All you need is data preparation: A systematic review of image harmonization techniques in Multi-center/device studies for medical support systems.

BACKGROUND AND OBJECTIVES: Artificial intelligence (AI) models trained on multi-centric and multi-device studies can provide more robust insights and research findings compared to single-center studies. However, variability in acquisition protocols and equipment can introduce inconsistencies that hamper the effective pooling of multi-source datasets. This systematic review evaluates strategies for image harmonization, which standardizes appearances to enable reliable AI analysis of multi-source medical imaging. METHODS: A literature search using PRISMA guidelines was conducted to identify relevant papers published between 2013 and 2023 analyzing multi-centric and multi-device medical imaging studies that utilized image harmonization approaches. RESULTS: Common image harmonization techniques included grayscale normalization (improving classification accuracy by up to 24.42 %), resampling (increasing the percentage of robust radiomics features from 59.5 % to 89.25 %), and color normalization (enhancing AUC by up to 0.25 in external test sets). Initially, mathematical and statistical methods dominated, but machine and deep learning adoption has risen recently. Color imaging modalities like digital pathology and dermatology have remained prominent application areas, though harmonization efforts have expanded to diverse fields including radiology, nuclear medicine, and ultrasound imaging. In all the modalities covered by this review, image harmonization improved AI performance, with increasing of up to 24.42 % in classification accuracy and 47 % in segmentation Dice scores. CONCLUSIONS: Continued progress in image harmonization represents a promising strategy for advancing healthcare by enabling large-scale, reliable analysis of integrated multi-source datasets using AI. Standardizing imaging data across clinical settings can help realize personalized, evidence-based care supported by data-driven technologies while mitigating biases associated with specific populations or acquisition protocols.

Impact of artificial intelligence-based color constancy on dermoscopical assessment of skin lesions: A comparative study.

BACKGROUND: The quality of dermoscopic images is affected by lighting conditions, operator experience, and device calibration. Color constancy algorithms reduce this variability by making images appear as if they were acquired under the same conditions, allowing artificial intelligence (AI)-based methods to achieve better results. The impact of color constancy algorithms has not yet been evaluated from a clinical dermatologist's workflow point of view. Here we propose an in-depth investigation of the impact of an AI-based color constancy algorithm, called DermoCC-GAN, on the skin lesion diagnostic routine. METHODS: Three dermatologists, with different experience levels, carried out two assignments. The clinical experts evaluated key parameters such as perceived image quality, lesion diagnosis, and diagnosis confidence. RESULTS: When the DermoCC-GAN color constancy algorithm was applied, the dermoscopic images were perceived to be of better quality overall. An increase in classification performance was observed, reaching a maximum accuracy of 74.67% for a six-class classification task. Finally, the use of normalized images results in an increase in the level of self-confidence in the qualitative diagnostic routine. CONCLUSIONS: From the conducted analysis, it is evident that the impact of AI-based color constancy algorithms, such as DermoCC-GAN, is positive and brings qualitative benefits to the clinical practitioner.

Spatially repeatable components from ultrafast ultrasound are associated with motor unit activity in human isometric contractions.

Objective.Ultrafast ultrasound (UUS) imaging has been used to detect intramuscular mechanical dynamics associated with single motor units (MUs). Detecting MUs from ultrasound sequences requires decomposing a velocity field into components, each consisting of an image and a signal. These components can be associated with putative MU activity or spurious movements (noise). The differentiation between putative MUs and noise has been accomplished by comparing the signals with MU firings obtained from needle electromyography (EMG). Here, we examined whether the repeatability of the images over brief time intervals can serve as a criterion for distinguishing putative MUs from noise in low-force isometric contractions.Approach.UUS images and high-density surface EMG (HDsEMG) were recorded simultaneously from 99 MUs in the biceps brachii of five healthy subjects. The MUs identified through HDsEMG decomposition were used as a reference to assess the outcomes of the ultrasound-based components. For each contraction, velocity sequences from the same eight-second ultrasound recording were separated into consecutive two-second epochs and decomposed. To evaluate the repeatability of components' images across epochs, we calculated the Jaccard similarity coefficient (JSC). JSC compares the similarity between two images providing values between 0 and 1. Finally, the association between the components and the MUs from HDsEMG was assessed.Main results.All the MU-matched components had JSC > 0.38, indicating they were repeatable and accounted for about one-third of the HDsEMG-detected MUs (1.8 ± 1.6 matches over 4.9 ± 1.8 MUs). The repeatable components (JSC > 0.38) represented 14% of the total components (6.5 ± 3.3 components). These findings align with our hypothesis that intra-sequence repeatability can differentiate putative MUs from noise and can be used for data reduction.Significance.This study provides the foundation for developing stand-alone methods to identify MU in UUS sequences and towards real-time imaging of MUs. These methods are relevant for studying muscle neuromechanics and designing novel neural interfaces.

Development of a Deep Learning-Based System for Optic Nerve Characterization in Transorbital Ultrasound Images on a Multicenter Data Set.

OBJECTIVE: Characterization of the optic nerve through measurement of optic nerve diameter (OND) and optic nerve sheath diameter (ONSD) using transorbital sonography (TOS) has proven to be a useful tool for the evaluation of intracranial pressure (ICP) and multiple neurological conditions. We describe a deep learning-based system for automatic characterization of the optic nerve from B-mode TOS images by automatic measurement of the OND and ONSD. In addition, we determine how the signal-to-noise ratio in two different areas of the image influences system performance. METHODS: A UNet was trained as the segmentation model. The training was performed on a multidevice, multicenter data set of 464 TOS images from 110 subjects. Fivefold cross-validation was performed, and the training process was repeated eight times. The final prediction was made as an ensemble of the predictions of the eight single models. Automatic OND and ONSD measurements were compared with the manual measurements taken by an expert with a graphical user interface that mimics a clinical setting. RESULTS: A Dice score of 0.719 ± 0.139 was obtained on the whole data set merging the test folds. Pearson's correlation was 0.69 for both OND and ONSD parameters. The signal-to-noise ratio was found to influence segmentation performance, but no clear correlation with diameter measurement performance was determined. CONCLUSION: The developed system has a good correlation with manual measurements, proving that it is feasible to create a model capable of automatically analyzing TOS images from multiple devices. The promising results encourage further definition of a standard protocol for the automatization of the OND and ONSD measurement process using deep learning-based methods. The image data and the manual measurements used in this work will be available at 10.17632/kw8gvp8m8x.1.

Texture analysis of ultrasound images obtained with different beamforming techniques and dynamic ranges - A robustness study.

Texture analysis of medical images gives quantitative information about the tissue characterization for possible pathology discrimination. Ultrasound B-mode images are generated through a process called beamforming. Then, to obtain the final 8-bit image, the dynamic range value must be set. It is currently unknown how different beamforming techniques or dynamic range values may alter the final image texture. We provide here a robustness analysis of first and higher order texture features using six beamforming methods and seven dynamic range values, on experimental phantom and in vivo musculoskeletal images acquired using two different ultrasound research scanners. To investigate the repeatability of the texture parameters, we applied the multivariate analysis of variance (MANOVA) and estimated the intraclass correlation coefficient (ICC) on the texture features calculated on the B-mode images created with different beamforming methods and dynamic range values. We demonstrated the high repeatability of texture features when varying the dynamic range and showed texture features can differentiate between beamforming methods through a MANOVA analysis, hinting at the potential future clinical application of specific beamformers.

AKASI and Near-Infrared Spectroscopy in the combined effectiveness evaluation of an actinic keratoses preventive product in immunocompetent and immunocompromised patients.

Introduction: The high incidence of actinic keratoses among both the elderly population and immunocompromised subjects and the considerable risk of progression from in situ to invasive neoplasms makes it essential to identify new prevention, treatment, and monitoring strategies. Objective: The aim of this study was to evaluate the efficacy on AKs of a topical product (®Rilastil AK Repair 100 +) containing high-protection sunscreens, a DNA Repair Complex with antioxidant and repairing action against UV-induced DNA damage, and nicotinamide, a water-soluble derivative of vitamin B3 that demonstrated several photoprotective effects both in vitro and in vivo. Methods: The study enrolled 74 Caucasian patients, which included 42 immunocompetent and 32 immunosuppressed subjects. The efficacy of the treatment has been evaluated through the clinical index AKASI score and the non-invasive Near-Infrared Spectroscopy method. Results: The AKASI score proved to be a valid tool to verify the efficacy of the product under study, highlighting an average percentage reduction at the end of treatment of 31.37% in immunocompetent patients and 22.76% in organ transplant recipients, in comparison to the initial values, with a statistically significant reduction also in the single time intervals (T0 vs. T1 and T1 vs. T2) in both groups. On the contrary, the Near-Infrared Spectroscopy (a non-invasive technique that evaluates hemoglobin relative concentration variations) did not find significant differences for O2Hb and HHb signals before and after the treatment, probably because the active ingredients of the product under study can repair the photo-induced cell damage, but do not significantly modify the vascularization of the treated areas. Conclusion: The results deriving from this study demonstrate the efficacy of the product under study, confirming the usefulness of the AKASI score in monitoring treated patients. Near-Infrared Spectroscopy could represent an interesting strategy for AK patients monitoring, even if further large-scale studies will be needed.

Detecting anatomical characteristics of single motor units by combining high density electromyography and ultrafast ultrasound: a simulation study.

Muscle force production is the result of a sequence of electromechanical events that translate the neural drive issued to the motor units (MUs) into tensile forces on the tendon. Current technology allows this phenomenon to be investigated non-invasively. Single MU excitation and its mechanical response can be studied through high-density surface electromyography (HDsEMG) and ultrafast ultrasound (US) imaging respectively. In this study, we propose a method to integrate these two techniques to identify anatomical characteristics of single MUs. Specifically, we tested two algorithms, combining the tissue velocity sequence (TVS, obtained from ultrafast US images), and the MU firings (extracted from HDsEMG decomposition). The first is the Spike Triggered Averaging (STA) of the TVS based on the occurrences of individual MU firings, while the second relies on the correlation between the MU firing patterns and the TVS spatio-temporal independent components (STICA). A simulation model of the muscle contraction was adapted to test the algorithms at different degrees of neural excitation (number of active MUs) and MU synchronization. The performances of the two algorithms were quantified through the comparison between the simulated and the estimated characteristics of MU territories (size, location). Results show that both approaches are negatively affected by the number of active MU and synchronization levels. However, STICA provides a more robust MU territory estimation, outperforming STA in all the tested conditions. Our results suggest that spatio-temporal independent component decomposition of TVS is a suitable approach for anatomical and mechanical characterization of single MUs using a combined HDsEMG and ultrafast US approach.

DermoCC-GAN: A new approach for standardizing dermatological images using generative adversarial networks.

BACKGROUND AND OBJECTIVE: Dermatological images are typically diagnosed based on visual analysis of the skin lesion acquired using a dermoscope. However, the final quality of the acquired image is highly dependent on the illumination conditions during the acquisition phase. This variability in the light source can affect the dermatologist's diagnosis and decrease the accuracy of computer-aided diagnosis systems. Color constancy algorithms have proven to be a powerful tool to address this issue by allowing the standardization of the image illumination source, but the most commonly used algorithms still present some inherent limitations due to assumptions made on the original image. In this work, we propose a novel Dermatological Color Constancy Generative Adversarial Network (DermoCC-GAN) algorithm to overcome the current limitations by formulating the color constancy task as an image-to-image translation problem. METHODS: A generative adversarial network was trained with a custom heuristic algorithm that performs well on the training set. The model hence learns the domain transfer task (from original to color standardized image) and is then able to accurately apply the color constancy on test images characterized by different illumination conditions. RESULTS: The proposed algorithm outperforms state-of-the-art color constancy algorithms for dermatological images in terms of normalized median intensity and when using the color-normalized images in a deep learning framework for lesion classification (accuracy of the seven-class classifier: 79.2%) and segmentation (dice score: 90.9%). In addition, we validated the proposed approach on two different external datasets with highly satisfactory results. CONCLUSIONS: The novel strategy presented here shows how it is possible to generalize a heuristic method for color constancy for dermatological image analysis by training a GAN. The overall approach presented here can be easily extended to numerous other applications.

Teledermoscopy in the Diagnosis of Melanocytic and Non-Melanocytic Skin Lesions: NurugoTM Derma Smartphone Microscope as a Possible New Tool in Daily Clinical Practice.

Background: Due to the COVID-19 pandemic, teledermoscopy has been increasingly used in the remote diagnosis of skin cancers. In a study conducted in 2020, we demonstrated a potential role of an inexpensive device (NurugoTM Derma) as a first triage to select the skin lesions that require a face-to-face consultation with dermatologists. Herein, we report the results of a novel study that aimed to better investigate the performance of NurugoTM. Objectives: (i) verify whether the NurugoTM can be a communication tool between the general practitioner (GP) and dermatologist in the first assessment of skin lesions, (ii) analyze the degree of diagnostic-therapeutic agreement between dermatologists, (iii) estimate the number of potentially serious diagnostic errors. Methods: One hundred and forty-four images of skin lesions were collected at the Dermatology Outpatient Clinic in Novara using a conventional dermatoscope (instrument F), the NurugoTM (instrument N), and the latter with the interposition of a laboratory slide (instrument V). The images were evaluated in-blind by four dermatologists, and each was asked to make a diagnosis and to specify a possible treatment. Results: Our data show that F gave higher agreement values for all dermatologists, concerning the real clinical diagnosis. Nevertheless, a medium/moderate agreement value was obtained also for N and V instruments and that can be considered encouraging and indicate that all examined tools can potentially be used for the first screening of skin lesions. The total amount of misclassified lesions was limited (especially with the V tool), with up to nine malignant lesions wrongly classified as benign. Conclusions: NurugoTM, with adequate training, can be used to build a specific support network between GP and dermatologist or between dermatologists. Furthermore, its use could be extended to the diagnosis and follow-up of other skin diseases, especially for frail patients in emergencies, such as the current pandemic context.

Physical and electrophysiological motor unit characteristics are revealed with simultaneous high-density electromyography and ultrafast ultrasound imaging.

Electromyography and ultrasonography provide complementary information about electrophysiological and physical (i.e. anatomical and mechanical) muscle properties. In this study, we propose a method to assess the electrical and physical properties of single motor units (MUs) by combining High-Density surface Electromyography (HDsEMG) and ultrafast ultrasonography (US). Individual MU firings extracted from HDsEMG were used to identify the corresponding region of muscle tissue displacement in US videos. The time evolution of the tissue velocity in the identified region was regarded as the MU tissue displacement velocity. The method was tested in simulated conditions and applied to experimental signals to study the local association between the amplitude distribution of single MU action potentials and the identified displacement area. We were able to identify the location of simulated MUs in the muscle cross-section within a 2 mm error and to reconstruct the simulated MU displacement velocity (cc > 0.85). Multiple regression analysis of 180 experimental MUs detected during isometric contractions of the biceps brachii revealed a significant association between the identified location of MU displacement areas and the centroid of the EMG amplitude distribution. The proposed approach has the potential to enable non-invasive assessment of the electrical, anatomical, and mechanical properties of single MUs in voluntary contractions.

Integration of Deep Learning and Active Shape Models for More Accurate Prostate Segmentation in 3D MR Images.

Magnetic resonance imaging (MRI) has a growing role in the clinical workup of prostate cancer. However, manual three-dimensional (3D) segmentation of the prostate is a laborious and time-consuming task. In this scenario, the use of automated algorithms for prostate segmentation allows us to bypass the huge workload of physicians. In this work, we propose a fully automated hybrid approach for prostate gland segmentation in MR images using an initial segmentation of prostate volumes using a custom-made 3D deep network (VNet-T2), followed by refinement using an Active Shape Model (ASM). While the deep network focuses on three-dimensional spatial coherence of the shape, the ASM relies on local image information and this joint effort allows for improved segmentation of the organ contours. Our method is developed and tested on a dataset composed of T2-weighted (T2w) MRI prostatic volumes of 60 male patients. In the test set, the proposed method shows excellent segmentation performance, achieving a mean dice score and Hausdorff distance of 0.851 and 7.55 mm, respectively. In the future, this algorithm could serve as an enabling technology for the development of computer-aided systems for prostate cancer characterization in MR imaging.

Carotid Ultrasound Boundary Study (CUBS): Technical considerations on an open multi-center analysis of computerized measurement systems for intima-media thickness measurement on common carotid artery longitudinal B-mode ultrasound scans.

After publishing an in-depth study that analyzed the ability of computerized methods to assist or replace human experts in obtaining carotid intima-media thickness (CIMT) measurements leading to correct therapeutic decisions, here the same consortium joined to present technical outlooks on computerized CIMT measurement systems and provide considerations for the community regarding the development and comparison of these methods, including considerations to encourage the standardization of computerized CIMT measurements and results presentation. A multi-center database of 500 images was collected, upon which three manual segmentations and seven computerized methods were employed to measure the CIMT, including traditional methods based on dynamic programming, deformable models, the first order absolute moment, anisotropic Gaussian derivative filters and deep learning-based image processing approaches based on U-Net convolutional neural networks. An inter- and intra-analyst variability analysis was conducted and segmentation results were analyzed by dividing the database based on carotid morphology, image signal-to-noise ratio, and research center. The computerized methods obtained CIMT absolute bias results that were comparable with studies in literature and they generally were similar and often better than the observed inter- and intra-analyst variability. Several computerized methods showed promising segmentation results, including one deep learning method (CIMT absolute bias = 106 ± 89 µm vs. 160 ± 140 µm intra-analyst variability) and three other traditional image processing methods (CIMT absolute bias = 139 ± 119 µm, 143 ± 118 µm and 139 ± 136 µm). The entire database used has been made publicly available for the community to facilitate future studies and to encourage an open comparison and technical analysis (https://doi.org/10.17632/m7ndn58sv6.1).

Deep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease assessment.

Ultrasound imaging is a patient-friendly and robust technique for studying physiological and pathological muscles. An automatic deep learning (DL) system for the analysis of ultrasound images could be useful to support an expert operator, allowing the study of large datasets requiring less human interaction. The purpose of this study is to present a deep learning algorithm for the cross-sectional area (CSA) segmentation in transverse musculoskeletal ultrasound images, providing a quantitative grayscale analysis which is useful for studying muscles, and to validate the results in a large dataset. The dataset included 3917 images of biceps brachii, tibialis anterior and gastrocnemius medialis acquired on 1283 subjects (mean age 50 ± 21 years, 729 male). The algorithm was based on multiple deep-learning architectures, and its performance was compared to a manual expert segmentation. We compared the mean grayscale value inside the automatic and manual CSA using Bland-Altman plots and a correlation analysis. Classification in healthy and abnormal muscles between automatic and manual segmentation were compared using the grayscale value z-scores. In the test set, a Precision of 0.88 ± 0.12 and a Recall of 0.92 ± 0.09 was achieved. The network segmentation performance was slightly less in abnormal muscles, without a loss of discrimination between healthy and abnormal muscle images. Bland-Altman plots showed no clear trend in the error distribution and the two readings have a 0.99 Pearson's correlation coefficient (p < 0.001, test set). The ICC(A, 1) calculated between the z-score readings was 0.99. The algorithm achieves robust CSA segmentation performance and gives mean grayscale level information comparable to a manual operator. This could provide a helpful tool for clinicians in neuromuscular disease diagnosis and follow-up. The entire dataset and code are made available for the research community.

Carotid Ultrasound Boundary Study (CUBS): An Open Multicenter Analysis of Computerized Intima-Media Thickness Measurement Systems and Their Clinical Impact.

Common carotid intima-media thickness (CIMT) is a commonly used marker for atherosclerosis and is often computed in carotid ultrasound images. An analysis of different computerized techniques for CIMT measurement and their clinical impacts on the same patient data set is lacking. Here we compared and assessed five computerized CIMT algorithms against three expert analysts' manual measurements on a data set of 1088 patients from two centers. Inter- and intra-observer variability was assessed, and the computerized CIMT values were compared with those manually obtained. The CIMT measurements were used to assess the correlation with clinical parameters, cardiovascular event prediction through a generalized linear model and the Kaplan-Meier hazard ratio. CIMT measurements obtained with a skilled analyst's segmentation and the computerized segmentation were comparable in statistical analyses, suggesting they can be used interchangeably for CIMT quantification and clinical outcome investigation. To facilitate future studies, the entire data set used is made publicly available for the community at http://dx.doi.org/10.17632/fpv535fss7.1.

The Role in Teledermoscopy of an Inexpensive and Easy-to-Use Smartphone Device for the Classification of Three Types of Skin Lesions Using Convolutional Neural Networks.

BACKGROUND: The use of teledermatology has spread over the last years, especially during the recent SARS-Cov-2 pandemic. Teledermoscopy, an extension of teledermatology, consists of consulting dermoscopic images, also transmitted through smartphones, to remotely diagnose skin tumors or other dermatological diseases. The purpose of this work was to verify the diagnostic validity of images acquired with an inexpensive smartphone microscope (NurugoTM), employing convolutional neural networks (CNN) to classify malignant melanoma (MM), melanocytic nevus (MN), and seborrheic keratosis (SK). METHODS: The CNN, trained with 600 dermatoscopic images from the ISIC (International Skin Imaging Collaboration) archive, was tested on three test sets: ISIC images, images acquired with the NurugoTM, and images acquired with a conventional dermatoscope. RESULTS: The results obtained, although with some limitations due to the smartphone device and small data set, were encouraging, showing comparable results to the clinical dermatoscope and up to 80% accuracy (out of 10 images, two were misclassified) using the NurugoTM demonstrating how an amateur device can be used with reasonable levels of diagnostic accuracy. CONCLUSION: Considering the low cost and the ease of use, the NurugoTM device could be a useful tool for general practitioners (GPs) to perform the first triage of skin lesions, aiding the selection of lesions that require a face-to-face consultation with dermatologists.

The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis.

Recently, deep learning frameworks have rapidly become the main methodology for analyzing medical images. Due to their powerful learning ability and advantages in dealing with complex patterns, deep learning algorithms are ideal for image analysis challenges, particularly in the field of digital pathology. The variety of image analysis tasks in the context of deep learning includes classification (e.g., healthy vs. cancerous tissue), detection (e.g., lymphocytes and mitosis counting), and segmentation (e.g., nuclei and glands segmentation). The majority of recent machine learning methods in digital pathology have a pre- and/or post-processing stage which is integrated with a deep neural network. These stages, based on traditional image processing methods, are employed to make the subsequent classification, detection, or segmentation problem easier to solve. Several studies have shown how the integration of pre- and post-processing methods within a deep learning pipeline can further increase the model's performance when compared to the network by itself. The aim of this review is to provide an overview on the types of methods that are used within deep learning frameworks either to optimally prepare the input (pre-processing) or to improve the results of the network output (post-processing), focusing on digital pathology image analysis. Many of the techniques presented here, especially the post-processing methods, are not limited to digital pathology but can be extended to almost any image analysis field.

Changes in supramaximal M-wave amplitude at different regions of biceps brachii following eccentric exercise of the elbow flexors.

PURPOSE: Previous evidence from surface electromyograms (EMGs) suggests that exercise-induced muscle damage (EIMD) may manifest unevenly within the muscle. Here we investigated whether these regional changes were indeed associated with EIMD or if they were attributed to spurious factors often affecting EMGs. METHODS: Ten healthy male subjects performed 3 × 10 eccentric elbow flexions. Maximal voluntary contraction (MVC), muscle soreness and ultrasound images from biceps brachii distal and proximal regions were measured immediately before (baseline) and during each of the following 4 days after the exercise. Moreover, 64 monopolar surface EMGs were detected while 10 supramaximal pulses were applied to the musculocutaneous nerve. The innervation zone (IZ), the number of electrodes detecting largest M-waves and their centroid longitudinal coordinates were assessed to characterize the spatial distribution of the M-waves amplitude. RESULTS: The MVC torque decreased (~ 25%; P < 0.001) while the perceived muscle soreness scale increased (~ 4 cm; 0 cm for no soreness and 10 cm for highest imaginable soreness; P < 0.005) across days. The echo intensity of the ultrasound images increased at 48 h (71%), 72 h (95%) and 96 h (112%) for both muscle regions (P < 0.005), while no differences between regions were observed (P = 0.136). The IZ location did not change (P = 0.283). The number of channels detecting the greatest M-waves significantly decreased (up to 10.7%; P < 0.027) and the centroid longitudinal coordinate shifted distally at 24, 48 and 72 h after EIMD (P < 0.041). CONCLUSION: EIMD consistently changed supramaximal M-waves that were detected mainly proximally from the biceps brachii, suggesting that EIMD takes place locally within the biceps brachii.

Automatic segmentation of ultrasound images of gastrocnemius medialis with different echogenicity levels using convolutional neural networks.

The purpose of this study was to develop an automatic method for the segmentation of muscle cross-sectional area on transverse B-mode ultrasound images of gastrocnemius medialis using a convolutional neural network(CNN). In the provided dataset images with both normal and increased echogenicity are present. The manually annotated dataset consisted of 591 images, from 200 subjects, 400 relative to subjects with normal echogenicity and 191 to subjects with augmented echogenicity. From the DICOM files, the image has been extracted and processed using the CNN, then the output has been post-processed to obtain a finer segmentation. Final results have been compared to the manual segmentations. Precision and Recall scores as mean ± standard deviation for training, validation, and test sets are 0.96 ± 0.05, 0.90 ± 0.18, 0.89 ± 0.15 and 0.97 ±0.03, 0.89± 0.17, 0.90 ± 0.14 respectively. The CNN approach has also been compared to another automatic algorithm, showing better performances. The proposed automatic method provides an accurate estimation of muscle cross-sectional area in muscles with different echogenicity levels.

Non-Invasive Analysis of Actinic Keratosis before and after Topical Treatment Using a Cold Stimulation and Near-Infrared Spectroscopy.

Background and objectives: The possible evolution of actinic keratoses (AKs) into invasive squamous cell carcinomas (SCC) makes their treatment and monitoring essential. AKs are typically monitored before and after treatment only through a visual analysis, lacking a quantitative measure to determine treatment effectiveness. Near-infrared spectroscopy (NIRS) is a non-invasive measure of the relative change of oxy-hemoglobin and deoxy-hemoglobin (O2Hb and HHb) in tissues. The aim of our study is to determine if a time and frequency analysis of the NIRS signals acquired from the skin lesion before and after a topical treatment can highlight quantitative differences between the AK skin lesion area. Materials and Methods: The NIRS signals were acquired from the skin lesions of twenty-two patients, with the same acquisition protocol: baseline signals, application of an ice pack near the lesion, removal of ice pack and acquisition of vascular recovery. We calculated 18 features from the NIRS signals, and we applied multivariate analysis of variance (MANOVA) to compare differences between the NIRS signals acquired before and after the therapy. Results: The MANOVA showed that the features computed on the NIRS signals before and after treatment could be considered as two statistically separate groups, after the ice pack removal. Conclusions: Overall, the NIRS technique with the cold stimulation may be useful to support non-invasive and quantitative lesion analysis and regression after a treatment. The results provide a baseline from which to further study skin lesions and the effects of various treatments.

Automatic Optic Nerve Measurement: A New Tool to Standardize Optic Nerve Assessment in Ultrasound B-Mode Images.

Transorbital sonography provides reliable information about the estimation of intra-cranial pressure by measuring the optic nerve sheath diameter (ONSD), whereas the optic nerve (ON) diameter (OND) may reveal ON atrophy in patients with multiple sclerosis. Here, an AUTomatic Optic Nerve MeAsurement (AUTONoMA) system for OND and ONSD assessment in ultrasound B-mode images based on deformable models is presented. The automated measurements were compared with manual ones obtained by two operators, with no significant differences. AUTONoMA correctly segmented the ON and its sheath in 71 out of 75 images. The mean error compared with the expert operator was 0.06 ± 0.52 mm and 0.06 ± 0.35 mm for the ONSD and OND, respectively. The agreement between operators and AUTONoMA was good and a positive correlation was found between the readers and the algorithm with errors comparable with the inter-operator variability. The AUTONoMA system may allow for standardization of OND and ONSD measurements, reducing manual evaluation variability.