Fingerprint analysis has long been a cornerstone in criminal investigations for suspect identification. Beyond this conventional role, recent efforts have aimed to extract additional demographic information from fingerprints, such as gender, age, and nationality. While studies have demonstrated promising accuracy in gender classification based on fingerprints, practical implementation faces challenges, including the often low quality of crime scene fingerprints. This study presents a pioneering comparison of gender classification across diverse datasets, considering variations in fingerprint image quality. We examine the results from four databases, encompassing both public and private sources, employing state-of-the-art Data-Centric AI (DCAI) approaches for enhanced classification. Our findings reveal that a conservative Convolutional Neural Network (CNN)—specifically VGG—proves effective, achieving an accuracy ranging from 70% to 95% based on fingerprint quality. DCAI methods contribute a noteworthy 1–4% improvement. Notably, for partial or low-quality fingerprints, the periphery emerges as a critical determinant of gender classification. This study contributes insights into practical gender classification from fingerprints, emphasizing the significance of the fingerprint periphery. Furthermore, we provide the source code for future research and accessibility in real-world applications.

Reverse osmosis (RO) is the most popular technology for brackish, seawater and wastewater desalination. An important drawback of RO is membrane fouling, which reduces filtration effectiveness and increase the cost of produced water. This study addresses two important topics of membrane fouling: (i) the impact of different divalent ions on the formation of organic fouling and (ii) online monitoring and prediction of fouling formation. In the absence of divalent ions, dissolved organic matter had little effect on fouling formation, even at 3.5 mgC/L, in the upper range of groundwater concentration. Calcium, strontium and iron enhanced (organic) fouling formation, whereas barium had negligible effect. However, while iron affected fouling throughout the entire tested range (0–0.5 mg/L), calcium and strontium enhanced organic fouling only at high concentrations: more than 140 mg/L and 10 mg/L for calcium and strontium, respectively. An online system was developed for monitoring the formation of organic fouling, consisting of (i) an ex-situ RO cell with a transparent cover, (ii) a video camera continually monitoring the surface of the membrane and (iii) an algorithm which automatically identified changes in the color of the membrane caused by fouling, using a specially designed membrane spacer with colored reference dots. Changes in the color of the membrane surface were normalized to the reference colors, to eliminate all non-fouling related interference. The system was used to record and analyze changes in membrane color during numerous filtration tests. The data was successfully correlated to changes in specific flux (and subsequently to fouling formation rate) and can be applied to monitor and predict the formation of membrane fouling during desalination.

Background Gingivitis is a nonpainful, inflammatory condition that can be managed at home. Left untreated, gingivitis can lead to tooth loss. Periodic dental examinations are important for early diagnosis and treatment of gum diseases. To contain the spread of the coronavirus, governments, including in Israel, have restricted movements of their citizens which might have caused routine dental checkups to be postponed. Objective This study aimed to examine the ability of a mobile health app, iGAM, to reduce gingivitis, and to determine the most effective interval between photograph submissions. Methods A prospective observational cohort study with 160 unpaid participants divided into 2 equal groups using the iGAM app was performed. The intervention group photographed their gums weekly for 8 weeks. The wait-list control group photographed their gums at the time of recruitment and 8 weeks later. After photo submission, the participants received the same message “we recommended that you read the information in the app regarding oral hygiene habits.” A single-blinded researcher examined all the images and scored them according to the Modified Gingival Index (MGI). Results The average age of the intervention group was 26.77 (SD 7.43) and 28.53 (SD 10.44) for the wait-list control group. Most participants were male (intervention group: 56/75,74.7%; wait-list control group: 34/51, 66.7%) and described themselves as “secular”; most were “single” non-smokers (intervention group: 56/75, 74.7%; wait-list control group: 40/51, 78.4%), and did not take medications (intervention group: 64/75, 85.3%; wait-list control group: 40/51, 78.4%). A total of 126 subjects completed the study. A statistically significant difference (P<.001) was found in the dependent variable (MGI). Improvements in gingival health were noted over time, and the average gingivitis scores were significantly lower in the intervention group (mean 1.16, SD 1.18) than in the wait-list control group (mean 2.16, SD 1.49) after 8 weeks. Those with more recent dental visits had a lower MGI (P=.04). No association was found between knowledge and behavior. Most participants were familiar with the recommendations for maintaining oral health, yet they only performed some of them. Conclusions A dental selfie taken once a week using an mobile health app (iGAM) reduced the signs of gingivitis and promoted oral health. Selfies taken less frequently yielded poorer results. During the current pandemic, where social distancing recommendations may be causing people to avoid dental clinics, this app can remotely promote gum health.

Background Gum infection, known as gingivitis, is a global issue. Gingivitis does not cause pain; however, if left untreated, it can worsen, leading to bad breath, bleeding gums, and even tooth loss, as the problem spreads to the underlying structures anchoring the teeth in the jaws. The asymptomatic nature of gingivitis leads people to postpone dental appointments until clinical signs are obvious or pain is evident. The COVID-19 pandemic has necessitated social distancing, which has caused many people to postpone dental visits and neglect gingival health. iGAM is a dental mobile health (mHealth) app that remotely monitors gum health, and an observational study demonstrated the ability of iGAM to reduce gingivitis. We found that a weekly dental selfie using the iGAM app reduced the signs of gingivitis and promoted oral health in a home-based setting. Objective The aim of this mixed methods study is to assess perceptions, attitudes, willingness to pay, and willingness to use an mHealth app. Methods The first qualitative phase of the study included eight semistructured interviews, and the second quantitative phase included data collected from responses to 121 questionnaires. Results There was a consensus among all interviewees that apps dealing with health-related issues (mHealth apps) can improve health. Three themes emerged from the interviews: the iGAM app is capable of improving health, the lack of use of medical apps, and a contradiction between the objective state of health and the self-definition of being healthy. Participants were grouped according to how they responded to the question about whether they believed that mHealth apps could improve their health. Participants who believed that mHealth apps can enhance health (mean 1.96, SD 1.01) had a higher willingness to pay for the service (depending on price) than those who did not believe in app efficacy (mean 1.31, SD 0.87; t119=−2417; P=.02). A significant positive correlation was found between the amount a participant was willing to pay and the benefits offered by the app (rs=0.185; P=.04). Conclusions Potential mHealth users will be willing to pay for app use depending on their perception of the app’s ability to help them personally, provided they define themselves as currently unhealthy.

<sec> &lt;title&gt;BACKGROUND&lt;/title&gt; &lt;p&gt;For most people, dental visits are unpleasant, usually accompanied by discomfort or pain. Patients seek treatment when the pain becomes intolerable, regardless, we have learned from the novel coronavirus disease 2019 (COVID-19) pandemic, that we must find solutions for times when patients cannot meet their dentist for an extended period. One of the prevalent oral diseases is gingivitis, characterized by red, swollen and bleeding gums. Gingivitis heals within 10 days of professional care and thorough daily oral hygiene practices. Without treatment, it progresses and eventually teeth may become mobile or be lost. There are many m-Health apps in medical fields, unfortunately none deal with the monitoring of gingivitis.&lt;/p&gt; </sec> <sec> &lt;title&gt;OBJECTIVE&lt;/title&gt; &lt;p&gt;The aim of this study is to present a characterization and development of an m-Health application called iGAM, which focuses on periodontal health. An m-Health app which improves the flow of information between dentists and their patients during the intervals between checkups.&lt;/p&gt; </sec> <sec> &lt;title&gt;METHODS&lt;/title&gt; &lt;p&gt;A quantitative design process based on the the Agile approach was used to develop iGAM and included the following steps: User story, Use Cases, Functional and Non-functional requirements followed by Agile Software Development cycles. A pilot study was conducted with a group of 18 participants aged 18-45, with different levels of health literacy. The participants were given a kit containing toothpaste, toothbrush, mouth wash, toothpicks and dental floss. After installing iGAM the participants were asked to photograph their gums once a week for four weeks.&lt;/p&gt; </sec> <sec> &lt;title&gt;RESULTS&lt;/title&gt; &lt;p&gt;The agile software development of iGAM had five cycles and demonstrated the importance of communication between dentists, expert app developers and "everyday people” testing the app. Prior to app the development we convened a focus group. All participants believed in the potential of a mobile app to effectively monitor gingivitis and reduce the severity of gingivitis, some voiced concern about information security and privacy issues. Subsequently, we conducted three semi-structured in-depth interviews on the use of cellphone applications for monitoring gum infections. Two themes emerged from the interviews: 1) What's in it for me? 2) Need for take home message. Qualitative analysis showed that participants: had difficulty using the camera therefore, mouth openers were given, had difficulty operating the phone, therefore we reprogrammed the app to be fully automated and a weekly reminder SMS was added, eventually we added an instructions document. Final interviews showed satisfaction.&lt;/p&gt; </sec> <sec> &lt;title&gt;CONCLUSIONS&lt;/title&gt; &lt;p&gt;The iGAM was developed to promote oral health and is the first m-Health app for monitoring gingivitis using self-photography. iGAM presents a novel solution to improve the flow of information between dentists and their patients between checkups and may be useful whenever patients cannot meet dentists for a long time like the current COVID-19 pandemic.&lt;/p&gt; </sec>

Background: Gum diseases are prevalent in a large proportion of the population worldwide. Unfortunately, most people do not follow a regular dental checkup schedule, and only seek treatment when experiencing acute pain. We aim to provide a system for classifying gum health status based on the MGI (Modified Gingival Index) score using dental selfies alone. Method: The input to our method is a manually cropped tooth image and the output is the MGI classification of gum health status. Our method consists of a cascade of two stages of robust, accurate, and highly optimized binary classifiers optimized per tooth position. Results: Dataset constructed from a pilot study of 44 participants taking dental selfies using our iGAM app. From each such dental selfie, eight single-tooth images were manually cropped, producing a total of 1520 images. The MGI score for each image was determined by a single examiner dentist. On a held-out test-set our method achieved an average AUC (Area Under the Curve) score of 95%. Conclusion: The paper presents a new method capable of accurately classifying gum health status based on the MGI score given a single dental selfie. Enabling personal monitoring of gum health—particularly useful when face-to-face consultations are not possible.

BACKGROUND:Dental visits are unpleasant; sometimes, patients only seek treatment when they are in intolerable pain. Recently, the novel coronavirus (COVID-19) pandemic has highlighted the need for remote communication when patients and dentists cannot meet in person. Gingivitis is very common and characterized by red, swollen, bleeding gums. Gingivitis heals within 10 days of professional care and with daily, thorough oral hygiene practices. If left untreated, however, its progress may lead to teeth becoming mobile or lost. Of the many medical apps currently available, none monitor gingivitis.OBJECTIVE:This study aimed to present a characterization and development model of a mobile health (mHealth) app called iGAM, which focuses on periodontal health and improves the information flow between dentists and patients.METHODS:A focus group discussed the potential of an app to monitor gingivitis, and 3 semistructured in-depth interviews were conducted on the use of apps for monitoring gum infections. We used a qualitative design process based on the Agile approach, which incorporated the following 5 steps: (1) user story, (2) use cases, (3) functional requirements, (4) nonfunctional requirements, and (5) Agile software development cycles. In a pilot study with 18 participants aged 18-45 years and with different levels of health literacy, participants were given a toothbrush, toothpaste, mouthwash, toothpicks, and dental floss. After installing iGAM, they were asked to photograph their gums weekly for 4 weeks.RESULTS:All participants in the focus group believed in the potential of a mobile app to monitor gingivitis and reduce its severity. Concerns about security and privacy issues were discussed. From the interviews, 2 themes were derived: (1) "what's in it for me?" and (2) the need for a take-home message. The 5 cycles of development highlighted the importance of communication between dentists, app developers, and the pilot group. Qualitative analysis of the data from the pilot study showed difficulty with: (1) the camera, which was alleviated with the provision of mouth openers, and (2) the operation of the phone, which was alleviated by changing the app to be fully automated, with a weekly reminder and an instructions document. Final interviews showed satisfaction.CONCLUSIONS:iGAM is the first mHealth app for monitoring gingivitis using self-photography. iGAM facilitates the information flow between dentists and patients between checkups and may be useful when face-to-face consultations are not possible (such as during the COVID-19 pandemic).

Real time object detection and classification is essential for outdoor surveillance. Current state of the art real time object detection CNNs are trained on natural image datasets. However, outdoor surveillance images have very different characteristics: objects tend to be small and difficult to distinguish (averaging only 3% of image size). In addition, images come in different modalities, for example, nighttime surveillance images are grayscale thermal images representing heat emission not light reflection. Our dataset of images acquired from surveillance videos is comprised of (similar to) 640 Daytime (DAY) color images and (similar to) 360 nighttime grayscale THERMAL images. The dataset included three object categories: animals, people and vehicles. Because of the lack of large datasets for these scenarios, we evaluated using the much larger VOC dataset to augment our datasets. We conducted a study to determine the best combination of images to include in the training dataset, and how different types of images (i.e. DAY, THERMAL and VOC) affect each-others performance. We examined state of the art object detection and classification CNN architectures, focusing on accuracy and real time performance. By combining different images types THERMAL, DAY and 1200 VOC images in one dataset, the best results were obtained using transfer learning on YOLO-V3 with SPP, achieving 89.5 mAP for DAY images, and 79.53 mAP for THERMAL images, running at 35 fps. This setup provides a robust solution for many surveillance scenarios: night and daytime; far, small objects, as well as zoomed-in, large objects.

It is an empirical observation that Software Engineering and Knowledge Engineering seem to converge to a single discipline which may be suitably called Software-Knowledge.However, mere empirical observations are not satisfactory.These should be justified by plausible arguments.There are three convergence aspects, semantic, algebraic and topological, and this paper focuses on the algebraic aspect.Linear algebra is the basis for Linear Software Models, a rigorous theory of software systems composition from sub-systems, recently developed.Linear algebra, with added non-linearity, is also the basis for Deep Learning, a successful Artificial Intelligence domain.This work suggests and analyzes Deep Software Learning, i.e.Deep Learning specific to Software development problems.We then conjecture on deep reasons for Software-Knowledge convergence.

Purpose The goal of medical content-based image retrieval (M-CBIR) is to assist radiologists in the decision-making process by retrieving medical cases similar to a given image. One of the key interests of radiologists is lesions and their annotations, since the patient treatment depends on the lesion diagnosis. Therefore, a key feature of M-CBIR systems is the retrieval of scans with the most similar lesion annotations. To be of value, M-CBIR systems should be fully automatic to handle large case databases. Methods We present a fully automatic end-to-end method for the retrieval of CT scans with similar liver lesion annotations. The input is a database of abdominal CT scans labeled with liver lesions, a query CT scan, and optionally one radiologist-specified lesion annotation of interest. The output is an ordered list of the database CT scans with the most similar liver lesion annotations. The method starts by automatically segmenting the liver in the scan. It then extracts a histogram-based features vector from the segmented region, learns the features' relative importance, and ranks the database scans according to the relative importance measure. The main advantages of our method are that it fully automates the end-to-end querying process, that it uses simple and efficient techniques that are scalable to large datasets, and that it produces quality retrieval results using an unannotated CT scan. Results Our experimental results on 9 CT queries on a dataset of 41 volumetric CT scans from the 2014 Image CLEF Liver Annotation Task yield an average retrieval accuracy (Normalized Discounted Cumulative Gain index) of 0.77 and 0.84 without/with annotation, respectively. Conclusions Fully automatic end-to-end retrieval of similar cases based on image information alone, rather that on disease diagnosis, may help radiologists to better diagnose liver lesions.

The goal of medical case-based image retrieval (M-CBIR) is to assist radiologists in the clinical decision-making process by finding medical cases in large archives that most resemble a given case. Cases are described by radiology reports comprised of radiological images and textual information on the anatomy and pathology findings. The textual information, when available in standardized terminology, e.g., the RadLex ontology, and used in conjunction with the radiological images, provides a substantial advantage for M-CBIR systems.

Automatic segmentation of anatomical structures in CT scans is an essential step in the analysis of radiological patient data and is a prerequisite for large-scale content-based image retrieval (CBIR). Many existing segmentation methods are tailored to a single structure and/or require an atlas, which entails multistructure deformable registration and is time-consuming. We present a fully automatic atlas-free segmentation of multiple organs of the ventral cavity in contrast-enhanced CT scans of the whole trunk (CECT). Our method uses a pipeline approach based on the rules that determine the order in which the organs are isolated and how they are segmented. Each organ is individually segmented with a generic four-step procedure. Our method is unique in that it does not require any predefined atlas or a costly registration step and in that it uses the same generic segmentation approach for all organs. Experimental results on the segmentation of seven organs—liver, left and right kidneys, left and right lungs, trachea, and spleen—on 20 CECT scans of the VISCERAL Anatomy training dataset and 10 CECT scans of the test dataset yield an average DICE volume overlap similarity score of 90.95 and 88.50%, respectively.

Variations in the shape and appearance of anatomical structures in medical images are often relevant radiological signs of disease. Automatic tools can help automate parts of this manual process. A cloud-based evaluation framework is presented in this paper including results of benchmarking current state-of-the-art medical imaging algorithms for anatomical structure segmentation and landmark detection: the VISCERAL Anatomy benchmarks. The algorithms are implemented in virtual machines in the cloud where participants can only access the training data and can be run privately by the benchmark administrators to objectively compare their performance in an unseen common test set. Overall, 120 computed tomography and magnetic resonance patient volumes were manually annotated to create a standard Gold Corpus containing a total of 1295 structures and 1760 landmarks. Ten participants contributed with automatic algorithms for the organ segmentation task, and three for the landmark localization task. Different algorithms obtained the best scores in the four available imaging modalities and for subsets of anatomical structures. The annotation framework, resulting data set, evaluation setup, results and performance analysis from the three VISCERAL Anatomy benchmarks are presented in this article. Both the VISCERAL data set and Silver Corpus generated with the fusion of the participant algorithms on a larger set of non-manually-annotated medical images are available to the research community.

Candecomp/Parafac Decomposition (CPD) has emerged as a framework for modeling N-way arrays (higher-order matrices). CPD is naturally well suited for the analysis of data sets comprised of observations of a function of multiple discrete indices. In this study we evaluate the prospects of using CPD for modeling MRI brain properties (i.e. brain volume and gray-level) for schizophrenia diagnosis. Taking into account that 3D imaging data consists of millions of pixels per patient, the diagnosis of a schizophrenia patient based on pixel analysis constitutes a methodological challenge (e.g. multiple comparison problem). We show that the CPD could potentially be used as a dimensionality redaction method and as a discriminator between schizophrenia patients and match control, using the gradient of pre- and post Gd-T1-weighted MRI data, which is strongly correlated with cerebral blood perfusion. Our approach was tested on 68 MRI scans: 40 first-episode schizophrenia patients and 28 matched controls. The CPD subject’s scores exhibit statistically significant result (P < 0.001). In the context of diagnosing schizophrenia with MRI, the results suggest that the CPD could potentially be used to discriminate between schizophrenia patients and matched control. In addition, the CPD model suggests for brain regions that might exhibit abnormalities in schizophrenia patients for future research.

We present a new method for the retrieval radiological cases from a database of clinical cases described by terms from the RadLex lexicon. The input is an database of cases and a query consisting of the patient volumetric scan, a user-defined region of interest in it, and a list of RadLex from the radiological report. The output is list of the most relevant cases from the database in decreasing order. Our method uses the RadLex terms and their hierarchical representation to define a similarity metric between terms based on their relative location in the hierarchy. For this purpose, we develop the Augmented RadLex Graph, a data structure that augments the RadLex hierarchy with links derived from the terms in the case reports, and a search algorithm that ranks case similarity based on the link distance between the terms in the graph. Our method was evaluated in the VISCERAL Retrieval Benchmark Challenge on 8 queries and a database of 1,813 cases. It ranked first in 6 out of the 8 cases tested.

The development of automatic analysis and classication methods for large databases of X-ray images is a pressing need that may have a great impact on clinical practice. To advance this objective the ImageCLEF-2015 clustering of body part X-ray images challenge was created. The aim of the challenge is to group digital X-ray images into ve structural groups: head-neck, upper-limb, body, lower-limb, and other. This paper presents the results of an experimental evaluation of X-ray images classication in the ImageCLEF-2015 challenge. We apply state-of-the-art classication and feature extraction methods for image classication and optimize them for the challenge task with emphasis on features indicating bone size and structure. The best classication results were obtained using the intensity, texture and HoG features and the KNN classier. This combination has an accuracy of 86% and 73% for the 500 training images and 250 test images, respectively.

We describe a new method for the automatic segmentation of multiple organs of the ventral cavity in CT scans. The method is based on a set of rules that determine the order in which the organs are isolated and segmented. First, the air-containing organs are segmented: the trachea and the lungs. Then, the organs with high blood content: the spleen, the kidneys and the liver, are segmented. Each organ is individually segmented with a generic four-step pipeline procedure. Our method is unique in that it uses the same generic segmentation approach for all organs and in that it relies on the segmentation difficulty of organs to guide the segmentation process. Experimental results on 20 CT scans of the VISCERAL Anatomy2 Challenge training datasets yield an average Dice volume overlap similarity score of 90.95. For the 10 CT scans test datasets, the average Dice scores is 88.5.

The rapid increase of CT scans and the limited number of radiologists present a unique opportunity for computer-based radiological Content-Based Image Retrieval (CBIR) systems. However, the current structure of the clinical diagnosis reports presents substantial variability, which significantly hampers the creation of effective CBIR systems. Researchers are currently looking for ways of standardizing the reports structure, e.g., by introducing uniform User Express (UsE) annotations and by automating the extraction of UsE annotations with Computer Generated (CoG) features. This paper presents an experimental evaluation of the derivation of UsE annotations from CoG features with a classifier that estimates each UsE annotation from the input CoG features. We used the datasets of the ImageCLEF-Liver CT Annotation challenge: 50 training and 10 testing CT scans with liver and liver lesion annotations. Our experimental results on the ImageCLEF-Liver CT Annotation challenge exhibit a completeness level of 95% and accuracy of 91% for 10 unseen cases. This is the second best result obtained in the Liver CT Annotation challenge and only 1% away from the rst place.