Efficient Photoacoustic Image Synthesis with Deep Learning.

Photoacoustic imaging potentially allows for the real-time visualization of functional human tissue parameters such as oxygenation but is subject to a challenging underlying quantification problem. While in silico studies have revealed the great potential of deep learning (DL) methodology in solving this problem, the inherent lack of an efficient gold standard method for model training and validation remains a grand challenge. This work investigates whether DL can be leveraged to accurately and efficiently simulate photon propagation in biological tissue, enabling photoacoustic image synthesis. Our approach is based on estimating the initial pressure distribution of the photoacoustic waves from the underlying optical properties using a back-propagatable neural network trained on synthetic data. In proof-of-concept studies, we validated the performance of two complementary neural network architectures, namely a conventional U-Net-like model and a Fourier Neural Operator (FNO) network. Our in silico validation on multispectral human forearm images shows that DL methods can speed up image generation by a factor of 100 when compared to Monte Carlo simulations with 5×108 photons. While the FNO is slightly more accurate than the U-Net, when compared to Monte Carlo simulations performed with a reduced number of photons (5×106), both neural network architectures achieve equivalent accuracy. In contrast to Monte Carlo simulations, the proposed DL models can be used as inherently differentiable surrogate models in the photoacoustic image synthesis pipeline, allowing for back-propagation of the synthesis error and gradient-based optimization over the entire pipeline. Due to their efficiency, they have the potential to enable large-scale training data generation that can expedite the clinical application of photoacoustic imaging.

Blue toe syndrome caused by emboli from anomalous left atrial septal pouch thrombus: a case report.

BACKGROUND: Left atrial septal pouches (LASPs) are a relatively newly described but common anatomical cardiac variant thought to be associated with atrial fibrillation (AF) and cardio-embolic stroke. Blue toe syndrome (BTS) describes ischemic changes in the toes due to microembolisation of the digital arteries. Establishing the etiology of BTS is vital so that the underlying cause can be treated. Here we describe the first case of BTS arising due to emboli from LASP thrombus arising on a background of new-onset AF. CASE PRESENTATION: A 65-year-old man presented with a two-day history of progressive painful swelling and bluish-purple discoloration of the second and fourth toes of his left foot and new-onset AF. Tests for hypercoagulability disorders were negative. Duplex ultrasound and CT angiography excluded deep venous thrombosis and an absence of embolus, thrombus, or occlusion in the arterial tree in the lower extremities bilaterally, so BTS was diagnosed. While transthoracic echocardiography and chest CT initially showed no cardiac abnormalities or mural thrombus, subsequent transesophageal echocardiography revealed a LASP with an associated pedunculated thrombus. The affected toes were amputated due to wet gangrene, but the patient recovered well with thrombus resolution after anticoagulation. CONCLUSION: The presence of a LASP in the absence of any other identifiable cause of BTS should trigger careful investigation of the interatrial septum, preferably using a multimodality imaging approach. The possibility that LASPs may not merely be an innocent bystander but a causative mechanism for peripheral ischemia must be considered.

Photoacoustic quantification of tissue oxygenation using conditional invertible neural networks.

Intelligent systems in interventional healthcare depend on the reliable perception of the environment. In this context, photoacoustic tomography (PAT) has emerged as a non-invasive, functional imaging modality with great clinical potential. Current research focuses on converting the high-dimensional, not human-interpretable spectral data into the underlying functional information, specifically the blood oxygenation. One of the largely unexplored issues stalling clinical advances is the fact that the quantification problem is ambiguous, i.e. that radically different tissue parameter configurations could lead to almost identical photoacoustic spectra. In the present work, we tackle this problem with conditional Invertible Neural Networks (cINNs). Going beyond traditional point estimates, our network is used to compute an approximation of the conditional posterior density of tissue parameters given the measurement. To this end, an automatic mode detection algorithm extracts the plausible solution from the sample-based posterior. According to a comprehensive validation study based on both synthetic and real images, our approach is well-suited for exploring ambiguity in quantitative PAT.

CholecTriplet2022: Show me a tool and tell me the triplet - An endoscopic vision challenge for surgical action triplet detection.

Formalizing surgical activities as triplets of the used instruments, actions performed, and target anatomies is becoming a gold standard approach for surgical activity modeling. The benefit is that this formalization helps to obtain a more detailed understanding of tool-tissue interaction which can be used to develop better Artificial Intelligence assistance for image-guided surgery. Earlier efforts and the CholecTriplet challenge introduced in 2021 have put together techniques aimed at recognizing these triplets from surgical footage. Estimating also the spatial locations of the triplets would offer a more precise intraoperative context-aware decision support for computer-assisted intervention. This paper presents the CholecTriplet2022 challenge, which extends surgical action triplet modeling from recognition to detection. It includes weakly-supervised bounding box localization of every visible surgical instrument (or tool), as the key actors, and the modeling of each tool-activity in the form of triplet. The paper describes a baseline method and 10 new deep learning algorithms presented at the challenge to solve the task. It also provides thorough methodological comparisons of the methods, an in-depth analysis of the obtained results across multiple metrics, visual and procedural challenges; their significance, and useful insights for future research directions and applications in surgery.

Photoacoustic image synthesis with generative adversarial networks.

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).

Periodontal damage after thermal inhalation injury - The impact of high temperature inhalation injury on long term periodontal health.

PURPOSE: Thermal inhalation injury is a common, life-threatening problem in burned patients. Whether or not this single event of damage to the oral integrity causes long term health problems is yet to be examined. MATERIAL AND METHODS: All consecutive burn patients between 2014 and 2017 of Marienhospital Stuttgart (MHS), Germany, with at least 10% of burned skin surface were included and compared. The Periodontal Screening Index as well as Vitamin D levels were examined. Vitamin D has been suspected to contribute to the genesis of periodontitis. Risk factors and subjective oral life quality were prompted. RESULTS: We included a total of 32 patients, 15 of which had an inhalation injury in their medical history. Risk factors were examined via Renatus' questionnaire. While risk factors were equally distributed in both groups we saw a remarkable difference in periodontal integrity, with the Periodontal Screening Index (PSI) per sextant differing drastically (with inhalation injury: 2.40, without inhalation injury: 1.10, p < 0.001). Patients with an inhalation injury had a mean of 5.2 out of 6 possible sextants with a pathologic PSI (with the median being 6/6), while patients without an inhalation injury had a mean of 1.83 out of 6 (median: 1/6), p < 0.001. The oral health impact profile showed a difference as well, albeit without statistical significance (with inhalation injury: median = 11, without: median = 3.5, p = 0.414). A correlation between Serum Vitamin D levels and periodontal integrity could not be seen in this group. CONCLUSION: Inhalation injury is a possible cause for periodontitis and hence impacts the quality of life of burned patients.

Tattoo tomography: Freehand 3D photoacoustic image reconstruction with an optical pattern.

PURPOSE: Photoacoustic tomography (PAT) is a novel imaging technique that can spatially resolve both morphological and functional tissue properties, such as 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 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 single tomographic image of it enables the recovery of the probe pose relative to the coordinate system of the pattern, which serves as a global coordinate system for image compounding. RESULTS: To investigate the feasibility of Tattoo tomography, we assessed the quality of 3D image reconstruction with experimental phantom data and in vivo forearm data. The results obtained with our prototype indicate that the Tattoo method enables the accurate and precise 3D reconstruction of PAT data and may be better suited for this task than the baseline method using optical tracking. CONCLUSIONS: 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.

[ECG score to predict ICD therapies in patients with nonischemic cardiomyopathy and primary prophylactic CRT-D]. / EKG-Score zur Vorhersage von ICD-Therapien bei nichtischämischer Kardiomyopathie und primärprophylaktischem CRT-D.

BACKGROUND AND PROBLEM: Recently published results of the DANISH study raise concerns, if primary prophylactic ICD implantations in patients with nonischemic cardiomyopathy (NICM) and severe reduced left ventricular ejection fraction (LVEF) should be performed without further risk stratification. There was no significant difference in the overall mortality of patients with or without ICD and CRT defibrillator (CRT-D) or CRT pacemaker (CRT-P), respectively. Clinical risk scores to identify patients with ischemic cardiomyopathy (ICM) who benefit most from an ICD have been recommended. The need for risk stratification systems concerning patients with NICM has been emphasized. STUDY DESIGN AND METHODS: A retrospective study of 434 consecutive patients with CRT-D implantation was performed. Patients with no regular follow-up at our institution (n = 132), secondary prophylactic ICD indication (n = 61), and upgrade to CRT (n = 95) were excluded. The occurrence of an adequate ICD therapy was defined as the endpoint. Left ventricular ejection fraction (LVEF), genesis of the cardiomyopathy as well as the modified Selvester ECG score (MSES) for evaluation of the left ventricular scar burden were documented among other characteristics. RESULTS: Within a median follow-up of 605 days, 24% of the patients experienced an adequate ICD therapy. These patients had significantly lower LVEF (20% vs. 23%), and the MSES was higher (7 vs. 3 points). There was no significant difference in patients suffering from ICM vs NICM. A receiver-operating-characteristic (ROC) analysis revealed a sensitivity of 0.914 and a specifity of 0.586 for MSES ≥4 to predict the occurrence of an ICD therapy. None of 35 patients suffering from NICM with MSES <4 experienced an ICD therapy. INTERPRETATION: The evaluation of the left ventricular scar burden using MSES can be useful for the decision between CRT-D and CRT-P in patients suffering from NICM.