable tumor tissue from therapy-induced changes on MRI remains a complex task. In this comprehensive review, we explore treatment options for rectal cancer based on resectability status, focusing on the role of MRI in guiding therapeutic decisions. We delve into the nuances of MRI-based evaluation of treatment response following neoadjuvant therapy, paying particular attention to emerging techniques like radiomics. Drawing from our insights based on the literature, we provide essential recommendations for post-neoadjuvant therapy management of rectal cancer, all within the context of MRI-based findings.

Effects of MRI radiomics combined with clinical data in evaluating lymph node metastasis in mrT1-3a staging rectal cancer

Objective

To investigate the value of a clinical-MRI radiomics model based on clinical characteristics and T2-weighted imaging (T2WI) for preoperatively evaluating lymph node (LN) metastasis in patients with MRI-predicted low tumor (T) staging rectal cancer (mrT1, mrT2, and mrT3a with extramural spread ≤ 5 mm).

Methods

This retrospective study enrolled 303 patients with low T-staging rectal cancer (training cohort, n = 213, testing cohort n = 90). A total of 960 radiomics features were extracted from T2WI. Minimum redundancy and maximum relevance (mRMR) and support vector machine were performed to select the best performed radiomics features for predicting LN metastasis. Multivariate logistic regression analysis was then used to construct the clinical and clinical-radiomics combined models. The model performance for predicting LN metastasis was assessed by receiver operator characteristic curve (ROC) and clinical utility implementing a nomogram and decision curve analysis (DCA). The predictive performance for LN metastasis was also compared between the combined model and human readers (2 seniors).

Results

Fourteen radiomics features and 2 clinical characteristics were selected for predicting LN metastasis. In the testing cohort, a higher positive predictive value of 75.9% for the combined model was achieved than those of the clinical model (44.8%) and two readers (reader 1: 54.9%, reader 2: 56.3%) in identifying LN metastasis. The interobserver agreement between 2 readers was moderate with a kappa value of 0.416. A clinical-radiomics nomogram and decision curve analysis demonstrated that the combined model was clinically useful.

Conclusion

T2WI-based radiomics combined with clinical data could improve the efficacy in noninvasively evaluating LN metastasis for the low T-staging rectal cancer and aid in tailoring treatment strategies.

Structured and shared MRI staging lexicon and report of rectal cancer: A consensus proposal by the French Radiology Group (GRERCAR) and Surgical Group (GRECCAR) for rectal cancer

PURPOSE

To develop French guidelines by experts to standardize data acquisition, image interpretation, and reporting in rectal cancer staging with magnetic resonance imaging (MRI).

MATERIALS AND METHODS

Evidence-based data and opinions of experts of GRERCAR (Groupe de REcherche en Radiologie sur le CAncer du Rectum [i.e., Rectal Cancer Imaging Research Group]) and GRECCAR (Groupe de REcherche en Chirurgie sur le CAncer du Rectum [i.e., Rectal Cancer Surgery Research Group]) were combined using the RAND-UCLA Appropriateness Method to attain consensus guidelines. Experts scoring of reporting template and protocol for data acquisition were collected; responses were analyzed and classified as "Recommended" versus "Not recommended" (when ≥ 80% consensus among experts) or uncertain (when < 80% consensus among experts).

RESULTS

Consensus regarding patient preparation, MRI sequences, staging and reporting was attained using the RAND-UCLA Appropriateness Method. A consensus was reached for each reporting template item among the experts. Tailored MRI protocol and standardized report were proposed.

CONCLUSION

These consensus recommendations should be used as a guide for rectal cancer staging with MRI.

Implementation of transanal minimally invasive surgery (TAMIS) for rectal neoplasms: results from a single centre

Background

Local excisions are important in a tailored approach to treatment of rectal neoplasms. In cases of low risk T1 local excision facilitates rectal-preserving treatment. Transanal minimally invasive surgery (TAMIS) is the most recent alternative developed for local excision. In this study we evaluate the results after implementing TAMIS as the routine procedure for local excision of rectal neoplasms.

Methods

All patients who underwent TAMIS from January 2016 to January 2020 at St. Olav’s University Hospital were included, and clinical, pathological and oncological data were prospectively registered. The primary endpoint was local recurrence, and the secondary endpoint was complications.

Results

There were 76 patients (42 men, mean age was 69 years [range 26–88 years]), The mean tumour level was 82 mm (range 20–140 mm) from the anal verge measured on rigid proctoscopy, and mean tumour size was 32 mm (range 8–73 mm). Three patients experienced complications needing intervention (Clavien–Dindo > 3A). Seventeen patients had rectal adenocarcinoma, 9 of whom underwent R0 completion total mesorectal excision (cTME). Fifty-five patients had an adenoma, 3 of whom developed recurrence (5.4%) within 12 months. All recurrences were treated successfully with a new TAMIS procedure. In addition, TAMIS was used in treatment of 2 patients with a neuroendocrine tumour, 1 patient with a haemangioma and 1 patient with a solitary rectal ulcer.

Conclusions

TAMIS surgery is associated with a low risk of complications and a low recurrence rate in rectal neoplasms. In cases of adenocarcinoma, R0 cTME surgery is feasible in the sub-group with high risk T1 and T2 tumours.

Utility of Restaging MRI Following Neoadjuvant Chemoradiotherapy for Stage II-III Rectal Adenocarcinoma

Background

Magnetic resonance imaging (MRI) is currently utilized for the pretreatment staging of locally advanced rectal cancer; however, there is no consensus regarding the utility of repeat MRI for restaging following neoadjuvant chemoradiotherapy (CRT). In this study, we aimed to investigate the clinical utility of restaging MRI after CRT in patients with clinical stage II-III rectal cancer.

Methodology

We performed a retrospective observational study at a tertiary care hospital. Our study population included patients with clinical stage II-III rectal cancer treated with neoadjuvant CRT who underwent both pre- and post-CRT MRI followed by surgical resection from 2012 to 2017. MRIs were reviewed by radiologists with an interest in rectal cancer MRI imaging using a standardized template. The utility of post-CRT MRI was evaluated by assessing its impact on change in surgical planning, concordance with pathologic staging, and prediction of surgical margins.

Results

A total of 30 patients were included in the study; 67% had clinical stage III and 33% had stage II disease based on pre-CRT MRI. Post-CRT MRI findings did not lead to a change in the originally outlined surgical plan in any patient. Compared to pre-CRT MRI, post-CRT MRI was not significantly more accurate in predicting T stage (k = 0.483), N stage (k = 0.268), or positive surgical margins (k = 0.839).

Conclusions

Due to poor concordance with pathologic staging, inability to more accurately predict surgical margin status and the absence of a demonstrable change in surgical treatment, post-CRT restaging with MRI, in its current form, appears to be of limited clinical utility.

Histogram analysis of diffusion-weighted magnetic resonance imaging as a biomarker to predict LNM in T3 stage rectal carcinoma

BACKGROUND

Preoperative identification of rectal cancer lymph node status is crucial for patient prognosis and treatment decisions. Rectal magnetic resonance imaging (MRI) plays an essential role in the preoperative staging of rectal cancer, but its ability to predict lymph node metastasis (LNM) is insufficient. This study explored the value of histogram features of primary lesions on multi-parametric MRI for predicting LNM of stage T3 rectal carcinoma.

METHODS

We retrospectively analyzed 175 patients with stage T3 rectal cancer who underwent preoperative MRI, including diffusion-weighted imaging (DWI) before surgery. 62 patients were included in the LNM group, and 113 patients were included in the non-LNM group. Texture features were calculated from histograms derived from T2 weighted imaging (T2WI), DWI, ADC, and T2 maps. Stepwise logistic regression analysis was used to screen independent predictors of LNM from clinical features, imaging features, and histogram features. Predictive performance was evaluated by receiver operating characteristic (ROC) curve analysis. Finally, a nomogram was established for predicting the risk of LNM.

RESULTS

The clinical, imaging and histogram features were analyzed by stepwise logistic regression. Preoperative carbohydrate antigen 199 level (p = 0.009), MRN stage (p < 0.001), _T2WIKurtosis (p = 0.010), _DWIMode (p = 0.038), _DWICV (p = 0.038), and _T2-mapP5 (p = 0.007) were independent predictors of LNM. These factors were combined to form the best predictive model. The model reached an area under the ROC curve (AUC) of 0.860, with a sensitivity of 72.8% and a specificity of 85.5%.

CONCLUSION

The histogram features on multi-parametric MRI of the primary tumor in rectal cancer were related to LN status, which is helpful for improving the ability to predict LNM of stage T3 rectal cancer.

Quality indicator selection for the Canadian Partnership against Cancer rectal cancer project: A modified Delphi study

AIM

It is well established that (i) magnetic resonance imaging, (ii) multidisciplinary cancer conference (MCCs), (iii) preoperative radiotherapy, (iv) total mesorectal excision surgery and (v) pathological assessment as described by Quirke are key processes necessary for high quality, rectal cancer care. The objective was to select a set of multidisciplinary quality indicators to measure the uptake of these clinical processes in clinical practice.

METHOD

A multidisciplinary panel was convened and a modified two-phase Delphi method was used to select a set of quality indicators. Phase 1 included a literature review with written feedback from the panel. Phase 2 included an in-person workshop with anonymous voting. The selection criteria for the indicators were strength of evidence, ease of capture and usability. Indicators for which ≥90% of the panel members voted 'to keep' were selected as the final set of indicators.

RESULTS

During phase 1, 68 potential indicators were generated from the literature and an additional four indicators were recommended by the panel. During phase 2, these 72 indicators were discussed; 48 indicators met the 90% inclusion threshold and included eight pathology, five radiology, 11 surgical, six radiation oncology and 18 MCC indicators.

CONCLUSION

A modified Delphi method was used to select 48 multidisciplinary quality indicators to specifically measure the uptake of key processes necessary for high quality care of patients with rectal cancer. These quality indicators will be used in future work to identify and address gaps in care in the uptake of these clinical processes.

Improving the completeness of structured MRI reports for rectal cancer staging

PURPOSE

Assess the impact of a multifaceted intervention to improve the completeness of structured MRI reports for patients undergoing initial staging for rectal cancer.

METHODS

This Institutional Review Board-approved retrospective study was performed at a large academic hospital. MRI reports for initial staging of rectal cancer in 2017 and 2019 were analyzed pre- and post-implementation of multiple quality improvement interventions in 2018, including harmonizing MRI protocols across the institution, educational conferences and modules, and requiring second opinion consultation for all MRI rectal cancer examinations. The primary outcome measure was the completeness of rectal cancer staging MRI reports, classified as optimal, satisfactory, or unsatisfactory based on the inclusion of 15 quality measures pre-defined by a consensus of abdominal and cancer imaging subspecialists, colorectal surgeons, and radiation oncologists at our institution, based on published recommendations. Fisher's exact test was used to evaluate changes in report quality and documentation of each quality measure.

RESULTS

The study included 138 MRI reports, of which 72 (52%) were completed in 2017 pre-intervention. Post intervention, the proportion of optimal reports increased significantly from 52.8% (38/72) to 71.2% (47/66) (p = 0.035). Documentation of 1 quality measure (N stage) increased post intervention from 91.7% (66/72) to 100% (66/66) (p = 0.029). Documentation of 7 quality measures was 100% post intervention, with a documentation rate of > 95% for all quality measures except radial location of tumor.

CONCLUSION

A combination of educational and system-wide interventions was associated with an improvement in the completeness of structured MRI reports for rectal cancer staging.

A deep learning nomogram kit for predicting metastatic lymph nodes in rectal cancer

Background

Preoperative diagnoses of metastatic lymph nodes (LNs) by the most advanced deep learning technology of Faster Region‐based Convolutional Neural Network (Faster R‐CNN) have not yet been reported.

Materials and Methods

In total, 545 patients with pathologically confirmed rectal cancer between January 2016 and March 2019 were included and were randomly allocated with a split ratio of 2:1 to the training and validation sets, respectively. The MRI images for metastatic LNs were evaluated by Faster R‐CNN. Multivariate regression analyses were used to develop the predictive models. Faster R‐CNN nomograms were constructed based on the multivariate analyses in the training sets and were validated in the validation sets.

Results

The Faster R‐CNN nomogram for predicting metastatic LN status contained predictors of age, metastatic LNs by Faster R‐CNN and differentiation degrees of tumors, with areas under the curves (AUCs) of 0.862 (95% CI: 0.816‐0.909) and 0.920 (95% CI: 0.876‐0.964) in the training and validation sets, respectively. The Faster R‐CNN nomogram for predicting LN metastasis degree contained predictors of metastatic LNs by Faster R‐CNN and differentiation degrees of tumors, with AUCs of 0.859 (95% CI: 0.804‐0.913) and 0.886 (95% CI: 0.822‐0.950) in the training and validation sets, respectively. Calibration plots and decision curve analyses demonstrated good calibrations and clinical utilities. The two nomograms were used jointly as a kit for predicting metastatic LNs.

Conclusion

The Faster R‐CNN nomogram kit exhibits excellent performance in discrimination, calibration, and clinical utility and is convenient and reliable for predicting metastatic LNs preoperatively.

Clinical trial registration: ChiCTR‐DDD‐17013842.

Deep learning-based fully automated detection and segmentation of lymph nodes on multiparametric-mri for rectal cancer: A multicentre study

Background

Accurate lymph nodes (LNs) assessment is important for rectal cancer (RC) staging in multiparametric magnetic resonance imaging (mpMRI). However, it is incredibly time-consumming to identify all the LNs in scan region. This study aims to develop and validate a deep-learning-based, fully-automated lymph node detection and segmentation (auto-LNDS) model based on mpMRI.

Methods

In total, 5789 annotated LNs (diameter ≥ 3 mm) in mpMRI from 293 patients with RC in a single center were enrolled. Fused T2-weighted images (T2WI) and diffusion-weighted images (DWI) provided input for the deep learning framework Mask R-CNN through transfer learning to generate the auto-LNDS model. The model was then validated both on the internal and external datasets consisting of 935 LNs and 1198 LNs, respectively. The performance for LNs detection was evaluated using sensitivity, positive predictive value (PPV), and false positive rate per case (FP/vol), and segmentation performance was evaluated using the Dice similarity coefficient (DSC).

Findings

For LNs detection, auto-LNDS achieved sensitivity, PPV, and FP/vol of 80.0%, 73.5% and 8.6 in internal testing, and 62.6%, 64.5%, and 8.2 in external testing, respectively, significantly better than the performance of junior radiologists. The time taken for model detection and segmentation was 1.3 s/case, compared with 200 s/case for the radiologists. For LNs segmentation, the DSC of the model was in the range of 0.81–0.82.

Interpretation

This deep learning–based auto-LNDS model can achieve pelvic LNseffectively based on mpMRI for RC, and holds great potential for facilitating N-staging in clinical practice.

Rectal cancer MR staging: pearls and pitfalls at baseline examination

In recent years, rectal MRI has become a central diagnostic tool in rectal cancer staging. Indeed, rectal MR has the ability to accurately evaluate a number of important findings that may impact patient management, including distance of the tumor to the mesorectal fascia, presence of extramural vascular invasion (EMVI), presence of lymph nodes, and involvement of the peritoneum/anterior peritoneal reflection. Many of these findings are difficult to assess in nonexpert hands. In this review, we present a practical approach for radiologists to provide high-quality interpretations at initial baseline exams, based on recent guidelines from the Society of Abdominal Radiology, Rectal and Anal Cancer Disease Focused Panel. Practical pearls and pitfalls are discussed, focusing on optimization of technique including, patient preparation and protocol recommendations, interpretation, and essentials of reporting.

An audit of performance, interpretation, and influence of pretherapeutic MRI in rectal cancer: a Swedish population-based cohort study

Background

The performance of magnetic resonance imaging (MRI) interpretation and communication of findings and its implication on treatment decisions has not fully been explored in rectal cancer.

Purpose

To investigate in a region the adherence to MRI protocol standards and the relation between MRI interpretation and selection to preoperative therapy in rectal cancer.

Material and Methods

Data on consecutive patients who underwent elective rectal cancer surgery in the region from January to June 2010 were obtained from the National Colorectal Cancer Registry. Pretherapeutic MRI images were re-evaluated. Agreement between the original reports and the re-evaluation was compared using Cohen’s kappa coefficient.

Results

Among the 94 patients included, 81 (86%) had pretherapeutic MRI in accordance with defined imaging guidelines. In 34% of the original MR reports, data on extramural venous invasion (mrEMVI) and mrT category were not reported. Complete tumor staging was not possible because of missing data in 33 (35%) of the patients. The agreement between the original MR reports and the re-evaluation regarding tumor stage was moderate (κ = 0.48). For decided treatment compared to recommended preoperative treatment according to the re-evaluation, the agreement was fair (κ = 0.33).

Conclusion

Established MRI protocol standards were not universally applied. Missing data and inadequacies in original MRI reports resulted in moderate agreement between the original report and the re-evaluation indicating a risk of inappropriate treatment selection. The results call for further educational efforts in rectal cancer MRI acquisition and repeated audits of image protocol adherence and interpretation quality.

Artificial intelligence system of faster region-based convolutional neural network surpassing senior radiologists in evaluation of metastatic lymph nodes of rectal cancer

BACKGROUND

An artificial intelligence system of Faster Region-based Convolutional Neural Network (Faster R-CNN) is newly developed for the diagnosis of metastatic lymph node (LN) in rectal cancer patients. The primary objective of this study was to comprehensively verify its accuracy in clinical use.

METHODS

Four hundred fourteen patients with rectal cancer discharged between January 2013 and March 2015 were collected from 6 clinical centers, and the magnetic resonance imaging data for pelvic metastatic LNs of each patient was identified by Faster R-CNN. Faster R-CNN based diagnoses were compared with radiologist based diagnoses and pathologist based diagnoses for methodological verification, using correlation analyses and consistency check. For clinical verification, the patients were retrospectively followed up by telephone for 36 months, with post-operative recurrence of rectal cancer as a clinical outcome; recurrence-free survivals of the patients were compared among different diagnostic groups, by methods of Kaplan-Meier and Cox hazards regression model.

RESULTS

Significant correlations were observed between any 2 factors among the numbers of metastatic LNs separately diagnosed by radiologists, Faster R-CNN and pathologists, as evidenced by rradiologist-Faster R-CNN of 0.912, rPathologist-radiologist of 0.134, and rPathologist-Faster R-CNN of 0.448 respectively. The value of kappa coefficient in N staging between Faster R-CNN and pathologists was 0.573, and this value between radiologists and pathologists was 0.473. The 3 groups of Faster R-CNN, radiologists and pathologists showed no significant differences in the recurrence-free survival time for stage N0 and N1 patients, but significant differences were found for stage N2 patients.

CONCLUSION

Faster R-CNN surpasses radiologists in the evaluation of pelvic metastatic LNs of rectal cancer, but is not on par with pathologists.

TRIAL REGISTRATION

www.chictr.org.cn (No. ChiCTR-DDD-17013842).

Standardised reports with a template format are superior to free text reports: the case for rectal cancer reporting in clinical practice

PURPOSE

Rectal cancer staging with magnetic resonance imaging (MRI) allows accurate assessment and preoperative staging of rectal cancers. Therefore, complete MRI reports are vital to treatment planning. Significant variability may exist in their content and completeness. Template-style reporting can improve reporting standards, but its use is not widespread. Given the implications for treatment, we have evaluated current clinical practice amongst specialist gastrointestinal (GI) radiologists to measure the quality of rectal cancer staging MRI reports.

MATERIALS AND METHODS

Sixteen United Kingdom (UK) colorectal cancer multi-disciplinary teams (CRC-MDTs) serving a population over 5 million were invited to submit up to 10 consecutive rectal cancer primary staging MRI reports from January 2016 for each radiologist participating in the CRC-MDT. Reports were compared to a reference standard based on recognised staging and prognostic factors influencing case management RESULTS: Four hundred ten primary staging reports were submitted from 41 of 42 (97.6%) eligible radiologists. Three hundred sixty reports met the inclusion criteria, of these, 81 (22.5%) used a template. Template report usage significantly increased recording of key data points versus non-template reports for extra-mural venous invasion (EMVI) status (98.8% v 51.6%, p < 0.01) and circumferential resection margin (CRM) status (96.3% v 65.9%, p < 0.01). Local tumour stage (97.5% v 93.5%, NS) and nodal status (98.8% v 96.1%, NS) were reported and with similar frequency.

CONCLUSION

Rectal cancer primary staging reports do not meet published standards. Template-style reports have significant increases in the inclusion of key tumour descriptors. This study provides further support for their use to improve reporting standards and outcomes in rectal cancer.

KEY POINTS

• MRI primary staging of rectal cancer requires detailed tumour descriptions as these alter the neoadjuvant and surgical treatments. • Currently, rectal cancer MRI reports in clinical practice do not provide sufficient detail on these tumour descriptors. • The use of template-style reports for primary staging of rectal cancer significantly improves report quality compared to free-text reports.

Use of magnetic resonance imaging in rectal cancer patients: Society of Abdominal Radiology (SAR) rectal cancer disease-focused panel (DFP) recommendations 2017

PURPOSE

To propose guidelines based on an expert-panel-derived unified approach to the technical performance, interpretation, and reporting of MRI for baseline and post-treatment staging of rectal carcinoma.

METHODS

A consensus-based questionnaire adopted with permission and modified from the European Society of Gastrointestinal and Abdominal Radiologists was sent to a 17-member expert panel from the Rectal Cancer Disease-Focused Panel of the Society of Abdominal Radiology containing 268 question parts. Consensus on an answer was defined as ≥ 70% agreement. Answers not reaching consensus (< 70%) were noted.

RESULTS

Consensus was reached for 87% of items from which recommendations regarding patient preparation, technical performance, pulse sequence acquisition, and criteria for MRI assessment at initial staging and restaging exams and for MRI reporting were constructed.

CONCLUSION

These expert consensus recommendations can be used as guidelines for primary and post-treatment staging of rectal cancer using MRI.

Identification of Metastatic Lymph Nodes in MR Imaging with Faster Region-Based Convolutional Neural Networks

MRI is the gold standard for confirming a pelvic lymph node metastasis diagnosis. Traditionally, medical radiologists have analyzed MRI image features of regional lymph nodes to make diagnostic decisions based on their subjective experience; this diagnosis lacks objectivity and accuracy. This study trained a faster region-based convolutional neural network (Faster R-CNN) with 28,080 MRI images of lymph node metastasis, allowing the Faster R-CNN to read those images and to make diagnoses. For clinical verification, 414 cases of rectal cancer at various medical centers were collected, and Faster R-CNN-based diagnoses were compared with radiologist diagnoses using receiver operating characteristic curves (ROC). The area under the Faster R-CNN ROC was 0.912, indicating a more effective and objective diagnosis. The Faster R-CNN diagnosis time was 20 s/case, which was much shorter than the average time (600 s/case) of the radiologist diagnoses.Significance: Faster R-CNN enables accurate and efficient diagnosis of lymph node metastases. Cancer Res; 78(17); 5135-43. ©2018 AACR.

Structured Reporting of Rectal Magnetic Resonance Imaging in Suspected Primary Rectal Cancer: Potential Benefits for Surgical Planning and Interdisciplinary Communication

OBJECTIVES

The aim of this study was to evaluate the effect of structured reports (SRs) in comparison to nonstructured, free-text (FT) rectal magnetic resonance imaging (MRI) reports in patients with histologically proven rectal cancer and potential effects of both types of reporting on referring surgeons' satisfaction, interdisciplinary communication, and further clinical decision making.

MATERIALS AND METHODS

The institutional review board approved this retrospective study with waiver of informed consent. Forty-nine patients with histologically proven rectal cancer were included in this study. All patients underwent rectal MRI for local rectal cancer staging before surgery. Free-text reports and SRs for local MR staging of rectal cancer were generated for all subjects by radiologists. Two experienced abdominal surgeons evaluated a questionnaire that included 9 questions regarding satisfaction with content, presence of reported key features, effort for information extraction, and report quality.

RESULTS

Structured reports achieved significantly higher satisfaction rates with report content and clarity, and included significantly more of the 13 predefined key features compared with FT reports (SRs: mean ± SD, 12.2 ± 4.6 [range, 9-13] versus FT reports: mean ± SD, 9.2 ± 10.8 [range, 5-13]) (P < 0.001). Definite further clinical decision making (surgery vs neoadjuvant radiochemotherapy) was possible in 96% of SRs and only in 60% of FT reports (P < 0.001). In case of surgery, the reported information was considered to be sufficient for surgical planning in 94% of SRs versus only 38% in FT reports (P < 0.001). Structured report received a significantly higher overall report quality rated on a Likert scale from 1 to 6 (1, insufficient; 6, excellent) with a mean of 5.8 ± 0.42 (range, 5-6) in comparison to FT reports with 3.6 ± 1.19 (range, 1-5) (P < 0.001).

CONCLUSIONS

Structured reporting of rectal MRI in patients with rectal cancer facilitates surgical planning and leads to a higher satisfaction level of referring surgeons in comparison to FT reports. Abdominal surgeons were more confident about report correctness and further clinical decision making on the basis of SRs.

Accuracy of pre-treatment locoregional rectal cancer staging in a national improvement project

BACKGROUND

The aim of this study was to assess the accuracy, particularly the predictive value, of locoregional clinical rectal cancer staging (cTN) and its variability in a national improvement project.

METHODS

cTN stages and the distance between tumour and mesorectal fascia (MRF) were compared with histopathological findings in 1168 patients who underwent radical resection without neoadjuvant treatment. Data were registered prospectively from 2006 to 2014.

RESULTS

Agreement between clinical and histopathological TN stages was 50%, independent of tumour location. Inter-hospital variability was within 99% prediction limits. Magnetic resonance imaging (MRI) was increasingly applied, but staging accuracy did not improve. Stage II-III was correctly predicted in 69% and pStage I was over-staged in 35%. The positive predictive value of endorectal ultrasonography (ERUS) for T1 lesions was 57%. MRI-based distances to MRF correlated poorly with the circumferential resection margin (r = 0.26). A negative resection margin was achieved in 91% when the distance to the MRF was >1 mm.

CONCLUSIONS

The accuracy of rectal cancer staging in general practice should be improved to avoid under- or overtreatment. Training and expert review of pre-treatment MR imaging could be helpful. A second ERUS is justified when transanal local resection for early lesions is planned.

A structured approach to reporting rectal cancer with magnetic resonance imaging

OBJECTIVE

Rectal cancers are the second most common GI carcinoma. Prognosis and therapeutic decisions hinge on the extent of disease. We present a comprehensive structured approach for staging rectal cancer using MRI to ensure the clear, concise, and standardized communication of disease extent to guide optimal treatment planning.

CONCLUSION

MRI is crucial for local staging of rectal cancer. A standardized approach to reporting of rectal MRI focused on communication of essential treatment planning and prognostic indicators ensures maximal added value to referring physicians to guide appropriate management.

Impact of a Structured Report Template on the Quality of MRI Reports for Rectal Cancer Staging

OBJECTIVE

The purpose of this study is to assess the impact of implementing a structured report template on the quality of MRI reports for rectal cancer staging.

MATERIALS AND METHODS

After excluding examinations performed after surgery or neoadjuvant therapy, we analyzed all rectal cancer staging MRI reports finalized at an academic medical center 12 months before and after an intervention consisting of implementing a structured report template integrated into the institution's speech recognition system. The primary outcome measure was the quality of rectal cancer staging MRI reports classified as optimal, satisfactory, or unsatisfactory, on the basis of the documentation of 14 quality measures predefined by a consensus of the institution's abdominal radiology subspecialists. Chi-square and t tests were used to assess differences in report quality and documentation of each discrete quality measure before and after the intervention.

RESULTS

The study cohort included 106 MRI reports from 104 patients (mean age, 60 years; 58.5% male); 52 (49.1%) of the reports were completed before implementation of the structured report template. After implementation, the proportion of total reports classified as optimal or satisfactory increased from 38.5% (20/52) to 70.4% (38/54) (p = 0.0010). No reports generated before the intervention were classified as optimal, whereas 40.7% (22/54) of reports were classified as optimal after the intervention.

CONCLUSION

Implementation and voluntary use of a structured report template improved the quality of MRI reports for rectal cancer staging compared with free-text format.

Multi-parametric MRI of rectal cancer - do quantitative functional MR measurements correlate with radiologic and pathologic tumor stages?

PURPOSE

The purpose of this study is two-fold. First, to evaluate, whether functional rectal MRI techniques can be analyzed in a reproducible manner by different readers and second, to assess whether different clinical and pathologic T and N stages can be differentiated by functional MRI measurements.

MATERIALS AND METHODS

54 patients (38 men, 16 female; mean age 63.2 ± 12.2 years) with pathologically proven rectal cancer were included in this retrospective IRB-approved study. All patients were referred for a multi-parametric MRI protocol on a 3 Tesla MR-system, consisting of a high-resolution, axial T2 TSE sequence, DWI and perfusion imaging (plasma flow -s PFTumor) prior to any treatment. Two experienced radiologists evaluated the MRI measurements, blinded to clinical data and outcome. Inter-reader correlation and the association of functional MRI parameters with c- and p-staging were analyzed.

RESULTS

The inter-reader correlation for lymph node (ρ 0.76-0.94; p<0.0002) and primary tumor (ρ 0.78-0.92; p<0.0001) apparent diffusion coefficient and plasma flow (PF) values was good to very good. PFTumor values decreased with cT stage with significant differences identified between cT2 and cT3 tumors (229 versus 107.6 ml/100ml/min; p=0.05). ADCTumor values did not differ significantly. No substantial discrepancies in lymph node ADCLn values or short axis diameter were found among cN1-3 stages, whereas PFLn values were distinct between cN1 versus cN2 stages (p=0.03). In the patients without neoadjuvant RCT no statistically significant differences in the assessed functional parameters on the basis of pathologic stage were found.

CONCLUSION

This study illustrates that ADC as well as MR perfusion values can be analyzed with good interobserver agreement in patients with rectal cancer. Moreover, MR perfusion parameters may allow accurate differentiation of tumor stages. Both findings suggest that functional MRI parameters may help to discriminate T and N stages for clinical decision making.