A security scheme for distributing analysis codes supporting CDM-based research in a multi-center environment.

BACKGROUND: Although the common data model (CDM) has achieved a standardization of medical data and a de-identification of personal patient information, hospitals still store CDM data in an on-premises environment, making it difficult for researchers to access medical data. OBJECTIVE: In this study, for easy access to CDM data in a multi-institutional participatory CDM research environment and to encourage data-driven research, researchers outside hospital networks securely access and analyze CDM data in the target medical center, analyze it, and respond to the results through a public network. We propose an automated security framework that operates on a public network, such as the Internet. METHOD: The proposed scheme allows authenticated researchers to securely deliver CDM data analysis codes to a medical institution distributed on the network. The institutional servers automatically execute authenticated codes and return the results to the researcher safely. For this purpose, we designed a scheme based on cryptography. The scheme operates on a group of servers consisting of an authentication process, a signing process, a ticket-granting process, a relaying process, and a data analysis process located at the hospital providing medical CDM data. The scheme consists of four phases for a secure medical data analysis in a distributed environment: authentication, code signing, ticket issuing, and distribution and return. RESULTS: Although the CDM has de-identified patient privacy, the issue still needs to be carefully addressed. Therefore, we established four security objectives to verify that the proposed scheme can be operated safely and formally proved them using BAN logic. CONCLUSION: As a result of the proof using BAN logic, the proposed scheme was verified to achieve the proposed security goal. Although this scheme was designed solely for CDM, it can be applied to systems with similar environments and functional goals.

Proposal and Assessment of a De-Identification Strategy to Enhance Anonymity of the Observational Medical Outcomes Partnership Common Data Model (OMOP-CDM) in a Public Cloud-Computing Environment: Anonymization of Medical Data Using Privacy Models.

BACKGROUND: De-identifying personal information is critical when using personal health data for secondary research. The Observational Medical Outcomes Partnership Common Data Model (CDM), defined by the nonprofit organization Observational Health Data Sciences and Informatics, has been gaining attention for its use in the analysis of patient-level clinical data obtained from various medical institutions. When analyzing such data in a public environment such as a cloud-computing system, an appropriate de-identification strategy is required to protect patient privacy. OBJECTIVE: This study proposes and evaluates a de-identification strategy that is comprised of several rules along with privacy models such as k-anonymity, l-diversity, and t-closeness. The proposed strategy was evaluated using the actual CDM database. METHODS: The CDM database used in this study was constructed by the Anam Hospital of Korea University. Analysis and evaluation were performed using the ARX anonymizing framework in combination with the k-anonymity, l-diversity, and t-closeness privacy models. RESULTS: The CDM database, which was constructed according to the rules established by Observational Health Data Sciences and Informatics, exhibited a low risk of re-identification: The highest re-identifiable record rate (11.3%) in the dataset was exhibited by the DRUG_EXPOSURE table, with a re-identification success rate of 0.03%. However, because all tables include at least one "highest risk" value of 100%, suitable anonymizing techniques are required; moreover, the CDM database preserves the "source values" (raw data), a combination of which could increase the risk of re-identification. Therefore, this study proposes an enhanced strategy to de-identify the source values to significantly reduce not only the highest risk in the k-anonymity, l-diversity, and t-closeness privacy models but also the overall possibility of re-identification. CONCLUSIONS: Our proposed de-identification strategy effectively enhanced the privacy of the CDM database, thereby encouraging clinical research involving multiple centers.

Recurrent GANs Password Cracker For IoT Password Security Enhancement.

Text-based passwords are a fundamental and popular means of authentication. Password authentication can be simply implemented because it does not require any equipment, unlike biometric authentication, and it relies only on the users' memory. This reliance on memory is a weakness of passwords, and people therefore usually use easy-to-remember passwords, such as "iloveyou1234". However, these sample passwords are not difficult to crack. The default passwords of IoT also are text-based passwords and are easy to crack. This weakness enables free password cracking tools such as Hashcat and JtR to execute millions of cracking attempts per second. Finally, this weakness creates a security hole in networks by giving hackers access to an IoT device easily. Research has been conducted to better exploit weak passwords to improve password-cracking performance. The Markov model and probabilistic context-free-grammar (PCFG) are representative research results, and PassGAN, which uses generative adversarial networks (GANs), was recently introduced. These advanced password cracking techniques contribute to the development of better password strength checkers. We studied some methods of improving the performance of PassGAN, and developed two approaches for better password cracking: the first was changing the convolutional neural network (CNN)-based improved Wasserstein GAN (IWGAN) cost function to an RNN-based cost function; the second was employing the dual-discriminator GAN structure. In the password cracking performance experiments, our models showed 10%-15% better performance than PassGAN. Through additional performance experiments with PCFG, we identified the cracking performance advantages of PassGAN and our models over PCFG. Finally, we prove that our models enhanced password strength estimation through a comparison with zxcvbn.

Quantitative color assessment of dermoscopy images using perceptible color regions.

BACKGROUND: Dermoscopy is a non-invasive in vivo skin imaging technique that assists dermatologists in diagnosing melanoma. However, the use of dermoscopy for diagnosis requires extensive training since this approach often provides extremely complex and subjective information. The presence of an imperceptible color difference in dermoscopy images is one of the serious problems associated with the use of this technique. This imperceptible color difference leads to inaccurate lesion extraction at the borders and hinders the assessment of lesion features. Therefore, objective and quantitative assessment based on perceptible color differences is important for the diagnosis of melanoma using dermoscopy. METHODS: In this study, we developed a method for assessing colors in a lesion. Twenty-seven perceptible color regions based on the multi-thresholding method in each color channel were constructed, and dominant color region (DCR), bluish dominant region (BDR), and the number of colors were assessed as three diagnostic parameters from these perceptible color regions on 150 dermoscopy images. RESULTS/CONCLUSION: Diagnostic accuracy was calculated by combination of three diagnostic parameters derived from DCR, BDR, and the number of colors. Diagnostic accuracy with 73.33% sensitivity and 90.67% specificity was obtained in case of positive features in more than two parameters.

A study of a method for distribution analysis of skin color.

BACKGROUND/AIMS: The objective and quantitative assessment of the skin is important in medical and cosmeceutical research. Assessment of color is an important element for analyzing the surface of the skin, which is usually determined subjectively by a doctor or using color analysis devices. These devices, however, cannot provide correct color information because color is construed from the mean value of the observation region, and analysis of color distribution is impossible. The purpose of this paper is to develop an objective analysis method to permit skin color measurement of each pixel unit of an image and analyze the distribution of skin surface color. METHODS: The Skin Color Distribution Analyzer (SCDA) is an analysis method newly developed at the Research Institute for Skin Image at Korea University. The SCDA system presented in this paper performed a novel form of quantitative and objective analysis of skin color distribution using each pixel color model parameter found in image wavelength information. In this paper, distribution analysis was conducted on normal skin and skin lesions and skin affected by artificially induced irritant contact dermatitis and pigmented nevous. The method selected a grade using a color model parameter. Twenty healthy Korean males participated in this study. A comparative study of the eight anatomical areas was performed, including the exposure and non-exposure parts and the medial aspect and the lateral aspect of the forearm. A reliability test for the SCDA system was also conducted with a spectrometer (SPEC) using the color analysis method. RESULTS: Each skin lesion was precisely segmented by grade and each parameter had a different statistical significance for results of analysis of distribution in pigmented nevous and the artificially induced irritant contact dermatitis. Parameters L(*), b(*), a(*), and EI showed salient traits. Showed resemble measured result in the SCDA system and the SPEC of normal skin. The exposed site, in comparison with the non-exposed site, showed a notable difference in the L(*) parameter and a significant statistical difference in the x and z parameters, except b(*). The comparison of the medial and lateral aspects of the forearm showed a notable difference in the L(*) parameter and a significant statistical difference in the parameters except y and b(*). In the reliability test result using the SCDA system and the SPEC, the SCDA system was highly reliable in terms of the CV value in all color model parameters. CONCLUSIONS: The color distribution analysis method using the SCDA system has revealed an aspect that the existent method of medical research has not shown, and is considered to be more reliable than other methods. This method can provide better study findings because it can be applied to other fields in addition to the medical science field and the ripple effect is thought to be bigger in other science field too.

Objective interpretation of severity of SLS induced edema by stereoimaging.

BACKGROUND: In the evaluation of the severity of skin inflammations, visual scoring system is widely being used as a subjective method. However, it is well known that interobserver variations occur even between the interpretations of experienced dermatologists. OBJECTIVE: To develop a new objective and quantitative method for the evaluation of skin surface contours and for the assessment of severity in SLS-induced edema, a new investigatory tool based on the concept of "stereoimaging" was studied. Differences between binocular images were used by a stereoimage optical topometer (SOT) system capable of calculating skin surface topographic information, which was then used to produce a three-dimensional image. METHODS: We compared the results obtained by SOT with a visual scoring system after applying sodium lauryl sulfate (SLS) to skin. The degree of edema was assessed qualitatively by visual scoring (0: none, 1: mild edema, 2: moderate edema, 3: severe edema). To quantify the severity, five three-dimensional parameters (S(a), S(z), SL, SA and SV) were used in the SOT analysis. RESULTS: The means of these five parameters increased significantly in visual grade 1+ compared to visual grade 0 and the means of the five parameters decreased significantly and proportionally as the visual grades increased from 1+ to 3+. A highly significant correlation was found to exist between the visual scoring results and the five SOT parameters. CONCLUSION: SOT can be used to evaluate the severity of SLS-induced edema objectively and can be extensively applied to evaluate the degree of severity in other inflammatory skin conditions.

Quantitative evaluation of severity in psoriatic lesions using three-dimensional morphometry.

The severity of psoriasis has been traditionally assessed by measures, such as the psoriasis area and severity index (PASI), the psoriasis severity scores, and the lesional severity scores. As a result, even experienced dermatologists show variations when attempting to determine the severity of psoriasis. Therefore, a better non-invasive and objective measurement of clinical signs is needed. In this study, an instrument, a so-called 'stereoimage optical topometer' (SOT), based on a new concept of 'stereoimaging' was used to measure the three-dimensional skin surface. The aim of this study was to compare the results obtained by the SOT with the visual score of psoriasis lesion. Thirty psoriatic patients were enrolled in this study. Initially, the severity of the infiltration and the scale of 134 psoriatic lesions were assessed by using a visual scoring system (0: none, 1: mild, 2: moderate, 3: severe, and 4: very severe), as scored by five dermatologists. The SOT was then used to quantify the severity of each psoriatic lesion using four three-dimensional SOT parameters (Sa, SL, SA, and SV). Secondly, the involved skin-surface area in the psoriasis cases was scored by the naked eye by the five dermatologists and by image analysis. Statistically significant differences were observed between grades 0, 1, 2, and 3 in terms of the severity measurements of the individual psoriatic lesions by SOT when using the parameters Sa, SL, SA, and SV. Therefore, it was concluded that there is a strong correlation between the results measured by visual scoring and by SOT in psoriasis.

Objective assessment of involved surface area in patients with psoriasis.

BACKGROUND/AIMS: Although difficult, it is essential to assess the disease severity of psoriasis objectively. The visual grading method currently used for assessing the involved surface area in patients with psoriasis, which is included on the Psoriasis Area and Severity Index (PASI) scoring system, is a subjective method. The aim of this study was to establish the reliable objective method, in estimating the involved surface area in patients with psoriasis. METHODS: Thirty patients with psoriasis participated in this study. The skin lesions of each patient were estimated using the visual grading method and an image analysis system. RESULTS: The differences between five dermatologists' estimates of the involved surface area obtained from the visual grading method were highly significant (P<0.05, Kruskal-Wallis test). The comparison between the visual grading method and the image analysis system showed that the involved areas measured by the visual grading method were significantly higher than those from the image analysis (P<0.05, Wilcoxon signed rank test). CONCLUSIONS: The visual grading method was neither objective nor reproducible. On the other hand, the image analysis system can be used as an objective method of measuring the involved surface area of patients with psoriasis. Therefore, the image analysis system can be used as a standard for the assessment of the involved area of patients with psoriasis.

A new technique for three-dimensional measurements of skin surface contours: evaluation of skin surface contours according to the ageing process using a stereo image optical topometer.

The evaluation of skin surface contours can be carried out by various techniques, including the use of a stylus profilometer, a laserprofilometer and a conventional optical profilometer (COP). But these methods have some drawbacks because their data are basically obtained from two-dimensional algorithms. So a new technique has been developed based on a new concept: a stereo image processing technique which is considered in this paper. Since a pair of stereo images contains depth information, the 'disparity', or the difference between the left and right images, enables the production of three-dimensional coordinates. This study was performed to evaluate the change of skin surface contours according to the ageing process. The stereo image optical topometer (SOT) is a new instrument used for the three-dimensional evaluation of skin surface contours. Thus. five new parameters have to be developed, such as mean surface roughness (S(a)), mean depth of roughness (S(z)), three-dimensional length (S(L)), three-dimensional area (S(A)), and three-dimensional volume (S(V)). S(a), S(L) and S(A) have shown a statistically significant increase in the seventies age group. S(z) has also shown a significant increase in the twenties and over-sixties age groups. The coefficient variation of the height of the skin surface using a COP varies between 14.76 and 6.57, but that using a SOT is between 2.18 and 2.69, according to age variation. In conclusion, the SOT system is a more reliable and useful method for evaluating skin surface contours than the COP system. Among the three-dimensional parameters which were made in this study, S(A), S(L) and S(a) seem to be useful as reliable parameters for evaluating skin surface contours in the ageing process.