BACKGROUND: The calcaneus is the most commonly fractured tarsal bone. Diagnosis is often challenging due to subtle radiographic changes and requires timely identification to prevent complications, including subtalar arthritis, neurovascular injury, malunion, osteomyelitis, and compartment syndrome. Treatment varies based on fracture type, with non-surgical methods for non-displaced stress fractures and surgical interventions for displaced or intra-articular fractures.
METHODS: This study utilized the Wisdom in Diagnostic Imaging Simulation (WIDI SIM) platform, an emergency imaging simulation designed to assess radiology resident preparedness for independent call. During an 8-hour simulation, residents were tested on 65 cases across various imaging modalities of varying complexity, including normal studies. A single, unique case of calcaneal fracture was included within the simulation in four separate years of testing. Cases were assessed using a standardized grading rubric by subspecialty radiology faculty, with errors subsequently classified by type.
RESULTS: A total of 1279 residents were tested in five separate years on the findings of calcaneal fractures of 5 different patients. Analysis revealed a consistent pattern of missed diagnoses across all training years, primarily attributed to observational errors. There was limited improvement with training progression as all training years exhibited similar average performance levels.
CONCLUSIONS: Calcaneal fractures pose a diagnostic challenge due to their frequent subtle radiographic findings, especially in stress fractures. Simulation-based evaluations using WIDI SIM highlighted challenges in radiology residents\' proficiency in diagnosing calcaneal fractures. Addressing these challenges through targeted education and exposure to diverse cases is essential to improve diagnostic accuracy and reduce complications with calcaneal fractures.

Patient-derived xenografts (PDXs) are increasingly utilized in preclinical drug efficacy studies due to their ability to retain the molecular, histological, and drug response characteristics of patient tumors. This study aimed to investigate the factors influencing the successful engraftment of PDXs. Lung adenocarcinoma PDXs were established using freshly resected tumor tissues obtained through surgery. Radiological data of pulmonary nodules from this PDX cohort were analyzed, categorizing them into solid tumors and tumors with ground-glass opacity (GGO) based on preoperative CT images. Gene mutation status was obtained from next generation sequencing data and MassARRAY panel. A total of 254 resected primary lung adenocarcinomas were utilized for PDX establishment, with successful initial engraftment in 58 cases (22.8 %); stable engraftment defined as at least three serial passages was observed in 43 cases (16.9 %). The stable engraftment rates of PDXs from solid tumors and tumors with GGO were 22.1 % (42 of 190 cases) and 1.6 % (1 of 64 cases), respectively (P < 0.001). Adenocarcinomas with advanced stage, poor differentiation, solid histologic subtype, and KRAS or TP53 gene mutations were associated with stable PDX engraftment. Avoiding tumors with GGO features could enhance the cost-effectiveness of establishing PDX models from early-stage resected lung adenocarcinomas.

BACKGROUND: Radiology reports are typically written in a free-text format, making clinical information difficult to extract and use. Recently, the adoption of structured reporting (SR) has been recommended by various medical societies thanks to the advantages it offers, e.g. standardization, completeness, and information retrieval. We propose a pipeline to extract information from Italian free-text radiology reports that fits with the items of the reference SR registry proposed by a national society of interventional and medical radiology, focusing on CT staging of patients with lymphoma.
METHODS: Our work aims to leverage the potential of Natural Language Processing and Transformer-based models to deal with automatic SR registry filling. With the availability of 174 Italian radiology reports, we investigate a rule-free generative Question Answering approach based on the Italian-specific version of T5: IT5. To address information content discrepancies, we focus on the six most frequently filled items in the annotations made on the reports: three categorical (multichoice), one free-text (free-text), and two continuous numerical (factual). In the preprocessing phase, we encode also information that is not supposed to be entered. Two strategies (batch-truncation and ex-post combination) are implemented to comply with the IT5 context length limitations. Performance is evaluated in terms of strict accuracy, f1, and format accuracy, and compared with the widely used GPT-3.5 Large Language Model. Unlike multichoice and factual, free-text answers do not have 1-to-1 correspondence with their reference annotations. For this reason, we collect human-expert feedback on the similarity between medical annotations and generated free-text answers, using a 5-point Likert scale questionnaire (evaluating the criteria of correctness and completeness).
RESULTS: The combination of fine-tuning and batch splitting allows IT5 ex-post combination to achieve notable results in terms of information extraction of different types of structured data, performing on par with GPT-3.5. Human-based assessment scores of free-text answers show a high correlation with the AI performance metrics f1 (Spearman\'s correlation coefficients>0.5, p-values<0.001) for both IT5 ex-post combination and GPT-3.5. The latter is better at generating plausible human-like statements, even if it systematically provides answers even when they are not supposed to be given.
CONCLUSIONS: In our experimental setting, a fine-tuned Transformer-based model with a modest number of parameters (i.e., IT5, 220 M) performs well as a clinical information extraction system for automatic SR registry filling task. It can extract information from more than one place in the report, elaborating it in a manner that complies with the response specifications provided by the SR registry (for multichoice and factual items), or that closely approximates the work of a human-expert (free-text items); with the ability to discern when an answer is supposed to be given or not to a user query.

OBJECTIVE: Spread of disease in the retroperitoneum is dictated by the complex anatomy of retroperitoneal fasciae and is still incompletely understood. Conflicting reports have led to insufficient and incorrect anatomical concepts in radiological literature.
METHODS: This review will discuss previous concepts prevalent in radiological literature and their shortcomings will be highlighted. New insights from recent anatomical and embryological research, together with imaging examples, will be used to clarify patterns of disease spread in the retroperitoneum that remain unexplained by these concepts.
RESULTS: The fusion fascia and the renal fascia in particular give rise to planes and spaces that act as vectors for spread of disease in the retroperitoneum. Some of these planes and structures, such as the caudal extension of the renal fascia, have previously not been described in radiological literature.
CONCLUSIONS: New insights, including the various fasciae, potential spaces and planes, are incorporated into an updated combined retroperitoneal fascial concept.

UNASSIGNED: Despite being generally treatable and preventative, pulmonary tuberculosis (PTB) is one of the most common infectious agents that cause death. Misdiagnosis of TB frequently leads to unwarranted diagnostic procedures and postpones the start of treatment.
UNASSIGNED: Pulmonary tuberculosis (PTB) can present with various unusual radiological and clinical characteristics. Misdiagnosis of TB frequently leads to unwarranted diagnostic procedures and postpones the start of treatment. Here, we describe a 50-year-old man who presented with a cancerous-type lesion on radiological findings and atypical symptoms that led to an initial diagnosis of lung cancer. However, histopathology and biopsy of the lung lesion revealed chronic granulomatous inflammation with caseous necrosis, confirming PTB as the true cause, with no further indications of malignancy.

Fibrosis is a pathological process involving the abnormal deposition of connective tissue, resulting from improper tissue repair in response to sustained injury caused by hypoxia, infection, or physical damage. It can impact any organ, leading to their dysfunction and eventual failure. Additionally, tissue fibrosis plays an important role in carcinogenesis and the progression of cancer.Early and accurate diagnosis of organ fibrosis, coupled with regular surveillance, is essential for timely disease-modifying interventions, ultimately reducing mortality and enhancing quality of life. While extensive research has already been carried out on the topics of aberrant wound healing and fibrogenesis, we lack a thorough understanding of how their relationship reveals itself through modern imaging techniques.This paper focuses on fibrosis of the genito-urinary system, detailing relevant imaging technologies used for its detection and exploring future directions.

A man in his 60s presented with diminution of vision of the left eye with nasal bleeding after accidental fall. On examination his left upper eyelid was lacerated and left temporal sclera was punctured which was repaired under local anaesthesia after which he was discharged by ophthalmologists but continued to complain of pain and left nasal obstruction. A non-contrast CT of paranasal sinuses revealed fracture of medial wall of left orbit, left ethmoid haemosinus and a metallic foreign body (FB) in the septum and anterior face of sphenoid. Diagnostic nasal endoscopy performed to remove the metallic FB showed plastic splinters embedded in the mucosa of nasal cavity which was unexpected. Hence, the FB was removed in two sittings because of diagnostic dilemma.

During the early growth phase, every individual is involved in a prolonged series of developmental processes in the maxillofacial region. Formation of cysts associated with such three-dimensional growth of the maxillofacial skeleton as well as deciduous and permanent tooth development. The origin of cystic jaw lesions may be odontogenic or non-odontogenic, developmental, or inflammatory and they are epithelial-lined or non-epithelial-lined cysts in nature. These cysts are considered to be aggressive cysts when they tend to grow rapidly and can cause significant damage to the surrounding bone and tissues if left untreated. Aggressive cystic lesion of the jaw needs special attention in order to prevent recurrences or even worsen and widespread disease. The management of the maxillary sinus requires individualisation based on its clinical and histopathological characteristics. Here, we report a case of an aggressive odontogenic cyst in a 30s-aged female patient in the left maxillary sinus with the literature review.

Sigmoid sinus diverticulum is a rare vascular anomaly often associated with pulsatile tinnitus. It can occur in cases of chronic otitis media squamous type (unsafe type) due to dehiscence of the sigmoid sinus plate caused by cholesteatoma. The presentation of which is that of pulsatile tinnitus. However, we present an unusual case of sigmoid sinus diverticulum occurring concurrently with chronic otitis media mucosal type (safe type) but in the absence of pulsatile tinnitus. This case report highlights the diagnostic challenges and management of this rare clinical scenario.

OBJECTIVE: To assess impact of image quality on prostate cancer extraprostatic extension (EPE) detection on MRI using a deep learning-based AI algorithm.
METHODS: This retrospective, single institution study included patients who were imaged with mpMRI and subsequently underwent radical prostatectomy from June 2007 to August 2022. One genitourinary radiologist prospectively evaluated each patient using the NCI EPE grading system. Each T2WI was classified as low- or high-quality by a previously developed AI algorithm. Fisher\'s exact tests were performed to compare EPE detection metrics between low- and high-quality images. Univariable and multivariable analyses were conducted to assess the predictive value of image quality for pathological EPE.
RESULTS: A total of 773 consecutive patients (median age 61 [IQR 56-67] years) were evaluated. At radical prostatectomy, 23% (180/773) of patients had EPE at pathology, and 41% (131/318) of positive EPE calls on mpMRI were confirmed to have EPE. The AI algorithm classified 36% (280/773) of T2WIs as low-quality and 64% (493/773) as high-quality. For EPE grade ≥ 1, high-quality T2WI significantly improved specificity for EPE detection (72% [95% CI 67-76%] vs. 63% [95% CI 56-69%], P = 0.03), but did not significantly affect sensitivity (72% [95% CI 62-80%] vs. 75% [95% CI 63-85%]), positive predictive value (44% [95% CI 39-49%] vs. 38% [95% CI 32-43%]), or negative predictive value (89% [95% CI 86-92%] vs. 89% [95% CI 85-93%]). Sensitivity, specificity, PPV, and NPV for EPE grades ≥ 2 and ≥ 3 did not show significant differences attributable to imaging quality. For NCI EPE grade 1, high-quality images (OR 3.05, 95% CI 1.54-5.86; P < 0.001) demonstrated a stronger association with pathologic EPE than low-quality images (OR 1.76, 95% CI 0.63-4.24; P = 0.24).
CONCLUSIONS: Our study successfully employed a deep learning-based AI algorithm to classify image quality of prostate MRI and demonstrated that better quality T2WI was associated with more accurate prediction of EPE at final pathology.