Jan H. C. L. Hendriks

Automated classification of clustered microcalcifications into malignant and benign types.

The objectives in this study were to design and test a fully automated method for classification of microcalcification clusters into malignant and benign types, and to compare the methods performance with that of radiologists. A novel aspect of the approach is that the relative location and orientation of clusters inside the breast was taken into account for feature calculation. Furthermore, correspondence of location of clusters in mediolateral oblique (MLO) and cranio-caudal (CC) views, was used in feature calculation and in final classification. Initially, microcalcifications were automatically detected by using a statistical method based on Bayesian techniques and a Markov random field model. To determine malignancy or benignancy of a cluster, a method based on two classification steps was developed. In the first step, classification of clusters was performed and in the second step a patient based classification was done. A total of 16 features was used in the study. To identify meaningful features, a feature selection was applied, using the area under the receiver operating characteristic (ROC) curve (Az value) as a criterion. For classification the k-nearest-neighbor method was used in a leave-one-patient-out procedure. A database of 192 mammograms with 280 true positive detected microcalcification clusters was used for evaluation of the method. The set consisted of cases that were selected for diagnostic work up during a 4 year period of screening in the Nijmegen region (The Netherlands). Because of the high positive predictive value in the screening program (50%), this set did not contain obvious benign cases. The methods best patient-based performance on this set corresponded with Az = 0.83, using nine features. A subset of the data set, containing mammograms from 90 patients, was used for comparing the computer results to radiologists performance. Ten radiologists read these cases on a light-box and assessed the probability of malignancy for each patient. All participants had experience in clinical mammography and participated in our observer study during the last 2 days of a 2-week training session leading to screening mammography certification. Results on the subset showed that the methods performance (Az = 0.83) was considerably higher than that of the radiologists (Az = 0.63).

Spatial resolution in digital mammography.

RATIONALE AND OBJECTIVES.Digital acquisition systems currently available limit spatial resolution in digital mammography to roughly 0.1 mm/pixel. The objective of this study is to determine if high-quality mammography is possible at this resolution. METHODS.The influence of spatial resolution on diagnostic quality was investigated by comparing observer performance on film to that on digitized film. A 0.1-mm sampling distance was used for digitization. Detection of mammographic details was studied by measuring threshold contrast as a function of detail size for small circular objects in the range of 0.12 to 2.5 mm. Characterization of microcalcifications was investigated in a receiver operating characteristic (ROC) study, in which 10 radiologists read 72 mammographic details with microcalcifications, both digitally and on film. RESULTS.Digitization improved the detectability of the larger, low contrast objects, whereas for small objects the detectability did not change. The authors found that even under the most optimal circumstances, isolated spherical calcifications with diameters smaller than 0.13 mm are not detectable with film-screen mammography, despite its resolution limit of 15 line patterns per mm (lp/mm). The ability to characterize microcalcification clusters did not change significantly with digitization. However, the results suggest that differentiation of benign from malignant cases decreases slightly, and that characterization of different types of malignancies somewhat improves by digitization. Mean differences between the two modalities were considerably smaller than the interobserver variability. CONCLUSION.A relatively low spatial resolution of 0.1 mm/ pixel does not prohibit high-quality diagnostic performance in digital mammography.

Personality factors and breast cancer risk: A 13-year follow-up

Consistent scientific evidence on the possible relationship between psychologic variables and breast cancer development is lacking. In 1996, our group first reported on the present prospective, longitudinal study. We found a weak association between a high score on the antiemotionality scale (indicating an absence of emotional behavior or a lack of trust in ones own feelings) and the development of breast cancer. No associations were found between any of the other 10 studied personality traits and breast cancer development. However, the study had a relatively short follow-up and did not investigate interaction effects between various personality traits. Therefore, the current follow-up study was conducted with the same cohort, which included the 9705 women who attended a biennial population surveillance program for breast cancer and completed a self-report personality questionnaire between January 1, 1989, and December 31, 1990. Women who developed breast cancer during the period from May 17, 1995, through January 1, 2003, formed the case group (n = 217) and were compared with age-matched women without breast cancer who formed the control group (n = 868) with regard to personality traits and medical risk factors for breast cancer. None of the personality factors were statistically significantly associated with an increased risk of breast cancer, with or without adjusting for the medical risk factors. Also, the occurrence of a combination of various personality traits (eg, a so-called cancer-prone personality) was not related to breast cancer development.

Does experience in colposcopy improve identification of high grade abnormalities

OBJECTIVEnThis study investigates whether experience in colposcopy improves identification of high grade abnormalities. The sensitivity and positive predictive value (PPV) of colposcopy in identifying high grade intra-epithelial lesions (HSIL) performed by relatively inexperienced as compared to experienced colposcopists are evaluated.nnnSTUDY DESIGNnOf 18,421 colposcopies performed at the Royal Womens Hospital, Melbourne, Australia, between 1999 and 2004 by 5 senior and 11 junior colposcopists, the colposcopic impression was correlated with the histopathology result of the biopsy taken at 6020 colposcopies, with respect to the experience of the colposcopist.nnnRESULTSnColposcopy had a 60% sensitivity and 60% PPV in identifying HSIL in this study. In case of a high-grade referral smear the sensitivity and PPV in identifying HSIL were, respectively 76% and 73%, compared with 26% and 48% in case of a low-grade referral smear, no difference in overall colposcopic performance between experienced and inexperienced colposcopists was observed. However, the sensitivity of identifying HSIL was significantly higher with inexperienced colposcopists, and the PPV was significantly higher with experienced colposcopists.nnnCONCLUSIONnIn this study experience did not improve colposcopic performance, but differences in colposcopic strategy between the two groups were noted. The rather low overall sensitivity and PPV of colposcopy in identifying HSIL, especially in case of a low-grade referral smear, indicate that the role of colposcopy in the detection and treatment of cervical abnormalities is to assess size, site, and extent of an abnormality, rather than to assess the severity of this abnormality. Histology must remain the gold standard for treatment.

Effect of soft-copy display supported by CAD on mammography screening performance.

Diagnostic performance and reading speed for conventional mammography film reading is compared to reading digitized mammograms on a dedicated workstation. A series of mammograms judged negative at screening and corresponding priors were collected. Half were diagnosed as cancer at the next screening, or earlier for interval cancers. The others were normal. Original films were read by fifteen experienced screening radiologists. The readers annotated potential abnormalities and estimated their likelihood of malignancy. More than 1xa0year later, five radiologists reread a subset of 271 cases (88 cancer cases having visible signs in retrospect and 183 normals) on a mammography workstation after film digitization. Markers from a computer-aided detection (CAD) system for microcalcifications were available to the readers. Performance was evaluated by comparison of Az-scores based on ROC and multiple-Reader multiple-case (MRMC) analysis, and localized receiver operating characteristic (LROC) analysis for the 271 cases. Reading speed was also determined. No significant difference in diagnostic performance was observed between conventional and soft-copy reading. Average Az-scores were 0.83 and 0.84 respectively. Soft-copy reading was only slightly slower than conventional reading. Using a mammography workstation including CAD for detection of microcalcifications, soft-copy reading is possible without loss of quality or efficiency.

Analysis of Changes in Masses Using Contrast and Size Measures

One of the techniques used by radiologist to detect developing abnormalities is comparison of the current screening mammogram with previous ones. An observed change from a previous examination may bring attention to subtle signs of malignancy such as a new or growing mass or new or increasing calcifications that may have been overlooked otherwise [1].

Optimized perception of lesion growth in mammograms using digital display

In this study we investigate two ways of presenting prior and current mammograms on a mammography workstation: next to each other and alternating at the same display (toggle). The experiment consisted of 420 trials with prior-current mammogram pairs, displayed on a dedicated mammography workstation. In two-alternative forced-choice (2AFC) experiment, observers were asked to select the image containing the largest lesion. The stimuli were created by pasting extracted lesions into normal mammograms. Results showed that the observers preformed more accurate in selecting the largest lesion when using the toggle option.

Optimized soft-copy display of digitized mammograms

Digitization and CRT display reduce sharpness of mammograms. To ensure image quality on a CRT, comparable to the quality of original films, a modified unsharp-masking (USM) algorithm is proposed to correct for this reduction. This study evaluates the clinical value of this algorithm and determines the optimal setting of its parameters. Eight complete mammographic cases were processed by a modified USM algorithm with 19 settings for three parameters, resulting in 152 stimuli. All cases showed a clearly visible mass; five also contained microcalcifications. The modification of the standard USM algorithm consisted of selectively improving low contrasts. Moreover, the USM enhancement was made grey value dependent to avoid clipping. Four experienced screening radiologists and four physicists (having experience with mammography imaging) rated all mammograms on a 1-10 point scale, according to image quality and suitability for diagnosis. The images were randomly presented. Before the experiment started, a subset of the images was shown to familiarize the observers to the range of images and parameter settings. For a contrast enhancement factor of about 0.4, the processed mammograms appeared to be significantly better than the original digitized mammograms (P<.001). Differences in the results for the radiologists and the physicists were small.

Using Information from Two Mammographic Views to Improve Computer-Aided Detection of Mass Lesions

A new approach to combine information from two Mammographic views for CAD of mass lesions is presented. Suspect regions in corresponding views are linked using feature probability distributions, and feature vectors are combined. Two k-Nearest Neighbor classifiers, one for single regions and one for regions with a corresponding region in the other view, are compared. Preliminary results show that this two view information improves the classifier performance.

The Comparison of Two Analgesic Regimes after Ambulatory Surgery: An Observational Study

Over the past 15 years, the number of ambulatory surgical procedures worldwide has increased continuously. Studies show that 30% to 40% of the patients experience moderate‐to‐severe pain in the first 48 hours. The objective of this observational study is to compare the percentage of moderate‐to‐severe pain, side effects, and the use of escape medication of two different analgesic regimes after ambulatory surgery.