Artificial Intelligence Assisted Multi-modal Photoacoustic-Ultrasound Imaging for Studying Renal Tissue Function and Hemodynamics.

Combined functional-anatomic imaging modalities, which integrate the benefits of visualizing gross anatomy along with the functional or metabolic information of tissue has revolutionized the world of medical imaging. However, such existing imaging modalities are very costly. An alternative option could be a hybrid modality combining contrast-enhanced ultrasound, doppler and photoacoustic imaging. In the current study, we propose an artificial intelligence assisted multi-modal imaging platform where we have used U-net model for segmenting the anatomical features from the ultrasound images obtained from an animal model study. The neural network has performed accurately for three different cases, each with a high dice score. The model was co-validated with doppler images. Further, blood perfusion and tissue oxygenation information from the predicted anatomical structures were also studied. The present findings confirm the feasibility of using this multimodal imaging modality facilitated by artificial intelligence for better understanding of the hemodynamics of the kidney.Clinical Relevance-A multi-modal imaging technique has been proposed which would provide anatomical and functional information to the clinicians for early detection and tracking of the disease prognosis. Unlike existing imaging modalities like PET-CT (Positron Emission Tomography- Computed Tomography), the proposed modality is much more costeffective and radiation free (non-ionizing nature).

Boosting Algorithms based Cuff-less Blood Pressure Estimation from Clinically Relevant ECG and PPG Morphological Features.

Blood Pressure (BP) is often coined as a critical physiological marker for cardiovascular health. Multiple studies have explored either Photoplethysmogram (PPG) or ECG-PPG derived features for continuous BP estimation using machine learning (ML); deep learning (DL) techniques. Majority of those derived features often lack a stringent biological explanation and are not significantly correlated with BP. In this paper, we identified several clinically relevant (bio-inspired) ECG and PPG features; and exploited them to estimate Systolic (SBP), and Diastolic Blood Pressure (DBP) values using CatBoost, and AdaBoost algorithms. The estimation performance was then compared against popular ML algorithms. SBP and DBP achieved a Pearson's correlation coefficient of 0.90 and 0.83 between estimated and target BP values. The estimated mean absolute error (MAE) values are 3.81 and 2.22 mmHg with a Standard Deviation of 6.24 and 3.51 mmHg, respectively, for SBP and DBP using CatBoost. The results surpassed the Advancement of Medical Instrumentation (AAMI) standards. For the British Hypertension Society (BHS) protocol, the results achieved for all the BP categories resided in Grade A. Further investigation reveals that bio-inspired features along with tuned ML models can produce comparable results w.r.t parameter-intensive DL networks. ln(HR × mNPV), HR, BMI index, ageing index, and PPG-K point were identified as the top five key features for estimating BP. The group-based analysis further concludes that a trade-off lies between the number of features and MAE. Increasing the no. of features beyond a certain threshold saturates the reduction in MAE.

Deep Learning based Skin-layer Segmentation for Characterizing Cutaneous Wounds from Optical Coherence Tomography Images.

Optical coherence tomography (OCT) is a medical imaging modality that allows us to probe deeper sub-structures of skin. The state-of-the-art wound care prediction and monitoring methods are based on visual evaluation and focus on surface information. However, research studies have shown that sub-surface information of the wound is critical for understanding the wound healing progression. This work demonstrated the use of OCT as an effective imaging tool for objective and non-invasive assessments of wound severity, the potential for healing, and healing progress by measuring the optical characteristics of skin components. We have demonstrated the efficacy of OCT in studying wound healing progress in vivo small animal models. Automated analysis of OCT datasets poses multiple challenges, such as limitations in the training dataset size, variation in data distribution induced by uncertainties in sample quality and experiment conditions. We have employed a U-Net-based model for segmentation of skin layers based on OCT images and to study epithelial and regenerated tissue thickness wound closure dynamics and thus quantify the progression of wound healing. In the experimental evaluation of the OCT skin image datasets, we achieved the objective of skin layer segmentation with an average intersection over union (IOU) of 0.9234. The results have been corroborated using gold-standard histology images and co-validated using inputs from pathologists.Clinical Relevance-To monitor wound healing progression without disrupting the healing procedure by superficial, non-invasive means via the identification of pixel characteristics of individual layers.

AR visualizations in laparoscopy: surgeon preferences and depth assessment of vascular anatomy.

Introduction: This study compares five augmented reality (AR) vasculature visualization techniques in a mixed-reality laparoscopy simulator with 50 medical professionals and analyzes their impact on the surgeon. Material and methods: ​​The different visualization techniques' abilities to convey depth were measured using the participant's accuracy in an objective depth sorting task. Demographic data and subjective measures, such as the preference of each AR visualization technique and potential application areas, were collected with questionnaires. Results: Despite measuring differences in objective measurements across the visualization techniques, they were not statistically significant. In the subjective measures, however, 55% of the participants rated visualization technique II, 'Opaque with single-color Fresnel highlights', as their favorite. Participants felt that AR could be useful for various surgeries, especially complex surgeries (100%). Almost all participants agreed that AR could potentially improve surgical parameters, such as patient safety (88%), complication rate (84%), and identifying risk structures (96%). Conclusions: More studies are needed on the effect of different visualizations on task performance, as well as more sophisticated and effective visualization techniques for the operating room. With the findings of this study, we encourage the development of new study setups to advance surgical AR.

Phantom study on surgical performance in augmented reality laparoscopy.

PURPOSE: Only a few studies have evaluated Augmented Reality (AR) in in vivo simulations compared to traditional laparoscopy; further research is especially needed regarding the most effective AR visualization technique. This pilot study aims to determine, under controlled conditions on a 3D-printed phantom, whether an AR laparoscope improves surgical outcomes over conventional laparoscopy without augmentation. METHODS: We selected six surgical residents at a similar level of training and had them perform a laparoscopic task. The participants repeated the experiment three times, using different 3D phantoms and visualizations: Floating AR, Occlusion AR, and without any AR visualization (Control). Surgical performance was determined using objective measurements. Subjective measures, such as task load and potential application areas, were collected with questionnaires. RESULTS: Differences in operative time, total touching time, and SurgTLX scores showed no statistical significance ([Formula: see text]). However, when assessing the invasiveness of the simulated intervention, the comparison revealed a statistically significant difference ([Formula: see text]). Participants felt AR could be useful for various surgeries, especially for liver, sigmoid, and pancreatic resections (100%). Almost all participants agreed that AR could potentially lead to improved surgical parameters, such as operative time (83%), complication rate (83%), and identifying risk structures (83%). CONCLUSION: According to our results, AR may have great potential in visceral surgery and based on the objective measures of the study, may improve surgeons' performance in terms of an atraumatic approach. In this pilot study, participants consistently took more time to complete the task, had more contact with the vascular tree, were significantly more invasive, and scored higher on the SurgTLX survey than with AR.

Local Shape Preserving Deformations for Augmented Reality Assisted Laparoscopic Surgery.

Image registration is a commonly required task in computer assisted surgical procedures. Existing registration methods in laparoscopic navigation systems suffer from several constraints, such as lack of deformation compensation. The proposed algorithm aims to provide the surgeons with updated navigational information about the deep-seated anatomy, which considers the continuous deformations in the operating environment. We extended an initial rigid registration to a shape-preserving deformable registration pathway by incorporating user interaction and an iterative mesh editing scheme which preserves local details. The proposed deformable registration workflow was tested with phantom and animal trial datasets. A qualitative evaluation based on expert feedback demonstrated satisfactory outcome, and an commensurate execution efficiency was achieved. The improvements offered by the method, couples with its relatively easy implementation, makes it an attractive method for adoption in future pre-clinical and clinical applications of augmented reality assisted surgeries.

Brilliant cresyl blue enhanced optoacoustic imaging enables non-destructive imaging of mammalian ovarian follicles for artificial reproduction.

In the field of reproductive biology, there is a strong need for a suitable tool capable of non-destructive evaluation of oocyte viability and function. We studied the application of brilliant cresyl blue (BCB) as an intra-vital exogenous contrast agent using multispectral optoacoustic tomography (MSOT) for visualization of porcine ovarian follicles. The technique provided excellent molecular sensitivity, enabling the selection of competent oocytes without disrupting the follicles. We further conducted in vitro embryo culture, molecular analysis (real-time and reverse transcriptase polymerase chain reaction) and DNA fragmentation analysis to comprehensively establish the safety of BCB-enhanced MSOT imaging in monitoring oocyte viability. Overall, the experimental results suggest that the method offers a significant advance in the use of contrast agents and molecular imaging for reproductive studies. Our technique improves the accurate prediction of ovarian reserve significantly and, once standardized for in vivo imaging, could provide an effective tool for clinical infertility management.

The Power of Light: Nobel Prize in Physics 2018.

The 2018 Nobel Prize in Physics was awarded to three scientists in the field of laser science: Dr. Arthur Ashkin for his invention of the optical tweezers and their application to biological systems, and Dr. Gérard Mourou and Dr. Donna Strickland for their method of generating high-intensity, ultrashort optical pulses. The awards integrate the far reaches of time and intensity scales in laser technologies, from the extremely high-intensity chirped pulse lasers (by Mourou and Strickland) to the ultralow-power beams (by Ashkin) that are capable of handling delicate biological objects and molecules [1], [2]. The IEEE family is indeed delighted to see two of its Life Fellows, Arthur Ashkin and Gérard Mourou, as co-recipients of the awards from the Royal Swedish Academy of Science. Mourou is a past recipient of the IEEE Photonics Quantum Electronics Award and the IEEE David Sarnoff Award. Strickland has been an active author in the IEEE Journal of Quantum Electronics and IEEE Journal of Selected Topics in Quantum Electronics.

Maximum Entropy Based Non-Negative Optoacoustic Tomographic Image Reconstruction.

OBJECTIVE: Optoacoustic (photoacoustic) tomography is aimed at reconstructing maps of the initial pressure rise induced by the absorption of light pulses in tissue. In practice, due to inaccurate assumptions in the forward model, noise, and other experimental factors, the images are often afflicted by artifacts, occasionally manifested as negative values. The aim of this work is to develop an inversion method which reduces the occurrence of negative values and improves the quantitative performance of optoacoustic imaging. METHODS: We present a novel method for optoacoustic tomography based on an entropy maximization algorithm, which uses logarithmic regularization for attaining non-negative reconstructions. The reconstruction image quality is further improved using structural prior-based fluence correction. RESULTS: We report the performance achieved by the entropy maximization scheme on numerical simulation, experimental phantoms, and in-vivo samples. CONCLUSION: The proposed algorithm demonstrates superior reconstruction performance by delivering non-negative pixel values with no visible distortion of anatomical structures. SIGNIFICANCE: Our method can enable quantitative optoacoustic imaging, and has the potential to improve preclinical and translational imaging applications.

Imaging Intelligence: AI Is Transforming Medical Imaging Across the Imaging Spectrum.

Artificial intelligence (AI) and machine learning (ML) have influenced medicine in myriad ways, and medical imaging is at the forefront of technological transformation. Recent advances in AI/ML fields have made an impact on imaging and image analysis across the board, from microscopy to radiology. AI has been an active field of research since the 1950s; however, for most of this period, algorithms achieved subhuman performance and were not broadly adopted in medicine. Recent enhancements for computational hardware is enabling researchers to revisit old AI algorithms and experiment with new mathematical ideas. Researchers are applying these methods to a broad array of medical technologies, ranging from microscopic image analysis to tomographic image reconstruction and diagnostic planning.

Advancing ovarian folliculometry with selective plane illumination microscopy.

Determination of ovarian status and follicle monitoring are common methods of diagnosing female infertility. We evaluated the suitability of selective plane illumination microscopy (SPIM) for the study of ovarian follicles. The large field of view and fast acquisition speed of our SPIM system enables rendering of volumetric image stacks from intact whole porcine ovarian follicles, clearly visualizing follicular features including follicle volume and average diameter (70 µm-2.5 mm), their spherical asymmetry parameters, size of developing cumulus oophorus complexes (40 µm-110 µm), and follicular wall thickness (90 µm-120 µm). Follicles at all developmental stages were identified. A distribution of the theca thickness was measured for each follicle, and a relationship between these distributions and the stages of follicular development was discerned. The ability of the system to non-destructively generate sub-cellular resolution 3D images of developing follicles, with excellent image contrast and high throughput capacity compared to conventional histology, suggests that it can be used to monitor follicular development and identify structural abnormalities indicative of ovarian ailments. Accurate folliculometric measurements provided by SPIM images can immensely help the understanding of ovarian physiology and provide important information for the proper management of ovarian diseases.

Visual Quality Enhancement in Optoacoustic Tomography Using Active Contour Segmentation Priors.

Segmentation of biomedical images is essential for studying and characterizing anatomical structures as well as for detection and evaluation of tissue pathologies. Segmentation has been further shown to enhance the reconstruction performance in many tomographic imaging modalities by accounting for heterogeneities in the excitation field and tissue properties in the imaged region. This is particularly relevant in optoacoustic tomography, where discontinuities in the optical and acoustic tissue properties, if not properly accounted for, may result in deterioration of the imaging performance. Efficient segmentation of optoacoustic images is often hampered by the relatively low intrinsic contrast of large anatomical structures, which is further impaired by the limited angular coverage of some commonly employed tomographic imaging configurations. Herein, we analyze the performance of active contour models for boundary segmentation in cross-sectional optoacoustic tomography. The segmented mask is employed to construct a two compartment model for the acoustic and optical parameters of the imaged tissues, which is subsequently used to improve accuracy of the image reconstruction routines. The performance of the suggested segmentation and modeling approach are showcased in tissue-mimicking phantoms and small animal imaging experiments.

Improving Optoacoustic Image Quality via Geometric Pixel Super-Resolution Approach.

High fidelity optoacoustic (photoacoustic) tomography requires dense spatial sampling of optoacoustic signals using point acoustic detectors. However, in practice, spatial resolution of the images is often limited by limited sampling either due to coarse multi-element arrays or time in raster scan measurements. Herein, we investigate a method that integrates information from multiple optoacoustic images acquired at sub-diffraction steps into one high resolution image by means of an iterative registration algorithm. Experimental validations performed in target phantoms and ex vivo tissue samples confirm that the suggested approach renders significant improvements in terms of optoacoustic image resolution and quality without introducing significant alterations into the signal acquisition hardware or inversion algorithms.

Simultaneous visualization of tumour oxygenation, neovascularization and contrast agent perfusion by real-time three-dimensional optoacoustic tomography.

OBJECTIVES: Intravital imaging within heterogenic solid tumours is important for understanding blood perfusion profiles responsible for establishment of multiple parameters within the tumour mass, such as hypoxic and nutrition gradients, cell viability, proliferation and drug response potentials. METHODS: Herein, we developed a method based on a volumetric multispectral optoacoustic tomography (vMSOT) for cancer imaging in preclinical models and explored its capacity for three-dimensional imaging of anatomic, vascular and functional tumour profiles in real time. RESULTS: In contrast to methods based on cross-sectional (2D) image acquisition as a basis for 3D rendering, vMSOT has attained concurrent observations from the entire tumour volume at 10 volumetric frames per second. This truly four dimensional imaging performance has enabled here the simultaneous assessment of blood oxygenation gradients and vascularization in solid breast tumours and revealed different types of blood perfusion profiles in-vivo. CONCLUSION: The newly introduced capacity for high-resolution three-dimensional tracking of fast tumour perfusion suggests vMSOT as a powerful method in preclinical cancer research and theranostics. As the imaging setup can be equally operated in both stationary and handheld mode, the solution is readily translatable for perfusion monitoring in a clinical setting. KEY POINTS: • vMSOT visualizes 3D anatomic, vascular and functional tumour profiles in real time. • Three types of blood perfusion profiles are revealed in breast tumour model. • The method is readily adaptable to operate in a handheld clinical mode.

Extending biological imaging to the fifth dimension: evolution of volumetric small animal multispectral optoacoustic tomography.

Despite the ancient discovery of the basic physical phenomenon underlying optoacoustic imaging and tomography [1], the lack of suitable laser sources, ultrasound detection technology, data acquisition, and processing capacities has long hindered the realization of efficient imaging devices. In fact, the first high-quality images from living animals were obtained about a decade ago (Figure 1), which was followed by an exponential growth of technical developments in instrumentation, algorithms, and biomedical applications surrounding this fascinating field. The ability of optoacoustics to probe optical contrast along a wide domain of penetration scales while maintaining excellent spatiotemporal resolution representative of ultrasound imaging, as shown in Figure 2, is unparalleled among the other optical imaging modalities [2], [3].

Enhancing professionalism among engineering students through involvements in technical societies.

A student chapter can be considered to be a miniature enterprise; however without the latter's major financial risks. Involvement in the student chapter of a professional society like IEEE at undergraduate level plays a pivotal role in the overall professional development of the student by keeping the students informed about the various career possibilities. A student chapter shapes the hitherto naive students into industry ready professionals and to suitable candidates for some of the best grad schools worldwide. This assertion has been discussed in-depth taking the example of IEEE EMBS Student Branch chapter of VIT University. It has been described how the entire process, - starting from inception of an idea to its materialization in to an activity, has shaped the volunteers and participants into better professionals.

Optimal self-calibration of tomographic reconstruction parameters in whole-body small animal optoacoustic imaging.

In tomographic optoacoustic imaging, multiple parameters related to both light and ultrasound propagation characteristics of the medium need to be adequately selected in order to accurately recover maps of local optical absorbance. Speed of sound in the imaged object and surrounding medium is a key parameter conventionally assumed to be uniform. Mismatch between the actual and predicted speed of sound values may lead to image distortions but can be mitigated by manual or automatic optimization based on metrics of image sharpness. Although some simple approaches based on metrics of image sharpness may readily mitigate distortions in the presence of highly contrasting and sharp image features, they may not provide an adequate performance for smooth signal variations as commonly present in realistic whole-body optoacoustic images from small animals. Thus, three new hybrid methods are suggested in this work, which are shown to outperform well-established autofocusing algorithms in mouse experiments in vivo.

Development of cardiac prescreening device for rural population using ultralow-power embedded system.

The invention is inspired by the desire to understand the opportunities and expectations of developing economies in terms of healthcare. The designed system is a point-of-care (POC) device that can deliver heart-care services to the rural population and bridge the rural-urban divide in healthcare delivery. The product design incorporates several innovations including the effective use of adaptive and multiresolution signal-processing techniques for acquisition, denoising, segmentation, and characterization of the heart sounds (HS) and murmurs using an ultralow-power embedded Mixed Signal Processor. The device is able to provide indicative diagnosis of cardiac conditions and classify a subject into either normal, abnormal, ischemic, or valvular abnormalities category. Preliminary results demonstrated by the prototype confirm the applicability of the device as a prescreening tool that can be used by paramedics in rural outreach programs. Feedback from medical professionals also shows that such a device is helpful in early detection of common congenital heart diseases. This letter aims to determine a framework for utilization of automated HS analysis system for community healthcare and healthcare inclusion.