Search

When developing machine learning models, image quality assessment (IQA) measures are a crucial component for evaluation. However, commonly used IQA measures have been primarily developed and optimized for natural images. In many specialized settings, such as medical images, this poses an often-overlooked problem regarding suitability. In previous studies, the IQA measure HaarPSI showed promising behavior for natural and medical images. HaarPSI is based on Haar wavelet representations and the framework allows optimization of two parameters. So far, these parameters have been aligned for natural images. Here, we optimize these parameters for two annotated medical data sets, a photoacoustic and a chest X-Ray data set. We observe that they are more sensitive to the parameter choices than the employed natural images, and on the other hand both medical data sets lead to similar parameter values when optimized. We denote the optimized setting, which improves the performance for the medical images notably, by HaarPSI$_{MED}$. The results suggest that adapting common IQA measures within their frameworks for medical images can provide a valuable, generalizable addition to the employment of more specific task-based measures., Comment: 5 pages, 3 figures, 2 tables

Image quality assessment (IQA) is standard practice in the development stage of novel machine learning algorithms that operate on images. The most commonly used IQA measures have been developed and tested for natural images, but not in the medical setting. Reported inconsistencies arising in medical images are not surprising, as they have different properties than natural images. In this study, we test the applicability of common IQA measures for medical image data by comparing their assessment to manually rated chest X-ray (5 experts) and photoacoustic image data (2 experts). Moreover, we include supplementary studies on grayscale natural images and accelerated brain MRI data. The results of all experiments show a similar outcome in line with previous findings for medical images: PSNR and SSIM in the default setting are in the lower range of the result list and HaarPSI outperforms the other tested measures in the overall performance. Also among the top performers in our medical experiments are the full reference measures FSIM, LPIPS and MS-SSIM. Generally, the results on natural images yield considerably higher correlations, suggesting that additional employment of tailored IQA measures for medical imaging algorithms is needed.

Image quality assessment (IQA) is not just indispensable in clinical practice to ensure high standards, but also in the development stage of novel algorithms that operate on medical images with reference data. This paper provides a structured and comprehensive collection of examples where the two most common full reference (FR) image quality measures prove to be unsuitable for the assessment of novel algorithms using different kinds of medical images, including real-world MRI, CT, OCT, X-Ray, digital pathology and photoacoustic imaging data. In particular, the FR-IQA measures PSNR and SSIM are known and tested for working successfully in many natural imaging tasks, but discrepancies in medical scenarios have been noted in the literature. Inconsistencies arising in medical images are not surprising, as they have very different properties than natural images which have not been targeted nor tested in the development of the mentioned measures, and therefore might imply wrong judgement of novel methods for medical images. Therefore, improvement is urgently needed in particular in this era of AI to increase explainability, reproducibility and generalizability in machine learning for medical imaging and beyond. On top of the pitfalls we will provide ideas for future research as well as suggesting guidelines for the usage of FR-IQA measures applied to medical images.

Significance: Photoacoustic imaging (PAI) promises to measure spatially-resolved blood oxygen saturation, but suffers from a lack of accurate and robust spectral unmixing methods to deliver on this promise. Accurate blood oxygenation estimation could have important clinical applications, from cancer detection to quantifying inflammation. Aim: This study addresses the inflexibility of existing data-driven methods for estimating blood oxygenation in PAI by introducing a recurrent neural network architecture. Approach: We created 25 simulated training dataset variations to assess neural network performance. We used a long short-term memory network to implement a wavelength-flexible network architecture and proposed the Jensen-Shannon divergence to predict the most suitable training dataset. Results: The network architecture can handle arbitrary input wavelengths and outperforms linear unmixing and the previously proposed learned spectral decolouring method. Small changes in the training data significantly affect the accuracy of our method, but we find that the Jensen-Shannon divergence correlates with the estimation error and is thus suitable for predicting the most appropriate training datasets for any given application. Conclusions: A flexible data-driven network architecture combined with the Jensen-Shannon Divergence to predict the best training data set provides a promising direction that might enable robust data-driven photoacoustic oximetry for clinical use cases., Comment: 37 pages, 7 figures

Accurate measurement of optical absorption coefficients from photoacoustic imaging (PAI) data would enable direct mapping of molecular concentrations, providing vital clinical insight. The ill-posed nature of the problem of absorption coefficient recovery has prohibited PAI from achieving this goal in living systems due to the domain gap between simulation and experiment. To bridge this gap, we introduce a collection of experimentally well-characterised imaging phantoms and their digital twins. This first-of-a-kind phantom data set enables supervised training of a U-Net on experimental data for pixel-wise estimation of absorption coefficients. We show that training on simulated data results in artefacts and biases in the estimates, reinforcing the existence of a domain gap between simulation and experiment. Training on experimentally acquired data, however, yielded more accurate and robust estimates of optical absorption coefficients. We compare the results to fluence correction with a Monte Carlo model from reference optical properties of the materials, which yields a quantification error of approximately 20%. Application of the trained U-Nets to a blood flow phantom demonstrated spectral biases when training on simulated data, while application to a mouse model highlighted the ability of both learning-based approaches to recover the depth-dependent loss of signal intensity. We demonstrate that training on experimental phantoms can restore the correlation of signal amplitudes measured in depth. While the absolute quantification error remains high and further improvements are needed, our results highlight the promise of deep learning to advance quantitative PAI., Comment: 20 pages, 14 figures

Synthetic medical image generation has evolved as a key technique for neural network training and validation. A core challenge, however, remains in the domain gap between simulations and real data. While deep learning-based domain transfer using Cycle Generative Adversarial Networks and similar architectures has led to substantial progress in the field, there are use cases in which state-of-the-art approaches still fail to generate training images that produce convincing results on relevant downstream tasks. Here, we address this issue with a domain transfer approach based on conditional invertible neural networks (cINNs). As a particular advantage, our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood training. To showcase our method's generic applicability, we apply it to two spectral imaging modalities at different scales, namely hyperspectral imaging (pixel-level) and photoacoustic tomography (image-level). According to comprehensive experiments, our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks (binary and multi-class). cINN-based domain transfer could thus evolve as an important method for realistic synthetic data generation in the field of spectral imaging and beyond.

Photoacoustic (PA) imaging has the potential to revolutionize functional medical imaging in healthcare due to the valuable information on tissue physiology contained in multispectral photoacoustic measurements. Clinical translation of the technology requires conversion of the high-dimensional acquired data into clinically relevant and interpretable information. In this work, we present a deep learning-based approach to semantic segmentation of multispectral photoacoustic images to facilitate image interpretability. Manually annotated photoacoustic {and ultrasound} imaging data are used as reference and enable the training of a deep learning-based segmentation algorithm in a supervised manner. Based on a validation study with experimentally acquired data from 16 healthy human volunteers, we show that automatic tissue segmentation can be used to create powerful analyses and visualizations of multispectral photoacoustic images. Due to the intuitive representation of high-dimensional information, such a preprocessing algorithm could be a valuable means to facilitate the clinical translation of photoacoustic imaging., Comment: 8 pages, 7 figures, 3 tables

Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties with high spatial resolution. However, previous attempts to solve the optical inverse problem with supervised machine learning were hampered by the absence of labeled reference data. While this bottleneck has been tackled by simulating training data, the domain gap between real and simulated images remains an unsolved challenge. We propose a novel approach to PAT image synthesis that involves subdividing the challenge of generating plausible simulations into two disjoint problems: (1) Probabilistic generation of realistic tissue morphology, and (2) pixel-wise assignment of corresponding optical and acoustic properties. The former is achieved with Generative Adversarial Networks (GANs) trained on semantically annotated medical imaging data. According to a validation study on a downstream task our approach yields more realistic synthetic images than the traditional model-based approach and could therefore become a fundamental step for deep learning-based quantitative PAT (qPAT)., Comment: 10 pages, 6 figures, 2 tables, update with paper published at Photoacoustics

Purpose: Photoacoustic tomography (PAT) is a novel imaging technique that can spatially resolve both morphological and functional tissue properties, such as the vessel topology and tissue oxygenation. While this capacity makes PAT a promising modality for the diagnosis, treatment and follow-up of various diseases, a current drawback is the limited field-of-view (FoV) provided by the conventionally applied 2D probes. Methods: In this paper, we present a novel approach to 3D reconstruction of PAT data (Tattoo tomography) that does not require an external tracking system and can smoothly be integrated into clinical workflows. It is based on an optical pattern placed on the region of interest prior to image acquisition. This pattern is designed in a way that a tomographic image of it enables the recovery of the probe pose relative to the coordinate system of the pattern. This allows the transformation of a sequence of acquired PA images into one common global coordinate system and thus the consistent 3D reconstruction of PAT imaging data. Results: An initial feasibility study conducted with experimental phantom data and in vivo forearm data indicates that the Tattoo approach is well-suited for 3D reconstruction of PAT data with high accuracy and precision. Conclusion: In contrast to previous approaches to 3D ultrasound (US) or PAT reconstruction, the Tattoo approach neither requires complex external hardware nor training data acquired for a specific application. It could thus become a valuable tool for clinical freehand PAT., Comment: 12 pages, 5 figures

Multispectral photoacoustic imaging (PAI) is an emerging imaging modality which enables the recovery of functional tissue parameters such as blood oxygenation. However, the underlying inverse problems are potentially ill-posed, meaning that radically different tissue properties may - in theory - yield comparable measurements. In this work, we present a new approach for handling this specific type of uncertainty by leveraging the concept of conditional invertible neural networks (cINNs). Specifically, we propose going beyond commonly used point estimates for tissue oxygenation and converting single-pixel initial pressure spectra to the full posterior probability density. This way, the inherent ambiguity of a problem can be encoded with multiple modes in the output. Based on the presented architecture, we demonstrate two use cases which leverage this information to not only detect and quantify but also to compensate for uncertainties: (1) photoacoustic device design and (2) optimization of photoacoustic image acquisition. Our in silico studies demonstrate the potential of the proposed methodology to become an important building block for uncertainty-aware reconstruction of physiological parameters with PAI., Comment: 7 pages, 4 figures, submitted to "Bildverarbeitung f\"ur die Medizin (BVM) 2021"

Photoacoustic imaging (PAI) is a promising emerging imaging modality that enables spatially resolved imaging of optical tissue properties up to several centimeters deep in tissue, creating the potential for numerous exciting clinical applications. However, extraction of relevant tissue parameters from the raw data requires the solving of inverse image reconstruction problems, which have proven extremely difficult to solve. The application of deep learning methods has recently exploded in popularity, leading to impressive successes in the context of medical imaging and also finding first use in the field of PAI. Deep learning methods possess unique advantages that can facilitate the clinical translation of PAI, such as extremely fast computation times and the fact that they can be adapted to any given problem. In this review, we examine the current state of the art regarding deep learning in PAI and identify potential directions of research that will help to reach the goal of clinical applicability, Comment: 31 pages, 8 figures, 3 tables, 169 references

Image-based tracking of medical instruments is an integral part of surgical data science applications. Previous research has addressed the tasks of detecting, segmenting and tracking medical instruments based on laparoscopic video data. However, the proposed methods still tend to fail when applied to challenging images and do not generalize well to data they have not been trained on. This paper introduces the Heidelberg Colorectal (HeiCo) data set - the first publicly available data set enabling comprehensive benchmarking of medical instrument detection and segmentation algorithms with a specific emphasis on method robustness and generalization capabilities. Our data set comprises 30 laparoscopic videos and corresponding sensor data from medical devices in the operating room for three different types of laparoscopic surgery. Annotations include surgical phase labels for all video frames as well as information on instrument presence and corresponding instance-wise segmentation masks for surgical instruments (if any) in more than 10,000 individual frames. The data has successfully been used to organize international competitions within the Endoscopic Vision Challenges 2017 and 2019., Comment: Submitted to Nature Scientific Data

Multispectral photoacoustic (PA) imaging is a prime modality to monitor hemodynamics and changes in blood oxygenation (sO2). Although sO2 changes can be an indicator of brain activity both in normal and in pathological conditions, PA imaging of the brain has mainly focused on small animal models with lissencephalic brains. Therefore, the purpose of this work was to investigate the usefulness of multispectral PA imaging in assessing sO2 in a gyrencephalic brain. To this end, we continuously imaged a porcine brain as part of an open neurosurgical intervention with a handheld PA and ultrasonic (US) imaging system in vivo. Throughout the experiment, we varied respiratory oxygen and continuously measured arterial blood gases. The arterial blood oxygenation (SaO2) values derived by the blood gas analyzer were used as a reference to compare the performance of linear spectral unmixing algorithms in this scenario. According to our experiment, PA imaging can be used to monitor sO2 in the porcine cerebral cortex. While linear spectral unmixing algorithms are well-suited for detecting changes in oxygenation, there are limits with respect to the accurate quantification of sO2, especially in depth. Overall, we conclude that multispectral PA imaging can potentially be a valuable tool for change detection of sO2 in the cerebral cortex of a gyrencephalic brain. The spectral unmixing algorithms investigated in this work will be made publicly available as part of the open-source software platform Medical Imaging Interaction Toolkit (MITK)., Comment: AAM Conference Proceedings, Photons Plus Ultrasound: Imaging and Sensing 2019; 108780C (2019)

Purpose: Optical imaging is evolving as a key technique for advanced sensing in the operating room. Recent research has shown that machine learning algorithms can be used to address the inverse problem of converting pixel-wise multispectral reflectance measurements to underlying tissue parameters, such as oxygenation. Assessment of the specific hardware used in conjunction with such algorithms, however, has not properly addressed the possibility that the problem may be ill-posed. Methods: We present a novel approach to the assessment of optical imaging modalities, which is sensitive to the different types of uncertainties that may occur when inferring tissue parameters. Based on the concept of invertible neural networks, our framework goes beyond point estimates and maps each multispectral measurement to a full posterior probability distribution which is capable of representing ambiguity in the solution via multiple modes. Performance metrics for a hardware setup can then be computed from the characteristics of the posteriors. Results: Application of the assessment framework to the specific use case of camera selection for physiological parameter estimation yields the following insights: (1) Estimation of tissue oxygenation from multispectral images is a well-posed problem, while (2) blood volume fraction may not be recovered without ambiguity. (3) In general, ambiguity may be reduced by increasing the number of spectral bands in the camera. Conclusion: Our method could help to optimize optical camera design in an application-specific manner., Comment: Accepted at IPCAI 2019

One of the main applications of photoacoustic (PA) imaging is the recovery of functional tissue properties, such as blood oxygenation (sO2). This is typically achieved by linear spectral unmixing of relevant chromophores from multispectral photoacoustic images. Despite the progress that has been made towards quantitative PA imaging (qPAI), most sO2 estimation methods yield poor results in realistic settings. In this work, we tackle the challenge by employing learned spectral decoloring for quantitative photoacoustic imaging (LSD-qPAI) to obtain quantitative estimates for blood oxygenation. LSD-qPAI computes sO2 directly from pixel-wise initial pressure spectra Sp0, which are vectors comprised of the initial pressure at the same spatial location over all recorded wavelengths. Initial results suggest that LSD-qPAI is able to obtain accurate sO2 estimates directly from multispectral photoacoustic measurements in silico and plausible estimates in vivo., Comment: 5 pages

Photoacoustic (PA) imaging systems based on clinical linear ultrasound arrays have become increasingly popular in translational PA research. Such systems can be more easily integrated in a clinical workflow due to the simultaneous access to ultrasonic imaging and their familiarity of use to clinicians. In contrast to more complex setups, hand held linear probes can be applied to a large variety of clinical use cases. However, most translational work with such scanners is based on proprietary development and as such not accessible to the community. In this contribution, we present a custom-built, hybrid, multispectral, real-time photoacoustic and ultrasonic imaging system with a linear array probe that is controlled by software developed within the Medical Imaging Interaction Toolkit (MITK) a highly customizable and extendable open-source software platform. Our software offers direct control of both the laser and the ultrasonic system and may serve as a starting point for various translational research projects and developments. To demonstrate the applicability of the platform, we used it to implement a new method for blood oxygenation estimation in the presence of non-rigid inter-frame motion caused by pulsing arteries. Initial results from experiments with healthy human volunteers demonstrate the suitability of the method with the sample clinical application of imaging the common carotid artery as well as peripheral extremity vessels., Comment: manuscript follow-up for Kirchner et al. "Real-time in vivo blood oxygenation measurements with an open-source software platform for translational photoacoustic research (Conference Presentation)", Proc. SPIE 10494, Photons Plus Ultrasound: Imaging and Sensing 2018, 1049407 (15 March 2018)

Spreading depolarization (SD) is a self-propagating wave of near-complete neuronal depolarization that is abundant in a wide range of neurological conditions, including stroke. SD was only recently documented in humans and is now considered a therapeutic target for brain injury, but the mechanisms related to SD in complex brains are not well understood. While there are numerous approaches to interventional imaging of SD on the exposed brain surface, measuring SD deep in brain is so far only possible with low spatiotemporal resolution and poor contrast. Here, we show that photoacoustic imaging enables the study of SD and its hemodynamics deep in the gyrencephalic brain with high spatiotemporal resolution. As rapid neuronal depolarization causes tissue hypoxia, we achieve this by continuously estimating blood oxygenation with an intraoperative hybrid photoacoustic and ultrasonic (PAUS) imaging system. Due to its high resolution, promising imaging depth and high contrast, this novel approach to SD imaging can yield new insights into SD and thereby lead to advances in stroke, and brain injury research.

Real-time monitoring of functional tissue parameters, such as local blood oxygenation, based on optical imaging could provide groundbreaking advances in the diagnosis and interventional therapy of various diseases. While photoacoustic (PA) imaging is a novel modality with great potential to measure optical absorption deep inside tissue, quantification of the measurements remains a major challenge. In this paper, we introduce the first machine learning based approach to quantitative PA imaging (qPAI), which relies on learning the fluence in a voxel to deduce the corresponding optical absorption. The method encodes relevant information of the measured signal and the characteristics of the imaging system in voxel-based feature vectors, which allow the generation of thousands of training samples from a single simulated PA image. Comprehensive in silico experiments suggest that context encoding (CE)-qPAI enables highly accurate and robust quantification of the local fluence and thereby the optical absorption from PA images., Comment: under review JBO