An Artificial Intelligence-Based Collaboration Approach in Industrial IoT Manufacturing: Key Concepts, Architectural Extensions and Potential Applications.

The digitization of manufacturing industry has led to leaner and more efficient production, under the Industry 4.0 concept. Nowadays, datasets collected from shop floor assets and information technology (IT) systems are used in data-driven analytics efforts to support more informed business intelligence decisions. However, these results are currently only used in isolated and dispersed parts of the production process. At the same time, full integration of artificial intelligence (AI) in all parts of manufacturing systems is currently lacking. In this context, the goal of this manuscript is to present a more holistic integration of AI by promoting collaboration. To this end, collaboration is understood as a multi-dimensional conceptual term that covers all important enablers for AI adoption in manufacturing contexts and is promoted in terms of business intelligence optimization, human-in-the-loop and secure federation across manufacturing sites. To address these challenges, the proposed architectural approach builds on three technical pillars: (1) components that extend the functionality of the existing layers in the Reference Architectural Model for Industry 4.0; (2) definition of new layers for collaboration by means of human-in-the-loop and federation; (3) security concerns with AI-powered mechanisms. In addition, system implementation aspects are discussed and potential applications in industrial environments, as well as business impacts, are presented.

Adaptive Physics-Based Non-Rigid Registration for Immersive Image-Guided Neuronavigation Systems.

Objective: In image-guided neurosurgery, co-registered preoperative anatomical, functional, and diffusion tensor imaging can be used to facilitate a safe resection of brain tumors in eloquent areas of the brain. However, the brain deforms during surgery, particularly in the presence of tumor resection. Non-Rigid Registration (NRR) of the preoperative image data can be used to create a registered image that captures the deformation in the intraoperative image while maintaining the quality of the preoperative image. Using clinical data, this paper reports the results of a comparison of the accuracy and performance among several non-rigid registration methods for handling brain deformation. A new adaptive method that automatically removes mesh elements in the area of the resected tumor, thereby handling deformation in the presence of resection is presented. To improve the user experience, we also present a new way of using mixed reality with ultrasound, MRI, and CT. Materials and methods: This study focuses on 30 glioma surgeries performed at two different hospitals, many of which involved the resection of significant tumor volumes. An Adaptive Physics-Based Non-Rigid Registration method (A-PBNRR) registers preoperative and intraoperative MRI for each patient. The results are compared with three other readily available registration methods: a rigid registration implemented in 3D Slicer v4.4.0; a B-Spline non-rigid registration implemented in 3D Slicer v4.4.0; and PBNRR implemented in ITKv4.7.0, upon which A-PBNRR was based. Three measures were employed to facilitate a comprehensive evaluation of the registration accuracy: (i) visual assessment, (ii) a Hausdorff Distance-based metric, and (iii) a landmark-based approach using anatomical points identified by a neurosurgeon. Results: The A-PBNRR using multi-tissue mesh adaptation improved the accuracy of deformable registration by more than five times compared to rigid and traditional physics based non-rigid registration, and four times compared to B-Spline interpolation methods which are part of ITK and 3D Slicer. Performance analysis showed that A-PBNRR could be applied, on average, in <2 min, achieving desirable speed for use in a clinical setting. Conclusions: The A-PBNRR method performed significantly better than other readily available registration methods at modeling deformation in the presence of resection. Both the registration accuracy and performance proved sufficient to be of clinical value in the operating room. A-PBNRR, coupled with the mixed reality system, presents a powerful and affordable solution compared to current neuronavigation systems.

Tackling Faults in the Industry 4.0 Era-A Survey of Machine-Learning Solutions and Key Aspects.

The recent advancements in the fields of artificial intelligence (AI) and machine learning (ML) have affected several research fields, leading to improvements that could not have been possible with conventional optimization techniques. Among the sectors where AI/ML enables a plethora of opportunities, industrial manufacturing can expect significant gains from the increased process automation. At the same time, the introduction of the Industrial Internet of Things (IIoT), providing improved wireless connectivity for real-time manufacturing data collection and processing, has resulted in the culmination of the fourth industrial revolution, also known as Industry 4.0. In this survey, we focus on the vital processes of fault detection, prediction and prevention in Industry 4.0 and present recent developments in ML-based solutions. We start by examining various proposed cloud/fog/edge architectures, highlighting their importance for acquiring manufacturing data in order to train the ML algorithms. In addition, as faults might also occur from sources beyond machine degradation, the potential of ML in safeguarding cyber-security is thoroughly discussed. Moreover, a major concern in the Industry 4.0 ecosystem is the role of human operators and workers. Towards this end, a detailed overview of ML-based human-machine interaction techniques is provided, allowing humans to be in-the-loop of the manufacturing processes in a symbiotic manner with minimal errors. Finally, open issues in these relevant fields are given, stimulating further research.

Histopathologic study of the carotid sheath in patients with oral squamous cell carcinoma.

PURPOSE: The carotid sheath has not been adequately assessed in the literature as a potential site of neck recurrence. The purpose of this prospective study was to investigate the histopathologic characteristics of the carotid sheath in patients with oral cancer, in an effort to clarify whether it is essential or redundant to include the carotid sheath in the neck dissection specimen. PATIENTS AND METHODS: A total of 29 patients underwent 32 selective neck dissections in the Department of Oral and Maxillofacial Surgery at "Evangelismos" General Hospital of Athens, Greece. Twenty-six unilateral and 3 bilateral neck dissections were performed. The carotid sheath specimens were examined to identify possible traces of metastatic disease. The existence of lymphatic vessels and the possible presence of cancer cells within their lumen was also investigated. RESULTS: Light microscopy of the 32 carotid sheath specimens showed that there was no evidence of tumor invasion. Immunohistochemical evaluation showed an abundance of lymphatic vessels in the carotid sheath with no evidence of microscopic intraluminal metastatic emboli. CONCLUSIONS: There was no evidence of carotid sheath invasion or presence of intraluminal lymphatic tumor emboli. Evidence of extracapsular spread warrants carotid sheath excision. Our findings suggest that if no extracapsular spread is present, there is no need to perform a tedious dissection of the carotid sheath. Preserving the carotid sheath adds protection to the neurovascular bundle, cuts operating time, and avoids possible injury to the major vessels and vagus nerve, as well as stimulation of the carotid body.

Mechanical and dose delivery accuracy evaluation in radiosurgery using polymer gels.

The polymer gel-Magnetic Resonance Imaging (MRI) dosimetry technique was employed to evaluate the mechanical and dose delivery accuracy in Leksell gamma knife stereotactic radiosurgery for the treatment of multiple targets. Two different polymer gel dosimeter formulations that have been reported in the literature were prepared in-house. A plan for the treatment of four brain metastases (targets) was generated. The plan involved the delivery of four, 8 mm collimator shots using different prescription isodose lines and different prescription doses for each target, keeping the maximum dose constant for all the targets. A sample of each gel formulation was irradiated using a custom made phantom with an experimental procedure capable of testing the increased nominal mechanical accuracy of stereotactic radiosurgery. The irradiated dosimeters were evaluated using a clinical 1.5 T Philips ACS NT MR imager. Result manipulation in 3-D allowed for the determination of the mechanical accuracy in the delivery of each shot through the comparison of measured versus planned shot center coordinates. Dose delivery accuracy was also evaluated by comparison of maximum dose values measured at the center of each shot as well as dose distribution measurements, with corresponding treatment planning calculations. Polymer gel dosimetry was found capable of verifying the complete chain of radiosurgery treatment in gamma knife applications involving the irradiation of multiple targets.

The effect of finite patient dimensions and tissue inhomogeneities on dosimetry planning of 192Ir HDR breast brachytherapy: a Monte Carlo dose verification study.

PURPOSE: To evaluate the accuracy of clinical dosimetry planning using commercially available treatment planning systems in (192)Ir high-dose-rate (HDR) breast brachytherapy, with emphasis on skin dose, in view of potential uncertainties owing to the patient finite dimensions and the presence of the lung. METHODS AND MATERIALS: A patient-equivalent mathematical phantom was constructed on the basis of the patient computed tomography scan used in the clinical treatment planning procedure. The actual treatment plan delivered to the patient, involving an implant of six plastic catheters and 26 programmed source dwell positions, was simulated by means of the Monte Carlo method. Results are compared with corresponding dose calculations of a commercially available treatment planning system in the form of prescribed dose percentage isodose contours and cumulative dose-volume histograms. RESULTS: The comparison of Monte Carlo results and treatment planning system calculations revealed that all percentage isodose contours greater than 60% of the prescribed dose are not affected by the finite breast dimensions or the presence of the lung. Treatment planning system calculations overestimate dose in the lung as well as lower isodose contours at points lying both close to the breast or lung surface and relatively away from the implant. In particular, skin dose is overestimated by 5% in the central breast region and within 10% at all other points. CONCLUSIONS: Dose-volume histogram and all other relevant planning quality indices for the planning target volume calculated by the treatment planning system are credible. Skin and lung dose calculations by the treatment planning system can be thought of as a conservative approach in view of the reported dose overestimation.

Superficial parotidectomy: technical modifications based on tumour characteristics.

AIM: The purpose of this study was to evaluate the adequacy of partial superficial parotidectomy and tumour enucleation in the surgical management of patients with pleomorphic adenoma of the parotid. MATERIAL AND METHODS: A total of 62 patients were treated for pleomorphic adenoma of the parotid during the years 1995-1999; 17 patients were treated with conventional superficial parotidectomy, whereas 42 patients were subjected to partial superficial parotidectomy. In three patients, tumour size and facial nerve proximity essentially resulted in enucleation of the parotid mass. In partial superficial parotidectomy, only the tumour-bearing area of the gland parenchyma was excised with identification of the main trunk and preservation of the facial nerve division that was adjacent to the tumour site with no need for more extensive facial nerve dissection. RESULTS: There was no incidence of recurrence or facial nerve injury in our group of patients. The incidence of Frey's syndrome was 4.8%.

Dose verification in clinical IMRT prostate incidents.

PURPOSE: In view of the need for dose-validation procedures on each individual intensity-modulated radiation therapy (IMRT) plan, dose-verification measurements by film, by ionization chamber, and by polymer gel-MRI dosimetry were performed for a prostate-treatment plan configuration. Treatment planning system (TPS) calculations were evaluated against dose measurements. METHODS AND MATERIALS: Intensity-modulated radiation therapy (IMRT) treatments were planned on a commercial TPS. Kodak EDR-2 films were used for the verification of two-dimensional (2D) dose distributions at 1 coronal and 5 axial planes in a water-equivalent phantom. Full three-dimensional (3D) dose distributions were measured by use of a novel polymer gel formulation and a 3D magnetic resonance imaging (MRI) readout technique. Calculations were compared against measurements by means of isocontour maps, gamma-index maps (3% dose difference, 3-mm distance to agreement) and dose-volume histograms. RESULTS: A good agreement was found between film measurements and TPS predictions for points within the 60% isocontour, for all the examined plans (gamma-index <1 for 96% of pixels). Three-dimensional dose distributions obtained with the polymer gel-MRI method were adequately matched with corresponding TPS calculations, for measurements in a gel phantom covering the planning-target volume (PTV). CONCLUSIONS: Measured 2D and 3D dose distributions suggest that, for the investigated prostate IMRT plan configuration, TPS calculations provide clinically acceptable accuracy.

Localized jaw enlargement in renal osteodystrophy: report of a case and review of the literature.

Renal osteodystrophy is a common long-term complication of end-stage renal disease. Involvement of the jaws is common and radiographic alterations are often one of the earliest signs of chronic renal disease. However, marked enlargement of the jaws is a rare complication of renal osteodystrophy. A case of localized asymptomatic enlargement of the mandible in a 38-year-old woman with chronic renal failure is presented. The clinical, radiographic, and histological findings were consistent with renal osteodystrophy. To our knowledge, this is the third case of localized mandibular enlargement of renal osteodystrophy reported in the English-language literature.

Dosimetric calculations and VIPAR polymer gel dosimetry close to the microSelectron HDR.

In the present study, different dosimetric methods were investigated for their ability to predict the energy dose in the vicinity of the microSelectron HDR 192Ir brachytherapy source. The results of a time-efficient Sievert integral model of proven accuracy in the cm distance range from all 192Ir sources were benchmarked against accurate Monte Carlo derived dosimetric data in the close vicinity of the source. This comparison revealed that the Sievert model is capable of accurate dosimetry even in the mm distance range from the source. The dose rate distributions were compared with results obtained from different versions (v. 13.7 and 14.2.2) of the Plato BPS commercial treatment planning system, for an application following the Paris trial intravascular irradiation protocol. The results of brachytherapy planning system calculations were found reliable at radial distances of clinical relevance. Noticeable errors existed only in the extreme case of dose calculations at 2 mm from the source axis using Plato v. 13.7. Experimental dosimetric data for the intravascular application, as obtained through the VIPAR polymer gel-MRI method, were also evaluated for dose verification purposes. This method allowed with reasonable accuracy the verification of absolute dose distributions for peripheral vessel applications using 192Ir sources.