Multiparametric Magnetic Resonance Imaging (MRI) can provide detailed information of the physical characteristics of rectum tumours. Several investigations suggest that volumetric analyses on ...anatomical and functional MRI contain clinically valuable information. However, manual delineation of tumours is a time consuming procedure, as it requires a high level of expertise. Here, we evaluate deep learning methods for automatic localization and segmentation of rectal cancers on multiparametric MR imaging. MRI scans (1.5T, T2-weighted, and DWI) of 140 patients with locally advanced rectal cancer were included in our analysis, equally divided between discovery and validation datasets. Two expert radiologists segmented each tumor. A convolutional neural network (CNN) was trained on the multiparametric MRIs of the discovery set to classify each voxel into tumour or non-tumour. On the independent validation dataset, the CNN showed high segmentation accuracy for reader1 (Dice Similarity Coefficient (DSC = 0.68) and reader2 (DSC = 0.70). The area under the curve (AUC) of the resulting probability maps was very high for both readers, AUC = 0.99 (SD = 0.05). Our results demonstrate that deep learning can perform accurate localization and segmentation of rectal cancer in MR imaging in the majority of patients. Deep learning technologies have the potential to improve the speed and accuracy of MRI-based rectum segmentations.
Selecting patients with peritoneal metastases from colorectal cancer (CRCPM) who might benefit from cytoreductive surgery followed by hyperthermic intraperitoneal chemotherapy (CRS-HIPEC) is ...challenging. Computed tomography generally underestimates the peritoneal tumor load. Diagnostic laparoscopy is often used to determine whether patients are amenable for surgery. Magnetic resonance imaging (MRI) has shown to be accurate in predicting completeness of CRS. The aim of this study is to determine whether MRI can effectively reduce the need for surgical staging.
The study is designed as a multicenter randomized controlled trial (RCT) of colorectal cancer patients who are deemed eligible for CRS-HIPEC after conventional CT staging. Patients are randomly assigned to either MRI based staging (arm A) or to standard surgical staging with or without laparoscopy (arm B). In arm A, MRI assessment will determine whether patients are eligible for CRS-HIPEC. In borderline cases, an additional diagnostic laparoscopy is advised. The primary outcome is the number of unnecessary surgical procedures in both arms defined as: all surgeries in patients with definitely inoperable disease (PCI > 24) or explorative surgeries in patients with limited disease (PCI < 15). Secondary outcomes include correlations between surgical findings and MRI findings, cost-effectiveness, and quality of life (QOL) analysis.
This randomized trial determines whether MRI can effectively replace surgical staging in patients with CRCPM considered for CRS-HIPEC.
Registered in the clinical trials registry of U.S. National Library of Medicine under NCT04231175 .
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Abstract Aim of the study In patients from the Dutch TME trial patterns of local recurrence (LR) in rectal cancer were studied. The purpose was to reconstruct the most likely mechanisms of LR and the ...effect of preoperative radiotherapy. Methods 1417 patients were analyzed; 713 were randomized into preoperative radiotherapy and total mesorectal excision (RT + TME), 704 into TME alone. Of the 114 patients with LR, the subsites of LR were determined and related to tumor and treatment factors. Results Overall 5-year LR-rate was 4.6% in the RT + TME group and 11.0% in the TME group. Presacral local recurrences occurred most in both groups. Radiotherapy reduced anastomotic LR significantly, except when after low anterior resection (LAR) distal margins were less than 5 mm. Abdominoperineal resection (APR) mainly resulted in presacral LR. Even after resection with a negative circumferential resection margin, LR-rates were high. Thirty percent of the patients had advanced tumors, which resulted in 58% of all LRs. Lateral LR comprised 20% of all LR. Presacral and lateral LR resulted in a poor prognosis, in contrast to anterior or anastomotic LRs with a relatively good prognosis. Conclusions RT reduces LR in all subsites and is especially effective in preventing anastomotic LR after LAR. APR-surgery mainly results in presacral LR, which may be prevented by a wider resection. In the TME trial many advanced tumors were included, rather requiring chemoradiotherapy instead of RT. Currently, with good imaging techniques, better selection can take place. Especially lateral LR might be a problem in the future.
Purpose
To compare the performance of advanced radiomics analysis to morphological assessment by expert radiologists to predict a good or complete response to chemoradiotherapy in rectal cancer using ...baseline staging MRI.
Materials and methods
We retrospectively assessed the primary staging MRIs prior to chemoradiotherapy (CRT) of 133 rectal cancer patients from 2 centers. First, two expert radiologists subjectively estimated the likelihood of achieving a “complete response” (ypT0) and “good response” (TRG 1–2), using a 5-point score (based on TN-stage, MRF/EMVI-status, size/signal/shape). Next, tumor volumes were segmented on high
b
value DWI (semi-automated, corrected by 2 non-expert and 2-expert readers, resulting in 5 segmentations), copied to the remaining sequences after which a total of 2505 radiomic features were extracted from T2W, low and high
b
value DWI and ADC. Stability of features for noise due to inter-reader and inter-scanner and protocol variations was assessed using intraclass correlation (ICC) and the Kruskal–Wallis test. Using data from center 1 (
n
= 86; training set), top 9 features were selected using minimum Redundancy Maximum Relevance and combined in a logistic regression model. Finally, diagnostic performance of the fitted models was assessed on data from center 2 (
n
= 47; validation set) and compared to the performance of the radiologists.
Results
The Radiomic models resulted in AUCs of 0.69–0.79 (with similar results for the segmentations performed by expert/non-expert readers) to predict response, results similar to the morphologic prediction by the expert radiologists (AUC 0.67–0.83). Radiomics using semi-automatically generated segmentations (without manual input) did not result in significant predictive performance.
Conclusions
Radiomics could predict response to therapy with comparable diagnostic performance as expert radiologists, regardless of whether image segmentation was performed by non-expert or expert readers, indicating that expert input is not required in order for the radiomics workflow to produce significant predictive performance.
Purpose
Detection of peritoneal metastases (PM) is key in the staging and management of gastrointestinal and ovarian cancer patients. The purpose of this meta-analysis was to determine the diagnostic ...performance of CT, PET(CT), and (DW)MRI in detecting PM.
Methods
A literature search in Pubmed, Embase (Ovid), and Scopus was performed (January 1997–May 2018) to identify studies reporting on the accuracy of imaging PM in the diagnostic workup of gastrointestinal or ovarian cancers. Inclusion criteria were region-based or patient-based studies comprising > 15 patients, surgery/histology/radiological follow-up as a reference standard, and sufficient data to construct a 2 × 2 contingency table. Two observers performed data extraction. The sensitivity, specificity, and diagnostic odds ratio (DOR) were calculated using a bivariate random-effects model and hierarchical summary operating curves (HSROC) were generated.
Results
Of 3457 citations retrieved, twenty-four articles met all inclusion criteria. Thirty-seven datasets could be extracted for analysis including 20 for CT, 10 for PET(CT), and 7 for (DW)MRI. The pooled sensitivity, specificity, and DOR for the detection of PM for region-based studies for CT were 68% (CI, 46–84%), 88%(CI, 81–93%), and 15.9 (CI, 4.4–58.0) respectively; 80% (CI, 57–92%), 90% (CI, 80–96%), and 36.5 (CI, 6.7–199.5) for PET(CT), respectively; 92% (CI, 84–96%), 85% (CI, 78–91%), 63.3 (CI, 31.5–127.3) for (DW)MRI. In the patient-based group, not enough studies were included to make a pooled analysis for (DW)MRI and PET(CT).
Conclusion
(DW)MRI and PET(CT) showed comparable diagnostic performance for the detection of peritoneal metastases in ovarian and gastrointestinal cancer patients. Since MRI is more widely available than PET(CT) in clinical practice, this potentially is the imaging method of choice in most centers in the future.
Key Points
• Detection of peritoneal metastases plays an important role in the accurate staging of cancer patients, however, there is no accepted reference standard for the imaging of peritoneal metastases
• This meta-analysis shows that (DW)MRI provided the highest sensitivity for the detection of peritoneal metastases in ovarian and gastrointestinal cancer patients
• Although (DW)MRI and PET(CT) show a comparable overall diagnostic performance, (DW)MRI seems to be the imaging method of choice since it is more available in daily practice than PET(CT).
Abstract Aim The purpose of this multicenter cohort study was to evaluate whether a differentiated treatment of primary rectal cancer based on magnetic resonance imaging (MRI) can reduce the number ...of incomplete resections and local recurrences and improve recurrence-free and overall survival. Methods From February 2003 until January 2008, 296 patients with rectal cancer underwent preoperative MRI using a lymph node specific contrast agent to predict circumferential resection margin (CRM), T- and N-stage. Based on expert reading of the MRI, patients were stratified in: (a) low risk for local recurrence (CRM > 2 mm and N0 status), (b) intermediate risk and (c) high risk (close/involved CRM, N2 status or distal tumours). Mainly based on this MRI risk assessment patients were treated with (a) surgery only (TME or local excision), (b) preoperative 5 × 5 Gy + TME and (c) a long course of chemoradiation therapy followed by surgery after a 6–8 week interval. Results Overall 228 patients underwent treatment with curative intent: 49 with surgery only, 86 with 5 × 5 Gy and surgery and 93 with chemoradiation and surgery. The number of complete resections (margin > 1 mm) was 218 (95.6%). At a median follow-up of 41 months the three-year local recurrence rate, disease-free survival rate and overall survival rate is 2.2%, 80% and 84.5%, respectively. Conclusion With a differentiated multimodality treatment based on dedicated preoperative MR imaging, local recurrence is no longer the main problem in rectal cancer treatment. The new challenges are early diagnosis and treatment, reducing morbidity of treatment and preferably prevention of metastatic disease.
To investigate the role of the apparent diffusion coefficient (ADC) as a potential imaging biomarker to predict metastasis (lymph node metastasis and distant metastasis) in colon cancer based on the ...ADC-value of the primary tumor.
Thirty patients (21M, 9F) were included retrospectively. All patients received a 1.5T MRI of the colon including T2 and DWI sequences. ADC maps were calculated for each patient. An expert reader manually delineated all colon tumors to measure mean ADC and histogram metrics (mean, min, max, median, standard deviation (SD), skewness, kurtosis, 5th-95th percentiles) were calculated. Advanced colon cancer was defined as lymph node mestastasis (N+) or distant metastasis (M+). The student Mann Whitney U-test was used to assess the differences between the ADC means of early and advanced colon cancer. To compare the accuracy of lymph node metastasis (N+) prediction based on morpholigical criteria versus ADC-value of the primary tumor, two blinded readers, determined the lymph node metastasis (N0 vs N+) based on morphological criteria. The sensitivity and specificity in predicting lymph node metastasis was calculated for both readers and for the ADC-value of the primary tumor, with histopathology results as the gold standard.
There was a significant difference between the mean ADC-value of advanced versus early tumors (p = 0.002). The optimal cut off value was 1179 * 10-3 mm2/s with an area under the curve (AUC) of 0.83 and a sensitivity and specificity of 81% and 86% respectively to predict advanced tumors. Histogram analyses did not add any significant additional value. The sensitivity and specificity for the prediction of lymph node metastasis based on morphological criteria were 40% and 63% for reader 1 and 30% and 88% for reader 2 respectively. The primary tumor ADC-value using 1.179 * 10-3 mm2/s as threshold had a 100% sensitivity and specificity in predicting lymph node metastasis.
The ADC-value of the primary tumor has the potential to predict advanced colon cancer, defined as lymph node metastasis or distant metastasis, with lower ADC values significantly associated with advanced tumors. Furthermore the ADC-value of the primary tumor increases the prediction accuracy of lymph node metastasis compared with morphological criteria.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Objectives
To identify the main problem areas in the applicability of the current TNM staging system (8
th
ed.) for the radiological staging and reporting of rectal cancer and provide practice ...recommendations on how to handle them.
Methods
A global case-based online survey was conducted including 41 image-based rectal cancer cases focusing on various items included in the TNM system. Cases reaching < 80% agreement among survey respondents were identified as problem areas and discussed among an international expert panel, including 5 radiologists, 6 colorectal surgeons, 4 radiation oncologists, and 3 pathologists.
Results
Three hundred twenty-one respondents (from 32 countries) completed the survey. Sixteen problem areas were identified, related to cT staging in low-rectal cancers, definitions for cT4b and cM1a disease, definitions for mesorectal fascia (MRF) involvement, evaluation of lymph nodes versus tumor deposits, and staging of lateral lymph nodes. The expert panel recommended strategies on how to handle these, including advice on cT-stage categorization in case of involvement of different layers of the anal canal, specifications on which structures to include in the definition of cT4b disease, how to define MRF involvement by the primary tumor and other tumor-bearing structures, how to differentiate and report lymph nodes and tumor deposits on MRI, and how to anatomically localize and stage lateral lymph nodes.
Conclusions
The recommendations derived from this global survey and expert panel discussion may serve as a practice guide and support tool for radiologists (and other clinicians) involved in the staging of rectal cancer and may contribute to improved consistency in radiological staging and reporting.
Key Points
•
Via a case-based online survey (incl. 321 respondents from 32 countries), we identified 16 problem areas related to the applicability of the TNM staging system for the radiological staging and reporting of rectal cancer.
•
A multidisciplinary panel of experts recommended strategies on how to handle these problem areas, including advice on cT-stage categorization in case of involvement of different layers of the anal canal, specifications on which structures to include in the definition of cT4b disease, how to define mesorectal fascia involvement by the primary tumor and other tumor-bearing structures, how to differentiate and report lymph nodes and tumor deposits on MRI, and how to anatomically localize and stage lateral lymph nodes.
•
These recommendations may serve as a practice guide and support tool for radiologists (and other clinicians) involved in the staging of rectal cancer and may contribute to improved consistency in radiological staging and reporting.
•Accurate preoperative assessment of the peritoneal tumor load can be done with Diffusion-Weighted MRI.•Diffusion-weighted MRI is able to predict per-operative findings using the Peritoneal Cancer ...Index.•The MRI-PCI showed able to predict whether a complete cytoreduction is feasible for advanced stage ovarian cancer patients.
To determine the diagnostic performance of MRI with diffusion-weighted imaging (DW-MRI) in assessing the peritoneal tumor load and predicting whether a complete cytoreduction can be achieved in patients with epithelial ovarian cancer (EOC).
For this observational prospective study, 25 patients with epithelial ovarian cancer scheduled for cytoreductive surgery were included. Patients underwent a 3 T DW-MRI scan prior to surgery. The MR protocol consisted of a T1 and T2 weighted, a contrast-enhanced T1 weighted, and a diffusion-weighted (b0, b1000) sequence. The Peritoneal Cancer Index (PCI) was determined on DW-MR images (MRI-PCI) by two readers, independently, and was compared to the PCI determined during surgery (S-PCI). The inter-observer agreement between the two radiologists was evaluated. In addition, receiver operating characteristics curves were calculated for predicting complete cytoreduction with the S-PCI and MRI-PCI.
Staging with DW-MRI showed a correlation to surgical staging with an intraclass correlation coefficient (ICC) 0.86 and 0.85 for reader 1 and 2, respectively. Inter-observer agreement was excellent with an ICC of 0.90 (95% CI: 0.64-0.96). The MRI-PCI scores of reader 1 (AUC = 0.96), reader 2 (AUC = 0.98), and the S-PCI (AUC = 0.92) showed similar predictive values for complete cytoreduction.
DW-MRI is accurate in predicting the S-PCI and can be helpful to predict whether a complete resection in ovarian cancer patients is feasible.
Patients with colorectal peritoneal metastases (PM) treated with cytoreductive surgery (CRS) and hyperthermic intraperitoneal chemotherapy (HIPEC) are at high risk of recurrent disease. Understanding ...where and why recurrences occur is the first step in finding solutions to reduce recurrence rates. Although diffusion-weighted (DW) MRI is not routinely used in the follow-up of CRC patients, it has a clear advantage over CT in detecting the location and spread of (recurrent) PM. This study aimed to identify common locations of recurrence in CRC patients after CRS-HIPEC with MRI.
This was a single-centre retrospective study of patients with recurrent PM after CRS-HIPEC performed between January 2016 and August 2020. Patients were eligible for inclusion if they had both an MRI preoperatively (MRI1) and at the time of recurrent disease (MRI2). Two abdominal radiologists reviewed in consensus and categorized recurrences according to their location on MRI2 and in correlation with previous disease location on prior imaging (MRI1) and the surgical report of the CRS-HIPEC.
Thirty patients were included, with a median surgical PCI of 7 (range 3–21) at the time of primary CRS-HIPEC. In total, 68 recurrent metastases were detected on MRI2, of which 14 were extra-peritoneal. Of the remaining 54 PM, 42 (78%) occurred where the peritoneum was damaged due to earlier resections or other surgical procedures (e.g. inserted surgical abdominal drains). Most recurrent metastases were found in the mesentery, lower abdomen/pelvis and abdominal wall (87%).
Most recurrent PMs appeared in the mesentery, lower abdomen/pelvis and abdominal wall, especially where the peritoneum was previously damaged.