Machine Learning for Renal Pathologies: An Updated Survey.

Within the literature concerning modern machine learning techniques applied to the medical field, there is a growing interest in the application of these technologies to the nephrological area, especially regarding the study of renal pathologies, because they are very common and widespread in our society, afflicting a high percentage of the population and leading to various complications, up to death in some cases. For these reasons, the authors have considered it appropriate to collect, using one of the major bibliographic databases available, and analyze the studies carried out until February 2022 on the use of machine learning techniques in the nephrological field, grouping them according to the addressed pathologies: renal masses, acute kidney injury, chronic kidney disease, kidney stone, glomerular disease, kidney transplant, and others less widespread. Of a total of 224 studies, 59 were analyzed according to inclusion and exclusion criteria in this review, considering the method used and the type of data available. Based on the study conducted, it is possible to see a growing trend and interest in the use of machine learning applications in nephrology, becoming an additional tool for physicians, which can enable them to make more accurate and faster diagnoses, although there remains a major limitation given the difficulty in creating public databases that can be used by the scientific community to corroborate and eventually make a positive contribution in this area.

Metrological Characterization and Comparison of D415, D455, L515 RealSense Devices in the Close Range.

RGB-D cameras are employed in several research fields and application scenarios. Choosing the most appropriate sensor has been made more difficult by the increasing offer of available products. Due to the novelty of RGB-D technologies, there was a lack of tools to measure and compare performances of this type of sensor from a metrological perspective. The recent ISO 10360-13:2021 represents the most advanced international standard regulating metrological characterization of coordinate measuring systems. Part 13, specifically, considers 3D optical sensors. This paper applies the methodology of ISO 10360-13 for the characterization and comparison of three RGB-D cameras produced by Intel® RealSense™ (D415, D455, L515) in the close range (100-1500 mm). ISO 10360-13 procedures, which focus on metrological performances, are integrated with additional tests to evaluate systematic errors (acquisition of flat objects, 3D reconstruction of objects). The present paper proposes an off-the-shelf comparison which considers the performance of the sensors throughout their acquisition volume. Results have exposed the strengths and weaknesses of each device. The D415 device showed better reconstruction quality on tests strictly related to the short range. The L515 device performed better on systematic depth errors; finally, the D455 device achieved better results on tests related to the standard.

Metrological and Critical Characterization of the Intel D415 Stereo Depth Camera.

Low-cost RGB-D cameras are increasingly being used in several research fields, including human⁻machine interaction, safety, robotics, biomedical engineering and even reverse engineering applications. Among the plethora of commercial devices, the Intel RealSense cameras have proven to be among the most suitable devices, providing a good compromise between cost, ease of use, compactness and precision. Released on the market in January 2018, the new Intel model RealSense D415 has a wide acquisition range (i.e., ~160⁻10,000 mm) and a narrow field of view to capture objects in rapid motion. Given the unexplored potential of this new device, especially when used as a 3D scanner, the present work aims to characterize and to provide metrological considerations for the RealSense D415. In particular, tests are carried out to assess the device performance in the near range (i.e., 100⁻1000 mm). Characterization is performed by integrating the guidelines of the existing standard (i.e., the German VDI/VDE 2634 Part 2) with a number of literature-based strategies. Performance analysis is finally compared against the latest close-range sensors, thus providing a useful guidance for researchers and practitioners aiming to use RGB-D cameras in reverse engineering applications.

Statistical and artificial intelligence techniques to identify risk factors for suicide in children and adolescents.

BACKGROUND: Suicidal Behaviors and Thoughts are a relevant public health issue that includes suicidal ideation, non-suicidal self-harm, attempted suicide, and failed suicides. Since there is a progression of suicidal behaviors, whereby suicide is more likely to be completed if there have already been previous behaviors or attempts to harm oneself, WHO has highlighted the need to detect early predictors of such suicidal behaviors, which can help identify individuals at risk, plan prevention strategies and implement specific therapeutic interventions, particularly in young people, thus reducing the number of deaths. This retrospective observational study aimed to identify early predictors of suicidal risk in 237 inpatients admitted for Suicidal Behaviors and Thoughts at Child and Adolescent Psychiatry Emergency Unit of the Meyer Children's Hospital, Florence, Italy. METHODS: The study was subdivided into three phases: data collection, statistical analysis, and neural network. For each patient, we collected epidemiological and psychopathological data. We stratified the inpatients into two groups: "suicidal volition patients" and "suicidal motivation patients." RESULTS: The hospitalization rate for suicidal behaviors and thoughts showed a growing trend from 2016 to 2020 (27.69 to 45.28%). Under 12 years of age, diagnosis of disruptive, impulse-control and conduct disorder, previous specialist care, history of attempted suicide, and intoxication as methods of suicide were statistically correlated to an increased risk of suicidal behaviors. Artificial intelligence, with an accuracy of 86.7%, confirmed these risk factors. LIMITATIONS: The most important limitation of the study is its retrospective nature. CONCLUSIONS: Our study identifies new early predictors of suicidal risk: age less than 12, diagnosis of disruptive, impulse-control and conduct disorder. In addition, suicidal volition behavior emerges as an important and underestimated risk factor. The use of artificial intelligence methods could be supporting the clinician in assessing suicidal risk.

3D-Printed Patient-Specific Casts for the Distal Radius in Children: Outcome and Pre-Market Survey.

BACKGROUND: Orthopaedic and Trauma surgery is expected to undergo profound transformation as a result of the adoption of 3D technology. Among the various applications, patient specific manufacturing of splints and casts would appear to be, particularly in children, an interesting implementation. This study aims to assess the safety of patient specific 3D casts obtained with a newly developed 3D-scanning devise in a small case series. We therefore conducted a clinical outcome and pre-marketing study in 10 consecutive patients with distal radius fractures treated at an Academic Level I Pediatric Trauma Center. After the application of the 3D cast, patients underwent three consecutive evaluations in the following 21 days. The main outcome measurements were: pain, skin lesions and general comfort, and acceptance of the cast. The three domains were measured with the Visual Analogue Scale (VAS), the NPUAP/EPUAP classification and the Positive affect-Negative affect Scale for Children (PANAS-C), the Self-Assessment Manikin (SAM) clinical psychology tests and a Likert-type five item questionnaire, respectively. A final mechanical analysis of the cast was carried out to confirm product integrity. RESULTS: The results obtained were consistently positive in the investigated domains of general comfort, efficacy of contention and mechanical integrity of the 3D-printed cast as well as in the practicability of the supply chain. CONCLUSIONS: This study provides Level IV evidence that patient specific 3D printed casts obtained with a specifically designed software were safe in the management of "buckle" fractures of the distal radius in children. These results encourage to extend the technology to the treatment of more demanding fractures.

U-net for auricular elements segmentation: a proof-of-concept study.

Convolutional neural networks are increasingly used in the medical field for the automatic segmentation of several anatomical regions on diagnostic and non-diagnostic images. Such automatic algorithms allow to speed up time-consuming processes and to avoid the presence of expert personnel, reducing time and costs. The present work proposes the use of a convolutional neural network, the U-net architecture, for the segmentation of ear elements. The auricular elements segmentation process is a crucial step of a wider procedure, already automated by the authors, that has as final goal the realization of surgical guides designed to assist surgeons in the reconstruction of the external ear. The segmentation, performed on depth map images of 3D ear models, aims to define of the contour of the helix, antihelix, tragus-antitragus and concha. A dataset of 131 ear depth map was created;70% of the data are used as the training set, 15% composes the validation set, and the remaining 15% is used as testing set. The network showed excellent performance, achieving 97% accuracy on the validation test.

G-ear: a user-friendly tool for assisted autologous ear reconstruction.

The major breakthroughs in the fields of reverse engineering and additive manufacturing have dramatically changed medical practice in recent years, pushing for a modern clinical model in which each patient is considered unique. Among the wide spectrum of medical applications, reconstructive surgery is experiencing the most benefits from this new paradigm. In this scenario, the present paper focuses on the design and development of a tool able to support the surgeon in the reconstruction of the external ear in case of malformation or total absence of the anatomy. In particular, the paper describes an appositely devised software tool, named G-ear, which enables the semi-automatic modeling of intraoperative devices to guide the physician through ear reconstruction surgery. The devised system includes 3D image segmentation, semi-automated CAD modelling and 3D printing to manufacture a set of patient-specific surgical guides for ear reconstruction. Usability tests were carried out among the surgeons of the Meyer Children's Hospital to obtain an assessment of the software by the end user. The devised system proved to be fast and efficient in retrieving the optimal 3D geometry of the surgical guides and, at the same time, to be easy to use and intuitive, thus achieving high degrees of likability.

A novel ear elements segmentation algorithm on depth map images.

The growing interest in the auricular anatomy is due to two different strands of research: 1) in the medical field it is associated with autologous ear reconstruction, a surgery adopted following trauma or congenital malformations; 2) in surveillance and law enforcement the ear is used for human detection and recognition. Alternative systems of ear analysis can be differentiated for the type of input data (two-dimensional, three-dimensional or both), for the type of acquisition tools (3D scanner, photographs, video surveillance, etc.) and finally for the adopted algorithms. Although the segmentation and recognition of the ear from the face is a widely discussed topic in literature, the detection and recognition of individual anatomical elements has not yet been studied in depth. To this end, this work lays the foundation for the identification of the auricular elements through image processing algorithms. The proposed algorithm automatically identifies the contours of the main anatomical elements by processing depth map images. The algorithm was tested qualitatively and quantitatively on a dataset composed of 150 ears. The qualitative evaluation was performed with the collaboration of medical staff and the quantitative tests were performed using manually annotated ground truth data.

Outpatient monitoring of Pectus Excavatum: a Neural Network-based approach.

Pectus Excavatum (PE) is a congenital anomaly of the ribcage, at the level of the sterno-costal plane, which consists of an inward angle of the sternum, in the direction of the spine. PE is the most common of all thoracic malformations, with an incidence of 1 in 300-400 people. To monitor the progress of the pathology, severity indices, or thoracic indices, have been used over the years. Among these indices, recent studies focus on the calculation of optical measures, calculated on the optical scan of the patient's chest, which can be very accurate without exposing the patient to invasive treatments such as CT scans. In this work, data from a sample of PE patients and corresponding doctors' severity assessments have been collected and used to create a decision tool to automatically assign a severity value to the patient. The idea is to provide the physician with an objective and easy to use measuring instrument that can be exploited in an outpatient clinic context. Among several classification tools, a Probabilistic Neural Network was chosen for this task for its simple structure and learning mode.

CAD-based automatic modelling of customized cutting templates for Pectus Arcuatum surgical correction.

Pectus Arcuatum (PA) is a congenital chest wall deformity which produces a superior manubrial and sternal protrusion, particularly at the sternal angle. PA surgical correction to reduce the angle of the sternum always includes the removal of bone portion by means of horizontal sternal osteotomies, resection of deformed rib cartilage and finally stabilization of the anterior thoracic wall. Within this process an incorrect assessment of the sternotomy angle during the procedure may lead to the need for bone or cartilage grafts to fill the left voids. This problem has been addressed with a patient-specific cutting template, realized with Reverse Engineering and Additive Manufacturing techniques, which proved to be a key element to simplify the procedure and avoid the occurrence of this type of complications. In this work is presented and validated a procedure that, through common CAD operations, realizes in a completely automatic way the CAD model of the custom cutting template, so as to make non-expert users independent in the realization of the medical device.

Pectus Carinatum: a non-invasive and objective measurement of severity.

To date, standard methods for assessing the severity of chest wall deformities are mostly linked to X-ray and CT scans. However, the use of radiations limits their use when there is a need to monitor the development of the pathology over time. This is particularly important when dealing with patients suffering from Pectus Carinatum, whose treatment mainly requires the use of corrective braces and a systematic supervision. In recent years, the assessment of severity of chest deformities by means of radiation-free devices became increasingly popular but not yet adopted as standard clinical practice. The present study aims to define an objective measure by defining a severity index (named External Pectus Carinatum Index) used to monitor the course of the disease during treatment. Computed on the optical acquisition of the patients' chest by means of an appositely devised, fast and easy-to-use, body scanner, the proposed index has been validated on a sample composed of a control group and a group of Pectus Carinatum patients. The index proved to be reliable and accurate in the characterization of the pathology, enabling the definition of a threshold that allows to distinguish the cases of patients with PC from those of healthy subjects. Graphical abstract.

A Novel Objective Approach to the External Measurement of Pectus Excavatum Severity by Means of an Optical Device.

BACKGROUND: Current approaches to quantifying the severity of pectus excavatum require internal measurements based on cross-sectional imaging. The aim of this study is to exploit a novel index evaluated on the external surface of the chest with a three-dimensional (3D) optical scanner. METHODS: Fifty-one children (41 male, 10 female) between 2 and 17 years of age were evaluated with a 3D optical scanner. Pectus excavatum severity was calculated by using an ad hoc instant 3D scanner and defining an automatic procedure to generate an optical 3D correction index (CI3D). For the latter, an ideal threshold was derived from a statistical analysis, and five blind surveys were collected from pediatric specialists on chest wall deformities. The CI3D was then correlated with blind clinical assessments of PE severity. RESULTS: The cutoff thresholds were determined to optimally discriminate between six degrees of severity of PE patients by a correlation analysis. The correlation coefficient obtained by matching the CI3D with the average subjective severity shows that the proposed method outperforms traditional approaches. CONCLUSIONS: The optical 3D index has a good match with the average subjective assessment in distinguishing patients with mild to severe PE. This innovative approach offers several advantages over existing indices, as it is repeatable and does not require cross-sectional imaging. The index might be particularly suitable for monitoring the efficacy of nonoperative treatment and, in the future, for designing an optimal personalized usage of therapeutic devices.