Pattern recognition in medical settings

A document is presented with the results of various investigations related to data patterns, more specifically those that have been designed with intelligent computational tools. The use of data patterns in medicine is something that has emerged in recent decades and that increasingly presents development alternatives for engineering projects. Various scientific publications are evaluated in this document to relate engineering applications in medicine, and contrast the possible technological impact offered by computational sciences. Keywords: Engineering in medicine, pattern recognition, computer science. References [1]R. Pallás-Areny, «LA INGENIERÍA ELECTRÓNICA Y LA MEDICINA,» [En línea]. Available: https://www.researchgate.net/profile/Ramon-Pallas-Areny/publication/239813249_La_Ingenieria_electronica_y_la_medicina/links/0deec539fea82baf03000000/La-Ingenieria-electronica-y-la-medicina.pdf. [Último acceso: 27 diciembre 2021].[2]H. Medellín, G. González, R. Espinosa, E. Govea y T. Lim, «Desarrollo de Aplicaciones de Realidad Virtual y Sistemas Hápticos en Ingeniería, medicina y arte,» de Ciencias de la Ingeniería y Tecnología, San Luis Potosí-Mexico, Universidad Autónoma de San Luis Potosí, 2014, pp. 77-93. [3]S. Chris, E. Ray, J. Andrew y L. Jason, «Designing cranial implants in a haptic augmented reality environment,» Communications of the ACM, vol. 47, nº 8, pp. 33-38, 2004. [4]G. Sabine, K. Erwin y G. Bernd, «Advances in interactive craniofacial surgery planning by 3D simulation and visualization.,» Oral and Maxillofacial Surgery, vol. 24, pp. 120-125, 1995. [5]P. Philipp, G. B. Alexander, P. Andreas, V. S. Norman, P. Bernhard, P. Andreas, H. Karl-Heinz, T. Ulf, S. Ingo y H. Max, «Virtual Dental Surgery as a New Educational Tool in Dental School,» Journal of Cranio- Maxillo-Facial Surgery, vol. 38, pp. 560-564, 2010. [6]C. Castañeda y F. Vázquez, «Realidad Virtual, un apoyo en la Terapia de Acrofobia, Claustrofobia y Agorafobia, » de Memorias del VIII Congreso Internacional sobre Innovación y Desarrollo Tecnológico (CIINDET 2011), Cuernavaca Morelos, México., 2011. [7]F. Suárez, O. Flor y L. Rosales, «Sistema de interpretación de conductas para identificación de situaciones de riesgo,» Revista Ibérica de Sistemas e Tecnologias de Informação, vol. E31, pp. 309-317, 2020.

Cranial Implant Design Applying Shape-Based Interpolation Method via Open-Source Software

Reconstructing a large skull defect is a challenge, as it normally involves the use of sophisticated proprietary image processing and expensive CAD software. As an alternative, open-source software can be used for this purpose. This study aimed to compare the 3D cranial implants reconstructed from computed tomography (CT) images using the open-source MITK software with commercial 3-matic software for ten decompressive craniectomy patients. The shape-based interpolation method was used, in which the technique of segmenting every fifth and tenth slice of CT data was performed. The final design of patient-specific implants from both software was exported to STL format for analysis. The results of the Kruskal–Wallis test for the surface and volume of cranial implants designed using 3-matic and the two MITK techniques showed no significant difference, p > 0.05. The results of the Hausdorff Distance (HD) and Dice Similarity Coefficient (DSC) analyses for cranial implants designed using 3-matic software and the two different MITK techniques showed that the average points distance for 3-matic versus MITK was 0.28 mm (every tenth slice) and 0.15 mm (every fifth slice), and the similarity between 3-matic and MITK on every tenth and fifth slices were 85.1% and 89.7%, respectively. The results also showed that the open-source MITK software is comparable with the commercial software for designing patient-specific implants.

Quantitative Assessment of Point-of-Care 3D-Printed Patient-Specific Polyetheretherketone (PEEK) Cranial Implants

Recent advancements in medical imaging, virtual surgical planning (VSP), and three-dimensional (3D) printing have potentially changed how today’s craniomaxillofacial surgeons use patient information for customized treatments. Over the years, polyetheretherketone (PEEK) has emerged as the biomaterial of choice to reconstruct craniofacial defects. With advancements in additive manufacturing (AM) systems, prospects for the point-of-care (POC) 3D printing of PEEK patient-specific implants (PSIs) have emerged. Consequently, investigating the clinical reliability of POC-manufactured PEEK implants has become a necessary endeavor. Therefore, this paper aims to provide a quantitative assessment of POC-manufactured, 3D-printed PEEK PSIs for cranial reconstruction through characterization of the geometrical, morphological, and biomechanical aspects of the in-hospital 3D-printed PEEK cranial implants. The study results revealed that the printed customized cranial implants had high dimensional accuracy and repeatability, displaying clinically acceptable morphologic similarity concerning fit and contours continuity. From a biomechanical standpoint, it was noticed that the tested implants had variable peak load values with discrete fracture patterns and failed at a mean (SD) peak load of 798.38 ± 211.45 N. In conclusion, the results of this preclinical study are in line with cranial implant expectations; however, specific attributes have scope for further improvements.

Cranioplasty of post-trepanation skull defects using additive 3D printing technologies

Introduction. Every year, there is an increase in the number of operations performed using personalized cranioplasts, which are made with additive 3D printing technologies. They allow surgical intervention, taking into account the characteristics of the shape of the patient's skull. This is especially important when closing large and complex defects extending from the cranial vault to the bones of the facial skeleton. One of the innovative applications of additive technologies in cranioplasty is the creation of implants, preformed based on individual 3D-printed models. However, no preliminary estimates of the results of treatment of patients using the traditional methods of cranial implants and individualized modeling methods were found in the available literary sources.The study objective is to compare the results of treatment using cranioplasts, preformed based on individual 3D-printed skull models and using traditional intraoperative modeling.Materials and methods. A study of 50 patients with post-craniotomy defects of the skull. All patients have undergone cranioplasty. Depending on the technique of individualization of the cranial implants, patients were divided into 2 groups: 1st - using individual 3D-printed models (n = 32), 2nd - traditional intraoperative modeling (n = 18).Results. Statistically, the groups differed significantly in terms of the duration of the intraoperative stage of cranioplasty, postoperative and total hospital stay, indicators of symmetry and financial costs. No differences were found in the duration of the preoperative hospital stay, the number of implant fixation points, the volume of intraoperative blood loss and the quality of life according to the SF-36. The first group (6.25 %) in comparison with the second (16.7 %) had a smaller number of postoperative complications.Conclusion. Modern 3D printing technologies recreate bone models based on patients' individual characteristics, thereby providing time for careful planning of the operation, even at the outpatient stage. The results of the study showed that the usage of cranioplasts preformed with 3D-printed models provides precise closure of post-craniotomy defects, better restoration of the skull contours, and a significant reduction in the duration of the cranioplasty stage. The use of the technology does not lead to a significant increase in the cost of treatment using traditional intraoperative modeling.

A fully adapted headstage for electrophysiological experiments with custom and scalable electrode arrays to record widely distributed brain regions

ABSTRACTElectrophysiological recordings lead amongst the techniques that aim to investigate the dynamics of neural activity sampled from large neural ensembles. However, the financial costs associated with the state-of-the-art technology used to manufacture probes and multi-channel recording systems make these experiments virtually inaccessible to small laboratories, especially if located in developing countries. Here, we describe a new method for implanting several tungsten electrode arrays, widely distributed over the brain. Moreover, we designed a headstage system, using the Intan® RHD2000 chipset, associated with a connector (replacing the expensive commercial Omnetics connector), that allows the usage of disposable and cheap cranial implants. Our results showed high-quality multichannel recording in freely moving animals (detecting local field, evoked responses and unit activities) and robust mechanical connections ensuring long-term continuous recordings. Our project represents an open source and inexpensive alternative to develop customized extracellular records from multiple brain regions.

Group Refractive Index of Nanocrystalline Yttria-Stabilized Zirconia Transparent Cranial Implants

Transparent “Window to the Brain” (WttB) cranial implants made from a biocompatible ceramic, nanocrystalline Yttria-Stabilized Zirconia (nc-YSZ), were recently reported. These reports demonstrated chronic brain imaging across the implants in mice using optical coherence tomography (OCT) and laser speckle imaging. However, optical properties of these transparent cranial implants are neither completely characterized nor completely understood. In this study, we measure optical properties of the implant using a swept source OCT system with a spectral range of 136 nm centered at 1,300 nm to characterize the group refractive index of the nc-YSZ window, over a narrow range of temperatures at which the implant may be used during imaging or therapy (20–43°C). Group refractive index was found to be 2.1–2.2 for OCT imaging over this temperature range. Chromatic dispersion for this spectral range was observed to vary over the sample, sometimes flipping signs between normal and anomalous dispersion. These properties of nc-YSZ should be considered when designing optical systems and procedures that propagate light through the window, and when interpreting OCT brain images acquired across the window.

Feasibility Study of the Cranial Implant Fabricated without Supports in Electron Beam Melting

Additive manufacturing (AM), particularly electron beam melting (EBM), is becoming increasingly common in the medical industry because of its remarkable benefits. The application of personalized titanium alloy implants produced using EBM has received considerable attention in recent times due to their simplicity and efficacy. However, these tailored implants are not cost-effective, placing a tremendous strain on the patient. The use of additional materials as support during the manufacturing process is one of the key causes of its high cost. A lot of research has been done to lessen the use of supports through various types of support designs. There is indeed a noticeable paucity of studies in the literature that have examined customized implants produced without or minimal supports. This research, therefore, reports on the investigation of cranial implants fabricated with and without supports. The two personalized implants are evaluated in terms of their cost, fabrication time, and accuracy. The study showed impressive results for cranial implants manufactured without supports that cost 39% less than the implants with supports. Similarly, the implant’s (without supports) build time was 18% less than its equivalent with supports. The two implants also demonstrated similar fitting accuracy with 0.2613 mm error in the instance of implant built without supports and 0.2544 mm for the implant with supports. The results indicate that cranial implants can be produced without EBM supports, which can minimize both production time and cost substantially. However, the manufacture of other complex implants without supports needs further study. The future study also requires a detailed review of the mechanical and structural characteristics of cranial implants built without supports.

Synthetic skull bone defects for automatic patient-specific craniofacial implant design

Patient-specific craniofacial implants are used to repair skull bone defects after trauma or surgery. Currently, cranial implants are designed and produced by third-party suppliers, which is usually time-consuming and expensive. Recent advances in additive manufacturing made the in-hospital or in-operation-room fabrication of personalized implants feasible. However, the implants are still manufactured by external companies. To facilitate an optimized workflow, fast and automatic implant manufacturing is highly desirable. Data-driven approaches, such as deep learning, show currently great potential towards automatic implant design. However, a considerable amount of data is needed to train such algorithms, which is, especially in the medical domain, often a bottleneck. Therefore, we present CT-imaging data of the craniofacial complex from 24 patients, in which we injected various artificial cranial defects, resulting in 240 data pairs and 240 corresponding implants. Based on this work, automatic implant design and manufacturing processes can be trained. Additionally, the data of this work build a solid base for researchers to work on automatic cranial implant designs.