ABSTRACT
Introduction In recent years, artificial intelligence (AI) in medical imaging has undergone unprecedented innovation and advancement, sparking a revolutionary transformation in healthcare. The field of radiology is particularly implicated, as clinical radiologists are expected to interpret an ever-increasing number of complex cases in record time. Machine learning software purchased by our institution is expected to help our radiologists come to a more prompt diagnosis by delivering point-of-care quantitative analysis of suspicious findings and streamlining clinical workflow. This paper explores AI's impact on neuroradiology, an area accounting for a substantial portion of recent radiology studies. We present a case series evaluating an AI software's performance in detecting neurovascular findings, highlighting five cases where AI interpretations differed from radiologists' assessments. Our study underscores common pitfalls of AI in the context of CT head angiograms, aiming to guide future AI algorithms. Methods We conducted a retrospective case series study at Stony Brook University Hospital, a large medical center in Stony Brook, New York, spanning from October 1, 2021 to December 31, 2021, analyzing 140 randomly sampled CT angiograms using AI software. This software assessed various neurovascular parameters, and AI findings were compared with neuroradiologists' interpretations. Five cases with divergent interpretations were selected for detailed analysis. Results Five representative cases in which AI findings were discordant with radiologists' interpretations are presented with diagnoses including diffuse anoxic ischemic injury, cortical laminar necrosis, colloid cyst, right superficial temporal artery-to-middle cerebral artery (STA-MCA) bypass, and subacute bilateral subdural hematomas. Discussion The errors identified in our case series expose AI's limitations in radiology. Our case series reveals that AI's incorrect interpretations can stem from complexities in pathology, challenges in distinguishing densities, inability to identify artifacts, identifying post-surgical changes in normal anatomy, sensitivity limitations, and insufficient pattern recognition. AI's potential for improvement lies in refining its algorithms to effectively recognize and differentiate pathologies. Incorporating more diverse training datasets, multimodal data, deep-reinforcement learning, clinical context, and real-time learning capabilities are some ways to improve AI's performance in the field of radiology. Conclusion Overall, it is apparent that AI applications in radiology have much room for improvement before becoming more widely integrated into clinical workflows. While AI demonstrates remarkable potential to aid in diagnosis and streamline workflows, our case series highlights common pitfalls that underscore the need for continuous improvement. By refining algorithms, incorporating diverse datasets, embracing multimodal information, and leveraging innovative machine learning strategies, AI's diagnostic accuracy can be significantly improved.
ABSTRACT
Merkel cell carcinoma (MCC) is a rare neuroendocrine dermal malignancy seen in elderly light-skinned individuals, associated with immunosuppression and Merkel cell polyomavirus infection. As a neuroendocrine tumor, the recurrence and metastasis of MCC can be evaluated using positron emission tomography-computed tomography (PET-CT) with the Gallium-68-DOTATATE (Ga-68-DOTATATE) radiotracer, which has demonstrated increased sensitivity to neuroendocrine metastases when compared to F-18 fluorodeoxyglucose (FDG). Here, we present the case of a patient with known metastatic MCC with a new, abnormal focus of increased radiotracer activity in the thoracic spine on Ga-68-DOTATATE PET-CT suspected to represent a metastatic lesion. Further evaluation with MRI revealed a benign vertebral hemangioma, highlighting the limitations of this radiotracer in the setting of benign spinal lesions. Multimodality imaging findings of metastatic MCC and potential pitfalls of Ga-68-DOTATATE PET-CT staging are discussed.
ABSTRACT
BACKGROUND: Reports of cerebrovascular ischemia and stroke occurring as predominant neurological sequelae of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, which causes coronavirus disease 2019 (COVID-19), are increasingly evident within the literature. While various pathophysiological mechanisms have been postulated, including hypercoagulability, endothelial invasion, and systemic inflammation, discrete mechanisms for viral neurotropism remain unclear and controversial. OBSERVATIONS: The authors present a unique case study of a 64-year-old male with acute COVID-19 infection and acute worsening of previously stable cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL), a rare heritable arteriopathy due to mutation in the Notch3 gene, which is critical for vascular development and tone. Delayed cranial neuropathies, brainstem fluid-attenuated inversion recovery signal, and enhancement of olfactory and vagus nerves on magnetic resonance neurography in this patient further support viral neurotropism via cranial nerves in addition to cerebral vasculature. LESSONS: To the authors' knowledge, this is the first case in the literature that not only demonstrates the consequences of COVID-19 infection in a patient with altered cerebrovascular autoregulation such as CADASIL but also highlights the tropism of SARS-CoV-2 for (1) cranial nerves as a mode of entry to the central nervous system and (2) vessels as a cause of cerebrovascular ischemia.
