An Efficient Segmentation Method for Ultrasound Images based on a Semi-supervised Approach and Patch-based Features

Segmenting ultrasound images is a challenging problemwhere standard unsupervised segmentation methods such asthe well-known Chan-Vese method fail. We propose in thispaper an efficient segmentation method for this class ofimages. Our proposed algorithm is based on asemi-supervised approach (user labels) and the use ofimage patches as data features. We also consider thePearson distance between patches, which has been shown tobe robust w.r.t speckle noise present in ultrasoundimages. Our results on phantom and clinical data show avery high similarity agreement with the ground truthprovided by a medical expert.

Lessons From the Swiss Medical Board Recommendation Against Mammography Screening Programs

When the US Preventive Services Task Force (USPSTF) in 2009 recommended against universal breast cancer screening with mammography in women aged 40 to 49 years, some scientists, radiologists, politicians, and patients strongly objected. The controversy has been called the "mammography wars." The latest chapter in these wars comes from the Swiss Medical Board, which is mandated by the Conference of Health Ministers of the Swiss Cantons, the Swiss Medical Association, and the Swiss Academy of Medical Sciences to conduct health technology assessments. In a February 2014 report, the Swiss Medical Board stated that new systematic mammography screening programs should not be introduced, irrespective of the age of the women, and that existing programs should be discontinued. The board's main argument was that the absolute reduction in breast cancer mortality was low and that the adverse consequences of the screening were substantial. The absolute risk reduction in breast cancer mortality has been estimated by the board at 0.16% for women screened during 6.2 years and followed-up over 13 years, based on the results of a recent Cochrane Review. The adverse consequences include falsepositive test results, overdiagnosis and overtreatment of patients, and high costs, including the expense of follow-up testing and procedures.

Whole-body 3D T1-weighted MR imaging in patients with prostate cancer: feasibility and evaluation in screening for metastatic disease.

PURPOSE: To develop and assess the diagnostic performance of a three-dimensional (3D) whole-body T1-weighted magnetic resonance (MR) imaging pulse sequence at 3.0 T for bone and node staging in patients with prostate cancer. MATERIALS AND METHODS This prospective study was approved by the institutional ethics committee; informed consent was obtained from all patients. Thirty patients with prostate cancer at high risk for metastases underwent whole-body 3D T1-weighted imaging in addition to the routine MR imaging protocol for node and/or bone metastasis screening, which included coronal two-dimensional (2D) whole-body T1-weighted MR imaging, sagittal proton-density fat-saturated (PDFS) imaging of the spine, and whole-body diffusion-weighted MR imaging. Two observers read the 2D and 3D images separately in a blinded manner for bone and node screening. Images were read in random order. The consensus review of MR images and the findings at prospective clinical and MR imaging follow-up at 6 months were used as the standard of reference. The interobserver agreement and diagnostic performance of each sequence were assessed on per-patient and per-lesion bases. RESULTS: The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were significantly higher with whole-body 3D T1-weighted imaging than with whole-body 2D T1-weighted imaging regardless of the reference region (bone or fat) and lesion location (bone or node) (P < .003 for all). For node metastasis, diagnostic performance (area under the receiver operating characteristic curve) was higher for whole-body 3D T1-weighted imaging (per-patient analysis; observer 1: P < .001 for 2D T1-weighted imaging vs 3D T1-weighted imaging, P = .006 for 2D T1-weighted imaging + PDFS imaging vs 3D T1-weighted imaging; observer 2: P = .006 for 2D T1-weighted imaging vs 3D T1-weighted imaging, P = .006 for 2D T1-weighted imaging + PDFS imaging vs 3D T1-weighted imaging), as was sensitivity (per-lesion analysis; observer 1: P < .001 for 2D T1-weighted imaging vs 3D T1-weighted imaging, P < .001 for 2D T1-weighted imaging + PDFS imaging vs 3D T1-weighted imaging; observer 2: P < .001 for 2D T1-weighted imaging vs 3D T1-weighted imaging, P < .001 for 2D T1-weighted imaging + PDFS imaging vs 3D T1-weighted imaging). CONCLUSION: Whole-body MR imaging is feasible with a 3D T1-weighted sequence and provides better SNR and CNR compared with 2D sequences, with a diagnostic performance that is as good or better for the detection of bone metastases and better for the detection of lymph node metastases.

Prévention primaire et dépistage chez l'adulte: mise à jour 2006 [Primary prevention and screening in adults: update 2006]

Several diseases can be prevented either by primary prevention, such as immunisation or behavioural counselling, or secondary prevention such as screening. The new clinical recommendations include screening of abdominal aortic aneurysm among male smokers and ex-smokers aged between 65 and 75 years and the extension of breast cancer screening by mammography for women aged between 40 and 49 years, as well as screening for diabetes among patients with hypertension or dyslipidemia.

Thalamic connectivity in patients with essential tremor treated with MR imaging-guided focused ultrasound: in vivo fiber tracking by using diffusion-tensor MR imaging.

PURPOSE: To use diffusion-tensor (DT) magnetic resonance (MR) imaging in patients with essential tremor who were treated with transcranial MR imaging-guided focused ultrasound lesion inducement to identify the structural connectivity of the ventralis intermedius nucleus of the thalamus and determine how DT imaging changes correlated with tremor changes after lesion inducement. MATERIALS AND METHODS: With institutional review board approval, and with prospective informed consent, 15 patients with medication-refractory essential tremor were enrolled in a HIPAA-compliant pilot study and were treated with transcranial MR imaging-guided focused ultrasound surgery targeting the ventralis intermedius nucleus of the thalamus contralateral to their dominant hand. Fourteen patients were ultimately included. DT MR imaging studies at 3.0 T were performed preoperatively and 24 hours, 1 week, 1 month, and 3 months after the procedure. Fractional anisotropy (FA) maps were calculated from the DT imaging data sets for all time points in all patients. Voxels where FA consistently decreased over time were identified, and FA change in these voxels was correlated with clinical changes in tremor over the same period by using Pearson correlation. RESULTS: Ipsilateral brain structures that showed prespecified negative correlation values of FA over time of -0.5 or less included the pre- and postcentral subcortical white matter in the hand knob area; the region of the corticospinal tract in the centrum semiovale, in the posterior limb of the internal capsule, and in the cerebral peduncle; the thalamus; the region of the red nucleus; the location of the central tegmental tract; and the region of the inferior olive. The contralateral middle cerebellar peduncle and bilateral portions of the superior vermis also showed persistent decrease in FA over time. There was strong correlation between decrease in FA and clinical improvement in hand tremor 3 months after lesion inducement (P < .001). CONCLUSION: DT MR imaging after MR imaging-guided focused ultrasound thalamotomy depicts changes in specific brain structures. The magnitude of the DT imaging changes after thalamic lesion inducement correlates with the degree of clinical improvement in essential tremor.

Mammographic screening for breast cancer: background of a pilot program in the Canton of Vaud.

For several years now, substantial efforts have been devoted to the development and the implementation of a screening program for breast cancer in the Canton of Vaud. A four-year pilot phase is now starting, involving two regional hospitals with their catchment areas; women over 50 and under 70 years old will be invited to participate in the program. A double view mammography will be made, with a double reading made by the hospital radiologists; a third reading will be made in case of discrepancy between the two first radiologists. Patients classified as positive for screening (e.g., with a suspect radiological image) will be referred to their practitioner for further diagnosis and treatment. The medical and public health background of this program is discussed, more specifically the reasons for developing a screening program, the choice of mammography rather than other tools, and the need to implement screening as an organized program.

Escarres et dénutrition: dépistage et évaluation de l'état nutritionnel [Pressure ulcers and undernutrition: screening and assessment of nutritional status]

Acquired pressure ulcer is associated with significant human, economic and functional consequences. Its prevalence varies between 3 and 23% in a community hospital and between 7 and 54% in an elderly home residency. Pressure ulcer healing is a complex process which involves numerous cellular and molecular mechanisms. An altered nutritional status is a contributing factor in the development of pressure ulcers and the delay in pressure ulcer healing. The key to management of undernutrition is screening and early intervention. According to the gravity of undernutrition, various degrees of intervention will be required. Systematic oral supplementation with various nutrients may provide benefit in the prevention of pressure ulcers, but further studies have to be completed in human subjects prior to being recommended for the treatment of pressure ulcers.

High prevalence of osteoporosis in Swiss women aged 60 and older: a 2-year pilot screening campaign.

Background: Osteoporosis (OP) is frequent in postmenopausal women, but remains underdiagnosed and undertreated. In Switzerland, DXA is not reimbursed by the insurances for screening, even if it is recommended to test women's Bone Mineral Density (BMD) at the age of 65. Methods: To assess the feasibility of a screening program for OP, the Bone diseases center of Lausanne has been mandated to perform a 2-year information and screening campaign (3 days per months) for women age 60 and older through the state of Vaud using a mobile unit for bone assessment. This project is still ongoing. Women are informed by media for dates and screening locations. Appointments are taken by phone. Women known for osteoporosis or already treated are excluded. During the evaluation every women is assessed by a questionnaire for risk factors, by a DXA measurement (Discovery C, Hololgic), and by Vertebral Fracture Assessment (VFA) for Genant's grades 2 and 3 prevalent vertebral fractures (VF). Women are considered at high risk of fracture if they have a hip fracture, a VF, another fragility fracture with a BMD T-score ≤-2 or a BMD T-score ≤-2.5. Results: After 17 months (50 days of screening), 752 women were assessed, mean age 66±6 yrs, mean BMI 26±5 kg/m2, mean lowest T-score -1.6±1.0 SD. 215 women (29%) were considered at high risk, 92 of them (12%) having established OP and 50 (7%) having one or more fragility VF. VF were unknown for 83% of the women and discovered by VFA. The number needed to screen (NNS) were 3.5 for high risk women, 8.2 for established OP and 15 for VF. Conclusions: After near ¾ of the project, prevalence of women at high risk of fracture was high, with a NNS below 4. Knowing the global cost of OP and that current treatment have a high efficacy for fracture risk reduction, such a screening program could have a positive economic impact. VFA allowed discovering many women with unknown VF, who were at very high risk of further fractures. A systematic screening for VF should be added to BMD measurements after the age of 60.