Because of the inherent complex anatomy and functional arrangement of the cranial nerves (CNs), neuroimaging of cranial neuropathy is challenging. With recent advances in magnetic resonance imaging (MRI) techniques, the cause of cranial neuropathy can now be detected in many cases. As an active multidisciplinary team member of cranial neuropathy, it is essential for the neuroradiologist to be familiar with the detailed anatomy of the CNs on MRI. This review contains the basic MRI anatomy of CNs III–XII according to a segmental classification from the brain stem to the extracranial region. The optimal imaging options to best evaluate the specific segment of the CNs will also be discussed briefly.

Ehlers-Danlos syndrome type IV (EDS IV) is a hereditary disorder of the connective tissue, characterized by easy bruising, thin skin with visible veins, and spontaneous rupture of the large arteries, uterus, or bowel. EDS IV is caused by mutations of the gene for type III procollagen (COL3A1), resulting in insufficient collagen production or a defect in the structure of collagen. EDS IV can have fatal complications such as the rupture of great vessels or organs, which can cause hemorrhaging and sudden unexpected death. Here, we report a case of a 43-year-old female who collapsed after a struggle with a neighbor. In this patient, the bifurcation of the bilateral common iliac artery ruptured, with no evidence of trauma, inflammation, or atherosclerosis. Genetic analysis of COL3A1 showed the presence of a c.2771G>A (p.Gly924Arg) mutation, which may be associated with EDS IV. The forensic pathologist should consider the possibility that the spontaneous visceral or arterial rupture was caused by EDS IV. Genetic analysis is not currently a routine procedure during autopsy. However, in this case, we suggest that the patient possibly had an underlying EDS IV condition, and we recommended family members of the deceased to seek genetic analysis and counseling.
Adult ; Aortic Rupture* ; Arteries ; Atherosclerosis ; Autopsy ; Collagen ; Collagen Type III ; Connective Tissue ; Counseling ; Ehlers-Danlos Syndrome* ; Female ; Humans ; Iliac Artery ; Inflammation ; Rupture ; Rupture, Spontaneous ; Skin ; Uterus ; Veins

Candida is a commensal organism that is frequently found in the human gastrointestinal tract. It is the most common organism that causes pancreatic fungal infections. However, magnetic resonance imaging findings of Candida infection in the pancreas have not been described. We report imaging findings of pancreatic candidiasis in a patient in immunocompetent condition. It presented as a multi-septated cystic mass with a peripheral solid component in the background of pancreatitis and restricted diffusion on diffusion-weighted image that mimicked a malignant pancreatic cystic tumor.
Candida/pathogenicity ; Candidiasis/*diagnosis/microbiology/radiography ; Diagnosis, Differential ; Humans ; Immunocompromised Host ; Magnetic Resonance Imaging/methods ; Male ; Middle Aged ; Pancreatic Neoplasms/*diagnosis/radiography ; Pancreatitis/*diagnosis/microbiology/radiography

Purpose: This study aimed to evaluate the quality of artificial intelligence (AI)/machine learning (ML) studies on hemorrhagic stroke using the Minimum Information for Medical AI Reporting (MINIMAR) and Minimum Information About Clinical Artificial Intelligence Modeling (MI-CLAIM) frameworks to promote clinical application. Materials and Methods: PubMed, MEDLINE, and Embase were searched for AI/ML studies on hemorrhagic stroke. Out of the 531 articles found, 29 relevant original research articles were included. MINIMAR and MI-CLAIM scores were assigned by two experienced radiologists to assess the quality of the studies. Results: We analyzed 29 investigations that utilized AI/ML in the field of hemorrhagic stroke, involving a median of 224.5 patients. The majority of studies focused on diagnostic outcomes using computed tomography scans (89.7%) and were published in computer science journals (48.3%). The overall adherence rates to reporting guidelines, as assessed through the MINIMAR and MI-CLAIM frameworks, were 47.6% and 46.0%, respectively. In MINIMAR, none of the studies reported the socioeconomic status of the patients or how missing values had been addressed. In MI-CLAIM, only two studies applied model-examination techniques to improve model interpretability. Transparency and reproducibility were limited, as only 10.3% of the studies had publicly shared their code. Cohen’s kappa between the two radiologists was 0.811 and 0.779 for MINIMAR and MI-CLAIM, respectively. Conclusion The overall reporting quality of published AI/ML studies on hemorrhagic stroke is suboptimal. It is necessary to incorporate model examination techniques for interpretability and promote code openness to enhance transparency and increase the clinical applicability of AI/ML studies.

Purpose: This study aimed to evaluate the quality of artificial intelligence (AI)/machine learning (ML) studies on hemorrhagic stroke using the Minimum Information for Medical AI Reporting (MINIMAR) and Minimum Information About Clinical Artificial Intelligence Modeling (MI-CLAIM) frameworks to promote clinical application. Materials and Methods: PubMed, MEDLINE, and Embase were searched for AI/ML studies on hemorrhagic stroke. Out of the 531 articles found, 29 relevant original research articles were included. MINIMAR and MI-CLAIM scores were assigned by two experienced radiologists to assess the quality of the studies. Results: We analyzed 29 investigations that utilized AI/ML in the field of hemorrhagic stroke, involving a median of 224.5 patients. The majority of studies focused on diagnostic outcomes using computed tomography scans (89.7%) and were published in computer science journals (48.3%). The overall adherence rates to reporting guidelines, as assessed through the MINIMAR and MI-CLAIM frameworks, were 47.6% and 46.0%, respectively. In MINIMAR, none of the studies reported the socioeconomic status of the patients or how missing values had been addressed. In MI-CLAIM, only two studies applied model-examination techniques to improve model interpretability. Transparency and reproducibility were limited, as only 10.3% of the studies had publicly shared their code. Cohen’s kappa between the two radiologists was 0.811 and 0.779 for MINIMAR and MI-CLAIM, respectively. Conclusion The overall reporting quality of published AI/ML studies on hemorrhagic stroke is suboptimal. It is necessary to incorporate model examination techniques for interpretability and promote code openness to enhance transparency and increase the clinical applicability of AI/ML studies.

Purpose: This study aimed to evaluate the quality of artificial intelligence (AI)/machine learning (ML) studies on hemorrhagic stroke using the Minimum Information for Medical AI Reporting (MINIMAR) and Minimum Information About Clinical Artificial Intelligence Modeling (MI-CLAIM) frameworks to promote clinical application. Materials and Methods: PubMed, MEDLINE, and Embase were searched for AI/ML studies on hemorrhagic stroke. Out of the 531 articles found, 29 relevant original research articles were included. MINIMAR and MI-CLAIM scores were assigned by two experienced radiologists to assess the quality of the studies. Results: We analyzed 29 investigations that utilized AI/ML in the field of hemorrhagic stroke, involving a median of 224.5 patients. The majority of studies focused on diagnostic outcomes using computed tomography scans (89.7%) and were published in computer science journals (48.3%). The overall adherence rates to reporting guidelines, as assessed through the MINIMAR and MI-CLAIM frameworks, were 47.6% and 46.0%, respectively. In MINIMAR, none of the studies reported the socioeconomic status of the patients or how missing values had been addressed. In MI-CLAIM, only two studies applied model-examination techniques to improve model interpretability. Transparency and reproducibility were limited, as only 10.3% of the studies had publicly shared their code. Cohen’s kappa between the two radiologists was 0.811 and 0.779 for MINIMAR and MI-CLAIM, respectively. Conclusion The overall reporting quality of published AI/ML studies on hemorrhagic stroke is suboptimal. It is necessary to incorporate model examination techniques for interpretability and promote code openness to enhance transparency and increase the clinical applicability of AI/ML studies.

Purpose: This study aimed to evaluate the quality of artificial intelligence (AI)/machine learning (ML) studies on hemorrhagic stroke using the Minimum Information for Medical AI Reporting (MINIMAR) and Minimum Information About Clinical Artificial Intelligence Modeling (MI-CLAIM) frameworks to promote clinical application. Materials and Methods: PubMed, MEDLINE, and Embase were searched for AI/ML studies on hemorrhagic stroke. Out of the 531 articles found, 29 relevant original research articles were included. MINIMAR and MI-CLAIM scores were assigned by two experienced radiologists to assess the quality of the studies. Results: We analyzed 29 investigations that utilized AI/ML in the field of hemorrhagic stroke, involving a median of 224.5 patients. The majority of studies focused on diagnostic outcomes using computed tomography scans (89.7%) and were published in computer science journals (48.3%). The overall adherence rates to reporting guidelines, as assessed through the MINIMAR and MI-CLAIM frameworks, were 47.6% and 46.0%, respectively. In MINIMAR, none of the studies reported the socioeconomic status of the patients or how missing values had been addressed. In MI-CLAIM, only two studies applied model-examination techniques to improve model interpretability. Transparency and reproducibility were limited, as only 10.3% of the studies had publicly shared their code. Cohen’s kappa between the two radiologists was 0.811 and 0.779 for MINIMAR and MI-CLAIM, respectively. Conclusion The overall reporting quality of published AI/ML studies on hemorrhagic stroke is suboptimal. It is necessary to incorporate model examination techniques for interpretability and promote code openness to enhance transparency and increase the clinical applicability of AI/ML studies.

Primary mucinous cystadenocarcinoma (MCA) of the breast is a rare but pathologically distinct breast tumor. There have been some case reports on primary MCA of the breast; however, they have all focused on pathologic findings. Here, we report the radiologic findings of two cases of MCA along with a review of the literature. Breast MCA shows a circumscribed mass with some calcifications on mammography, an intracystic solid mass without increased vascularity or a vascular stalk on ultrasound, and a heterogeneously enhancing mass within a rim-enhancing cyst with intermediate signal intensity on T2-weighted magnetic resonance imaging. These radiologic findings and the presence of mucin in the percutaneous biopsy specimen should suggest the possibility of MCA in the differential diagnosis of a breast tumor.
Biopsy ; Breast Neoplasms ; Breast* ; Cystadenocarcinoma, Mucinous* ; Diagnosis, Differential ; Magnetic Resonance Imaging ; Mammography ; Mucins* ; Ultrasonography

Sturge Weber syndrome (SWS) is a rare, congenital neurocutaneous syndrome. We rarely experienced neurocutaneous disorders in forensic practice but there are unexpected sudden deaths of patients with SWS due to epilepsy, intracranial hemorrhage, thromboses and secondary accident. We introduce a case of drowning death probably due to an epileptic attack of a person diagnosed as a patient of SWS by an autopsy. We review some of the neurocutaneous syndromes and a discussion of autopsy approach is presented.
Autopsy ; Death, Sudden ; Drowning ; Epilepsy ; Humans ; Intracranial Hemorrhages ; Neurocutaneous Syndromes ; Sturge-Weber Syndrome ; Thrombosis

Portal vein thrombosis (PVT) is a form of venous thrombosis that usually presents in chronic form without any sequalae in patients with hepatocellular carcinoma (HCC) or liver cirrhosis. Accurate differential diagnosis of bland PVT from neoplastic PVT is an important step for planning treatment options, but the acute form can be challenging. Here we present a case of acute hepatic infarction caused by acute bland PVT combined with pylephlebitis, which was misdiagnosed as infiltrative hepatic malignancy with neoplastic PVT owing to the perplexing imaging results and elevated tumor markers.
Biomarkers, Tumor ; Carcinoma, Hepatocellular ; Diagnosis, Differential ; Hepatitis B, Chronic ; Humans ; Infarction* ; Liver Cirrhosis ; Portal Vein* ; Tenofovir ; Thrombophlebitis* ; Thrombosis* ; Venous Thrombosis