Mattias Ohlsson

A Novel Automated Platform for Quantifying the Extent of Skeletal Tumour Involvement in Prostate Cancer Patients Using the Bone Scan Index

BACKGROUND There is little consensus on a standard approach to analysing bone scan images. The Bone Scan Index (BSI) is predictive of survival in patients with progressive prostate cancer (PCa), but the popularity of this metric is hampered by the tedium of the manual calculation. OBJECTIVE Develop a fully automated method of quantifying the BSI and determining the clinical value of automated BSI measurements beyond conventional clinical and pathologic features. DESIGN, SETTING, AND PARTICIPANTS We conditioned a computer-assisted diagnosis system identifying metastatic lesions on a bone scan to automatically compute BSI measurements. A training group of 795 bone scans was used in the conditioning process. Independent validation of the method used bone scans obtained ≤3 mo from diagnosis of 384 PCa cases in two large population-based cohorts. An experienced analyser (blinded to case identity, prior BSI, and outcome) scored the BSI measurements twice. We measured prediction of outcome using pretreatment Gleason score, clinical stage, and prostate-specific antigen with models that also incorporated either manual or automated BSI measurements. MEASUREMENTS The agreement between methods was evaluated using Pearsons correlation coefficient. Discrimination between prognostic models was assessed using the concordance index (C-index). RESULTS AND LIMITATIONS Manual and automated BSI measurements were strongly correlated (ρ=0.80), correlated more closely (ρ=0.93) when excluding cases with BSI scores≥10 (1.8%), and were independently associated with PCa death (p<0.0001 for each) when added to the prediction model. Predictive accuracy of the base model (C-index: 0.768; 95% confidence interval [CI], 0.702-0.837) increased to 0.794 (95% CI, 0.727-0.860) by adding manual BSI scoring, and increased to 0.825 (95% CI, 0.754-0.881) by adding automated BSI scoring to the base model. CONCLUSIONS Automated BSI scoring, with its 100% reproducibility, reduces turnaround time, eliminates operator-dependent subjectivity, and provides important clinical information comparable to that of manual BSI scoring.

Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room

OBJECTIVE Patients with suspicion of acute coronary syndrome (ACS) are difficult to diagnose and they represent a very heterogeneous group. Some require immediate treatment while others, with only minor disorders, may be sent home. Detecting ACS patients using a machine learning approach would be advantageous in many situations. METHODS AND MATERIALS Artificial neural network (ANN) ensembles and logistic regression models were trained on data from 634 patients presenting an emergency department with chest pain. Only data immediately available at patient presentation were used, including electrocardiogram (ECG) data. The models were analyzed using receiver operating characteristics (ROC) curve analysis, calibration assessments, inter- and intra-method variations. Effective odds ratios for the ANN ensembles were compared with the odds ratios obtained from the logistic model. RESULTS The ANN ensemble approach together with ECG data preprocessed using principal component analysis resulted in an area under the ROC curve of 80%. At the sensitivity of 95% the specificity was 41%, corresponding to a negative predictive value of 97%, given the ACS prevalence of 21%. Adding clinical data available at presentation did not improve the ANN ensemble performance. Using the area under the ROC curve and model calibration as measures of performance we found an advantage using the ANN ensemble models compared to the logistic regression models. CONCLUSION Clinically, a prediction model of the present type, combined with the judgment of trained emergency department personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS.

Evaluation of a previously suggested plasma biomarker panel to identify Alzheimer's disease.

There is an urgent need for biomarkers in plasma to identify Alzheimers disease (AD). It has previously been shown that a signature of 18 plasma proteins can identify AD during pre-dementia and dementia stages (Ray et al, Nature Medicine, 2007). We quantified the same 18 proteins in plasma from 174 controls, 142 patients with AD, and 88 patients with other dementias. Only three of these proteins (EGF, PDG-BB and MIP-1δ) differed significantly in plasma between controls and AD. The 18 proteins could classify patients with AD from controls with low diagnostic precision (area under the ROC curve was 63%). Moreover, they could not distinguish AD from other dementias. In conclusion, independent validation of results is important in explorative biomarker studies.

Track finding with deformable templates — the elastic arms approach

A novel algorithm for particle tracking is presented and evaluated. It is based on deformable templates that converge using a deterministic annealing algorithm. These deformable templates are initialized by Hough transforms. The algorithm, which effectively represents a merger between neuronic decision making and parameter fitting, naturally lends itself to parallel execution. Very good performance is obtained for both non-magnetic and magnetic tracks. For the latter simulated TPC tracks from the CERN DELPHI detector are used.

Detecting acute myocardial infarction in the 12-lead ECG using Hermite expansions and neural networks

We use artificial neural networks (ANNs) to detect signs of acute myocardial infarction (AMI) in ECGs. The 12-lead ECG is decomposed into Hermite basis functions, and the resulting coefficients are used as inputs to the ANNs. Furthermore, we present a case-based method that qualitatively explains the operation of the ANNs, by showing regions of each ECG critical for ANN response. Key ingredients in this method are: (i) a cost function used to find local ECG perturbations leading to the largest possible change in ANN output and (ii) a minimization scheme for this cost function using mean field annealing. Our approach was tested on 2238 ECGs recorded at an emergency department. The obtained ROC areas for ANNs trained with the Hermite representation and standard ECG measurements were 83.4 and 84.3% (P=0.4), respectively. We believe that the proposed method has potential as a decision support system that can provide good advice for diagnosis, as well as providing the physician with insight into the reason underlying the advice.

Artificial neural networks for recognition of electrocardiographic lead reversal.

Misplacement of electrodes during the recording of an electrocardiogram (ECG) can cause an incorrect interpretation, misdiagnosis, and subsequent lack of proper treatment. The purpose of this study was twofold: (1) to develop artificial neural networks that yield peak sensitivity for the recognition of right/left arm lead reversal at a very high specificity; and (2) to compare the performances of the networks with those of 2 widely used rule-based interpretation programs. The study was based on 11,009 ECGs recorded in patients at an emergency department using computerized electrocardiographs. Each of the ECGs was used to computationally generate an ECG with right/left arm lead reversal. Neural networks were trained to detect ECGs with right/left arm lead reversal. Different networks and rule-based criteria were used depending on the presence or absence of P waves. The networks and the criteria all showed a very high specificity (99.87% to 100%). The neural networks performed better than the rule-based criteria, both when P waves were present (sensitivity 99.1%) or absent (sensitivity 94.5%). The corresponding sensitivities for the best criteria were 93.9% and 39.3%, respectively. An estimated 300 million ECGs are recorded annually in the world. The majority of these recordings are performed using computerized electrocardiographs, which include algorithms for detection of right/left arm lead reversals. In this study, neural networks performed better than conventional algorithms and the differences in sensitivity could result in 100,000 to 400,000 right/left arm lead reversals being detected by networks but not by conventional interpretation programs.

Molecular serum portraits in patients with primary breast cancer predict the development of distant metastases

The risk of distant recurrence in breast cancer patients is difficult to assess with current clinical and histopathological parameters, and no validated serum biomarkers currently exist. Using a recently developed recombinant antibody microarray platform containing 135 antibodies against 65 mainly immunoregulatory proteins, we screened 240 sera from 64 patients with primary breast cancer. This unique longitudinal sample material was collected from each patient between 0 and 36 mo after the primary operation. The velocity for each serum protein was determined by comparing the samples collected at the primary operation and then 3–6 mo later. A 21-protein signature was identified, using leave-one-out cross-validation together with a backward elimination strategy in a training cohort. This signature was tested and evaluated subsequently in an independent test cohort (prevalidation). The risk of developing distant recurrence after primary operation could be assessed for each patient, using her molecular portraits. The results from this prevalidation study showed that patients could be classified into high- versus low-risk groups for developing metastatic breast cancer with a receiver operating characteristic area under the curve of 0.85. This risk assessment was not dependent on the type of adjuvant therapy received by the patients. Even more importantly, we demonstrated that this protein signature provided an added value compared with conventional clinical parameters. Consequently, we present here a candidate serum biomarker signature able to classify patients with primary breast cancer according to their risk of developing distant recurrence, with an accuracy outperforming current procedures.

Computer-Assisted Interpretation of Planar Whole-Body Bone Scans

The purpose of this study was to develop a computer-assisted diagnosis (CAD) system based on image-processing techniques and artificial neural networks for the interpretation of bone scans performed to determine the presence or absence of metastases. Methods: A training group of 810 consecutive patients who had undergone bone scintigraphy due to suspected metastatic disease were included in the study. Whole-body images, anterior and posterior views, were obtained after an injection of 99mTc-methylene diphosphonate. The image-processing techniques included algorithms for automatic segmentation of the skeleton and automatic detection and feature extraction of hot spots. Two sets of artificial neural networks were used to classify the images, 1 classifying each hot spot separately and the other classifying the whole bone scan. A test group of 59 patients with breast or prostate cancer was used to evaluate the CAD system. The patients in the test group were selected to reflect the spectrum of pathology found in everyday clinical work. As the gold standard for the test group, we used the final clinical assessment of each case. This assessment was based on follow-up scans and other clinical data, including the results of laboratory tests, and available diagnostic images, such as from MRI, CT, and radiography, from a mean follow-up period of 4.8 y. Results: The CAD system correctly identified 19 of the 21 patients with metastases in the test group, showing a sensitivity of 90%. False-positive classification of metastases was made in 4 of the 38 patients not classified as having metastases by the gold standard, resulting in a specificity of 89%. Conclusion: A completely automated CAD system can be used to detect metastases in bone scans. Application of the method as a clinical decision support tool appears to have significant potential.

Detection of frequently overlooked electrocardiographic lead reversals using artificial neural networks

Artificial neural networks can be used to recognize lead reversals in the 12-lead electrocardiogram at very high specificity, and the sensitivity is much higher than that of a conventional interpretation program. The neural networks developed in this and an earlier study for detection of lead reversals, in combination with an algorithm for the right arm/right foot lead reversal, would recognize approximately 75% of lead reversals encountered in clinical practice.

WeAidU-a decision support system for myocardial perfusion images using artificial neural networks

This paper presents a computer-based decision support system for automated interpretation of diagnostic heart images (called WeAidU), which is made available via the Internet. The system is based on image processing techniques, artificial neural networks (ANNs) and large well-validated medical databases. We present results using artificial neural networks, and compare with two other classification methods, on a retrospective data set containing 1320 images from the clinical routine. The performance of the artificial neural networks detecting infarction and ischemia in different parts of the heart, measured as areas under the receiver operating characteristic curves, is in the range 0.83-0.96. These results indicate a high potential for the tool as a clinical decision support system.