Computer-aided diagnosis in two-phase 201Tl-SPECT of thoracic lesions.

AIM: The retention index, a traditionally quantitative analysis of two-phase (201)Tl single photon emission computed tomography (SPECT) of the chest, is manually calculated by experienced physicians from comparable 2-D ROI. However, a 3-D ROI would provide more information than a 2-D ROI extracted from a single frame of SPECT. We propose a new diagnostic system, computer-aided diagnosis (CAD), to automatically detect suspicious lesions as 3-D objects on chest (201)Tl-SPECT, and assist the physician in interpreting these images. PATIENTS, METHODS: Seventy patients with thoracic lesions and confirmed diagnoses were enrolled to test this automatic CAD system. The reliability of the CAD system in detecting lesions as 3-D objects was compared to the 2-D ROI of (201)Tl-SPECT found by the manually visualized method. Furthermore, we also proposed a novel index, the retention index using the heart (RIH), to differentiate high retention (slow clearance, increasing target to heart ratio) as a criterion for a malignant lesion, from low retention (faster clearance, small or no increase of the target to heart ratio) for benign lesions. RESULTS: The CAD system can achieve a detection rate of 100% in automatically searching for thoracic lesions in (201)Tl-SPECT. In diagnostic performance, the CAD system with the RIH of comparable 3-D objects has an area under the ROC curve of 0.86, higher than the 0.78 of the traditional RI method (p=0.198). CONCLUSION: The CAD system of two-phase (201)Tl-SPECT is a promising tool for detecting and diagnosing thoracic lesions with a diagnostic accuracy of 0.81.

Microcalcification detection in 3-d breast ultrasound.

The appearance of cluster of microcalcifications in mammography or sonography is an important indicator for malignancy. Microcalcifications are calcium deposits, which can be identified as tiny areas that are slightly brighter than surrounding tissue. Detection of mammographic microcalcification has been proposed in many studies. Since a microcalcification cluster is a three-dimensional (3-D) entity, its projection onto a two-dimensional (2-D) image results in a loss of spatial information and may also cause superimposition of individual calcifications within the cluster. This paper aims to use the 3-D ultrasound to determine microcalcifications. In each slice, the proposed method adopts the top-hat filter to find bright spots, and employs four 2-D criteria to select the spots as candidate microcalcifications. Finally, spots appearing in sequent slices at the same position are considered as a microcalcification. We suggest using a computer automatically to detect the microcalcification being feasible and microcalcifications being a very important criterion of malignancy on future developing the computer-aided diagnosis for ultrasound. In the future, this technique can be adopted in a computer-aided diagnosis system combined with other diagnosis features for improving the diagnosis performance.

Data mining with decision trees for diagnosis of breast tumor in medical ultrasonic images.

To increase the ability of ultrasonographic (US) technology for the differential diagnosis of solid breast tumors, we describe a novel computer-aided diagnosis (CADx) system using data mining with decision tree for classification of breast tumor to increase the levels of diagnostic confidence and to provide the immediate second opinion for physicians. Cooperating with the texture information extracted from the region of interest (ROI) image, a decision tree model generated from the training data in a top-down, general-to-specific direction with 24 co-variance texture features is used to classify the tumors as benign or malignant. In the experiments, accuracy rates for a experienced physician and the proposed CADx are 86.67% (78/90) and 95.50% (86/90), respectively.

Texture analysis of breast tumors on sonograms.

We performed a feasibility study to determine if the texture features extracted from sonograms can be used to predict malignant or benign breast pathology by the proposed artificial neural network and to compare the diagnostic results with the radiologists' results. A total of 1,020 images (4 different rectangular regions from the 2 orthogonal imaging planes of each tumor) from 255 patients were used as samples. When a sonogram was performed, 1 physician identified the region of interest in the sonogram; then, a neural network model, using 24 autocorrelation texture features, classified the tumor as benign or malignant. Three radiologists who were unfamiliar with the samples also classified these images. The receiver operating characteristic (ROC) area index for the proposed neural network system is 0.9840 +/- 0.0072. The neural network identified 35 of 36 malignancies and 211 of 219 benign tumors using all 4 regions of interest. The radiologists, on average, identified 19 of 36 malignancies, with 12 tumors called indeterminate and 4 tumors called benign. We conclude that benign and malignant breast tumors can be distinguished using interpixel correlation in digital ultrasonic images.

Computer-aided diagnosis for surgical office-based breast ultrasound.

HYPOTHESIS: The computer-aided diagnostic system is an intelligent system with great potential for categorizing solid breast nodules. It can be used conveniently for surgical office-based digital ultrasonography (US) of the breast. DESIGN: Retrospective, nonrandomized study. SETTING: University teaching hospital. PATIENTS: We retrospectively reviewed 243 medical records of digital US images of the breast of pathologically proved, benign breast tumors from 161 patients (ie, 136 fibroadenomas and 25 fibrocystic nodules), and carcinomas from 82 patients (ie, 73 invasive duct carcinomas, 5 invasive lobular carcinomas, and 4 intraductal carcinomas). The digital US images were consecutively recorded from January 1, 1997, to December 31, 1998. INTERVENTION: The physician selected the region of interest on the digital US image. Then a learning vector quantization model with 24 autocorrelation texture features is used to classify the tumor as benign or malignant. In the experiment, 153 cases were arbitrarily selected to be the training set of the learning vector quantization model and 90 cases were selected to evaluate the performance. One experienced radiologist who was completely blind to these cases was asked to classify these tumors in the test set. MAIN OUTCOME MEASURE: Contribution of breast US to diagnosis. RESULTS: The performance comparison results illustrated the following: accuracy, 90%; sensitivity, 96.67%; specificity, 86.67%; positive predictive value, 78.38%; and negative predictive value, 98.11% for the computer-aided diagnostic (CAD) system and accuracy, 86.67%; sensitivity, 86.67%; specificity, 86.67%; positive predictive value, 76.47%; and negative predictive value, 92.86% for the radiologist. CONCLUSION: The proposed CAD system provides an immediate second opinion. An accurate preoperative diagnosis can be routinely established for surgical office-based digital US of the breast. The diagnostic rate was even better than the results of an experienced radiologist. The high negative predictive rate by the CAD system can avert benign biopsies. It can be easily implemented on existing commercial diagnostic digital US machines. For most available diagnostic digital US machines, all that would be required for the CAD system is only a personal computer loaded with CAD software.

Breast cancer diagnosis using self-organizing map for sonography.

The purpose of this study was to evaluate the performance of neural network model self-organizing maps (SOM) in the classification of benign and malignant sonographic breast lesions. A total of 243 breast tumors (82 malignant and 161 benign) were retrospectively evaluated. When a sonogram was performed, the analog video signal was captured to obtain a digitized sonographic image. The physician selected the region of interest in the sonography. An SOM model using 24 autocorrelation texture features classified the tumor as benign or malignant. In the experiment, cases were sampled with k-fold cross-validation (k = 10) to evaluate the performance using receiver operating characteristic (ROC) curves. The ROC area index for the proposed SOM system is 0.9357 +/- 0.0152, the accuracy is 85. 6%, the sensitivity is 97.6%, the specificity is 79.5%, the positive predictive value is 70.8%, and the negative predictive value is 98. 5%. This computer-aided diagnosis system can provide a useful tool and its high negative predictive value could potentially help avert benign biopsies.

Computer-aided diagnosis applied to US of solid breast nodules by using neural networks.

PURPOSE: To increase the capabilities of ultrasonographic (US) technology for the differential diagnosis of solid breast tumors by using a neural network. MATERIALS AND METHODS: One hundred forty US images of solid breast nodules were evaluated. When a sonogram was obtained, an analog video signal from the VCR output of the scanner was transmitted to a notebook computer. A frame grabber connected to the printer port of the computer was then used to digitize the data. The suspicious tumor region on the digitized US image was manually selected. The texture information of the subimage was extracted, and a neural network classifier with autocorrelation features was used to classify the tumor as benign or malignant. In this experiment, 140 pathologically proved tumors (52 malignant and 88 benign tumors) were sampled with k-fold cross-validation (k = 10) to evaluate the performance with receiver operating characteristic curves. RESULTS: The accuracy of neural networks for classifying malignancies was 95.0% (133 of 140 tumors), the sensitivity was 98% (51 of 52), the specificity was 93% (82 of 88), the positive predictive value was 89% (51 of 57), and the negative predictive value was 99% (82 of 83). CONCLUSION: This system differentiated solid breast nodules with relatively high accuracy and helped inexperienced operators to avoid misdiagnoses. Because the neural network is trainable, it could be optimized if a larger set of tumor images is supplied.

Adaptive predictive multiplicative autoregressive model for medical image compression.

In this paper, an adaptive predictive multiplicative autoregressive (APMAR) method is proposed for lossless medical image coding. The adaptive predictor is used for improving the prediction accuracy of encoded image blocks in our proposed method. Each block is first adaptively predicted by one of the seven predictors of the JPEG lossless mode and a local mean predictor. It is clear that the prediction accuracy of an adaptive predictor is better than that of a fixed predictor. Then the residual values are processed by the MAR model with Huffman coding. Comparisons with other methods [MAR, SMAR, adaptive JPEG (AJPEG)] on a series of test images show that our method is suitable for reversible medical image compression.

Evaluation of asymmetric poly(vinyl alcohol) membranes for use in artificial islets.

Islets of Langerhans surrounded by a semipermeable membrane to prevent the host immunosystem is a potential way to treat type I diabetes mellitus. In this study, a series of poly (vinyl alcohol) membranes were formed by adding polyethylene glycols to create pores in the skin layer. The permeability study showed the skin layer structure had an influence on the diffusion of low molecular weight glucose, vitamin B12 and insulin. The mass transfer coefficient was improved from 1.04 x 10(-4) to 2.16 x 10(-4) cm/ sec for glucose, from 2.84 x 10(-5) to 8.36 x 10(-5) cm/sec for vitamin B12 and from 1.45 x 10(-6) to 4.15 x 10(-6) cm/sec for insulin, whereas the passage of immunoglobulin G was completely prevented, indicating that these membranes could be effective in protecting islets from immunorejection. Thus such a membrane is an alternative potential material for artificial islets. In addition, we examined the insulin secretory response of islets separated by a poly(vinyl alcohol) membrane. We found that the insulin-secretion rate is relatively rapid compared to the permeation rate of insulin; thus, the process of the artificial islets is insulin-diffusion-controlled.

Finite-state vector quantization by exploiting interband and intraband correlations for subband image coding.

Subband coding (SBC) with vector quantization (VQ) has been shown to be an effective method for coding images at low bit rates. We split the image spectrum into seven nonuniform subbands. Threshold vector quantization (TVQ) and finite state vector quantization (FSVQ) methods are employed in coding the subband images by exploiting interband and intraband correlations. Our new SBC-FSVQ schemes have the advantages of the subband-VQ scheme while reducing the bit rate and improving the image quality. Experimental results are given and comparisons are made using our new scheme and some other coding techniques. In the experiments, it is found that SBC-FSVQ schemes achieve the best peak signal-to-noise ratio (PSNR) performance when compared to other methods at the same bit rate.

Adaptive edge-based side-match finite-state classified vector quantization with quadtree map.

Vector quantization (VQ) is an effective image coding technique at low bit rate. The side-match finite-state vector quantizer (SMVQ) exploits the correlations between neighboring blocks (vectors) to avoid large gray level transition across block boundaries. A new adaptive edge-based side-match finite-state classified vector quantizer (classified FSVQ) with a quadtree map has been proposed. In classified FSVQ, blocks are arranged into two main classes, edge blocks and nonedge blocks, to avoid selecting a wrong state codebook for an input block. In order to improve the image quality, edge vectors are reclassified into 16 classes. Each class uses a master codebook that is different from the codebooks of other classes. In our experiments, results are given and comparisons are made between the new scheme and ordinary SMVQ and VQ coding techniques. As is shown, the improvement over ordinary SMVQ is up to 1.16 dB at nearly the same bit rate, moreover, the improvement over ordinary VQ can be up to 2.08 dB at the same bit rate for the image, Lena. Further, block boundaries and edge degradation are less visible because of the edge-vector classification. Hence, the perceptual image quality of classified FSVQ is better than that of ordinary SMVQ.

Image coding using variable-rate side-match finite-state vector quantization.

Future B-ISDN (broadband integrated services digital network) users will be able to send various kinds of information, such as voice, data, and image, over the same network and send information only when necessary. It has been recognized that variable-rate encoding techniques are more suitable than fixed-rate techniques for encoding images in a B-ISDN environment. A new variable-rate side-match finite-state vector quantization with a block classifier (CSMVQ) algorithm is described. In an ordinary fixed-rate SMVQ, the size of the state codebook is fixed. In the CSMVQ algorithm presented, the size of the state codebook is changed according to the characteristics of the current vector which can be predicted by a block classifier. In experiments, the improvement over SMVQ was up to 1.761 dB at a lower bit rate. Moreover, the improvement over VQ can be up to 3 dB at nearly the same bit rate.

Laser ranging retro-reflector: continuing measurements and expected results.

After successful acquisition in August of reflected ruby laser pulses from the Apollo 11 laser ranging retro-reflector (LRRR) with the telescopes at the Lick and McDonald observatories, repeated measurements of the round-trip travel time of light have been made from the McDonald Observatory in September with an equivalent range precision of +/-2.5 meters. These acquisition period observations demonstrated the performance of the LRRR through lunar night and during sunlit conditions on the moon. Instrumentation activated at the McDonald Observatory in October has yielded a precision of +/-0.3 meter, and improvement to +/-0.15 meter is expected shortly. Continued monitoring of the changes in the earth-moon distance as measured by the round-trip travel time of light from suitably distributed earth stations is expected to contribute to our knowledge of the earth-moon system.

Apollo 11 Laser Ranging Retro-Reflector: Initial Measurements from the McDonald Observatory.

Acquisition measurements of the round-trip travel time of light, from the McDonald Observatory to the Laser Ranging Retro-Reflector deployed on the moon by the Apollo 11 astronauts, were made on 20 August and on 3, 4, and 22 September 1969. The uncertainty in the round-trip travel time was +/- 15 nanoseconds, with the pulsed ruby laser and timing system used for the acquisition. The uncertainty in later measurements of a planned long-term sequence from this observatory is expected to be an order of magnitude smaller. The successful performance of the retro-reflector at several angles of solar illumination, as well as during and after a lunar night, confirms the prediction of thermal design analyses.