Synergizing photon-counting CT with deep learning: potential enhancements in medical imaging.

This review article highlights the potential of integrating photon-counting computed tomography (CT) and deep learning algorithms in medical imaging to enhance diagnostic accuracy, improve image quality, and reduce radiation exposure. The use of photon-counting CT provides superior image quality, reduced radiation dose, and material decomposition capabilities, while deep learning algorithms excel in automating image analysis and improving diagnostic accuracy. The integration of these technologies can lead to enhanced material decomposition and classification, spectral image analysis, predictive modeling for individualized medicine, workflow optimization, and radiation dose management. However, data requirements, computational resources, and regulatory and ethical concerns remain challenges that need to be addressed to fully realize the potential of this technology. The fusion of photon-counting CT and deep learning algorithms is poised to revolutionize medical imaging and transform patient care.

"Ring-shaped" meniscus and accompanying intermeniscal bridge meniscus: a rare combined variant resembling a bucket-handle tear.

Many anatomical variations have been described in the menisci, especially in the lateral meniscus. Among these, discoid meniscus is the most common variation. Others are described in the literature as double-layered meniscus, accessory meniscus, ring-shaped meniscus, and hypoplastic meniscus. Also, combined variations associated with ring-shaped meniscus have been described, and they can be confused with fragmented complex tears and cause unnecessary surgery. Increasing awareness of the imaging features of these accompanying combined variations may aid in the recognition and differentiation of this entity from meniscus tears. We report the case of a ring-shaped meniscus and accompanying intermeniscal bridge meniscus, which has not been described before in the literature, highlighting the MRI and arthroscopic imaging findings of it.

MRI radiomics based machine learning model of the periaqueductal gray matter in migraine patients.

Background and purpose:

The aim of the study was to investigate the question: Can MRI radiomics analysis of the periaqueductal gray region elucidate the pathophysiological mechanisms underlying various migraine subtypes, and can a machine learning model using these radiomics features accurately differentiate between migraine patients and healthy individuals, as well as between migraine subtypes, including atypical cases with overlapping symptoms?

The study analyzed initial MRI images of individuals taken after their first migraine diagnosis, and additional MRI scans were acquired from healthy subjects. Radiomics modeling was applied to analyze all the MRI images in the periaqueductal gray region. The dataset was randomized, and oversampling was used if there was class imbalance between groups. The optimal algorithm-based feature selection method was employed to select the most important 5-10 features to differentiate between the two groups. The classification performance of AI algorithms was evaluated using receiver operating characteristic analysis to calculate the area under the curve, classification accuracy, sensitivity, and specificity values. Participants were required to have a confirmed diagnosis of either episodic migraine, probable migraine, or chronic migraine. Patients with aura, those who used migraine-preventive medication within the past six months, or had chronic illnesses, psychiatric disorders, cerebrovascular conditions, neoplastic diseases, or other headache types were excluded from the study. Additionally, 102 healthy subjects who met the inclusion and exclusion criteria were included. 

The algorithm-based information gain method for feature reduction had the best performance among all methods, with the first-order, gray-level size zone matrix, and gray-level co-occurrence matrix classes being the dominant feature classes. The machine learning model correctly classified 82.4% of migraine patients from healthy subjects. Within the migraine group, 74.1% of the episodic migraine-probable migraine patients and 90.5% of the chronic migraine patients were accurately classified. No significant difference was found between probable migraine and episodic migraine patients in terms of the periaqueductal gray region radiomics features. The kNN algorithm showed the best performance for classifying episodic migraine-probable migraine subtypes, while the Random Forest algorithm demonstrated the best performance for classifying the migraine group and chronic migraine subtype.

A radiomics-based machine learning model, utilizing standard MR images obtained during the diagnosis and follow-up of migraine patients, shows promise not only in aiding migraine diagnosis and classification for clinical approach, but also in understanding the neurological mechanisms underlying migraines. 

A mimicker of inflammatory breast carcinoma: Lupus mastitis and evolving imaging features.

Rare case of lupus mastitis in a 58-year-old female with discoid lupus erythematosus presented with fever, left breast swelling, and painful palpable lesion. Accurate imaging and histopathologic evaluation allowed for appropriate management and regression of breast findings with hydroxychloroquine treatment, emphasizing the need to avoid unnecessary biopsies and surgeries.

Educating the next generation of radiologists: a comparative report of ChatGPT and e-learning resources

Rapid technological advances have transformed medical education, particularly in radiology, which depends on advanced imaging and visual data. Traditional electronic learning (e-learning) platforms have long served as a cornerstone in radiology education, offering rich visual content, interactive sessions, and peer-reviewed materials. They excel in teaching intricate concepts and techniques that necessitate visual aids, such as image interpretation and procedural demonstrations. However, Chat Generative Pre-Trained Transformer (ChatGPT), an artificial intelligence (AI)-powered language model, has made its mark in radiology education. It can generate learning assessments, create lesson plans, act as a round-the-clock virtual tutor, enhance critical thinking, translate materials for broader accessibility, summarize vast amounts of information, and provide real-time feedback for any subject, including radiology. Concerns have arisen regarding ChatGPT's data accuracy, currency, and potential biases, especially in specialized fields such as radiology. However, the quality, accessibility, and currency of e-learning content can also be imperfect. To enhance the educational journey for radiology residents, the integration of ChatGPT with expert-curated e-learning resources is imperative for ensuring accuracy and reliability and addressing ethical concerns. While AI is unlikely to entirely supplant traditional radiology study methods, the synergistic combination of AI with traditional e-learning can create a holistic educational experience.

A Case of Subdural Hematoma without Subarachnoid Hemorrhage Secondary to Rupture of Posterior Communicating Artery-infundibular Dilatation.

INTRODUCTION: Subdural hematoma without subarachnoid hemorrhage secondary to intracranial aneurysm rupture is rare and may complicate patient management due to delay in diagnosis and subsequent treatment. Herein, we describe a case presenting with pure SDH secondary to the rupture of a posterior communicating artery infundibular dilatation (PcoA-ID). To the best of our knowledge, this is the first case of rupture of a PcoA-ID with SDH in the convexity and tentorium, which also tracked into the upper cervical spine along the subdural space. Additionally, we briefly discuss the previously published cases of pure SDH secondary to intracranial aneurysm rupture. CASE REPORT: A 44-year-old female presented with headache, dizziness, nausea and left-sided diplopia to an outside institution. Initial diagnostic work-up showed no intracranial hemorrhage, however, magnetic resonance angiography and subsequent digital subtraction angiography revealed left posterior communicating artery infundibular dilatation. Two days later, the patient presented with a loss of consciousness. Computed tomography was positive for bilateral hemispheric subdural hematoma with no evidence of subarachnoid hemorrhage. Digital subtraction angiography showed left posterior communicating artery infundibular dilatation and pseudoaneurysm originating from the inferior area of the infundibular dilatation, concerning recent rupture. Balloon assisted coil embolization was performed and the patient had a good outcome without any neurological deficit. CONCLUSION: Subdural hematoma in a young adult without a history of trauma or coagulopathy warrants additional vascular imaging to search for underlying vascular lesions. It should also be kept in mind that infundibular dilatation may rupture and cause a pure subdural hematoma.

18 F-FDG PET-Positive Large Pelvic Granuloma Mimicking Malignant Bladder Tumor.

ABSTRACT: An 88-year-old man was admitted to our hospital with a recurrent lower urinary tract infection. He had a history of open prostatectomy for benign prostatic hyperplasia 15 years ago and smoking. A mass arising within a bladder diverticula was suspected on the left lateral wall of the bladder on ultrasonography. Although no mass was observed in the bladder lumen on the cystoscopy, abdominal CT detected a left-sided pelvic soft tissue mass. A hypermetabolic mass was detected on 18 F-FDG PET/CT performed because of suspicion of malignancy, and it was excised. Granuloma secondary to chronic vasitis was diagnosed histopathologically.

Benign multicystic peritoneal mesothelioma mimicking mucinous ovarian neoplasm with pseudomyxoma peritonei.

Cystic mesothelioma, also known as benign multicystic peritoneal mesothelioma (BMPM), is a rare neoplasm and one of the five main histological types of peritoneal mesothelioma. Although it is usually considered benign histologically, it is increasingly accepted as a 'borderline malignancy' because the local recurrence rate is high. It is more common in middle-aged women and is generally asymptomatic. Considering that BMPM is often found in the pelvis, it is difficult to differentiate from other pelvic and abdominal lesions, such as cystic ovarian masses, especially mucinous cystadenoma-adenocarcinoma, pseudomyxoma peritonei, etc. Preoperative diagnosis is very difficult due to its rarity and lack of specific diagnostic imaging and clinical findings. Definitive diagnosis is made only by pathological evaluation. In this article, we aimed to present the imaging findings of a BMPM case in a woman who was diagnosed with mucinous ovarian neoplasm with pseudomyxoma peritonei preoperatively and underwent cytoreductive surgery with hyperthermic intraperitoneal chemotherapy.

Differentiation of pure cystic sellar lesions on magnetic resonance imaging.

BACKGROUND AND PURPOSE: Cystic pituitary adenomas and cystic craniopharyngiomas may mimic Rathke cleft cysts when there is no solid enhancing component on magnetic resonance imaging (MRI). This study aims to investigate the efficiency of MRI findings in differentiating Rathke cleft cysts from pure cystic pituitary adenoma and pure cystic craniopharyngioma. MATERIALS AND METHODS: 109 patients were included in this study (56 Rathke cleft cysts, 38 pituitary adenomas, and 15 craniopharyngiomas). Preoperative magnetic resonance images were evaluated using 9 imaging findings. These findings include intralesional fluid-fluid level, intralesional septations, midline /off-midline location, suprasellar extension, an intracystic nodule, a hypointense rim on T2-weighted images, ≥ 2 mm thickness of contrast-enhancing wall, T1 hyperintensity and T2 hypointensity. p < 0.01 was considered statistically significant. RESULTS: There was a statistically significant difference among groups for these 9 findings. Intracystic nodule and T2 hypointensity were the most specific MRI findings in differentiating Rathke cleft cyst from the others (98.1% and 100%, respectively). Intralesional septation and thick contrast-enhancing wall were the most sensitive MRI findings ruling out Rathke cleft cysts with 100% sensitivity. CONCLUSION: Rathke cleft cysts can be distinguished from pure cystic adenoma and craniopharyngioma with the presence of an intracystic nodule, T2 hypointensity, the absence of the thick contrast-enhancing wall, and absence of intralesional septations.

Progressive MRI findings of West Nile virus encephalitis in a patient with diabetes mellitus.

A man in his 70s was admitted to our hospital with complaints of fatigue, loss of appetite and fever. His neurological examination was normal. He had a medical history of diabetes mellitus for 25 years. Urine analysis showed many leucocytes. Empirical antibiotic treatment was started for urinary system infection. Three days later, his mental status worsened with confusion and disorientation. MRI of the brain was normal. Two days later, the patient was intubated because of respiratory insufficiency. MRI showed restricted diffusion in bilateral thalamic nuclei. Encephalitis and ischaemia were considered in the differential diagnosis. Cerebrospinal fluid IgM antibody for West Nile virus was positive. Sixteen days later, cranial nerve reflexes were lost. MRI showed restricted diffusion and increased T2 signal intensity in the dorsal medulla and increased T2 signal intensity without diffusion restriction in bilateral substantia nigra and dentate nuclei. He died of cardiac arrest 40 days after hospitalisation.