Publications
274 results found
Alvarez RM, Biliatis I, Rockall A, et al., 2018, MRI measurement of residual cervical length after radical trachelectomy for cervical cancer and the risk of adverse pregnancy outcomes: a blinded imaging analysis, BJOG-AN INTERNATIONAL JOURNAL OF OBSTETRICS AND GYNAECOLOGY, Vol: 125, Pages: 1726-1733, ISSN: 1470-0328
- Author Web Link
- Cite
- Citations: 28
Kanavati F, Islam S, Aboagye EO, et al., 2018, Automatic L3 slice detection in 3D CT images using fully-convolutional networks, Publisher: arXiv
The analysis of single CT slices extracted at the third lumbar vertebra (L3) has garnered significant clinical interest in the past few years, in particular in regards to quantifying sarcopenia (muscle loss). In this paper, we propose an efficient method to automatically detect the L3 slice in 3D CT images. Our method works with images with a variety of fields of view, occlusions, and slice thicknesses. 3D CT images are first converted into 2D via Maximal Intensity Projection (MIP), reducing the dimensionality of the problem. The MIP images are then used as input to a 2D fully-convolutional network to predict the L3 slice locations in the form of 2D confidence maps. In addition we propose a variant architecture with less parameters allowing 1D confidence map prediction and slightly faster prediction time without loss of accuracy. Quantitative evaluation of our method on a dataset of 1006 3D CT images yields a median error of 1mm, similar to the inter-rater median error of 1mm obtained from two annotators, demonstrating the effectiveness of our method in efficiently and accurately detecting the L3 slice.
Soneji ND, Bharwani N, Ferri A, et al., 2018, Pre-operative MRI staging of endometrial cancer in a multicentre cancer network: can we match single centre study results?, EUROPEAN RADIOLOGY, Vol: 28, Pages: 4725-4734, ISSN: 0938-7994
- Author Web Link
- Cite
- Citations: 17
Patel A, Rockall A, Guthrie A, et al., 2018, Can the completeness of radiological cancer staging reports be improved using proforma reporting? A prospective multicentre non-blinded interventional study across 21 centres in the UK, BMJ Open, Vol: 8, ISSN: 2044-6055
Objectives: Following a diagnosis of cancer, the detailed assessment of prognostic stage by radiology is a crucial determinant of initial therapeutic strategy offered to patients. Pre-therapeutic stage by imaging is known to be inconsistently documented. We tested whether the completeness of cancer staging radiology reports could be improved through a nationally introduced pilot of proforma-based reporting for a selection of six common cancers.Design: Prospective interventional study comparing the completeness of radiology cancer staging reports before and after the introduction of proforma reportingSetting: Twenty-one UK NHS Hospitals Participants: 1283 cancer staging radiology reports were submitted Main Outcome Measures: Radiology staging reports across the six cancers types were evaluated before and after the implementation of proforma based reporting. Report completeness was assessed using scoring forms listing the presence or absence of pre-determined key staging data. Qualitative data regarding proforma implementation and usefulness was collected from questionnaires provided to radiologists and end-users. Results: Electronic proforma based reporting was successfully implemented in 15 of the 21 centres during the evaluation period. A total of 787 pre-proforma and 496 post-proforma staging reports were evaluated. In the pre-proforma group, only 48.7% (5586/11470) of key staging items were present compared with 87.3% (6043/6920) in the post-proforma group. Thus, proforma reporting achieved an absolute improvement in staging completeness of 38.6% (95%CI,0.37-0.40%,p<0.001). An increase was seen across all cancer types and centres. The majority of respondents found proforma reporting improved report quality. Conclusion: The implementation of proforma reporting results in a significant improvement in completeness of cancer staging reports. Proforma based assessment of radiological stage facilitates objective comparison of quality and outcomes. It should be
Blagden SP, Rizzuto I, Suppiah P, et al., 2018, Anti-tumour activity of a first-in-class agent NUC-1031 in patients with advanced cancer: results of a phase I study, British Journal of Cancer, Vol: 119, Pages: 815-822, ISSN: 0007-0920
BackgroundGemcitabine is used to treat a wide range of tumours, but its efficacy is limited by cancer cell resistance mechanisms. NUC-1031, a phosphoramidate modification of gemcitabine, is the first anti-cancer ProTide to enter the clinic and is designed to overcome these key resistance mechanisms.MethodsSixty-eight patients with advanced solid tumours who had relapsed after treatment with standard therapy were recruited to a dose escalation study to determine the recommended Phase II dose (RP2D) and assess the safety of NUC-1031. Pharmacokinetics and anti-tumour activity was also assessed.ResultsSixty-eight patients received treatment, 50% of whom had prior exposure to gemcitabine. NUC-1031 was well tolerated with the most common Grade 3/4 adverse events of neutropaenia, lymphopaenia and fatigue occurring in 13 patients each (19%). In 49 response-evaluable patients, 5 (10%) achieved a partial response and 33 (67%) had stable disease, resulting in a 78% disease control rate. Cmax levels of the active intracellular metabolite, dFdCTP, were 217-times greater than those reported for equimolar doses of gemcitabine, with minimal toxic metabolite accumulation. The RP2D was determined as 825 mg/m2 on days 1, 8 and 15 of a 28-day cycle.ConclusionsNUC-1031 was well tolerated and demonstrated clinically significant anti-tumour activity, even in patients with prior gemcitabine exposure and in cancers not traditionally perceived as gemcitabine-responsive.
Valindria V, Lavdas I, Cerrolaza J, et al., 2018, Small organ segmentation in whole-body MRI using a two-stage FCN and weighting schemes, International Workshop on Machine Learning in Medical Imaging (MLMI) 2018, Publisher: Springer Verlag, Pages: 346-354, ISSN: 0302-9743
Accurate and robust segmentation of small organs in whole-body MRI is difficult due to anatomical variation and class imbalance. Recent deep network based approaches have demonstrated promising performance on abdominal multi-organ segmentations. However, the performance on small organs is still suboptimal as these occupy only small regions of the whole-body volumes with unclear boundaries and variable shapes. A coarse-to-fine, hierarchical strategy is a common approach to alleviate this problem, however, this might miss useful contextual information. We propose a two-stage approach with weighting schemes based on auto-context and spatial atlas priors. Our experiments show that the proposed approach can boost the segmentation accuracy of multiple small organs in whole-body MRI scans.
Lavdas I, Rockall AG, Daulton E, et al., 2018, Histogram analysis of apparent diffusion coefficient from whole-body diffusion-weighted MRI to predict early response to chemotherapy in patients with metastatic colorectal cancer: preliminary results, Clinical Radiology, Vol: 73, Pages: 832.e9-832.e16, ISSN: 0009-9260
AimTo evaluate apparent diffusion coefficient (ADC) histogram analysis parameters, acquired from whole-body diffusion-weighted magnetic resonance imaging (DW-MRI), as very early predictors of response to chemotherapy in patients with metastatic colorectal cancer (mCRC).Materials and methodsThis was a single-institution prospective study, approved by the West Midlands-South Birmingham research ethics committee. All patients gave fully informed consent prior to imaging. Sixteen patients with histologically confirmed mCRC were enrolled to the study and 11 were successfully scanned with whole-body DW-MRI before (baseline) and 10.8±2.7 days after commencing chemotherapy (follow-up). Therapy response was assessed by RECIST 1.1. Mean ADC and histogram parameters (skewness, kurtosis, 25th, 50th, and 75th percentiles) were compared between progressors and non-progressors at baseline and follow-up. Receiver operating characteristics (ROC) analysis was performed for the statistically significant parameters. Data from metastases were also compared to normative tissue data acquired from healthy volunteers.ResultsThree patients had progressive disease (progressors) and eight had partial response/stable disease (non-progressors). Mean, 25th, 50th, and 75th percentiles were significantly lower for progressors at baseline (p=0.012, 0.012, 0.012 and 0.025 respectively) with areas under the ROC curves (AUC)=0.58, 0.50, 0.58 and 0.63, respectively. Skewness and kurtosis were significantly lower for non-progressors at follow-up (p=0.001 and 0.003 respectively) with AUC=0.67 and 0.79 respectively.ConclusionADC histogram analysis shows potential in discriminating progressive from non-progressive disease in patients with mCRC, who underwent whole-body DW-MRI. The technique can potentially be tested as a response assessment methodology in larger trials.
Sadowski EA, Rockall AG, Maturen KE, et al., 2018, Adnexal lesions: Imaging strategies for ultrasound and MR imaging, Diagnostic and Interventional Imaging
© 2018 Adnexal lesions are routinely encountered in general practice. Ultrasound is the first line of investigation in determining the benign or malignant potential of an adnexal lesion. In the cases of classic simple cysts, hemorrhagic cysts, endometriomas, dermoids and obviously malignant lesions, ultrasound may be sufficient for management recommendations. In cases where there is an isolated adnexal lesion, without peritoneal disease or serum CA-125 elevation, and in lesions considered indeterminate on ultrasound, MR imaging with incorporation of the ADNEx MR score can increase the specificity for the diagnosis of benignity or malignancy. This article will review the imaging evaluation of adnexal lesions and how to incorporate the ADNEx MR score to help guide clinical management.
Kubik-Huch RA, Weston M, Nougaret S, et al., 2018, European Society of Urogenital Radiology (ESUR) guidelines: MR imaging of leiomyomas, European Radiology, Vol: 28, Pages: 3125-3137, ISSN: 0938-7994
ObjectiveThe aim of the Female Pelvic Imaging Working Group of the European Society of Urogenital Radiology (ESUR) was to develop imaging guidelines for MR work-up in patients with known or suspected uterine leiomyomas.MethodsGuidelines for imaging uterine leiomyomas were defined based on a survey distributed to all members of the working group, an expert consensus meeting at European Congress of Radiology (ECR) 2017 and a critical review of the literature.ResultsThe 25 returned questionnaires as well as the expert consensus meeting have shown reasonable homogeneity of practice among institutions. Expert consensus and literature review lead to an optimized MRI protocol to image uterine leiomyomas. Recommendations include indications for imaging, patient preparation, MR protocols and reporting criteria. The incremental value of functional imaging (DWI, DCE) is highlighted and the role of MR angiography discussed.ConclusionsMRI offers an outstanding and reproducible map of the size, site and distribution of leiomyomas. A standardised imaging protocol and method of reporting ensures that the salient features are recognised. These imaging guidelines are based on the current practice among expert radiologists in the field of female pelvic imaging and also incorporate essentials of the current published MR literature of uterine leiomyomas.
Valindria VV, Lavdas I, Bai W, et al., 2018, Domain adaptation for MRI organ segmentation using reverse classification accuracy, International Conference on Medical Imaging with Deep Learning (MIDL)
The variations in multi-center data in medical imaging studies have broughtthe necessity of domain adaptation. Despite the advancement of machine learningin automatic segmentation, performance often degrades when algorithms areapplied on new data acquired from different scanners or sequences than thetraining data. Manual annotation is costly and time consuming if it has to becarried out for every new target domain. In this work, we investigate automaticselection of suitable subjects to be annotated for supervised domain adaptationusing the concept of reverse classification accuracy (RCA). RCA predicts theperformance of a trained model on data from the new domain and differentstrategies of selecting subjects to be included in the adaptation via transferlearning are evaluated. We perform experiments on a two-center MR database forthe task of organ segmentation. We show that subject selection via RCA canreduce the burden of annotation of new data for the target domain.
Valindria V, Pawlowski N, Rajchl M, et al., 2018, Multi-modal learning from unpaired images: Application to multi-organ segmentation in CT and MRI, IEEE Winter Conference on Applications of Computer Vision, Publisher: IEEE
Convolutional neural networks have been widely used in medical image segmentation. The amount of training data strongly determines the overall performance. Most approaches are applied for a single imaging modality, e.g., brain MRI. In practice, it is often difficult to acquire sufficient training data of a certain imaging modality. The same anatomical structures, however, may be visible in different modalities such as major organs on abdominal CT and MRI. In this work, we investigate the effectiveness of learning from multiple modalities to improve the segmentation accuracy on each individual modality. We study the feasibility of using a dual-stream encoder-decoder architecture to learn modality-independent, and thus, generalisable and robust features. All of our MRI and CT data are unpaired, which means they are obtained from different subjects and not registered to each other. Experiments show that multi-modal learning can improve overall accuracy over modality-specific training. Results demonstrate that information across modalities can in particular improve performance on varying structures such as the spleen.
Wale A, Wexner SD, Saur NM, et al., 2018, Session 1: The evolution and development of the multidisciplinary team approach: USA, European and UK experiences - what can we do better?, COLORECTAL DISEASE, Vol: 20, Pages: 17-27, ISSN: 1462-8910
Evans REC, Taylor SA, Beare S, et al., 2018, Perceived patient burden and acceptability of whole body MRI for staging lung and colorectal cancer; comparison with standard staging investigations, BRITISH JOURNAL OF RADIOLOGY, Vol: 91, ISSN: 0007-1285
Sadowski EA, Robbins JB, Rockall AG, et al., 2018, A systematic approach to adnexal masses discovered on ultrasound: the ADNEx MR scoring system, Abdominal Radiology, Vol: 43, Pages: 679-695, ISSN: 2366-004X
© 2018, Springer Science+Business Media, LLC. Adnexal lesions are a common occurrence in radiology practice and imaging plays a crucial role in triaging women appropriately. Current trends toward early detection and characterization have increased the need for accurate imaging assessment of adnexal lesions prior to treatment. Ultrasound is the first-line imaging modality for assessing adnexal lesions; however, approximately 20% of lesions are incompletely characterized after ultrasound evaluation. Secondary assessment with MR imaging using the ADNEx MR Scoring System has been demonstrated as highly accurate in the characterization of adnexal lesions and in excluding ovarian cancer. This review will address the role of MR imaging in further assessment of adnexal lesions discovered on US, and the utility of the ADNEx MR Scoring System.
Barnes A, Alonzi R, Blackledge M, et al., 2018, UK quantitative WB-DWI technical workgroup: consensus meeting recommendations on optimisation, quality control, processing and analysis of quantitative whole-body diffusion-weighted imaging for cancer, British Journal of Radiology, Vol: 91, Pages: 1-12, ISSN: 0007-1285
Objective: Application of whole body diffusion-weightedMRI (WB-DWI) for oncology are rapidly increasingwithin both research and routine clinical domains.However, WB-DWI as a quantitative imaging biomarker(QIB) has significantly slower adoption. To date, challenges relating to accuracy and reproducibility, essentialcriteria for a good QIB, have limited widespread clinicaltranslation. In recognition, a UK workgroup was established in 2016 to provide technical consensus guidelines(to maximise accuracy and reproducibility of WB-MRIQIBs) and accelerate the clinical translation of quantitative WB-DWI applications for oncology.Methods: A panel of experts convened from cancercentres around the UK with subspecialty expertise inquantitative imaging and/or the use of WB-MRI withDWI. A formal consensus method was used to obtainconsensus agreement regarding best practice. Questionswere asked about the appropriateness or otherwise onscanner hardware and software, sequence optimisation,acquisition protocols, reporting, and ongoing qualitycontrol programs to monitor precision and accuracy andagreement on quality control.Results: The consensus panel was able to reach consensuson 73% (255/351) items and based on consensus areasmade recommendations to maximise accuracy andreproducibly of quantitative WB-DWI studies performedat 1.5T. The panel were unable to reach consensus onthe majority of items related to quantitative WB-DWIperformed at 3T.Conclusion: This UK Quantitative WB-DWI TechnicalWorkgroup consensus provides guidance on maximising accuracy and reproducibly of quantitative WB-DWIfor oncology. The consensus guidance can be usedby researchers and clinicians to harmonise WB-DWIprotocols which will accelerate clinical translation ofWB-DWI-derived QIBs.
Bazot M, Bharwani N, Huchon C, et al., 2017, European Society of Urogenital Radiology (ESUR) guidelines: MR imaging of pelvic endometriosis, IMAGERIE DE LA FEMME, Vol: 27, Pages: 267-279, ISSN: 1776-9817
Seebacher V, Rockall A, Nobbenhuis M, et al., 2017, MALNUTRITION AND SARCOPENIA: RISK FACTORS FOR SHORTER SURVIVAL IN PATIENTS TREATED WITH PELVIC EXENTERATION FOR RECURRENT GYNECOLOGICAL MALIGNANCY., Publisher: LIPPINCOTT WILLIAMS & WILKINS, Pages: 1376-1376, ISSN: 1048-891X
Seebacher V, Rockall A, Nobbenhuis M, et al., 2017, MALNUTRITION AND SARCOPENIA: RISK FACTORS FOR SHORTER SURVIVAL IN PATIENTS TREATED WITH PELVIC EXENTERATION FOR RECURRENT GYNECOLOGICAL MALIGNANCY., Publisher: LIPPINCOTT WILLIAMS & WILKINS, Pages: 492-492, ISSN: 1048-891X
Lu H, Fotopoulou C, Rockall A, et al., 2017, PRE-OPERATIVE RADIOMIC MODELS ANNOTATE EPITHELIAL OVARIAN CANCER PROGNOSTIC PHENOTYPES, Publisher: LIPPINCOTT WILLIAMS & WILKINS, Pages: 502-502, ISSN: 1048-891X
Lu H, Fotopoulou C, Rockall A, et al., 2017, PRE-OPERATIVE RADIOMIC MODELS ANNOTATE EPITHELIAL OVARIAN CANCER PROGNOSTIC PHENOTYPES, Publisher: LIPPINCOTT WILLIAMS & WILKINS, Pages: 1490-1490, ISSN: 1048-891X
Querleu D, Planchamp F, Chiva L, et al., 2017, European Society of Gynaecological Oncology (ESGO) Guidelines for Ovarian Cancer Surgery, INTERNATIONAL JOURNAL OF GYNECOLOGICAL CANCER, Vol: 27, Pages: 1534-1542, ISSN: 1048-891X
Evans R, Taylor S, Janes S, et al., 2017, Patient experience and perceived acceptability of whole-body magnetic resonance imaging for staging colorectal and lung cancer compared with current staging scans: a qualitative study, BMJ Open, Vol: 7, Pages: 1-9, ISSN: 2044-6055
Objective To describe the experience and acceptability of whole-body magnetic resonance imaging (WB-MRI) staging compared with standard scans among patients with highly suspected or known colorectal or lung cancer.Design Qualitative study using one-to-one interviews with thematic analysis.Setting Patients recruited from 10 hospitals in London, East and South East England between March 2013 and July 2014.Participants 51 patients (31 male, age range 40–89 years), with varying levels of social deprivation, were recruited consecutively from two parallel clinical trials comparing the diagnostic accuracy and cost-effectiveness of WB-MRI with standard scans for staging colorectal and lung cancer (‘Streamline-C’ and ‘Streamline-L’). WB-MRI was offered as an additional scan as part of the trials.Results In general WB-MRI presented a greater challenge than standard scans, although all but four patients completed the WB-MRI. Key challenges were enclosed space, noise and scan duration; reduced patient tolerance was associated with claustrophobia, pulmonary symptoms and existing comorbidities. Coping strategies facilitated scan tolerance and were grouped into (1) those intended to help with physical and emotional challenges, and (2) those focused on motivation to complete the scan, for example focusing on health benefit. Our study suggests that good staff communication could reduce anxiety and boost coping strategies.Conclusions Although WB-MRI was perceived as more challenging than standard scans, it was sufficiently acceptable and tolerated by most patients to potentially replace them if appropriate.Trial registration number ISRCTN43958015 and ISRCTN50436483.
Lavdas I, Glocker B, Kamnitsas K, et al., 2017, Fully automatic, multi-organ segmentation in normal whole body magnetic resonance imaging (MRI), using classification forests (CFs), convolutional neural networks (CNNs) and a multi-atlas (MA) approach., Medical Physics, Vol: 44, Pages: 5210-5220, ISSN: 0094-2405
PURPOSE: As part of a programme to implement automatic lesion detection methods for whole body magnetic resonance imaging (MRI) in oncology, we have developed, evaluated and compared three algorithms for fully automatic, multi-organ segmentation in healthy volunteers. METHODS: The first algorithm is based on classification forests (CFs), the second is based on 3D convolutional neural networks (CNNs) and the third algorithm is based on a multi-atlas (MA) approach. We examined data from 51 healthy volunteers, scanned prospectively with a standardised, multi-parametric whole body MRI protocol at 1.5T. The study was approved by the local ethics committee and written consent was obtained from the participants. MRI data were used as input data to the algorithms, while training was based on manual annotation of the anatomies of interest by clinical MRI experts. Five-fold cross-validation experiments were run on 34 artefact-free subjects. We report three overlap and three surface distance metrics to evaluate the agreement between the automatic and manual segmentations, namely the Dice similarity coefficient (DSC), recall (RE), precision (PR), average surface distance (ASD), root mean square surface distance (RMSSD) and Hausdorff distance (HD). Analysis of variances was used to compare pooled label metrics between the three algorithms and the DSC on a 'per-organ' basis. A Mann-Whitney U test was used to compare the pooled metrics between CFs and CNNs and the DSC on a 'per-organ' basis, when using different imaging combinations as input for training. RESULTS: All three algorithms resulted in robust segmenters that were effectively trained using a relatively small number of data sets, an important consideration in the clinical setting. Mean overlap metrics for all the segmented structures were: CFs: DSC=0.70±0.18, RE=0.73±0.18, PR=0.71±0.14, CNNs: DSC=0.81±0.13, RE=0.83±0.14, PR=0.82±0.10, MA: DSC=0.71±0.22, RE=0.70±0.34
Bazot M, Bharwani N, Huchon C, et al., 2017, European society of urogenital radiology (ESUR) guidelines: MR imaging of pelvic endometriosis, EUROPEAN RADIOLOGY, Vol: 27, Pages: 2765-2775, ISSN: 0938-7994
- Author Web Link
- Cite
- Citations: 135
Forstner R, Thomassin-Naggara I, Cunha TM, et al., 2017, ESUR recommendations for MR imaging of the sonographically indeterminate adnexal mass: an update (vol 27, pg 2248, 2017), EUROPEAN RADIOLOGY, Vol: 27, Pages: 2258-2258, ISSN: 0938-7994
Forstner R, Thomassin-Naggara I, Cunha TM, et al., 2017, ESUR recommendations for MR imaging of the sonographically indeterminate adnexal mass: an update, EUROPEAN RADIOLOGY, Vol: 27, Pages: 2248-2257, ISSN: 0938-7994
- Author Web Link
- Cite
- Citations: 94
Taylor SA, Mallett S, Miles A, et al., 2017, Streamlining staging of lung and colorectal cancer with whole body MRI; study protocols for two multicentre, non-randomised, single-arm, prospective diagnostic accuracy studies (Streamline C and Streamline L), BMC Cancer, Vol: 17, Pages: 1-10, ISSN: 1471-2407
Background and aimsRapid and accurate cancer staging following diagnosis underpins patient management, in particular the identification of distant metastatic disease. Current staging guidelines recommend sequential deployment of various imaging platforms such as computerised tomography (CT) and positron emission tomography (PET) which can be time and resource intensive and onerous for patients. Recent studies demonstrate that whole body magnetic resonance Imaging (WB-MRI) may stage cancer efficiently in a single visit, with potentially greater accuracy than current staging investigations. The Streamline trials aim to evaluate whether WB-MRI increases per patient detection of metastases in non-small cell lung and colorectal cancer compared to standard staging pathways.MethodsThe Streamline trials are multicentre, non-randomised, single-arm, prospective diagnostic accuracy studies with a novel design to capture patient management decisions during staging pathways. The two trials recruit adult patients with proven or highly suspected new diagnosis of primary colorectal (Streamline C) or non-small cell lung cancer (Streamline L) referred for staging. Patients undergo WB-MRI in addition to standard staging investigations. Strict blinding protocols are enforced for those interpreting the imaging. A first major treatment decision is made by the multi-disciplinary team prior to WB-MRI revelation based on standard staging investigations only, then based on the WB-MRI and any additional tests precipitated by WB-MRI, and finally based on all available test results. The reference standard is derived by a multidisciplinary consensus panel who assess 12 months of follow-up data to adjudicate on the TNM stage at diagnosis. Health psychology assessment of patients’ experiences of the cancer staging pathway will be undertaken via interviews and questionnaires. A cost (effectiveness) analysis of WB-MRI compared to standard staging pathways will be performed.DiscussionWe describ
Valindria V, Lavdas I, Bai W, et al., 2017, Reverse classification accuracy: predicting segmentation performance in the absence of ground truth, IEEE Transactions on Medical Imaging, Vol: 36, Pages: 1597-1606, ISSN: 1558-254X
When integrating computational tools such as au-tomatic segmentation into clinical practice, it is of utmostimportance to be able to assess the level of accuracy on newdata, and in particular, to detect when an automatic methodfails. However, this is difficult to achieve due to absence of groundtruth. Segmentation accuracy on clinical data might be differentfrom what is found through cross-validation because validationdata is often used during incremental method development, whichcan lead to overfitting and unrealistic performance expectations.Before deployment, performance is quantified using differentmetrics, for which the predicted segmentation is compared toa reference segmentation, often obtained manually by an expert.But little is known about the real performance after deploymentwhen a reference is unavailable. In this paper, we introduce theconcept ofreverse classification accuracy(RCA) as a frameworkfor predicting the performance of a segmentation method onnew data. In RCA we take the predicted segmentation froma new image to train a reverse classifier which is evaluatedon a set of reference images with available ground truth. Thehypothesis is that if the predicted segmentation is of good quality,then the reverse classifier will perform well on at least some ofthe reference images. We validate our approach on multi-organsegmentation with different classifiers and segmentation methods.Our results indicate that it is indeed possible to predict the qualityof individual segmentations, in the absence of ground truth. Thus,RCA is ideal for integration into automatic processing pipelines inclinical routine and as part of large-scale image analysis studies.
Lakhani A, Khan SR, Bharwani N, et al., 2017, FDG PET/CT Pitfalls in Gynecologic and Genitourinary Oncologic Imaging., Radiographics, Vol: 37, Pages: 577-594
The role of whole-body positron emission tomography (PET)/computed tomography (CT) with fluorodeoxyglucose ( FDG fluorodeoxyglucose ) is now established in the assessment of many gynecologic and genitourinary malignant tumors. FDG fluorodeoxyglucose PET/CT has been widely adopted for staging assessments in patients with suspected advanced disease, in cases of suspected disease recurrence, and for determining prognosis in a number of malignancies. A number of pitfalls are commonly encountered when reviewing FDG fluorodeoxyglucose PET/CT scans in gynecologic and genitourinary cases; these pitfalls can be classified into those that yield potential false-positive or false-negative results. Potential false positives include physiologic uptake of FDG fluorodeoxyglucose by the endometrium and ovaries in premenopausal patients, physiologic renal excretion of FDG fluorodeoxyglucose into the ureters and the urinary bladder, and increased FDG fluorodeoxyglucose activity in benign conditions such as uterine fibroids, pelvic inflammatory disease, and benign endometriotic cysts. Potential false negatives include low-level FDG fluorodeoxyglucose uptake by necrotic, mucinous, cystic, or low-grade tumors and the masking of serosal and peritoneal disease by adjacent physiologic bowel or bladder activity. In addition, there are inherent technical limitations-such as motion artifact (from respiratory motion and bowel peristalsis) and the limited spatial resolution of PET-that may limit the assessment of small-volume malignant disease. Knowledge of the key imaging features of physiologic and nonphysiologic FDG fluorodeoxyglucose uptake, in addition to understanding the principles of adequate patient preparation and PET scanning protocols, is important for accurate interpretation of gynecologic and genitourinary oncologic FDG fluorodeoxyglucose PET/CT studies. ©RSNA, 2017.
Sundin A, Arnold R, Baudin E, et al., 2017, ENETS Consensus Guidelines for the Standards of Care in Neuroendocrine Tumors: Radiological, Nuclear Medicine and Hybrid Imaging, NEUROENDOCRINOLOGY, Vol: 105, Pages: 212-244, ISSN: 0028-3835
- Author Web Link
- Cite
- Citations: 239
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.