Abstract: Statistical Shape Model (SSM) for infant cranial analysis is challenging due to open sutures, which complicate the process of establishing anatomical correspondences between models. This study proposes a Wrap4D-based methodology for accurate preparation of newborn’s cranial samples used in SSM. The approach integrates skin and skull segmentation with a guided wrapping technique that supports suture filling through anatomically-guided surface adaptation, while ensuring high fidelity in shape alignment. SSM algorithm uses the prepared dataset of 75 normal infant skulls from Meyer Children’s Hospital IRCCS for the creation of a template, which serves as the reference model for defining a standard newborn’s cranial shape. The methodology offers a rapid, reproducible and anatomically accurate solution for modelling suture closure. Preliminary results led to a Generalization of 1.245 mm, a Specificity of 2.659 mm and a Compactness of 98% with 20 modes of variation. Finally, quantitative comparison with traditional wrapping techniques reveals Wrap4D superior anatomical preservation in the region of suture.

Keywords: Newborn Skull | Statistical Shape Model | Suture closure | Wrapping

Abstract: This paper presents a comprehensive application of an automated surgical planning workflow for bone tumor resection, integrating two previously developed algorithms into a real clinical case. The study focuses on a patient with a left tibial osteosarcoma, demonstrating how the automated framework streamlines the entire preoperative process, from tumor resection planning to allograft selection. The cutting plane optimization tool reduced manual planning time from hours to just 19 min while ensuring complete tumor removal with minimal healthy bone resection. For reconstruction, the system automatically reconstructed the patient’s premorbid anatomy and selected the best-matched allograft from a virtual donor database, achieving a high degree of anatomical precision (mean distance: 0.29 mm). The results highlight the clinical potential of this integrated approach, which improves efficiency, reduces subjectivity, and enhances reproducibility in complex bone tumor surgeries.

Keywords: Allograft | Design Method | Optimization | PSO | Tumor Resection | Virtual Prototyping

Abstract: Point clouds have become a widely used data format in computer vision, driven by the increasing availability of 3D scanning devices in applications such as robotics and autonomous driving. However, challenges in data acquisition, such as occlusion, reflection, and limited sensor resolution, often result in incomplete scans. Consequently, point cloud completion, the task of reconstructing the complete geometry of a point cloud object from partial data, has emerged as a key area of research. Numerous deep learning-based methods have been proposed to tackle this problem. Although some surveys on shape completion exist, the rapid growth of research in recent years calls for an updated review. In this work, we present a comprehensive survey of recent advancements in deep neural networks for point cloud completion, covering literature from 2024 up to December 2025. After establishing a reference context by analyzing the major foundational methods up to the year 2023, we review the most recent methods with an analytical perspective based on how they have improved each specific component of the network. Furthermore, we present a comparative analysis of the performance of the reviewed methods on the main benchmark datasets, and finally, we discuss open challenges, offering insights and suggestions for future research directions.

Keywords: 3D Object Reconstruction | Computer Vision | Deep Learning | Point Cloud Completion | Review | Shape Completion

Abstract: In tumor resection surgery, an approach to the reconstruction of the bone anatomy, after removal of the tumor, is represented by allografts. A good match between the donor and recipient is crucial in enhancing integration and minimizing failure rate. However, the recipient bone is often altered by the tumor, making the comparison unreliable. Moreover, evaluating multiple donors is often a complex and time-consuming process. Thus, in this work, an algorithm is proposed that is able to automatically reconstruct the virtual healthy bone anatomy of the recipient and to use this reconstruction to select the most suitable donor. The proposed algorithm first reconstructs the healthy anatomy by aligning the bone to the mirrored contralateral using the Iterative Closest Point (ICP) algorithm. Then, to select the optimal donor, the algorithm queries a digital bone bank by aligning the reconstructed template to donor candidates using a localized search strategy. Finally, L1-Chamfer Distance and a newly devised metric called Surface Distance are computed to evaluate the similarity and assess the optimal donor. The algorithm was validated on a dataset of 49 healthy femurs by creating 980 simulated resections. A retrospective study on two real cases was also conducted. The algorithm achieved a median L1-Chamfer Distance of 0.7217 mm and a Surface Distance of 0.3225 mm for the reconstruction of the healthy anatomy and 0.8621 mm and 0.5338 mm, respectively, for the best donor. The retrospective studies showed how the algorithm was able to outperform the manual procedure in both time and accuracy of the allograft. These case studies highlighted how the algorithm performs efficiently even in real case scenarios, enhancing the shape matching between the recipient and donor bone and thus possibly improving post-operative outcomes.

Abstract: 3D part segmentation is critical for applications ranging from robotics to shape modification, but supervised methods require costly point-level annotations and struggle to generalize beyond their training categories. Recent approaches address this limitation by transferring knowledge from 2D base models, pretrained on large-scale image datasets, to 3D shapes through multi-view rendering and backprojection. However, most existing methods still rely on prompt optimization, fine-tuning with few shots, or distillation into dedicated 3D networks. We propose DirectPart, a fully zero-shot pipeline that leverages the Segment Anything Model 3 (SAM3) for 3D part segmentation without any training, fine-tuning, or prompt engineering. The method renders 3D meshes from multiple viewpoints sampled on an icosphere, applies SAM3 with minimal text prompts to segment each view, and aggregates 2D predictions onto 3D surfaces via depth-buffer unprojection and majority voting. We evaluate the full ShapeNetPart benchmark covering all 16 categories. Our method achieves 68.5% mean IoU, 73.6% median IoU, and 83.1% accuracy.

Keywords: 3D part segmentation | Multi-view aggregation | Point cloud segmentation | Segment anything model | Zero-shot learning

Abstract: The placement of irregular three-dimensional components, such as the ones designed for customized packaging, inside a container is a crucial task in the field of CAD-based design. This operation typically involves a number of numerical optimization problems, typically followed by spatial decision process in which designers iteratively, and often manually, evaluate and refine alternative configurations under geometric constraints. This process is often time-consuming, and the final result can be far from optimal. To solve this issue, the present paper proposes 2POS-3D, a two-phase strategy for supporting 3D container placement. In the first phase (called neural stage), a Dynamic Graph Convolutional Neural Network rapidly provides a placement suggestion directly processing point cloud data. This enables real-time visual feedback during design exploration. In the second phase (called evolutionary stage), a Covariance Matrix Adaptation Evolution Strategy optimization procedure refines the initial hypothesis by imposing geometric compatibility and non-penetration constraints. In particular, the neural stage employs a Curvature-Adaptive Normal-Guided Chamfer Distance to emphasize geometrically complex regions during learning. The evolutionary stage implements a computationally efficient Normal-Guided Chamfer variant suitable for real-time refinement. The method is validated against a synthetic dataset of 1000 generated piece–container pairs. The proposed strategy significantly improves over baseline strategies, including pure neural network-based prediction and uninformed evolutionary initialization. In detail, an average Euclidean placement error of 0.06 units and a 96.5% success rate under a 0.2-unit tolerance threshold was in fact reached. The average computation time results in approximately 1.3 s per piece. This is compatible with a possible development in scenarios where rapid placement of parts is required. Finally, additional multi-piece placement experiments demonstrate the possibility of scaling the approach for more complex scenarios.

Keywords: 3D geometric optimization | CMA-ES | DGCNN | Interactive 3D placement

Abstract: Quality control is considered one of the most important tasks by manufacturing industries, as being able to guarantee certain quality levels is necessary in order to meet customer expectations, reduce waste and costs. Requiring an inspection for each of the products manufactured, being able to have a tool capable of automating the detection of possible defects would simplify this procedure, making it faster and more optimised. This is the specific case of the company Esaote, which carries out accurate quality control for each of its ultrasound probes. In particular, concerning the inspection of the shell, that is currently carried out manually by the staff. To create a tool capable of automating this inspection, a defect detection algorithm based on machine learning is proposed. The algorithm processes the images according to a patch-based strategy, following three steps: splits the image in patches, classifies and localizes the defects in the patches, and finally combines the results to obtain the complete list of all the defects present. Performance was analysed for different configurations related to the three steps, with particular emphasis on the percentage of overlap between patches, the total number of patches to be analysed, and the voting algorithm used to combine results between several patches. The best configuration identified an accuracy of 83.63%, an f-score of 89.87%, a precision of 81.60%, a recall of 88.97%, an AP of 77.63% and finally an AUC of 83.48%.

Keywords: Artificial Intelligence | Computer vision | Convolutional neural network | Image Processing | Visual inspection

Abstract: In bone tumor resection surgery, patient-specific cutting guides aid the surgeon in the resection of a precise part of the bone. Despite the use of automation methodologies in surgical guide modeling, to date, the placement of cutting planes is a manual task. This work presents an algorithm for the automatic positioning of cutting planes to reduce healthy bone resected and thus improve post-operative outcomes. The algorithm uses particle swarm optimization to search for the optimal positioning of points defining a cutting surface composed of planes parallel to a surgical approach direction. The quality of a cutting surface is evaluated by an objective function that considers two key variables: the volumes of healthy bone resected and tumor removed. The algorithm was tested on three tumor cases in long bone epiphyses (two tibial, one humeral) with varying plane numbers. Optimal optimization parameters were determined, with varying parameters through iterations providing lower mean and standard deviation of the objective function. Initializing particle swarm optimization with a plausible cutting surface configuration further improved stability and minimized healthy bone resection. Future work is required to reach 3D optimization of the planes positioning, further improving the solution.

Keywords: Computer-aided surgery | Optimization | Orthopedic surgery | Surgical planning | Tumor resection

Abstract: Lung sequestration is a rare congenital anomaly characterized by an abnormal mass of lung tissue. It can occur in two forms, either intralobar, where the mass is embedded within the lung tissue, or extralobar, where it develops outside the lung's boundaries. In both cases, removal of this defect involves a complex minimally invasive procedure during which, in brief, the sequestration is isolated and removed. The surgical removal of the pulmonary sequestration represents a complex challenge for surgeons who have to deal with many critical aspects, such as the heartbeat-induced movement of the lung and, in pediatric cases, very limited operating space. For this reason, it is crucial to create a realistic training program that faithfully reproduces the operating conditions and enables surgeons to become familiar with this procedure. The simulator proposed in this work offers a higher level of anatomical realism than existing systems, including critical details such as the visceral pleura and accurately reproduce spatial relationships between anatomical structures. Moreover, the simulation of cardiac motion adds an element of complexity that simulate the challenges of surgery. The simulator was tested in a realistic operating room setup, validating its practical applicability.

Keywords: CAD modeling | Cardiac motion simulation | Minimally invasive thoracic surgery | Pediatric surgical simulator | Pulmonary sequestration

Abstract: In radiotherapy treatments of mobile lesions, several strategies are used to treat the tumour while sparing the surrounding tissues [1]. The ADAM phantom (Anthropomorphic Dynamic breAthing Model) was developed to test dose delivery in lung cancer treatment. The aim of this study is to create ADAM A symbol representing the male gender, depicted as a circle with an arrow pointing diagonally upwards to the right. (Anthropomorphic Dynamic breAthing Model - Chemical structure diagram showing a hexagonal benzene ring with alternating double bonds. Attached to the ring is a hydroxyl group (OH) and a methyl group (CH3). The structure is labeled with standard chemical notation. male&female), a new modular phantom based on ADAM, to test free-breathing and deep inspiration breath hold (DIBH) breast radiotherapy treatments [2, 3]. The 3D model of ADAM was reconstructed using computed tomography (CT) scans to ensure a high level of anatomical accuracy. This digital model of ADAM served as the starting point for the design and development of ADAM Symbol representing a combination of male and female gender symbols, featuring a circle with an arrow pointing diagonally upward to the right and a cross extending downward. . 3D printable materials with tissue mimicking properties were selected to replicate tissues and organs [4, 5, 6, 7, 8–9]. The torso and chest were printed in PLA and the ribs and spine were printed in PLA StoneFil™ [10]. Tests have shown that ADAM A symbol representing the male gender, depicted as a circle with an arrow pointing diagonally upwards to the right. closely mimics human tissue in terms of Hounsfield Units. Its modular structure allows rapid transition between male and female configurations, making it suitable for realistic simulation of many clinical situations. ADAM A symbol combining the male and female gender symbols, featuring a circle with an arrow pointing diagonally upwards to the right and a cross extending downwards. demonstrates adequate performance for future testing gating and tracking devices in the treatment of moving breast and lung lesions. Chemical structure diagram showing a hexagonal benzene ring with alternating double bonds. Attached to the ring is a hydroxyl group (OH) and a methyl group (CH3). The structure is labeled with standard chemical notation.

Keywords: 3D Modelling | 3D Printing | Anthropomorphic Breathing Phantom | Tissue Mimicking

Abstract: With approximately 431,000 cases, kidney cancer ranks 14th in terms of diagnostic frequency and accounts for 2.2% of all new cancer cases worldwide.12. For malignant clear cell renal cell carcinoma (ccRCC), which necessitates WHO/ISUP grading based on tissue microscopic analysis, early diagnosis is critical for targeted treatment. With the use of a convolutional neural network with three blocks, this study presents a machine learning-based system to grade kidney tumors using CT scans. The system divides tumours into low-grade (grades 1 and 2) and high-grade (grades 3 and 4), which corresponds to the tumour’s aggressiveness and helps determine the prognosis. The challenge kits21 database’s 237 preoperative CT scans were used to train the model, which yielded an accuracy of 93.67% and an f-score of 91.80%. For reliable performance validation, the approach consists of data preprocessing, augmentation, and a binary classifier with a majority voting ensemble model. The objective of this non-invasive method is to improve diagnostic accuracy in clinical settings by decreasing inter-observer variability. The dataset will be enlarged in future work to enable wider application. Although there is hope for the system’s clinical support, more validation is necessary before generalization can occur.

Keywords: AI | ccRCC | Deep learning | grading | image processing | kidney cancer

Abstract: Optimizing olive oil extraction process could be a key aspect to improve the quality of the final product. This study aims to develop an automatic olive oil and water content percentage predictor within olive paste or pomace samples using near-infrared (NIR) spectroscopy and machine learning. The samples were collected from two olive mills in Tuscany, Italy, and their NIR spectra were acquired. To ensure more accurate results a wide range for the olive oil content (3.23% to 30.54%) and water content (43.23% to 75.54%) has been collected. Several techniques are considered, trained and evaluated using k-fold cross-validation. The results shows that the Bayesian Ridge Regression model outperforms the other techniques, achieving a Root Mean Squared Error (RMSE) of 3.22% and 2.03% respectively for olive oil and water content considering the original spectral data. After denoising the spectral data, the model's performance improves further, reaching an RMSE of 3.00% for olive oil and 1.85% for water on the hold-out test set. Starting from these findings it is possible to understand the effectiveness of the developed of automatic predictor to accurately estimate olive oil and water percentages within olive pomace. Introducing this technique in a real scenario could help to optimize the olive oil extraction process and the utilization of this agricultural by-product, also enabling the possibility to rapidly and objectively understand the quality of the product.

Keywords: Machine learning | Near-infrared spectroscopy | Olive pomace | Regression

Abstract: Industry 4.0 conceptualizes the automation of processes through the introduction of technologies such as artificial intelligence and advanced robotics, resulting in a significant production improvement. Detecting defects in the production process, predicting mechanical malfunctions in the assembly line, and identifying defects of the final product are just a few examples of applications of these technologies. In this context, this work focuses on the detection of ultrasound probes’ surface defects, with a focus on Esaote S.p.A.’s production line probes. To date, this control is performed manually and therefore biased by many factors such as surface morphology, color, size of the defect, and by lighting conditions (which can cause reflections preventing detection). To overcome these shortfalls, this work proposes a fully automatic machine vision system for surface acquisition of ultrasound probes coupled with an automated defect detection system that leverage artificial intelligence. The paper addresses two crucial steps: (i) the development of the acquisition system (i.e., selection of the acquisition device, analysis of the illumination system, and design of the camera handling system); (ii) the analysis of neural network models for defect detection and classification by comparing three possible solutions (i.e., MMSD-Net, ResNet, EfficientNet). The results suggest that the developed system has the potential to be used as a defect detection tool in the production line (full image acquisition cycle takes ~ 200 s), with the best detection accuracy obtained with the EfficientNet model being 98.63% and a classification accuracy of 81.90%.

Keywords: Artificial intelligence | Image processing | Inspection system | Product characterization | Virtual prototyping

Abstract: Background: In recent years, the treatment of wrist fractures has been the focus of numerous studies, particularly in the development of casts modeled on the patient's anatomy using additive manufacturing techniques. A 3D printed cast offers several advantages over traditional treatment methods, including washability, lightness, and ventilation. Objective: This work introduces an automatic procedure for designing patient-specific wrist orthoses from a 3D scan of the arm using open-source mesh-processing libraries. Methods: The procedure consists of seven steps that generate a customized orthosis model. Due to the absence of a single library capable of completing the entire modeling process, we defined the best execution strategy for each step and established a communication flow between the various blocks. Results: The resulting orthosis comprises two halves, secured by three appropriately positioned bands and perforated with ventilation holes. The modeling procedure takes approximately 5 min to complete and was evaluated on 20 scans of arms of different shapes and sizes. The process proved to be fast, reliable, and suitable for direct use by medical personnel. Conclusions: The developed automatic procedure for designing patient-specific wrist orthoses is efficient and effective, facilitating the use of 3D printed casts in medical practice.

Keywords: 3D modelling | 3D printed orthosis | Personalized medicine | Reverse engineering | Wrist orthosis

Abstract: Autologous ear reconstruction is a surgical procedure aimed at total or partial reconstruction of the ear of patients with microtia, which is a malformation or absence of the anatomical element. This procedure involves harvesting cartilage material from the patient at the costal level, cut and sculpt the tissue to create the skeleton of the ear, which is then inserted into a subcutaneous pocket in the malformed region. The sculping procedure takes inspiration from the geometry of the patient’s contralateral healthy ear and can be very complex given the particularity of the elements to be reconstructed. Taking advantage of Reverse Engineering and Additive Manufacturing technologies, the authors, in collaboration with hospital staff, proposed patient-specific three-dimensional cutting guides that can facilitate the surgeon in sculpting the ear structure. In this work, a fully automated procedure for creating the printable digital model of such guides is proposed: at first is performed the segmentation of ear elements, which represent the starting data for the automated CAD modelling of the surgical guides. The automatic CAD modelling procedure was tested and validated by medical personnel.

Keywords: CAD Modelling | Ear Reconstruction | Reverse Engineering | Surgical Guide

Abstract: Autologous ear reconstruction is a surgical procedure performed in the case of defects of the outer ear in which the malformed anatomy is reconstructed with autologous cartilage tissue and often involves the use of surgical guides modelled from a digital reconstruction of the ear anatomy. To obtain such three-dimensional anatomy, traditional imaging methods, which are expensive and invasive, can be replaced by professional 3D scanners or low-cost commercial devices. In this context, this paper focuses on the evaluation of two devices for the acquisition of the outer ear, the Intel® RealSense D405™ (stereo camera) and the TrueDepth camera of the iPhone® 13 (structured light camera), proposing a comparison based on four parameters: accuracy, precision, deviation range and point-to-point distance, in order to assess their usability in the medical field, and in particular in the context of autologous ear reconstruction. The results show that, despite significantly different handling of the raw data, the performance of the two devices is comparable: average accuracy is 0.76 mm for the D405 and 0.95 mm for the iPhone 13, average precision is 0.071 mm for the D405 and 0.065 mm for the iPhone 13, average range of deviation is 3.12 mm for the D405 and 3.64 mm for the iPhone 13.

Keywords: 3D scanning | Accuracy assessment | Ear reconstruction | RealSense D405 | TrueDepth camera

Abstract: The treatment of burn scars is a hotly debated and delicate subject since ineffective therapy can significantly lower quality of life. Ideally, medical evaluation should leverage objective assessments of progress over time to provide an adequate assessment of scar health and related treatment. In contrast, common clinical practice involves medical examination that rely on subjective assessment scales such as Vancouver Scar Scale and the Patient and Observer Scar Assessment Scale. Recently, extraction of objective parameters for the investigation of scar surface were studied by objectively analyzing the surface topography and extracting scar roughness through a transposition of standard mechanical surface evaluation methods, which are based on ISO 4287 and ISO 4288, to the clinical field. The most advanced methods analyze the scar roughness globally and after subdividing it in sub-patches of pre-fixed dimension. In both cases, it is not considered that the scar may be located in non-planar portions of the body, therefore, roughness values are dependent from the principal roughness evaluation direction. In the present work these shortfalls are overcome using a systematic procedure to subdivide the patches in a consistent manner and analyze smaller portions of the surface providing a roughness value independent of the filtering direction.

Keywords: 3D scar model | Automatic assessment | Burn scar | Surface roughness

Abstract: RGB-D cameras have been widely used in various research fields and applications in recent years. With the growing availability of commercial products, choosing the most suitable sensor for a specific application has become more complex. The lack of tools to evaluate and compare the metrological performance of these sensors was addressed by the recent ISO 10360-13:2021 standard, which defines the standards for the metrological characterization of 3D optical coordinate measuring systems. This paper applies the ISO 10360-13 methodology to characterize and compare four RGB-D cameras: three Intel® RealSense™ (D415, D435i, D455) and one Microsoft® Azure Kinect DK. The procedures described in the standard were integrated with three tests: the analysis of systematic errors measured acquiring a planar surface at increasing distances; a test to analyze the resolution performances with a specifically devised artifact; the evaluation of 3D reconstruction performances on two objects with different geometric characteristics. The results highlighted the strengths and weaknesses of each device. The D415 showed better performance in reconstructions from close-range acquisitions. The Azure Kinect DK had the best results for systematic error and resolution. The D455 generally achieved the best performance in the standard tests, followed by the D435i.

Keywords: device characterization | Intel RealSense | ISO 10360-13:2021 standard | Microsoft Azure Kinect DK | performance evaluation

Abstract: Autologous ear reconstruction is a surgical procedure which aims to restore the anatomy of the outer ear whenever there are malformations due to congenital defects (microtia) or as a result of trauma and burns. Reconstruction involves the cutting, carving, and modeling of a portion of costal cartilage harvested from the patient. The aesthetic results of the surgery are highly dependent on the manual skill of the surgeon, which therefore needs a wide range of surgical experience. Appropriate simulation and training tools are essential to acquire adequate familiarity with the procedure without compromising the patient’s aesthetic appearance. In such a context, the present work aims to create replicas of the costal cartilage that allow a realistic simulation of the surgery, thus taking into account important characteristics of the cartilage tissue such as the behavior to cut and suture, hardness, etc. The problem is approached with well-established Additive Manufacturing and Reverse Engineering techniques, which are increasingly being used in the medical field, addressing both the problem of identifying the most suitable materials and the possibility of providing medical personnel with simple interactive procedures for the fabrication of multilayer replicas, without the need to turn to expert CAD modelers.

Keywords: CAD modeling | Costal cartilage mold | Ear reconstruction | Medical simulation

Abstract: The Fourth Industrial Revolution conceptualizes the rapid change of industries resulting from the convergence of technologies such as artificial intelligence, genetic editing, and advanced robotics that enable increasing interconnectivity and machines that can analyze and diagnosing problems without human intervention, through intelligent automation. In this scenario, the use of augmented reality technologies is of great interest. The paper aims to explore the use of augmented reality in support of traditional inspections for assisting textile experts in fabric defect detection. The contribution of this study consists of three main phases, necessary for the future development of the system: (1) the analysis of possible automatic defect detection techniques; (2) the analysis of hardware solutions for the realization of a system based on important criteria such as operator comfort, system footprint, and so on; (3) the proposal of a possible comprehensive solution. Considering these aspects this paper identifies and investigate the best scenario for the introduction of artificial intelligence and augmented reality technologies to help the operator in the detection of textile defects.

Keywords: Artificial intelligence | augmented reality | machine vision | textile defect detection

Abstract: This article presents a methodology for the design and production of custom prostheses for complex surgical interventions on long bones due to oncological surgical treatment. This type of intervention considers the complete or partial removal of bone tissue that might be affected by bone tumors. In this scenario it is important to limit the loss of functionality of the patients’ joints. Accordingly, it is important to salvage, whenever possible, the original articulation surfaces of the joints; nevertheless, a complete evaluation of the tumor extension and of the state of bone tissue might be difficult to be performed in the preparation phase. The article presents an approach for geometrical modelling of a modular prosthesis for long bones, that leaves the surgeon free to tailor the resection according to their feedback in the operating theatre. Specifically, the devised methodology allows to salvage part of the original bone by switching modules of the prosthesis. The dissertation is tackled from a technical perspective, taking into account the constraints and key features that need to be considered in the design and production of a long bone prosthesis via additive manufacturing technologies. The methodology is presented with reference to a complex custom prosthesis design that was carried out with the support of T3Ddy’s - Personalized pediatrics by inTegrating 3D aDvanced technologies research laboratory.

Keywords: Additive Manufacturing | Custom prosthesis | Design for Additive Manufacturing

Abstract: Despite technological advances in diagnostic imaging, to distinguish the type of renal tumor without performing a biopsy is still an unsolved challenge. In particular, this is even more striking in the case of clear cell renal cell carcinoma and small oncocytomas. To tackle this problem, a fully automated tool is proposed that can provide decision support for physicians to distinguish between these two types of masses in the most critical cases. In this work three approaches for the development of this tool are implemented and compared, specifically two approaches are based on the use of radiomic features and one on the use of deep features. The nnU-net is exploited to achieve tumor segmentation necessary to obtain the different types of features. The architectures are trained and tested by combining two different datasets, the public dataset KiTS2019 and data from the Careggi University Hospital. The best method is able to obtain 73.77% balanced accuracy, 94.59% sensitivity, 52.94% specificity and 86.84% accuracy.

Keywords: Cancer classification | clear cell renal cell carcinoma | computer aided diagnosis | deep learning | oncocytoma | radiomics

Abstract: The use of customized surgical guides for the removal of bone tumors is an increasingly common practice in advanced hospitals. These devices are modeled directly on the 3D model of the patient's anatomy and produced using additive techniques; therefore, they have the ability to perfectly anchor to the bone anatomy and allow the tissue of the tumor mass to be removed according to cutting paths predetermined by the physician during preoperative planning. This work proposes a semi-automatic framework for modeling custom surgical guides composed of two main modules: 1) a web application, called Precise, that allows the surgeon to visualize and manipulate 3D anatomical models and enter a set of cutting planes that determine the correct tumor resection paths and other useful information for modeling the surgical guide; 2) a fully automatic procedure that based on this information creates the guide's STL model. The entire procedure aims to create a specific type of cutting guide designed to guide an oscillating saw in a series of planar cuts, thus isolating the tumor. The cutting guides produced are composed of three main elements: a base, the blade slot, and pin’s holes.

Keywords: Medical 3D Model | Medical Application | Rapid Prototyping | Surgical Planning

Abstract: 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.

Keywords: artificial intelligence | children and adolescents | risk of suicide and predictive factors | Suicidal behaviors and thoughts

Abstract: Background: Microtia is a congenital anomaly of the ear. We present an innovative technique using a 3D personalized framework that could simplify and standardize the sculpting phase, thanks to reverse engineering and additive manufacturing techniques. Methods: Three-dimensional models were realized by T3Ddy, a joint laboratory between the department of industrial engineering and Meyer Children's Hospital. Data were obtained retrospectively and included patient demographics, primary diagnosis, side of the affected ear, microtia classification, surgical time, length of hospitalization, type of skin approach and framework, complications, aesthetic results, and level of satisfaction using specific questionnaires. Data are reported as median and IQR. Results: A total of 17 children (female gender: four) underwent auricular reconstruction surgery with autologous cartilage in our center, between 2019 and 2022. Median age at surgery was 14 years [interquartile range (IQR), 13-17], and the median hospitalization length was 5 days (IQR, 3-5). Median surgical time was 420 minutes (IQR, 406-452). Complications occurred in four patients out of 19 procedures, with a complication rate of 21%. Aesthetic results were satisfactory in all cases. Conclusions: The three-dimensional models allow for an intuitive and precise approach. Having developed specific models for each component of the framework, we aimed to improve the aesthetic result and simplify the surgical intervention, guaranteeing a standardized yet personalized experience for each patient. The interprofessional partnership is fundamental to achieving this result.

Abstract: This paper presents a collaborative platform developed to allow the communication between surgeons and engineers in the process of designing patient-specific surgical instruments. To date, only a few applications are available to collaboratively create surgical instruments from medical 3D models, mostly dedicated to expert CAD modelers. This makes the preoperative planning process time-consuming and inefficient limiting the usability of applications and making planning difficult and inaccurate. Accordingly, we propose a solution in the form of a web-based, interactive, extendable, 3D navigation and manipulation application, called Precise, which does not require client installation. Precise is a lightweight, high-performance application built to provide easy-to-use, powerful, on-demand visualization and manipulation of 3D images, implemented using open-source libraries.

Keywords: 3D manipulation | Medical application | Rapid prototyping | Surgical planning

Abstract: The development of eco-sustainable systems for the textile industry is a trump card for attracting expanding markets aware of the ecological challenges that society expects in the future. For companies willing to use regenerated wool as a raw material for creating plain, colored yarns and/or fabrics, building up a number of procedures and tools for classifying the conferred recycled materials based on their color is crucial. Despite the incredible boost in automated or semi-automated methods for color classification, this task is still carried out manually by expert operators, mainly due to the lack of systems taking into account human-related classification. Accordingly, the main aim of the present work was to devise a simple, yet effective, machine vision-based system combined with a probabilistic neural network for carrying out reliable color classification of plain, colored, regenerated wool fabrics. The devised classification system relies on the definition of a set of color classes against which to classify the recycled wool fabrics and an appositely devised acquisition system. Image-processing algorithms were used to extract helpful information about the image color after a set of images has been acquired. These data were then used to train the neural network-based algorithms, which categorized the fabric samples based on their color. When tested against a dataset of fabrics, the created system enabled automatic classification with a reliability index of approximately 83%, thus demonstrating its effectiveness in comparison to other color classification approaches devised for textile and industrial fields.

Keywords: color | fabrics | machine vision | neural networks

Abstract: Purpose: Among thoracic malformations, pectus deformities have the highest incidence and can result in a wide range of severe and mild clinical manifestations. Recently, the treatment of pectus deformities is shifting from traditional approaches toward customized solutions. This occurs by leveraging innovative rapid prototyping tools that allow for the design and fabrication of patient-specific treatments and medical devices. This paper aims to provide a comprehensive view of the growing literature in this area to analyze the progress made in this direction. Design/methodology/approach: The search was performed on major search engines through keywords inherent to reverse engineering (RE) and additive manufacturing (AM) technologies applied to pectus deformities and related treatments, selecting 54 papers. These were analyzed according to the addressed pathology, the hardware and software tools used and/or implemented and their integration within the clinical pathway. Findings: First, the analysis led to analyze and divide the papers according to how RE and AM technologies are applied for surgical and non-surgical treatments, pathological assessment and preoperative simulation and planning. Second, all papers were considered within the typical rapid prototyping framework consisting of the three phases of three-dimensional (3D) scanning, 3D modelling and 3D printing. Originality/value: To the best of the authors’ knowledge, to date, no survey has provided a comprehensive view of innovative and personalized treatment strategies for thoracic malformations; the present work fills this gap, allowing researchers in this field to have access to the most promising findings on the treatment and evaluation of pathology.

Keywords: 3D printing | Additive manufacturing | Pectus carinatum | Pectus excavatum | Reverse engineering