Mary E. Roddie

Computer-Assisted Reader Software Versus Expert Reviewers for Polyp Detection on CT Colonography

OBJECTIVE The purpose of our study was to assess the sensitivity of computer-assisted reader (CAR) software for polyp detection compared with the performance of expert reviewers. MATERIALS AND METHODS A library of colonoscopically validated CT colonography cases were collated and separated into training and test sets according to the time of accrual. Training data sets were annotated in consensus by three expert radiologists who were aware of the colonoscopy report. A subset of 45 training cases containing 100 polyps underwent batch analysis using ColonCAR version 1.2 software to determine the optimum polyp enhancement filter settings for polyp detection. Twenty-five consecutive positive test data sets were subsequently interpreted individually by each expert, who was unaware of the endoscopy report, and before generation of the annotated reference via an unblinded consensus interpretation. ColonCAR version 1.2 software was applied to the test cases, at optimized polyp enhancement filter settings, to determine diagnostic performance. False-positive findings were classified according to importance. RESULTS The 25 test cases contained 32 nondiminutive polyps ranging from 6 to 35 mm in diameter. The ColonCAR version 1.2 software identified 26 (81%) of 32 polyps compared with an average sensitivity of 70% for the expert reviewers. Eleven (92%) of 12 polyps > or = 10 mm were detected by ColonCAR version 1.2. All polyps missed by experts 1 (n = 4) and 2 (n = 3) and 12 (86%) of 14 polyps missed by expert 3 were detected by ColonCAR version 1.2. The median number of false-positive highlights per case was 13, of which 91% were easily dismissed. CONCLUSION ColonCAR version 1.2 is sensitive for polyp detection, with a clinically acceptable false-positive rate. ColonCAR version 1.2 has a synergistic effect to the reviewer alone, and its standalone performance may exceed even that of experts.

Computer-aided detection for CT colonography: incremental benefit of observer training

The purpose of this study was to investigate the incremental effect of focused training on observer performance when using computer-assisted detection (CAD) software to interpret CT colonography (CTC). Six radiologists who were relatively inexperienced with CTC interpretation underwent 1 day of focused training before reading 20 patient datasets with the assistance of CAD software (ColonCAR 1.3, Medicsight PLC). Sensitivity, specificity and interpretation times were determined and compared with previous performance when reading the same datasets but without the benefit of focused training, using the binomial exact test and Wilcoxons signed rank test. Per-polyp sensitivity improved after training by 18% overall (95% confidence interval (CI): 14-24%, p<0.001) and was greatest for polyps of 6-9 mm (26%, 95% CI: 18-34%, p<0.001). Absolute sensitivity was 23% (9-36%), 51% (33-71%) and 74% (44-100%) for polyps of <or=5 mm, 6-9 mm and >or=10 mm, respectively. Specificity fell significantly after focused training (median of 5.5 false positives per 20 datasets (interquartile range (IQR): 4-6) post-training vs median of 2.5 (IQR: 1-5) pre-training, p = 0.03). Interpretation time also increased significantly after training (from a median of 9.3 min (IQR: 9.3-14.5 min) to a median of 17.1 min (IQR: 15.4-19.4 min), p = 0.03). In conclusion, one day of training increases observer polyp sensitivity when using CAD for CTC at the expense of increased reporting time and reduction in specificity.

Patency of side branches after peripheral placement of metallic biliary endoprostheses.

During a 28-month period, the authors placed 91 Wallstent endoprostheses in 55 patients with malignant obstructive jaundice. Five patients developed recurrent jaundice between 2 and 60 weeks after stent insertion due to stent occlusion by tumor overgrowth on seven occasions. To assess long-term segmental side-branch drainage through the walls of such endoprostheses, the cholangiograms obtained following stent occlusion were reviewed. In all five patients, evidence of drainage of intrahepatic ducts through the side of the mesh was observed. Although the number of patients in the series is small, this initial experience suggests that long metallic endoprostheses can be placed peripherally in the intrahepatic bile ducts without the potential risk of infection or occlusion of undrained, noninvolved segments. This policy may delay or prevent endoprosthesis occlusion in many patients.

Acute cholecystitis: radiological management

Acute cholecystitis is a common condition which may be difficult to diagnose with confidence on clinical grounds alone. A large number of techniques are now available for imaging the gall bladder but, in practice, ultrasonography and cholescintigraphy are of greatest value. The former is cheap, readily available and features such as the presence of gall stones, gall bladder wall inflammation and a positive sonographic Murphy sign strongly suggest the diagnosis of acute cholecystitis. In addition to its diagnostic uses, ultrasonographically guided percutaneous cholecystostomy provides an alternative and sometimes life-saving form of treatment in those patients who are unfit for surgery. Cholescintigraphy is a highly accurate, non-invasive method for assessing patency of the cystic duct but is not always available in the emergency situation and takes longer to perform than an ultrasound examination. Acute cholecystitis, however, has many manifestations and may be calculous or acalculous, be associated with a patent or obstructed cystic duct, and may be complicated or uncomplicated. Imagining modalities other than those mentioned above may be useful in certain circumstances and this chapter aims to present the advantages and disadvantages of each technique in order to provide guidance for the clinician caring for a patient with suspected acute cholecystitis.

Metallic stents in biliary disease

The development of self-expanding metallic endoprostheses which can be implanted easily, with minimal trauma, has revolutionized the non-surgical treatment of both benign and malignant biliary strictures. The Wallstent (Medinvent SA, Lausanne, Switzerland), a pliable, tubular stainless steel mesh, is the metallic stent of choice for treatment of malignant strictures and can be implanted in a single session resulting in a shortened hospital stay for patients undergoing palliation of irresectable biliary tumours. Although follow-up is currently rather limited, it appears that the occlusion rate of Wallstents will be lower than that of plastic endoprostheses and no cases of stent migration have been reported. The Gianturco zigzag stent (Cook Inc., Bloomington, Ind, USA) should not be used in malignant strictures because of rapid occlusion due to tumour ingrowth through the struts. However, it exerts a strong, continuous, outward radial force and is ideally suited for use in the small, but difficult to manage, group of patients with benign biliary strictures which recur despite surgery and repeated balloon dilations.

Automatic identification of colonic polyp in high-resolution CT images

Automatic polyp detection is a challenging task as polyps come in different sizes and shape. The detection generally consists of colon segmentation, identification of suspected polyps and classification. Classification involves discriminating polyps from among many suspected regions based on a number of features extracted from the detected regions. This paper presents the work on the first two stages of the detection. For the colon segmentation, the fuzzy connectivity region growing technique is used while for the identification of suspected polyps concave region searching is applied. A rule-based filtering based on 3D volumetric features is used to reduce a large number of non-polyp structures (false positives). The method is fast, robust and validated with a number of high-resolution colon datasets.

Power Doppler Quantification in assessing Gestational Trophoblastic Neoplasia.

PURPOSE  The FIGO score cannot accurately stratify low-risk gestational trophoblastic neoplasia (GTN) patients who develop chemoresistance to single agent methotrexate chemotherapy. Tumour vascularisation is a key risk factor and its quantification may provide non-invasive way of complementing risk assessment. MATERIALS AND METHODS  187 FIGO-staged, low-risk GTN patients were prospectively recruited. Power Doppler ultrasound was analysed using a quantification program. Four diagnostic indicators were obtained comprising the number of colour pixels (NCP), mean dB, power Doppler quantification (PDQ), and percentage of colour pixels (%CP). Each indicator performance was assessed to determine if they could distinguish the subset of low-risk patients who became chemoresistant. RESULTS  There were 111 non-resistant and 76 resistant patients. NCP performed best at distinguishing these two groups where the non-resistant group had an average 3435 (± 2060) pixels and the resistant group 6151 (± 3192) pixels (p < 0.001). PDQ and %CP showed significant differences (p < 0.001) but had poorer performance (area under ROC curves were 72 % and 67 % respectively compared with 75 % for NCP). The mean dB index was not significantly different (p = 0.133). CONCLUSION  Power Doppler ultrasound quantification shows potential for non-invasive assessment of tumour vascularity and can distinguish low-risk GTN patients who become chemoresistant from those who have an uncomplicated course with first line treatment.

Computer-assisted detection (CAD) of pulmonary nodules on thoracic CT scans using image processing and classification techniques

Computer assisted methods for the detection of pulmonary nodules have become more important as the resolution of CT scanners has increased and as more accurate and reproducible detections are needed. In this paper we describe the results of a CAD system for the detection of lung nodules and compare them against the interpretations of three independent radiologists.