Current state and promise of user-centered design to harness explainable AI in clinical decision-support systems for patients with CNS tumors.

In neuro-oncology, MR imaging is crucial for obtaining detailed brain images to identify neoplasms, plan treatment, guide surgical intervention, and monitor the tumor's response. Recent AI advances in neuroimaging have promising applications in neuro-oncology, including guiding clinical decisions and improving patient management. However, the lack of clarity on how AI arrives at predictions has hindered its clinical translation.

Differentiating Benign from Malignant Causes of Splenomegaly: Is Acoustic Radiation Force Impulse Elastography Helpful?

Purpose: To evaluate the ability of acoustic radiation force impulse (ARFI) elastography in differentiating benign from malignant etiologies of splenomegaly based on differences in splenic stiffness.

Materials And Methods: Between September 2020 and November 2022, we evaluated 40 patients with splenomegaly-defined by a splenic long axis greater than 13 cm and/or a short axis greater than 6 cm, without visible focal or infiltrative mass lesions-using abdominal ultrasound at our university hospital. Each patient also underwent a standardized ARFI elastographic assessment of the enlarged spleen, with data collected prospectively.

SHAPE: A visual computing pipeline for interactive landmarking of 3D photograms and patient reporting for assessing craniosynostosis.

3D photogrammetry is a cost-effective, non-invasive imaging modality that does not require the use of ionizing radiation or sedation. Therefore, it is specifically valuable in pediatrics and is used to support the diagnosis and longitudinal study of craniofacial developmental pathologies such as craniosynostosis - the premature fusion of one or more cranial sutures resulting in local cranial growth restrictions and cranial malformations. Analysis of 3D photogrammetry requires the identification of craniofacial landmarks to segment the head surface and compute metrics to quantify anomalies.

A Visual Analytics Framework for Assessing Interactive AI for Clinical Decision Support.

Human involvement remains critical in most instances of clinical decision-making. Recent advances in AI and machine learning opened the door for designing, implementing, and translating interactive AI systems to support clinicians in decision-making. Assessing the impact and implications of such systems on patient care and clinical workflows requires in-depth studies.

Comments and Illustrations of the European Federation of Societies for Ultrasound in Medicine (EFSUMB) Guidelines: Rare Malignant Pulmonal and Pleural Tumors: Primary Pulmonary Sarcoma and Mesothelioma, Imaging Features on Transthoracic Ultrasound.

Primary pulmonary sarcoma and mesothelioma are rare malignancies. The review article discusses the appearance of these tumors in B-mode ultrasound (US), color Doppler ultrasound and contrast-enhanced ultrasound (CEUS). In particular, the article is intended to inspire the examination of thoracic wall tumors and pleural masses with the possibilities of ultrasonography and to obtain histologically evaluable material using US or CEUS-guided sampling.

Perfusion Patterns of Peripheral Pulmonary Metastasis Using Contrast-Enhanced Ultrasound (CEUS) and Their Correlation with Immunohistochemically Detected Vascularization Pattern.

Purpose: Description of the perfusion of pulmonary metastasis by contrast-enhanced ultrasound (CEUS) and their correlation with vascularization patterns represented by immunohistochemical CD34 endothelial staining.

Patients And Methods: The data of 54 patients with histologic proven peripheral pulmonary metastasis, investigated between 2004 and 2023 by CEUS. These CEUS parameters were evaluated: time to enhancement (TE), categorized as early pulmonary-arterial (PA) or delayed bronchial-arterial (BA) patterns; extent of enhancement (EE), either marked or reduced; homogeneity of enhancement (HE), homogeneous or inhomogeneous; and decrease of enhancement (DE), rapid washout (<120 s) or late washout (≥120 s).

Comments and illustrations of the WFUMB CEUS liver guidelines: rare benign hematological focal liver lesions (hepatic extramedullary hematopoiesis, Hemophagocytic lymphohistiocytosis, reactive lymphoid hyperplasia).

The manifestation of benign hematological infiltration in the liver is a challenge due to their rare occurrence and therefore, limited awareness and the general need for biopsy and histological confirmation. Owing to the rarity of these lesions, there are limited data concerning their appearance on ultrasound and, specifically, contrast-enhanced ultrasound. In a series of papers, we have compiled the US and CEUS characteristics of rare FLL, where there are few reports and images available, in order to build up a library of these cases.

The Iterative Design Process of an Explainable AI Application for Non-Invasive Diagnosis of CNS Tumors: A User-Centered Approach.

Artificial Intelligence (AI) is well-suited to help support complex decision-making tasks within clinical medicine, including clinical imaging applications like radiographic differential diagnosis of central nervous system (CNS) tumors. So far, there have been numerous examples of theoretical AI solutions for this space, for example, large-scale corporate efforts like IBM's Watson AI. However, clinical implementation remains limited due to factors related to the alignment of this technology in the clinical setting.

EASL: A Framework for Designing, Implementing, and Evaluating ML Solutions in Clinical Healthcare Settings.

We introduce the Explainable Analytical Systems Lab (EASL) framework, an end-to-end solution designed to facilitate the development, implementation, and evaluation of clinical machine learning (ML) tools. EASL is highly versatile and applicable to a variety of contexts and includes resources for data management, ML model development, visualization and user interface development, service hosting, and usage analytics. To demonstrate its practical applications, we present the EASL framework in the context of a case study: designing and evaluating a deep learning classifier to predict diagnoses from medical imaging.

The value of contrast-enhanced ultrasound in differentiating benign from malignant retroperitoneal masses.

Objectives: To evaluate the value of contrast-enhanced ultrasound (CEUS) perfusion patterns in the differentiation of benign and malignant retroperitoneal masses (RMs).

Methods: Between 2006 and 2023, 122 consecutive patients with an RM visualizable by B-mode US were investigated additionally with CEUS. On CEUS, the extent of enhancement (classified as marked, reduced, or absent) and the homogeneity of enhancement (HE; classified as homogeneous or inhomogeneous) were evaluated.

The Value of Contrast-Enhanced Ultrasound (CEUS) in the Evaluation of Central Lung Cancer with Obstructive Atelectasis.

: To assess the diagnostic performance of contrast-enhanced ultrasound (CEUS) alongside contrast-enhanced computed tomography (CECT) in evaluating central lung cancer (CLC). : From 2006 to 2022, 54 patients with CLC and obstructive atelectasis (OAT) underwent standardized examinations using CEUS in addition to CECT. The ability to differentiate CLC from atelectatic tissue in CECT and CEUS was categorized as distinguishable or indistinguishable.

Model-agnostic explanations for survival prediction models.

Advanced machine learning methods capable of capturing complex and nonlinear relationships can be used in biomedical research to accurately predict time-to-event outcomes. However, these methods have been criticized as "black boxes" that are not interpretable and thus are difficult to trust in making important clinical decisions. Explainable machine learning proposes the use of model-agnostic explainers that can be applied to predictions from any complex model.

Prevention of life-threatening bleeding complication from splenic venous ectasia by B-mode-, color Doppler- and contrast-enhanced ultrasound in a patient with ALL.

Aim Of The Study: Spontaneous splenic rupture is a serious complication of pathologically altered spleen tissue, associated with a high mortality rate.

Case Description: We describe a spontaneous splenic rupture in a patient with acute lymphoblastic leukemia undergoing chemotherapy. Ultrasound revealed splenomegaly, and diffuse splenic acute lymphoblastic leukemia-infiltration was suspected.

Lung Ultrasound and Pleural Artifacts: A Pictorial Review.

Lung ultrasound is a well-established diagnostic approach used in detecting pathological changes near the pleura of the lung. At the acoustic boundary of the lung surface, it is necessary to differentiate between the primary visualization of pleural parenchymal pathologies and the appearance of secondary artifacts when sound waves enter the lung or are reflected at the visceral pleura. The aims of this pictorial essay are to demonstrate the sonographic patterns of various pleural interface artifacts and to illustrate the limitations and pitfalls of the use of ultrasound findings in diagnosing any underlying pathology.

Comments on and illustrations of the WFUMB CEUS liver guidelines: Rare malignant neuroendocrine and predominant epithelioid liver lesions.

The diagnosis or rare, non-hematologic malignant lesions of the liver may be a challenge owing to the rarity of the disease, and is usually made by histological confirmation. Ultrasound with color Doppler and contrast-enhanced, if required, taking into account the clinical background of the patient, may help to focus the differential diagnosis. In this review, we describe the pathological and ultrasound features of rare malignant neuroendocrine and predominantly epithelioid liver lesions including primary neuroendocrine tumor of the liver, Invasive mucinous cystic neoplasm of the liver, and also hepatoblastoma.

Sonography of the pleura.

The CME review presented here is intended to explain the significance of pleural sonography to the interested reader and to provide information on its application. At the beginning of sonography in the 80 s of the 20th centuries, with the possible resolution of the devices at that time, the pleura could only be perceived as a white line. Due to the high impedance differences, the pleura can be delineated particularly well.

Comments on and illustrations of the WFUMB CEUS liver guidelines: Rare malignant mesenchymal liver lesions.

The diagnosis or rare mesenchymal malignant lesions of the liver may be a challenge owing to the rarity of the disease and is usually made by histological confirmation. An ultrasound examination with, if required, color Doppler sonography and contrast-enhanced ultrasound, taking into account the clinical background of the patient, may help to focus the differential diagnosis. In this review, we describe the pathological and ultrasound features of several rare mesenchymal malignant liver lesions which include undifferentiated sarcoma of the liver, leiomyosarcoma, angiosarcoma, fibrosarcoma, liposarcoma, and epithelioid hemangioendothelioma.

Comments and illustrations of the WFUMB CEUS liver guidelines: Rare malignant hematological liver lesions.

Diagnosing rare hematological malignancies in the liver is often challenging owing to their infrequency, and confirmation generally necessitates histological examination. Due to the rarity of these lesions, there are limited data concerning their appearance on ultrasound and, specifically, contrast-enhanced ultrasound. In this review, we describe the pathological and ultrasound features of several hematological malignant liver lesions, including lymphoma of the liver and chloroma.

[Multimodal ultrasound techniques for the differential diagnosis of splenic lesions - A diagnostic challenge].

Background: Splenic tumors are rare and can pose a differential diagnostic challenge, especially as an incidental imaging finding. Due to a lack of large scale biopsy studies the available literature is limited with respect to clear imaging criteria for dignity.

Objective: The present work is intended to show the chances of a targeted elicitation of the medical history as well as the possibilities and limitations of multimodal sonography in order to achieve the correct diagnosis of a splenic lesion using simple and gentle methods.

Prospective Assessment of Treatment-Induced Liver Injury as a Cause of Diffuse Pathologic Hepatic Enhancement in Contrast-Enhanced Ultrasound.

Objective: A hypo-enhancement of the liver in contrast-enhanced ultrasound (CEUS), pathologic one-minute hepatic enhancement (pOMHE), was recently observed in 70% of allogeneic hematopoietic stem cell transplantation patients with a high-risk profile for veno-occlusive disease (VOD). Whether pOMHE was a pre-clinical sign of VOD or an unspecific feature of liver damage secondary to intensive chemotherapy is unclear.

Methods: To investigate this, we studied CEUS patterns in patients receiving high-dose chemotherapy prior to autologous hematopoietic stem cell transplantation (auto-HSCT) or intensive induction therapy (IT) for the treatment of acute leukemia.