Automated delineation of thyroid nodules in ultrasound images using spatial neutrosophic clustering and level set

An accurate contour estimation plays a significant role in classification and estimation of shape, size, and position of thyroid nodule. This helps to reduce the number of false positives, improves the accurate detection and efficient diagnosis of thyroid nodules. This paper introduces an automated delineation method that integrates spatial information with neutrosophic clustering and level-sets for accurate and effective segmentation of thyroid nodules in ultrasound images. The proposed delineation method named as Spatial Neutrosophic Distance Regularized Level Set (SNDRLS) is based on Neutrosophic L-Means (NLM) clustering which incorporates spatial information for Level Set evolution. The SNDRLS takes rough estimation of region of interest (ROI) as input provided by Spatial NLM (SNLM) clustering for precise delineation of one or more nodules. The performance of the proposed method is compared with level set, NLM clustering, Active Contour Without Edges (ACWE), Fuzzy C-Means (FCM) clustering and Neutrosophic based Watershed segmentation methods using the same image dataset. To validate the SNDRLS method, the manual demarcations from three expert radiologists are employed as ground truth. The SNDRLS yields the closest boundaries to the ground truth compared to other methods as revealed by six assessment measures (true positive rate is 95.45 ± 3.5%, false positive rate is 7.32 ± 5.3% and overlap is 93.15 ± 5. 2%, mean absolute distance is 1.8 ± 1.4 pixels, Hausdorff distance is 0.7 ± 0.4 pixels and Dice metric is 94.25 ± 4.6%). The experimental results show that the SNDRLS is able to delineate multiple nodules in thyroid ultrasound images accurately and effectively. The proposed method achieves the automated nodule boundary even for low-contrast, blurred, and noisy thyroid ultrasound images without any human intervention. Additionally, the SNDRLS has the ability to determine the controlling parameters adaptively from SNLM clustering.     

Optimization of the implant diameter and length in type B/2 bone for improved biomechanical properties: A three-dimensional finite element analysis

In this paper, effects of the implant diameter and length on the maximum equivalent stresses were evaluated in jaw bones, and maximum displacements examined in an implant–abutment complex by a finite element method. The implant diameter ranged from 3.0 mm to 5.0 mm, and implant length ranged from 6.0 mm to 16.0 mm. Results suggested that under axial load, the maximum equivalent stresses in cortical and cancellous bones decreased by 77.4% and 68.4% with the increasing of diameter and length respectively. Under buccolingual load, those decreased by 64.9% and 82.8%, respectively. The maximum displacements of implant-abutment complex decreased by 56.9% and 78.2% under axial and buccolingual load respectively. When the diameter exceeded 3.9 mm and the length exceeded 9.5 mm, the minimum stress/displacement was obtained. The evaluating targets were more sensitive to the diameter change than that of the length. Data indicated that the implant diameter affected stress distribution in jaw bone more than length did; and an implant diameter exceeding 3.9 mm and implant length exceeding 9.5 mm was the optimal selection for type B/2 bone in a cylinder implant by biomechanical considerations.     

Early-stage atherosclerosis detection using deep learning over carotid ultrasound images

This paper proposes a computer-aided diagnosis tool for the early detection of atherosclerosis. This pathology is responsible for major cardiovascular diseases, which are the main cause of death worldwide. Among preventive measures, the intima-media thickness (IMT) of the common carotid artery stands out as early indicator of atherosclerosis and cardiovascular risk. In particular, IMT is evaluated by means of ultrasound scans. Usually, during the radiological examination, the specialist detects the optimal measurement area, identifies the layers of the arterial wall and manually marks pairs of points on the image to estimate the thickness of the artery. Therefore, this manual procedure entails subjectivity and variability in the IMT evaluation. Instead, this article suggests a fully automatic segmentation technique for ultrasound images of the common carotid artery. The proposed methodology is based on machine learning and artificial neural networks for the recognition of IMT intensity patterns in the images. For this purpose, a deep learning strategy has been developed to obtain abstract and efficient data representations by means of auto-encoders with multiple hidden layers. In particular, the considered deep architecture has been designed under the concept of extreme learning machine (ELM). The correct identification of the arterial layers is achieved in a totally user-independent and repeatable manner, which not only improves the IMT measurement in daily clinical practice but also facilitates the clinical research. A database consisting of 67 ultrasound images has been used in the validation of the suggested system, in which the resulting automatic contours for each image have been compared with the average of four manual segmentations performed by two different observers (ground-truth). Specifically, the IMT measured by the proposed algorithm is 0.625 ± 0.167 mm (mean ± standard deviation), whereas the corresponding ground-truth value is 0.619 ± 0.176 mm. Thus, our method shows a difference between automatic and manual measures of only 5.79 ± 34.42 μm. Furthermore, different quantitative evaluations reported in this paper indicate that this procedure outperforms other methods presented in the literature.     

Selection of the implant thread pitch for optimal biomechanical properties: A three-dimensional finite element analysis

In this paper, effects of the implant thread pitch on the maximum Von Mises stresses were evaluated in jaw bones and implant–abutment complex by a finite element method. The thread pitch ranged from 0.5 mm to 1.6 mm. Results suggested that under axial load, the maximum equivalent stresses in cortical bone, cancellous bone and implant–abutment complex decreased by 6.7%, 55.2% and 22.3%, respectively with the variation of thread pitch; and under buccolingual load, 2.7%, 22.4% and 13.0%, respectively. When thread pitch exceeded 0.8 mm, minimum stresses were obtained. Data indicated that cancellous bone was more sensitive to thread pitch than cortical bone did; thread pitch played a great role in protecting dental implant under axial load than under buccolingual load; and thread pitch exceeding 0.8 mm were optimal selection for a screwed implant by biomechanical consideration.     

Designing of potential inhibitors against Staphylococcus aureus sortase A: Combined analogue and structure based approach with in vitro validation

Staphylococcus aureus sortase A is an attractive target of Gram-positive bacteria that plays a crucial role in anchoring of surface proteins to peptidoglycan present in bacterial cell wall. Inhibiting sortase A is an elementary and essential effort in preventing the pathogenesis. In this context, in silico virtual screening of in-house database was performed using ligand based pharmacophore model as a filter. The developed pharmacophore model AAHR 11 consists of two acceptors, one hydrophobic and one ring aromatic feature. Top ranked molecule KKR1 was docked into the active site of the target. After profound analysis, it was analyzed and optimized based on the observations from its binding pose orientation. Upgraded version of KKR1 was KKR2 and has improved docking score, binding interactions and best fit in the binding pocket. KKR1 along with KKR2 were further validated using 100 ns molecular dynamic studies. Both KKR1 and KKR2 contain Indole-thiazolidine moiety and were synthesized. The disk diffusion assay has good initial results (ZI of KKR1, KKR2 were 24, 38 mm at 10 μg/mL and ZI of Ampicillin was 22 at 10 μg/mL) and calculated MICs of the molecules (KKR1 5.56 ± 0.28 μg/mL, KKR2 1.32 ± 0.12 μg/mL, Ampicillin 8 ± 1.1 μg/mL) were in good agreement with standard drug Ampicillin. KKR1 has shown IC₅₀ of 1.23 ± 0.14 μM whereas the optimized lead molecule KKR2 show IC₅₀ of 0.008 ± 0.07 μM. Results from in silico were validated by in vitro studies and proved that indole-thiazolidine molecules would be useful for future development as lead molecules against S. aureus sortase A.     

Continuous blood pressure estimation based on multiple parameters from eletrocardiogram and photoplethysmogram by Back-propagation neural network

The cuff-less continuous blood pressure monitoring provides reliable and invaluable information about the individuals’ health condition. Conventional sphygmomanometer with a cuff measures only the value of the blood pressure intermittently and the measurement process is sometimes inconvenient. In this work, a systematic approach with multi-parameter fusion has been proposed to estimate the non-invasive beat-to-beat systolic and diastolic blood pressure with high accuracy. The methods involve real-time monitoring of the electrocardiogram (ECG) and photoplethysmogram (PPG), and extracting the R peak from the ECG and relevant feature parameters from the synchronous PPG. Also, it covers the creation of the topological model of back-propagation neural network that has fifteen neurons in the input layer, ten neurons in the single interlayer, and two neurons in the output layer, where all the neurons are fully connected. As for the results, the proposed method was validated on the volunteers. The reference blood pressure (BP) is from Finometer (MIDI, Finapres Medical System, Netherlands). The results showed that the mean ± S.D. for the estimated systolic BP (SBP) and diastolic BP (DBP) with the proposed method against reference were −0.41 ± 2.02 mmHg and 0.46 ± 2.21 mmHg, respectively. Thus, the continuous blood pressure algorithm based on Back-Propagation neural network provides a continuous BP with a high accuracy.     

Thin film temperature sensor for real-time measurement of electrolyte temperature in a polymer electrolyte fuel cell

This paper describes a technique for the measurement of the electrolyte temperature in an operating polymer electrolyte fuel cell (PEFC). A patterned thin film gold thermistor embedded in a 16 μm thick parylene film was laminated in the Nafion^® electrolyte layer for in situ temperature measurements. Experimental results show that the sensor has a linear response of (3.03 ± 0.09) × 10⁻³ °C⁻¹ in the 20–100 °C temperature range and is robust enough to withstand the electrolyte expansion forces that occur during water uptake. An electrolyte temperature increase of 1.5 °C was observed in real-time when operating the fuel cell at 0.2 V and a current density of 0.19 A/cm². The temperature sensitivity of the present sensor is in an order of magnitude better than the conventional micro-thermocouples that have been reported. Additionally, use of micro-fabrication techniques allows for an accurate placement of the temperature sensor within the fuel cell. Simulation results show that the sensor has no significant effect on the local temperature distribution.     

Performance comparison of artificial neural network and logistic regression model for differentiating lung nodules on CT scans

PurposeTo compare the diagnostic performances of artificial neural networks (ANNs) and multivariable logistic regression (LR) analyses for differentiating between malignant and benign lung nodules on computed tomography (CT) scans.MethodsThis study evaluated 135 malignant nodules and 65 benign nodules. For each nodule, morphologic features (size, margins, contour, internal characteristics) on CT images and the patient’s age, sex and history of bloody sputum were recorded. Based on 200 bootstrap samples generated from the initial dataset, 200 pairs of ANN and LR models were built and tested. The area under the receiver operating characteristic (ROC) curve, Hosmer–Lemeshow statistic and overall accuracy rate were used for the performance comparison.ResultsANNs had a higher discriminative performance than LR models (area under the ROC curve: 0.955 ± 0.015 (mean ± standard error) and 0.929 ± 0.017, respectively, p < 0.05). The overall accuracy rate for ANNs (90.0 ± 2.0%) was greater than that for LR models (86.9 ± 1.6%, p < 0.05). The Hosmer–Lemeshow statistic for the ANNs was 8.76 ± 6.59 vs. 6.62 ± 4.03 (p > 0.05) for the LR models.ConclusionsWhen used to differentiate between malignant and benign lung nodules on CT scans based on both objective and subjective features, ANNs outperformed LR models in both discrimination and clinical usefulness, but did not outperform for the calibration.     

Glaucoma detection using adaptive neuro-fuzzy inference system

Purpose. To develop an automated classifier based on adaptive neuro-fuzzy inference system (ANFIS) to differentiate between normal and glaucomatous eyes from the quantitative assessment of summary data reports of the Stratus optical coherence tomography (OCT) in Taiwan Chinese population.Methods. This observational non-interventional, cross-sectional, case–control study included one randomly selected eye from each of the 341 study participants (135 patients with glaucoma and 206 healthy controls). Measurements of glaucoma variables (retinal nerve fiber layer thickness and optic nerve head topography) were obtained by Stratus OCT. Decision making was performed in two stages: feature extraction using the orthogonal array and the selected variables were treated as the feeder to adaptive neuro-fuzzy inference system (ANFIS), which was trained with the back-propagation gradient descent method in combination with the least squares method. With the Stratus OCT parameters used as input, receiver operative characteristic (ROC) curves were generated by ANFIS to classify eyes as either glaucomatous or normal.Results. The mean deviation was −0.67 ± 0.62 dB in the normal group and −5.87 ± 6.48 dB in the glaucoma group (P < 0.0001). The inferior quadrant thickness was the best individual parameter for differentiating between normal and glaucomatous eyes (ROC area, 0.887). With ANFIS technique, the ROC area was increased to 0.925.Conclusions. With Stratus OCT parameters used as input, the results from ANFIS showed promise for discriminating between glaucomatous and normal eyes. ANFIS may be preferable since the output concludes the if–then rules and membership functions, which enhances the readability of the output.     

Precipitation forecasting by using wavelet-support vector machine conjunction model

A new wavelet-support vector machine conjunction model for daily precipitation forecast is proposed in this study. The conjunction method combining two methods, discrete wavelet transform and support vector machine, is compared with the single support vector machine for one-day-ahead precipitation forecasting. Daily precipitation data from Izmir and Afyon stations in Turkey are used in the study. The root mean square errors (RMSE), mean absolute errors (MAE), and correlation coefficient (R) statistics are used for the comparing criteria. The comparison results indicate that the conjunction method could increase the forecast accuracy and perform better than the single support vector machine. For the Izmir and Afyon stations, it is found that the conjunction models with RMSE=46.5 mm, MAE=13.6 mm, R=0.782 and RMSE=21.4 mm, MAE=9.0 mm, R=0.815 in test period is superior in forecasting daily precipitations than the best accurate support vector regression models with RMSE=71.6 mm, MAE=19.6 mm, R=0.276 and RMSE=38.7 mm, MAE=14.2 mm, R=0.103, respectively. The ANN method was also employed for the same data set and found that there is a slight difference between ANN and SVR methods.     

Colonic fold detection from computed tomographic colonography images using diffusion-FCM and level sets

Colon cancer is the second major cause of cancer related deaths in industrial nations. Computed tomographic colonography (CTC) has emerged in the last decade as a new less invasive colon diagnostic alternative to the usually practiced optical colonoscopy. The overall goal is to increase the effectiveness of virtual endoscopic navigation of the existing computer-aided detection (CAD) system. The colonic/haustral folds serve as important landmarks for various associated tasks in the virtual endoscopic navigation like prone–supine registration, colonic polyp detection and tenia coli extraction. In this paper, we present two different techniques, first in isolation and then in synergism, for the detection of haustral folds. Our input is volumetric computed tomographic colonography (CTC) images. The first method, which uses a combination of heat diffusion and fuzzy c-means algorithm (FCM), has a tendency of over-segmentation. The second method, which employs level sets, suffers from under-segmentation. A synergistic combination, where the output of the first is used as an input for the second, is shown to improve the segmentation quality. Experimental results are presented on digital colon phantoms as well as real patient scans. The combined method has a total erroneous (over-segmentation plus under-segmentation) detection of (6.5 ± 2)% of the total number of folds per colon as compared to (12.5 ± 5)% for the diffusion-FCM-based method and (11.5 ± 3)% for the level set-based method. The p-values obtained from the associated ANOVA tests indicate that the performance improvements are statistically significant.     

Characterization of a capacitive tactile shear sensor for application in robotic and upper limb prostheses

This paper presents the characterization of a novel tactile sensor designed to measure shear forces. The sensor design is targeted for use in robotic and prosthetic hands, where haptic feedback or ability to detect shear forces associated with slip are critical. The presented sensor utilizes the principle of differential capacitance to measure the mechanical deflection of the sensor element. The dynamic range of the sensor can be varied by encapsulating the sensor terminal within silicone of varying hardness. The design features ease of mass production, low per-unit-cost, novel overload protection and low wire count, while still preserving the ability to achieve reasonable spatial resolutions and array densities. Mathematical and COMSOL multiphysics models of the sensor are presented, in addition to results from practical experiments. Sensors with a full scale displacement range of ±0.525 mm were produced and the differential capacitance was measured. Shear force transduction was characterized over the range of 0 N–4 N with the sense terminal encapsulated by silicone with a shore A hardness of 20. The effect of elastomer hardness on the sensor's dynamic range was analyzed. The differential capacitance, when measured at each fixed interval, was found experimentally to have a maximum standard deviation of 4.28e?16 F over a ±2 N range. A maximum standard deviation of 1.35e?15 F was measured across characterized full scale sensor range of ±4 N. The sensor design has a sensitivity of 1.967 fF/N of applied force and the sensor output was found to be approximately linear. The coefficient of determination, r², was found to be 0.941.     

Compound Linguistic Scale

Rating scales are the essential interfaces for many research areas such as in decision making and recommendation. Some issues concerning syntactic and sematic structures are still open to discuss. This research proposes a Compound Linguistic Scale (CLS), a two dimension rating scale, as a promising rating interface. The CLS is comprised of Compound Linguistic Variable (CLV) and Deductive Rating Strategy (DRS). CLV can ideally produce 21 to 73 ((7 ± 2)((7 ± 2) − 1) + 1) ordinal-in-ordinal rating items, which extends the classic rating scales usually on the basis of 7 ± 2 principle, to better reflect the raters’ preferences whilst DRS is a double step rating approach for a rater to choose a compound linguistic term among two dimensional options on a dynamic rating interface. The numerical analyses show that the proposed CLS can address rating dilemma for a single rater and more accurately reflects consistency among various raters. CLS can be applied to surveys, questionnaires, psychometrics, recommender systems and decision analysis of various application domains.     

Using of hydrogen ion-selective poly(vinyl chloride) membrane electrode based on calix[4]arene as thiocyanate ion-selective electrode

A hydrogen ion-selective electrode (ISE) is prepared by using 5,11,17,23-tetra-tert-butyl-25,26,27,28-tetracyanometoxy-calix[4]arene and an investigation about whether it could be used as a thiocyanate ion-selective electrode is made by using its characteristic of becoming thiocyanate sensitive in acidic regions. The electrode of the optimum characteristic has a composition of 1% ionophore, 66% 2-NPOE and 33% poly(vinyl chloride) (PVC). This electrode exhibits a linear response over the range 1.0 × 10⁻¹ to 3.0 × 10⁻⁵ M of thiocyanate with a slope of 52.0 ± 0.2 mV/pSCN. The effects of the pH and the membrane composition are also investigated. The lifetime of the electrode is at least 4 months and its response time is found to be 10–15 s. The selectivity coefficients of some anions are calculated by using mixed solution interference method. Application of the electrode to the potentiometric titration of thiocyanate ion with silver nitrate is reported. There is a good agreement between the results obtained by the proposed electrode and the Mohr method at 95% confidence level.     

Calorimetric measurement of the standard enthalpy of formation of ZnSb at 298 K

After a critical review of the literature data on the standard enthalpy of formation of ZnSb, discrepancies between various experimental studies are highlighted. Moreover, experimental values disagree with values calculated by ab initio methods. As many of the experimental methods used suffer from some serious drawbacks, a new determination of the standard enthalpy of formation of ZnSb by an alternative calorimetric method, drop solution calorimetry in liquid tin, has been performed. Two different synthesis methods have been used to obtain a pure ZnSb phase and drop solution experiments were performed at 665 and at 974 K. The standard enthalpy of formation values derived from these experiments are − 6.1±2.5 kJ mol of atoms⁻¹ for the ZnSb sample prepared by ball milling and − 7.9±0.4 kJ mol of atoms⁻¹ for the ZnSb sample prepared by melting. These results are discussed and compared to literature data.     

Sleep in a live-in mining operation: The influence of start times and restricted non-work activities

The amount of sleep obtained between shifts is influenced by numerous factors including the length of work and rest periods, the timing of the rest period relative to the endogenous circadian cycle and personal choices about the use of non-work time. The current study utilised a real-world live-in mining environment to examine the amount of sleep obtained when access to normal domestic, family and social activities was restricted. Participants were 29 mining operators (26 male, average age 37.4 ± 6.8 years) who recorded sleep, work and fatigue information and wore an activity monitor for a cycle of seven day shifts and seven night shifts (both 12 h) followed by either seven or fourteen days off. During the two weeks of work participants lived on-site. Total sleep time was significantly less (p < 0.01) while on-site on both day (6.1 ± 1.0 h) and night shifts (5.7 ± 1.5 h) than days off (7.4 ± 1.4 h). Further, night shift sleep was significantly shorter than day-shift sleep (p < 0.01). Assessment of subjective fatigue ratings showed that the sleep associated with both days off and night shifts had a greater recovery value than sleep associated with day shifts (p < 0.01). While on-site, participants obtained only 6 h of sleep indicating that the absence of competing domestic, family and social activities did not convert to more sleep. Factors including shift start times and circadian influences appear to have been more important.     

A distributed optical fiber sensor for temperature detection in power cables

The power transfer capacity of an underground power cable is limited by high-temperature regions that occur along the cable. It is very difficult to determine and control these ‘hot spots’. Optimum use and temperature profile control of power cables before and during load transmission can be achieved with real-time processing of temperature data. There are various methods developed for this purpose such as conventional point temperature measurement method, where a large number of sensors and connectors are required, and methods based on mathematical models which can only approach real values by approximation.In this study, temperature detection in an XLPE insulated 154 kV power cable is performed using a distributed sensing method where the optical fiber itself behaves as a sensor. Therefore, there is no need for the devices of conventional method. Moreover, contrary to methods based on mathematical models, where it is difficult to predict environmental variations, this method considers the variations with a temperature resolution of ±1 °C. Distributed temperature sensing (DTS) method, detection system configuration and required system parameters are explained in the paper. Experimental results obtained for 126 and 412 m cables show a temperature resolution of ±1 °C and a spatial resolution of 1.22 m. Simulations for a 10 km cable are also given. Results show that DTS is a reliable method for both short and long range cable systems.     

Discovery of novel anti-leishmanial agents targeting LdLip3 lipase

Leishmaniasis is a neglected tropical disease, caused by several species of Leishmania. Being an opportunistic lipid-scavenging pathogen, Leishmania relies extensively on lipid metabolism especially for host–pathogen interaction, utilizing host lipids for energy and virulence. The rational approach is to target lipid metabolism of the pathogen focusing lipid-catabolizing lipases. The LdLip3 lipase is considered as drug target as it is constitutively expressed in both promastigote and amastigote forms. Since the LdLip3 structure is not known, we modeled its three-dimensional structure to implement structure-based drug discovery approach. Similarity-based virtual screening was carried out to identify potential inhibitors utilizing NCI diversity set on ZINC database including natural products. Implementing computational and experimental approaches, four anti-leishmanial agents were discovered. The screened molecules ZINC01821375, ZINC04008765, ZINC06117316 and ZINC12653571 had anti-leishmanial activity with IC₅₀ (% viable promastigotes vs. concentration) of 5.2 ± 1.8 μM, 13.1 ± 2.6 μM, 9.4 ± 2.6 μM and 17.3 ± 3.1 μM, respectively. The molecules showed negligible toxicity toward mouse macrophages. Based on the contact footprinting analysis, new molecules were designed with better predicted free energy of binding than discovered anti-leishmanial agents. Further validation for the therapeutic utility of discovered molecules can be carried out by the research community to combat leishmaniasis.     

Guaranteed-quality all-quadrilateral mesh generation with feature preservation

In this paper, a quadtree-based mesh generation method is described to create guaranteed-quality, geometry-adapted all-quadrilateral (all-quad) meshes with feature preservation for arbitrary planar domains. Given point cloud, our method generates all-quad meshes with these points as vertices and all the angles are within [45°, 135°]. For given planar curves, quadtree-based spatial decomposition is governed by the curvature of the boundaries and narrow regions. 2-refinement templates are chosen for local mesh refinement without creating any hanging nodes. A buffer zone is created by removing elements around the boundary. To guarantee the mesh quality, the angles facing the boundary are improved via template implementation, and two buffer layers are inserted in the buffer zone. It is proved that all the elements of the final mesh are quads with angles between 45° ± ε and 135° ± ε (ε ≤ 5°) with the exception of badly shaped elements that may be required by the sharp angles in the input geometry. We also prove that the scaled Jacobians defined by two edge vectors are in the range of [sin(45° ? ε), sin90°], or [0.64, 1.0]. Furthermore, sharp features and narrow regions are detected and preserved automatically. Boundary layer meshes are generated by splitting elements of the second buffer layer. We have applied our algorithm to a set of complicated geometries, including the Lake Superior map and the air foil with multiple components.     

Development of a slender continuum robotic system for on-wing inspection/repair of gas turbine engines

The maintenance works (e.g. inspection, repair) of aero-engines while still attached on the airframes requires a desirable approach since this can significantly shorten both the time and cost of such interventions as the aerospace industry commonly operates based on the generic concept “power by the hour”. However, navigating and performing a multi-axis movement of an end-effector in a very constrained environment such as gas turbine engines is a challenging task. This paper reports on the development of a highly flexible slender (i.e. low diameter-to-length ratios) continuum robot of 25 degrees of freedom capable to uncoil from a drum to provide the feeding motion needed to navigate into crammed environments and then perform, with its last 6 DoF, complex trajectories with a camera equipped machining end-effector for allowing in-situ interventions at a low-pressure compressor of a gas turbine engine. This continuum robot is a compact system and presents a set of innovative mechatronics solutions such as: (i) twin commanding cables to minimise the number of actuators; (ii) twin compliant joints to enable large bending angles (±90°) arranged on a tapered structure (start from 40 mm to 13 mm at its end); (iii) feeding motion provided by a rotating drum for coiling/uncoiling the continuum robot; (iv) machining end-effector equipped with vision system. To be able to achieve the in-situ maintenance tasks, a set of innovative control algorithms to enable the navigation and end-effector path generation have been developed and implemented. Finally, the continuum robot has been tested both for navigation and movement of the end-effector against a specified target within a gas turbine engine mock-up proving that: (i) max. deviations in navigation from the desired path (1000 mm length with bends between 45° and 90°) are ±10 mm; (ii) max. errors in positioning the end-effector against a target situated at the end of navigation path is 1 mm. Thus, this paper presents a compact continuum robot that could be considered as a step forward in providing aero-engine manufacturers with a solution to perform complex tasks in an invasive manner.