The potential for machine learning algorithms to improve and reduce the cost of 3-dimensional printing for surgical planning

3D printing of biologics-what has been accomplished to date?

Three-dimensional (3D) printing is a promising approach for the stabilization and delivery of non-living biologics. This versatile tool builds complex structures and customized resolutions, and has significant potential in various industries, especially pharmaceutics and biopharmaceutics. Biologics have become increasingly prevalent in the field of medicine due to their diverse applications and benefits. Stability is the main attribute that must be achieved during the development of biologic formulations. 3D printing could help to stabilize biologics by entrapment, support binding, or crosslinking. Furthermore, gene fragments could be transited into cells during co-printing, when the pores on the membrane are enlarged. This review provides: (i) an introduction to 3D printing technologies and biologics, covering genetic elements, therapeutic proteins, antibodies, and bacteriophages; (ii) an overview of the applications of 3D printing of biologics, including regenerative medicine, gene therapy, and personalized treatments; (iii) information on how 3D printing could help to stabilize and deliver biologics; and (iv) discussion on regulations, challenges, and future directions, including microneedle vaccines, novel 3D printing technologies and artificial-intelligence-facilitated research and product development. Overall, the 3D printing of biologics holds great promise for enhancing human health by providing extended longevity and enhanced quality of life, making it an exciting area in the rapidly evolving field of biomedicine.

The Role of 3D Printing in Treatment Planning of Spine and Sacral Tumors

Three-dimensional (3D) printing technology has proven to have many advantages in spine and sacrum surgery. 3D printing allows the manufacturing of life-size patient-specific anatomic and pathologic models to improve preoperative understanding of patient anatomy and pathology. Additionally, virtual surgical planning using medical computer-aided design software has enabled surgeons to create patient-specific surgical plans and simulate procedures in a virtual environment. This has resulted in reduced operative times, decreased complications, and improved patient outcomes. Combined with new surgical techniques, 3D-printed custom medical devices and instruments using titanium and biocompatible resins and polyamides have allowed innovative reconstructions.

Recent advances on 3D-printed PCL-based composite scaffolds for bone tissue engineering

Population ageing and various diseases have increased the demand for bone grafts in recent decades. Bone tissue engineering (BTE) using a three-dimensional (3D) scaffold helps to create a suitable microenvironment for cell proliferation and regeneration of damaged tissues or organs. The 3D printing technique is a beneficial tool in BTE scaffold fabrication with appropriate features such as spatial control of microarchitecture and scaffold composition, high efficiency, and high precision. Various biomaterials could be used in BTE applications. PCL, as a thermoplastic and linear aliphatic polyester, is one of the most widely used polymers in bone scaffold fabrication. High biocompatibility, low cost, easy processing, non-carcinogenicity, low immunogenicity, and a slow degradation rate make this semi-crystalline polymer suitable for use in load-bearing bones. Combining PCL with other biomaterials, drugs, growth factors, and cells has improved its properties and helped heal bone lesions. The integration of PCL composites with the new 3D printing method has made it a promising approach for the effective treatment of bone injuries. The purpose of this review is give a comprehensive overview of the role of printed PCL composite scaffolds in bone repair and the path ahead to enter the clinic. This study will investigate the types of 3D printing methods for making PCL composites and the optimal compounds for making PCL composites to accelerate bone healing.

Review of Intelligence for Additive and Subtractive Manufacturing: Current Status and Future Prospects

Additive manufacturing (AM), an enabler of Industry 4.0, recently opened limitless possibilities in various sectors covering personal, industrial, medical, aviation and even extra-terrestrial applications. Although significant research thrust is prevalent on this topic, a detailed review covering the impact, status, and prospects of artificial intelligence (AI) in the manufacturing sector has been ignored in the literature. Therefore, this review provides comprehensive information on smart mechanisms and systems emphasizing additive, subtractive and/or hybrid manufacturing processes in a collaborative, predictive, decisive, and intelligent environment. Relevant electronic databases were searched, and 248 articles were selected for qualitative synthesis. Our review suggests that significant improvements are required in connectivity, data sensing, and collection to enhance both subtractive and additive technologies, though the pervasive use of AI by machines and software helps to automate processes. An intelligent system is highly recommended in both conventional and non-conventional subtractive manufacturing (SM) methods to monitor and inspect the workpiece conditions for defect detection and to control the machining strategies in response to instantaneous output. Similarly, AM product quality can be improved through the online monitoring of melt pool and defect formation using suitable sensing devices followed by process control using machine learning (ML) algorithms. Challenges in implementing intelligent additive and subtractive manufacturing systems are also discussed in the article. The challenges comprise difficulty in self-optimizing CNC systems considering real-time material property and tool condition, defect detections by in-situ AM process monitoring, issues of overfitting and underfitting data in ML models and expensive and complicated set-ups in hybrid manufacturing processes.

Exploring a global interpretation mechanism for deep learning networks when predicting sepsis

The purpose of this study is to identify additional clinical features for sepsis detection through the use of a novel mechanism for interpreting black-box machine learning models trained and to provide a suitable evaluation for the mechanism. We use the publicly available dataset from the 2019 PhysioNet Challenge. It has around 40,000 Intensive Care Unit (ICU) patients with 40 physiological variables. Using Long Short-Term Memory (LSTM) as the representative black-box machine learning model, we adapted the Multi-set Classifier to globally interpret the black-box model for concepts it learned about sepsis. To identify relevant features, the result is compared against: (i) features used by a computational sepsis expert, (ii) clinical features from clinical collaborators, (iii) academic features from literature, and (iv) significant features from statistical hypothesis testing. Random Forest was found to be the computational sepsis expert because it had high accuracies for solving both the detection and early detection, and a high degree of overlap with clinical and literature features. Using the proposed interpretation mechanism and the dataset, we identified 17 features that the LSTM used for sepsis classification, 11 of which overlaps with the top 20 features from the Random Forest model, 10 with academic features and 5 with clinical features. Clinical opinion suggests, 3 LSTM features have strong correlation with some clinical features that were not identified by the mechanism. We also found that age, chloride ion concentration, pH and oxygen saturation should be investigated further for connection with developing sepsis. Interpretation mechanisms can bolster the incorporation of state-of-the-art machine learning models into clinical decision support systems, and might help clinicians to address the issue of early sepsis detection. The promising results from this study warrants further investigation into creation of new and improvement of existing interpretation mechanisms for black-box models, and into clinical features that are currently not used in clinical assessment of sepsis.

Establishing a Point-of-Care Virtual Planning and 3D Printing Program

Virtual surgical planning (VSP) and three-dimensional (3D) printing have become a standard of care at our institution, transforming the surgical care of complex patients. Patient-specific, anatomic models and surgical guides are clinically used to improve multidisciplinary communication, presurgical planning, intraoperative guidance, and the patient informed consent. Recent innovations have allowed both VSP and 3D printing to become more accessible to various sized hospital systems. Insourcing such work has several advantages including quicker turnaround times and increased innovation through collaborative multidisciplinary teams. Centralizing 3D printing programs at the point-of-care provides a greater cost-efficient investment for institutions. The following article will detail capital equipment needs, institutional structure, operational personnel, and other considerations necessary in the establishment of a POC manufacturing program.

Leveraging law and ethics to promote safe and reliable AI/ML in healthcare

Artificial intelligence and machine learning (AI/ML) is poised to disrupt the structure and delivery of healthcare, promising to optimize care clinical care delivery and information management. AI/ML offers potential benefits in healthcare, such as creating novel clinical decision support tools, pattern recognition software, and predictive modeling systems. This raises questions about how AI/ML will impact the physician-patient relationship and the practice of medicine. Effective utilization and reliance on AI/ML also requires that these technologies are safe and reliable. Potential errors could not only pose serious risks to patient safety, but also expose physicians, hospitals, and AI/ML manufacturers to liability. This review describes how the law provides a mechanism to promote safety and reliability of AI/ML systems. On the front end, the Food and Drug Administration (FDA) intends to regulate many AI/ML as medical devices, which corresponds to a set of regulatory requirements prior to product marketing and use. Post-development, a variety of mechanisms in the law provide guardrails for careful deployment into clinical practice that can also incentivize product improvement. This review provides an overview of potential areas of liability arising from AI/ML including malpractice, informed consent, corporate liability, and products liability. Finally, this review summarizes strategies to minimize risk and promote safe and reliable AI/ML.

Evaluation of the Clinical, Technical, and Financial Aspects of Cost-Effectiveness Analysis of Artificial Intelligence in Medicine: Scoping Review and Framework of Analysis

BACKGROUND

Cost-effectiveness analysis of artificial intelligence (AI) in medicine demands consideration of clinical, technical, and economic aspects to generate impactful research of a novel and highly versatile technology.

OBJECTIVE

We aimed to systematically scope existing literature on the cost-effectiveness of AI and to extract and summarize clinical, technical, and economic dimensions required for a comprehensive assessment.

METHODS

A scoping literature review was conducted to map medical, technical, and economic aspects considered in studies on the cost-effectiveness of medical AI. Based on these, a framework for health policy analysis was developed.

RESULTS

Among 4820 eligible studies, 13 met the inclusion criteria for our review. Internal medicine and emergency medicine were the clinical disciplines most frequently analyzed. Most of the studies included were from the United States (5/13, 39%), assessed solutions requiring market access (9/13, 69%), and proposed optimization of direct resources as the most frequent value proposition (7/13, 53%). On the other hand, technical aspects were not uniformly disclosed in the studies we analyzed. A minority of articles explicitly stated the payment mechanism assumed (5/13, 38%), while it remained unspecified in the majority (8/13, 62%) of studies.

CONCLUSIONS

Current studies on the cost-effectiveness of AI do not allow to determine if the investigated AI solutions are clinically, technically, and economically viable. Further research and improved reporting on these dimensions seem relevant to recommend and assess potential use cases for this technology.

Innovative Application of Three-Dimensional-Printed Breast Model-Aided Reduction Mammaplasty

Symptomatic macromastia places a severe physical and psychological burden on patients. Reduction mammaplasty is the primary treatment; however, conventional surgery may lead to postoperative nipple-areolar complex necrosis due to damage to the dominant supplying arteries. In this study, we designed and fabricated an innovative, three-dimensional-printed breast vascular model to provide surgical guidance for reduction mammaplasty. Preoperative computed tomography angiography scanning data of patients were collected. The data were then processed and reconstructed using the E3D digital medical modeling software (version 17.06); the reconstructions were then printed into a personalized model using stereolithography. The three-dimensional-printed breast vascular model was thus developed for individualized preoperative surgical design. This individualized model could be used to intuitively visualize the dominant supplying arteries’ spatial location in the breasts, thereby allowing effective surgical planning for reduction mammaplasty. The three-dimensional-printed breast vascular model can therefore provide an individualized preoperative design and patient education, avoid necrosis of the nipple-areolar complex, shorten operation duration, and ensure safe and effective surgery in patients.

Deep Learning-Based Automatic Segmentation of Mandible and Maxilla in Multi-Center CT Images

Sophisticated segmentation of the craniomaxillofacial bones (the mandible and maxilla) in computed tomography (CT) is essential for diagnosis and treatment planning for craniomaxillofacial surgeries. Conventional manual segmentation is time-consuming and challenging due to intrinsic properties of craniomaxillofacial bones and head CT such as the variance in the anatomical structures, low contrast of soft tissue, and artifacts caused by metal implants. However, data-driven segmentation methods, including deep learning, require a large consistent dataset, which creates a bottleneck in their clinical applications due to limited datasets. In this study, we propose a deep learning approach for the automatic segmentation of the mandible and maxilla in CT images and enhanced the compatibility for multi-center datasets. Four multi-center datasets acquired by various conditions were applied to create a scenario where the model was trained with one dataset and evaluated with the other datasets. For the neural network, we designed a hierarchical, parallel and multi-scale residual block to the U-Net (HPMR-U-Net). To evaluate the performance, segmentation with in-house dataset and with external datasets from multi-center were conducted in comparison to three other neural networks: U-Net, Res-U-Net and mU-Net. The results suggest that the segmentation performance of HPMR-U-Net is comparable to that of other models, with superior data compatibility.

Artificial Intelligence in hepatology, liver surgery and transplantation: Emerging applications and frontiers of research

The integration of artificial intelligence (AI) and augmented realities into the medical field is being attempted by various researchers across the globe. As a matter of fact, most of the advanced technologies utilized by medical providers today have been borrowed and extrapolated from other industries. The introduction of AI into the field of hepatology and liver surgery is relatively a recent phenomenon. The purpose of this narrative review is to highlight the different AI concepts which are currently being tried to improve the care of patients with liver diseases. We end with summarizing emerging trends and major challenges in the future development of AI in hepatology and liver surgery.

Automatic Segmentation of Mandible from Conventional Methods to Deep Learning-A Review

Medical imaging techniques, such as (cone beam) computed tomography and magnetic resonance imaging, have proven to be a valuable component for oral and maxillofacial surgery (OMFS). Accurate segmentation of the mandible from head and neck (H&N) scans is an important step in order to build a personalized 3D digital mandible model for 3D printing and treatment planning of OMFS. Segmented mandible structures are used to effectively visualize the mandible volumes and to evaluate particular mandible properties quantitatively. However, mandible segmentation is always challenging for both clinicians and researchers, due to complex structures and higher attenuation materials, such as teeth (filling) or metal implants that easily lead to high noise and strong artifacts during scanning. Moreover, the size and shape of the mandible vary to a large extent between individuals. Therefore, mandible segmentation is a tedious and time-consuming task and requires adequate training to be performed properly. With the advancement of computer vision approaches, researchers have developed several algorithms to automatically segment the mandible during the last two decades. The objective of this review was to present the available fully (semi)automatic segmentation methods of the mandible published in different scientific articles. This review provides a vivid description of the scientific advancements to clinicians and researchers in this field to help develop novel automatic methods for clinical applications.

Recurrent Convolutional Neural Networks for 3D Mandible Segmentation in Computed Tomography

Purpose: Classic encoder–decoder-based convolutional neural network (EDCNN) approaches cannot accurately segment detailed anatomical structures of the mandible in computed tomography (CT), for instance, condyles and coronoids of the mandible, which are often affected by noise and metal artifacts. The main reason is that EDCNN approaches ignore the anatomical connectivity of the organs. In this paper, we propose a novel CNN-based 3D mandible segmentation approach that has the ability to accurately segment detailed anatomical structures. Methods: Different from the classic EDCNNs that need to slice or crop the whole CT scan into 2D slices or 3D patches during the segmentation process, our proposed approach can perform mandible segmentation on complete 3D CT scans. The proposed method, namely, RCNNSeg, adopts the structure of the recurrent neural networks to form a directed acyclic graph in order to enable recurrent connections between adjacent nodes to retain their connectivity. Each node then functions as a classic EDCNN to segment a single slice in the CT scan. Our proposed approach can perform 3D mandible segmentation on sequential data of any varied lengths and does not require a large computation cost. The proposed RCNNSeg was evaluated on 109 head and neck CT scans from a local dataset and 40 scans from the PDDCA public dataset. The final accuracy of the proposed RCNNSeg was evaluated by calculating the Dice similarity coefficient (DSC), average symmetric surface distance (ASD), and 95% Hausdorff distance (95HD) between the reference standard and the automated segmentation. Results: The proposed RCNNSeg outperforms the EDCNN-based approaches on both datasets and yields superior quantitative and qualitative performances when compared to the state-of-the-art approaches on the PDDCA dataset. The proposed RCNNSeg generated the most accurate segmentations with an average DSC of 97.48%, ASD of 0.2170 mm, and 95HD of 2.6562 mm on 109 CT scans, and an average DSC of 95.10%, ASD of 0.1367 mm, and 95HD of 1.3560 mm on the PDDCA dataset. Conclusions: The proposed RCNNSeg method generated more accurate automated segmentations than those of the other classic EDCNN segmentation techniques in terms of quantitative and qualitative evaluation. The proposed RCNNSeg has potential for automatic mandible segmentation by learning spatially structured information.

A semi-automatic seed point-based method for separation of individual vertebrae in 3D surface meshes: a proof of principle study

PURPOSE

The purpose of this paper is to present and validate a new semi-automated 3D surface mesh segmentation approach that optimizes the laborious individual human vertebrae separation in the spinal virtual surgical planning workflow and make a direct accuracy and segmentation time comparison with current standard segmentation method.

METHODS

The proposed semi-automatic method uses the 3D bone surface derived from CT image data for seed point-based 3D mesh partitioning. The accuracy of the proposed method was evaluated on a representative patient dataset. In addition, the influence of the number of used seed points was studied. The investigators analyzed whether there was a reduction in segmentation time when compared to manual segmentation. Surface-to-surface accuracy measurements were applied to assess the concordance with the manual segmentation.

RESULTS

The results demonstrated a statically significant reduction in segmentation time, while maintaining a high accuracy compared to the manual segmentation. A considerably smaller error was found when increasing the number of seed points. Anatomical regions that include articulating areas tend to show the highest errors, while the posterior laminar surface yielded an almost negligible error.

CONCLUSION

A novel seed point initiated surface based segmentation method for the laborious individual human vertebrae separation was presented. This proof-of-principle study demonstrated the accuracy of the proposed method on a clinical CT image dataset and its feasibility for spinal virtual surgical planning applications.