Design and Implementation of a Cloud PACS Architecture.

The limitations of the classic PACS (picture archiving and communication system), such as the backward-compatible DICOM network architecture and poor security and maintenance, are well-known. They are challenged by various existing solutions employing cloud-related patterns and services. However, a full-scale cloud-native PACS has not yet been demonstrated. The paper introduces a vendor-neutral cloud PACS architecture. It is divided into two main components: a cloud platform and an access device. The cloud platform is responsible for nearline (long-term) image archive, data flow, and backend management. It operates in multi-tenant mode. The access device is responsible for the local DICOM (Digital Imaging and Communications in Medicine) interface and serves as a gateway to cloud services. The cloud PACS was first implemented in an Amazon Web Services environment. It employs a number of general-purpose services designed or adapted for a cloud environment, including Kafka, OpenSearch, and Memcached. Custom services, such as a central PACS node, queue manager, or flow worker, also developed as cloud microservices, bring DICOM support, external integration, and a management layer. The PACS was verified using image traffic from, among others, computed tomography (CT), magnetic resonance (MR), and computed radiography (CR) modalities. During the test, the system was reliably storing and accessing image data. In following tests, scaling behavior differences between the monolithic Dcm4chee server and the proposed solution are shown. The growing number of parallel connections did not influence the monolithic server's overall throughput, whereas the performance of cloud PACS noticeably increased. In the final test, different retrieval patterns were evaluated to assess performance under different scenarios. The current production environment stores over 450 TB of image data and handles over 4000 DICOM nodes.

An Automatic Biopsy Needle Detection and Segmentation on Ultrasound Images Using a Convolutional Neural Network.

Needle visualization in the ultrasound image is essential to successfully perform the ultrasound-guided core needle biopsy. Automatic needle detection can significantly reduce the procedure time, false-negative rate, and highly improve the diagnosis. In this paper, we present a CNN-based, fully automatic method for detection of core needle in 2D ultrasound images. Adaptive moment estimation optimizer is proposed as CNN architecture. Radon transform is applied to locate the needle. The network's model was trained and tested on the total of 619 2D images from 91 cases of breast cancer. The model has achieved an average weighted intersection over union (the weighted Jaccard Index) of 0.986, F1 Score of 0.768, and angle RMSE of 3.73°. The obtained results exceed the other solutions by at least 0.27 and 7° in case of F1 score and angle RMSE, respectively. Finally, the needle is detected in a single frame averagely in 21.6 ms on a modern PC.

Chronic wounds multimodal image database.

A multimodal wound image database was created to allow fast development of computer-aided approaches for wound healing monitoring. The developed system with parallel camera optical axes enables multimodal images: photo, thermal, stereo, and depth map of the wound area to be acquired. As a result of using this system a multimodal database of chronic wound images is introduced. It contains 188 image sets of photographs, thermal images, and 3D meshes of the surfaces of chronic wounds acquired during 79 patient visits. Manual wound outlines delineated by an expert are also included in the dataset. All images of each case are additionally coregistered, and both numerical registration parameters and the transformed images are covered in the database. The presented database is publicly available for the research community at https://chronicwounddatabase.eu. That is the first publicly available database for evaluation and comparison of new image-based algorithms in the wound healing monitoring process with coregistered photographs, thermal maps, and 3D models of the wound area. Easily available database of coregistered multimodal data with the raw data set allows faster development of algorithms devoted to wound healing analysis and monitoring.

Supporting diagnostics and therapy planning for percutaneous ablation of liver and abdominal tumors and pre-clinical evaluation.

Percutaneous ablation methods are used to treat primary and metastatic liver tumors. Image guided navigation support minimally invasive interventions of rigid anatomical structures. When working with the displacement and deformation of soft tissues during surgery, as in the abdomen, imaging navigation systems are in the preliminary implementation stage. In this study a multi-stage approach has been developed to support percutaneous liver tumors ablation. It includes CT image acquisition protocol with the amplitude of respiratory motion that yields images subjected to a semi-automatic method able to deliver personalized abdominal model. Then, US probe and ablation needle calibration, as well as patient position adjustment method during the procedure for the preoperative anatomy model, have been combined. Finally, an advanced module for fusion of the preoperative CT with intraoperative US images was designed. These modules have been tested on a phantom and in the clinical environment. The final average Spatial calibration error was 1,7 mm, the average error of matching the position of the markers was about 2 mm during the entire breathing cycle, and average markers fusion error 495 mm. The obtained results indicate the possibility of using the developed method of navigation in clinical practice.

Electroconvulsive therapy in 77-year-old patient with pacemaker: a case report.

The treatment of a 77-year-old patient suffering from severe psychotic depression with a cardiac pacemaker is described. Because of treatment-resistant depression, electroconvulsive therapy (ECT) was introduced. In the course of ECT, there was a great improvement in his mental state without any cardiac complications. This case may be evidence for the safety and effectiveness of ECT in the elderly, even with cardiac comorbidities. Some recommendations for ECT in patients with pacemakers are discussed.

Biopsy needle tracking technique in US images.

Fast development of imaging techniques in last decades has offered the intra-operative visualization as the integral part of surgical tools. Therefore, on-going research activities still focus on efficient and robust analysis of ultrasound images. The paper meets these requirements targeting in detection of biopsy needle, estimation of the needle trajectory and tracking the needle tip motion inside the examined tissue. The developed novel method uses ultrasound data supported by elastography images. The investigated detection algorithm introduces Histogram of Oriented Gradients and image entropy, whereas the tracking part employs Hough transform, Gabor filter and Kanade-Lucas-Tomasi optical flow estimation technique. The developed methodology is verified by the stereoscopic navigation system. The verification phase proves the accuracy of 3-5mm and encourages the further improvement of the methods.

Time-Of-Flight Camera, Optical Tracker and Computed Tomography in Pairwise Data Registration.

PURPOSE: A growing number of medical applications, including minimal invasive surgery, depends on multi-modal or multi-sensors data processing. Fast and accurate 3D scene analysis, comprising data registration, seems to be crucial for the development of computer aided diagnosis and therapy. The advancement of surface tracking system based on optical trackers already plays an important role in surgical procedures planning. However, new modalities, like the time-of-flight (ToF) sensors, widely explored in non-medical fields are powerful and have the potential to become a part of computer aided surgery set-up. Connection of different acquisition systems promises to provide a valuable support for operating room procedures. Therefore, the detailed analysis of the accuracy of such multi-sensors positioning systems is needed. METHODS: We present the system combining pre-operative CT series with intra-operative ToF-sensor and optical tracker point clouds. The methodology contains: optical sensor set-up and the ToF-camera calibration procedures, data pre-processing algorithms, and registration technique. The data pre-processing yields a surface, in case of CT, and point clouds for ToF-sensor and marker-driven optical tracker representation of an object of interest. An applied registration technique is based on Iterative Closest Point algorithm. RESULTS: The experiments validate the registration of each pair of modalities/sensors involving phantoms of four various human organs in terms of Hausdorff distance and mean absolute distance metrics. The best surface alignment was obtained for CT and optical tracker combination, whereas the worst for experiments involving ToF-camera. CONCLUSION: The obtained accuracies encourage to further develop the multi-sensors systems. The presented substantive discussion concerning the system limitations and possible improvements mainly related to the depth information produced by the ToF-sensor is useful for computer aided surgery developers.

Granular computing in model based abdominal organs detection.

Detection of region specific voxel is a true challenge in many segmentation procedures. In this study a concept of implementing granular computing in the detection of anatomical structures in abdominal computed tomography (CT) scans is introduced. After proving the usefulness of the information granules to identify voxels that mark certain organs, an automatic model-based approach has been developed. A three-parameter granule that combines the interval and density distribution of voxels has been introduced and employed to identify organ specific voxels of the liver, spleen and kidneys. The specificity of the information granules varies between 90 and 99% for the liver and spleen and over 85% for the kidneys.

Patient Specific Phantom in bimodal image navigation system.

The paper presents the multistep methodology of bimodal Patient Specific Phantom (PSP) development. First, CT based abdominal digital model is designed. It serves as a source for designing organ moulds manufactured by means of a 3D-printer. The collagen based colloid fills the moulds yielding the organ casts. The PSP permits a bimodal navigation system to be developed that employs a realistic CT-based digital model and US imaging. Highly accurate results were achieved with mean Dice similarity coefficient value of 0.92 and Hausdorff distance 9.67 mm.