scholarly journals MSBC-Net: Automatic Rectal Cancer Segmentation from MR Scans

2021 ◽  
Author(s):  
Ping Meng ◽  
Chao Sun ◽  
Yi Li ◽  
Long Zhou ◽  
Xinyu Zhao ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Rectal Wall ◽  
Region Of Interest ◽  
Cancer Staging ◽  
Medical Image Segmentation ◽  
Research Progress ◽  
Dice Similarity Coefficient ◽  
Boundary Constraints ◽  
Segmentation Strategy ◽  
Magnetic Resonance Imaging Mri

<div>Accurate segmentation of rectal cancer and rectal wall based on high-resolution T2-weighted magnetic resonance imaging (MRI-HRT2) is the basis of rectal cancer staging. However, complex imaging background, highly characteristics variation and poor contrast hindered the research progress of the automatic rectal cancer segmentation. In this study, a multi-task learning network, namely mask segmentation with boundary constraints (MSBC-Net), is proposed to overcome these limitations and to obtain accurate segmentation results by locating and segmenting rectal cancer and rectal wall automatically. Specifically, at first, a region of interest (RoI)-based segmentation strategy is designed to enable end-to-end multi-task training, where a sparse object detection module is used to automatically localize and classify rectal cancer and rectal wall to mitigate the problem of background interference, and a mask and boundary segmentation block is used to finely segment the RoIs; second, a modulated deformable backbone is introduced to handle the variable features of rectal cancer, which effectively improves the detection performance of small objects and adaptability of the proposed model. Moreover, the boundary head is fused into the mask head to segment the ambiguous boundary of the target and constrain the mask head to obtain more refined segmentation results. In total, 592 annotated rectal cancer patients in MRI-HRT2 are enrolled, and the comprehensive results show that the proposed MSBC-Net outperforms state-of-the-art methods with a dice similarity coefficient (DSC) of 0.801 (95\% CI, 0.791-0.811), which can be well extended to other medical image segmentation tasks with high potential clinical applicability.</div>

scholarly journals MSBC-Net: Automatic Rectal Cancer Segmentation from MR Scans

2021 ◽  
Author(s):  
Ping Meng ◽  
Chao Sun ◽  
Yi Li ◽  
Long Zhou ◽  
Xinyu Zhao ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Rectal Wall ◽  
Region Of Interest ◽  
Cancer Staging ◽  
Medical Image Segmentation ◽  
Research Progress ◽  
Dice Similarity Coefficient ◽  
Boundary Constraints ◽  
Segmentation Strategy ◽  
Magnetic Resonance Imaging Mri

<div>Accurate segmentation of rectal cancer and rectal wall based on high-resolution T2-weighted magnetic resonance imaging (MRI-HRT2) is the basis of rectal cancer staging. However, complex imaging background, highly characteristics variation and poor contrast hindered the research progress of the automatic rectal cancer segmentation. In this study, a multi-task learning network, namely mask segmentation with boundary constraints (MSBC-Net), is proposed to overcome these limitations and to obtain accurate segmentation results by locating and segmenting rectal cancer and rectal wall automatically. Specifically, at first, a region of interest (RoI)-based segmentation strategy is designed to enable end-to-end multi-task training, where a sparse object detection module is used to automatically localize and classify rectal cancer and rectal wall to mitigate the problem of background interference, and a mask and boundary segmentation block is used to finely segment the RoIs; second, a modulated deformable backbone is introduced to handle the variable features of rectal cancer, which effectively improves the detection performance of small objects and adaptability of the proposed model. Moreover, the boundary head is fused into the mask head to segment the ambiguous boundary of the target and constrain the mask head to obtain more refined segmentation results. In total, 592 annotated rectal cancer patients in MRI-HRT2 are enrolled, and the comprehensive results show that the proposed MSBC-Net outperforms state-of-the-art methods with a dice similarity coefficient (DSC) of 0.801 (95\% CI, 0.791-0.811), which can be well extended to other medical image segmentation tasks with high potential clinical applicability.</div>

scholarly journals Region-of-Interest-Based Cardiac Image Segmentation with Deep Learning

2021 ◽  
Vol 11 (4) ◽  
pp. 1965
Author(s):  
Raul-Ronald Galea ◽  
Laura Diosan ◽  
Anca Andreica ◽  
Loredana Popa ◽  
Simona Manole ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Diagnostic System ◽  
Region Of Interest ◽  
General Purpose ◽  
Medical Image Segmentation ◽  
Dice Similarity Coefficient ◽  
Learning Methods ◽  
Study Results ◽  
Whole Heart

Despite the promising results obtained by deep learning methods in the field of medical image segmentation, lack of sufficient data always hinders performance to a certain degree. In this work, we explore the feasibility of applying deep learning methods on a pilot dataset. We present a simple and practical approach to perform segmentation in a 2D, slice-by-slice manner, based on region of interest (ROI) localization, applying an optimized training regime to improve segmentation performance from regions of interest. We start from two popular segmentation networks, the preferred model for medical segmentation, U-Net, and a general-purpose model, DeepLabV3+. Furthermore, we show that ensembling of these two fundamentally different architectures brings constant benefits by testing our approach on two different datasets, the publicly available ACDC challenge, and the imATFIB dataset from our in-house conducted clinical study. Results on the imATFIB dataset show that the proposed approach performs well with the provided training volumes, achieving an average Dice Similarity Coefficient of the whole heart of 89.89% on the validation set. Moreover, our algorithm achieved a mean Dice value of 91.87% on the ACDC validation, being comparable to the second best-performing approach on the challenge. Our approach provides an opportunity to serve as a building block of a computer-aided diagnostic system in a clinical setting.

Radiology reporting in rectal cancer using MRI: adherence to national template for structured reporting

2021 ◽  
pp. 028418512110572
Author(s):  
Gustav Alvfeldt ◽  
Peter Aspelin ◽  
Lennart Blomqvist ◽  
Nina Sellberg
Keyword(s):  
Rectal Cancer ◽  
Qualitative Content Analysis ◽  
Cancer Staging ◽  
Free Text ◽  
Reporting Practice ◽  
Key Factor ◽  
Content Coverage ◽  
Magnetic Resonance Imaging Mri ◽  
National Workshop ◽  
Completeness Of Reporting

Background In 2014, a national workshop program was initiated and a reporting template and manual for rectal cancer primary staging using magnetic resonance imaging (MRI) was introduced and made available by the national Swedish Colorectal Cancer Registry. Purpose To evaluate the effect of the national template program by identify if there was a gap between the content in Swedish MRI reports from 2016 and the national reporting template from 2014. The aim was to explore and compare differences in content in reporting practice in different hospitals in relation to the national reporting template, with focus on: (i) identifying any implementational differences in reporting styles; and (ii) evaluating if reporting completeness vary based on such implementational differences. Material and Methods A total of 250 MRI reports from 10 hospitals in four healthcare regions in Sweden were collected. Reports were analyzed using qualitative content analysis with a deductive thematic coding scheme based on the national reporting template. Results Three different implemented reporting styles were identified with variations of content coverage in relation to the template: (i) standardized and structured protocol (reporting style A); (ii) standardized semi-structured free-text (reporting style B); and (iii) regular free-text (reporting style C). The relative completeness of reporting practice of rectal cancer staging in relation to the national reporting template were 92.9% for reporting style A, 77.5% for reporting style B, and 63.9% for reporting style C. Conclusion The implementation of template-based reporting according to reporting style A is a key factor to conform to evidence-based practice for rectal cancer reporting using MRI.

scholarly journals Role of Imaging in Rectal Cancer

JMS SKIMS ◽  
2012 ◽  
Vol 15 (1) ◽  
pp. 4-6
Author(s):  
Ajaz Ahmad Malik
Keyword(s):  
Rectal Cancer ◽  
Rectal Wall ◽  
Preoperative Staging ◽  
Positron Emission ◽  
Adjacent Structures ◽  
Tumor Involvement ◽  
Magnetic Resonance Imaging Mri ◽  
Optimal Treatment Strategy

THIS ARTICLE HAS NO ABSTRACT (FIRST 100 WORDS OF THE ARTICLE ARE DISPLAYED): Staging of rectal cancer is necessary to provide the optimal treatment strategy although proctoscopy or sigmoidoscopy with biopsy are diagnostic. This is achieved by locoregional assessment of the disease by various available radiological investigations. Staging information includes extent of tumor involvement of the rectal wall and adjacent structures, presence or absence of adjacent lymphadenopathy, and determination of distant metastasis. Several modalities exist for the preoperative staging of rectal cancer, like computed tomography (CT); magnetic resonance imaging (MRI) with traditional body, endorectal, or phasedarray coils; endorectal ultrasonography (ERUS) with rigid or flexible probes; and positron emission tomography (PET) with and without. JMS 2012;15(1):4-6.

scholarly journals Rectal cancer staging using MRI: adherence in reporting to evidence-based practice

2020 ◽  
Vol 61 (11) ◽  
pp. 1463-1472
Author(s):  
Gustav Alvfeldt ◽  
Peter Aspelin ◽  
Lennart Blomqvist ◽  
Nina Sellberg
Keyword(s):  
Rectal Cancer ◽  
Evidence Based Practice ◽  
Imaging Modality ◽  
Anal Verge ◽  
Cancer Staging ◽  
Evidence Based ◽  
Mri Staging ◽  
Line Imaging ◽  
Magnetic Resonance Imaging Mri ◽  
Local Lymph Node

Background Magnetic resonance imaging (MRI) is the first-line imaging modality for local staging of rectal cancer. The radiology report should deliver all relevant available imaging information to guide treatment. Purpose To explore and describe if there was a gap between the contents in MRI reports for primary staging of rectal cancer in Sweden in 2010 compared to evidence-based practice. Material and Methods A total of 243 primary MRI staging reports from 2010, collected from 10 hospitals in four healthcare regions in Sweden, were analyzed using content analysis with a deductive thematic coding scheme based on evidence-based practice. Focus was on: (i) most frequently reported findings; (ii) correlation to key prognostic findings; and (iii) identifying if any findings being reported were beyond the information defined in evidence-based practice. Results Most frequently reported findings were spread through the bowel wall or not, local lymph node description, tumor length, and distance of tumor from anal verge. These items accounted for 35% of the reporting content. Of all reported content, 86% correlated with the evidence-based practice. However, these included more information than was generally found in the reports. When adjusting for omitted information, 48% of the reported content were accounted for. Of the reported content, 20% correlated to key pathological prognostic findings. Six types of findings were reported beyond the evidence-based practice, representing 14% of the total reporting content. Conclusion There was a gap between everyday practice and evidence-based practice in 2010. This indicates a need for national harmonization and implementation of standardized structured reporting templates.

scholarly journals The Role of 3-D Endorectal Ultrasound in Rectal Cancer: Our Experience

2014 ◽  
Vol 99 (2) ◽  
pp. 106-111 ◽  
Author(s):  
Nikola Y. Kolev ◽  
Anton Y. Tonev ◽  
Valentin L. Ignatov ◽  
Aleksander K. Zlatarov ◽  
Vasil M. Bojkov ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Rectal Wall ◽  
Preoperative Staging ◽  
Three Dimensional ◽  
Cancer Staging ◽  
Endorectal Ultrasound ◽  
Diagnostic Methods ◽  
Diagnostic Modality ◽  
Locoregional Staging

Abstract In the last 20 years, endorectal ultrasound (ERUS) has been one of the main diagnostic methods for locoregional staging of rectal cancer. ERUS is accurate modality for evaluating local invasion of rectal carcinoma into the rectal wall layers (T category). Adding the three-dimensional modality (3-D) increases the capabilities of this diagnostic tool in rectal cancer patients. We review the literature and report our experience in preoperative 3-D ERUS in rectal cancer staging. In the group of 71 patients, the staging of preoperative 3-D endorectal ultrasonography was compared with the postoperative morphologic examination. Three-dimensional ERUS preoperative staging was confirmed with morphologic evaluation in 66 out of 71 cases (92.9%). The detection sensitivities of rectal cancer with 3-D ERUS were as follows: T1, 92.8%; T2, 93.1%; T3, 91.6%; and T4, 100.0%; with specificity values of T1, 98.2%; T2, 95.4%; T3, 97.8%; and T4, 98.5%. Three-dimensional ERUS correctly categorized patients with T1, 97.1%; T2, 94.3%; T3, 95.7%; and T4, 98.5%. The percentage of total overstaged cases was 2.75% and that of understaged cases was 6.87%. The metastatic status of the lymph nodes was determined with a sensitivity of 79.1% (19 of 24), specificity of 91.4% (43 of 47), and diagnostic accuracy of 87.3% (62 of 71). In our experience, 3-D ERUS has the potential to become the diagnostic modality of choice for the preoperative staging of rectal cancer.

scholarly journals MRI-detected extramural venous invasion of rectal cancer: Multimodality performance and implications at baseline imaging and after neoadjuvant therapy

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Akitoshi Inoue ◽  
Shannon P. Sheedy ◽  
Jay P. Heiken ◽  
Payam Mohammadinejad ◽  
Rondell P. Graham ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Rectal Wall ◽  
Venous Invasion ◽  
Cancer Staging ◽  
Observer Agreement ◽  
High Signal ◽  
Post Contrast ◽  
Diffusion Weighted Images ◽  
Diffusion Weighted ◽  
Clinical Scenarios

AbstractMRI is routinely used for rectal cancer staging to evaluate tumor extent and to inform decision-making regarding surgical planning and the need for neoadjuvant and adjuvant therapy. Extramural venous invasion (EMVI), which is intravenous tumor extension beyond the rectal wall on histopathology, is a predictor for worse prognosis. T2-weighted images (T2WI) demonstrate EMVI as a nodular-, bead-, or worm-shaped structure of intermediate T2 signal with irregular margins that arises from the primary tumor. Correlative diffusion-weighted images demonstrate intermediate to high signal corresponding to EMVI, and contrast enhanced T1-weighted images demonstrate tumor signal intensity in or around vessels. Diffusion-weighted and post contrast images may increase diagnostic performance but decrease inter-observer agreement. CT may also demonstrate obvious EMVI and is potentially useful in patients with a contraindication for MRI. This article aims to review the spectrum of imaging findings of EMVI of rectal cancer on MRI and CT, to summarize the diagnostic accuracy and inter-observer agreement of imaging modalities for its presence, to review other rectal neoplasms that may cause EMVI, and to discuss the clinical significance and role of MRI-detected EMVI in staging and restaging clinical scenarios.

scholarly journals Cortical microinfarcts in memory clinic patients are associated with reduced cerebral perfusion

2019 ◽  
Vol 40 (9) ◽  
pp. 1869-1878 ◽  
Author(s):  
Doeschka A Ferro ◽  
Henri JJM Mutsaerts ◽  
Saima Hilal ◽  
Hugo J Kuijf ◽  
Esben T Petersen ◽  
...  
Keyword(s):  
Arterial Spin Labeling ◽  
Cerebral Perfusion ◽  
Region Of Interest ◽  
Resonance Imaging ◽  
Memory Clinic ◽  
Anterior Circulation ◽  
Cortical Gray Matter ◽  
Arterial Transit Time ◽  
Magnetic Resonance Imaging Mri ◽  
Continuous Arterial Spin Labeling

Cerebral cortical microinfarcts (CMIs) are small ischemic lesions associated with cognitive impairment and dementia. CMIs are frequently observed in cortical watershed areas suggesting that hypoperfusion contributes to their development. We investigated if presence of CMIs was related to a decrease in cerebral perfusion, globally or specifically in cortex surrounding CMIs. In 181 memory clinic patients (mean age 72 ± 9 years, 51% male), CMI presence was rated on 3-T magnetic resonance imaging (MRI). Cerebral perfusion was assessed from cortical gray matter of the anterior circulation using pseudo-continuous arterial spin labeling parameters cerebral blood flow (CBF) (perfusion in mL blood/100 g tissue/min) and spatial coefficient of variation (CoV) (reflecting arterial transit time (ATT)). Patients with CMIs had a 12% lower CBF (beta = −.20) and 22% higher spatial CoV (beta = .20) (both p < .05) without a specific regional pattern on voxel-based CBF analysis. CBF in a 2 cm region-of-interest around the CMIs did not differ from CBF in a reference zone in the contralateral hemisphere. These findings show that CMIs in memory clinic patients are primarily related to global reductions in cerebral perfusion, thus shedding new light on the etiology of vascular brain injury in dementia.

scholarly journals Structured Reporting of Rectal Cancer Staging and Restaging: A Consensus Proposal

Cancers ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 2135
Author(s):  
Vincenza Granata ◽  
Damiano Caruso ◽  
Roberto Grassi ◽  
Salvatore Cappabianca ◽  
Alfonso Reginelli ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Correlation Coefficient ◽  
Clinical Decision Making ◽  
Intraclass Correlation ◽  
Clinical Decision ◽  
Cancer Staging ◽  
Structured Reporting ◽  
Quality Analysis ◽  
Promising Tool ◽  
Structured Reports

Background: Structured reporting (SR) in oncologic imaging is becoming necessary and has recently been recognized by major scientific societies. The aim of this study was to build MRI-based structured reports for rectal cancer (RC) staging and restaging in order to provide clinicians all critical tumor information. Materials and Methods: A panel of radiologist experts in abdominal imaging, called the members of the Italian Society of Medical and Interventional Radiology, was established. The modified Delphi process was used to build the SR and to assess the level of agreement in all sections. The Cronbach’s alpha (Cα) correlation coefficient was used to assess the internal consistency of each section and to measure the quality analysis according to the average inter-item correlation. The intraclass correlation coefficient (ICC) was also evaluated. Results: After the second Delphi round of the SR RC staging, the panelists’ single scores and sum of scores were 3.8 (range 2–4) and 169, and the SR RC restaging panelists’ single scores and sum of scores were 3.7 (range 2–4) and 148, respectively. The Cα correlation coefficient was 0.79 for SR staging and 0.81 for SR restaging. The ICCs for the SR RC staging and restaging were 0.78 (p < 0.01) and 0.82 (p < 0.01), respectively. The final SR version was built and included 53 items for RC staging and 50 items for RC restaging. Conclusions: The final version of the structured reports of MRI-based RC staging and restaging should be a helpful and promising tool for clinicians in managing cancer patients properly. Structured reports collect all Patient Clinical Data, Clinical Evaluations and relevant key findings of Rectal Cancer, both in staging and restaging, and can facilitate clinical decision-making.

scholarly journals Meyer’s Loop Anatomy Demonstrated Using Diffusion Tensor MR Imaging and Fiber Tractography at 3T

2014 ◽  
Vol 60 (5) ◽  
pp. 215-222 ◽  
Author(s):  
Cristina Goga ◽  
Zeynep Firat ◽  
Klara Brinzaniuc ◽  
Is Florian
Keyword(s):  
Diffusion Tensor Imaging ◽  
Diffusion Tensor ◽  
Region Of Interest ◽  
Fiber Tractography ◽  
Brain Images ◽  
3 Dimensional ◽  
Software Release ◽  
Magnetic Resonance Imaging Mri ◽  
Meyer’S Loop

Abstract Objective: The ultimate anatomy of the Meyer’s loop continues to elude us. Diffusion tensor imaging (DTI) and diffusion tensor tractography (DTT) may be able to demonstrate, in vivo, the anatomy of the complex network of white matter fibers surrounding the Meyer’s loop and the optic radiations. This study aims at exploring the anatomy of the Meyer’s loop by using DTI and fiber tractography. Methods: Ten healthy subjects underwent magnetic resonance imaging (MRI) with DTI at 3 T. Using a region-of-interest (ROI) based diffusion tensor imaging and fiber tracking software (Release 2.6, Achieva, Philips), sequential ROI were placed to reconstruct visual fibers and neighboring projection fibers involved in the formation of Meyer’s loop. The 3-dimensional (3D) reconstructed fibers were visualized by superimposition on 3-planar MRI brain images to enhance their precise anatomical localization and relationship with other anatomical structures. Results: Several projection fiber including the optic radiation, occipitopontine/parietopontine fibers and posterior thalamic peduncle participated in the formation of Meyer’s loop. Two patterns of angulation of the Meyer’s loop were found. Conclusions: DTI with DTT provides a complimentary, in vivo, method to study the details of the anatomy of the Meyer’s loop.

Sign in / Sign up

Export Citation Format

Share Document