Ono, Daisuke

AbstractINTRODUCTIONParkinsonism in patients with Alzheimer's disease (AD) is often attributed to Lewy‐related pathology, given its high comorbidity. In the era of anti‐amyloid therapy, recognizing parkinsonism caused by AD pathology is needed to optimize the treatment.METHODSThis study aimed to quantitatively characterize parkinsonism and nigral neuropathology in AD without Lewy bodies (LB). Nigral neurons were counted automatically. Fine‐tuned ChatGPT collected structured clinical data.RESULTSAmong 635 AD patients without LB, 62 (9.7%) presented parkinsonism, which correlated with reduced nigral neuron density (p < 0.01). Tau burden did not explain the nigral neuronal loss. TAR DNA‐binding protein 43 (TDP‐43) pathology correlated with reduced nigral pigmented neuron density (p = 0.03).DISCUSSIONOur findings suggest that parkinsonism in AD without LB is related to nigral neuronal loss in association with TDP‐43 pathology. Recognition of parkinsonism in AD without LB is crucial for appropriate therapy.Highlights One in 10 Alzheimer's disease (AD) patients without Lewy bodies had parkinsonism. Parkinsonism in AD was correlated with reduced nigral neuron density. TAR DNA‐binding protein 43 pathology was associated with nigral degeneration in AD. AD should be included in the differential diagnosis of dementia with parkinsonism.

AbstractBackgroundParkinson’s disease and dementia with Lewy bodies are characterized by abnormal iron deposition in the substantia nigra, which can be measured with quantitative susceptibility mapping (QSM) on MRI. However, neuropathologic validation of the increased QSM in the substantia nigra associated with Lewy body disease (LBD) is lacking. We compared substantia nigra QSM on antemortem MRI between patients with and without Lewy‐related pathology which was confirmed by autopsy in all cases.MethodWe studied cases with antemortem QSM who underwent autopsy from the Mayo Clinic Alzheimer’s Disease Research Center and Mayo Clinic Study of Aging (n=54). Immunohistochemistry was performed with rabbit NACP antibody against the amino acids 98‐115 of the α‐synuclein protein to detect Lewy‐related pathology. After neuropathologic evaluation, cases were classified as LBD‐present (n=13) if they had Lewy‐related pathology and LBD‐absent (n=42) if they did not have Lewy‐related pathology. Alzheimer’s disease co‐pathology was present in 9 of the LBD‐present cohort (70%). QSM was calculated for the whole substantia nigra and the two sub‐regions: pars compacta and pars reticulata. Non‐parametric Wilcoxon rank‐sum test was used to compare substantia nigra QSM values between LBD‐present and LBD‐absent cases. Area under the curve (AUC) analyses tested the accuracy of QSM to distinguish the two groups.ResultsLBD‐present group had higher QSM values in the substantia nigra than LBD‐absent group. Furthermore, sub‐regional analyses showed that the LBD‐present group had higher QSM in the substantia nigra pars compacta (p=0.008) but not in the pars reticulata than the LBD‐absent group (Figure 1). QSM of the substantia nigra pars compacta distinguished LBD‐present and LBD‐absent cases with good accuracy (AUC=0.74; p=0.006; Figure 2).ConclusionThis study provides neuropathologic insight into the relevance of QSM of substantia nigra pars compacta as an in‐vivo biomarker of autopsy‐confirmed LBD. These findings indicate that imaging evidence of abnormal iron deposition in the substantia nigra may serve as a biomarker of Lewy‐related pathology in patients with primary LBD (i.e., Parkinson disease, dementia with Lewy bodies) and patients with potential LBD co‐pathology (e.g., patients with Alzheimer disease).

Abstract Introduction/Objective Recent advancements in artificial intelligence (AI), particularly with Large Language Models like ChatGPT-4Vision (GPT-4V), have expanded the potential for automated interpretation of medical images. This study evaluates the diagnostic accuracy of GPT-4V in histopathological analysis of neurodegenerative diseases and compares its performance with traditional Convolutional Neural Networks (CNNs). Methods/Case Report We utilized 1515 histopathological images, including hematoxylin and eosin (H&E) staining and tau immunohistochemistry, from patients with various neurodegenerative diseases, such as Alzheimer’s disease, progressive supranuclear palsy, and corticobasal degeneration. GPT-4V’s performance was assessed through multi- step prompts to assess how textual context influences the image interpretation. In the quantitative analysis, the diagnostic accuracy of GPT-4V and the CNN-based model YOLOv8 was assessed for classifying three tau lesions—astrocytic plaques, neuritic plaques, and tufted astrocytes. The analysis used both zero-shot and few-shot learning methods, where GPT-4V and YOLOv8 were evaluated on their ability to distinguish these lesions using ten hold-out test images and 490 training images per lesion. Results (if a Case Study enter NA) GPT-4V accurately recognized Lewy bodies in all cases, but it showed limited accuracy in identifying neurofibrillary tangles (20%) and Pick bodies (0%) on H&E slides. Notably, GPT-4V often suggested Alzheimer’s disease as a potential diagnosis, relying more on contextual clues, such as the prevalence of certain diseases, rather than direct image analysis. In the tau immunohistochemical analysis, GPT-4V’s diagnoses were strongly influenced by additional information about staining and brain region. However, few-shot learning markedly improved GPT-4V’s diagnostic capabilities from 40% accuracy with zero-shot learning to 90% with few-shot learning, reaching best accuracy with 20-shot learning. This performance compared favorably against YOLOv8, which also achieved 90% accuracy but required 100-shot learning. Conclusion While GPT-4V faces challenges in independently interpreting histopathological images, few-shot learning significantly improves its accuracy. This approach is particularly promising for neuropathology, where acquiring extensive labeled datasets is challenging. The findings highlight the need for ongoing refinement of AI applications in pathology, emphasizing balanced integration of textual and visual data to optimize diagnostic efficacy and reliability.

AbstractAimsRecent advances in artificial intelligence, particularly with large language models like GPT‐4Vision (GPT‐4V)—a derivative feature of ChatGPT—have expanded the potential for medical image interpretation. This study evaluates the accuracy of GPT‐4V in image classification tasks of histopathological images and compares its performance with a traditional convolutional neural network (CNN).MethodsWe utilised 1520 images, including haematoxylin and eosin staining and tau immunohistochemistry, from patients with various neurodegenerative diseases, such as Alzheimer's disease (AD), progressive supranuclear palsy (PSP) and corticobasal degeneration (CBD). We assessed GPT‐4V's performance using multi‐step prompts to determine how textual context influences image interpretation. We also employed few‐shot learning to enhance improvements in GPT‐4V's diagnostic performance in classifying three specific tau lesions—astrocytic plaques, neuritic plaques and tufted astrocytes—and compared the outcomes with the CNN model YOLOv8.ResultsGPT‐4V accurately recognised staining techniques and tissue origin but struggled with specific lesion identification. The interpretation of images was notably influenced by the provided textual context, which sometimes led to diagnostic inaccuracies. For instance, when presented with images of the motor cortex, the diagnosis shifted inappropriately from AD to CBD or PSP. However, few‐shot learning markedly improved GPT‐4V's diagnostic capabilities, enhancing accuracy from 40% in zero‐shot learning to 90% with 20‐shot learning, matching the performance of YOLOv8, which required 100‐shot learning to achieve the same accuracy.ConclusionsAlthough GPT‐4V faces challenges in independently interpreting histopathological images, few‐shot learning significantly improves its performance. This approach is especially promising for neuropathology, where acquiring extensive labelled datasets is often challenging.

Abstract Introduction: Recent advancements in artificial intelligence, particularly with large language models like GPT-4Vision (GPT-4V)—a derivative feature of ChatGPT—have expanded the potential for medical image interpretation. This study evaluates the accuracy of GPT-4V in image classification tasks of histopathological images and compares its performance with traditional convolutional neural network (CNN). Methods: We utilized 1515 images, including hematoxylin and eosin staining and tau immunohistochemistry, from patients with various neurodegenerative diseases, such as Alzheimer’s disease (AD), progressive supranuclear palsy (PSP), and corticobasal degeneration (CBD). We assessed GPT-4V’s performance using multi-step prompts to determine how textual context influences image interpretation. We also employed few-shot learning to enhance improvements in GPT-4V’s diagnostic accuracy in classifying three specific tau lesions—astrocytic plaques, neuritic plaques, and tufted astrocytes—and compared the outcomes with the CNN model YOLOv8. Results: GPT-4V accurately recognized staining techniques and tissue origin but struggled with specific lesion identification. The interpretation of images was notably influenced by the provided textual context, which sometimes led to diagnostic inaccuracies. For instance, when presented with images of the motor cortex, the diagnosis shifted inappropriately from AD to CBD or PSP. However, few-shot learning markedly improved GPT-4V’s diagnostic capabilities, enhancing accuracy from 40% in zero-shot learning to 90% with 20-shot learning, matching the performance of YOLOv8, which required 100-shot learning to achieve the same accuracy. Conclusions: Although GPT-4V faces challenges in independently interpreting histopathological images, few-shot learning significantly improves its accuracy. This approach is especially promising for neuropathology, where acquiring extensive labeled datasets is often challenging.

Abstract Aim The morphometry of sural nerve biopsies, such as fibre diameter and myelin thickness, helps us understand the underlying mechanism of peripheral neuropathies. However, in current clinical practice, only a portion of the specimen is measured manually because of its labour‐intensive nature. In this study, we aimed to develop a machine learning‐based application that inputs a whole slide image (WSI) of the biopsied sural nerve and automatically performs morphometric analyses. Methods Our application consists of three supervised learning models: (1) nerve fascicle instance segmentation, (2) myelinated fibre detection and (3) myelin sheath segmentation. We fine‐tuned these models using 86 toluidine blue‐stained slides from various neuropathies and developed an open‐source Python library. Results Performance evaluation showed (1) a mask average precision (AP) of 0.861 for fascicle segmentation, (2) box AP of 0.711 for fibre detection and (3) a mean intersection over union (mIoU) of 0.817 for myelin segmentation. Our software identified 323,298 nerve fibres and 782 fascicles in 70 WSIs. Small and large fibre populations were objectively determined based on clustering analysis. The demyelination group had large fibres with thinner myelin sheaths and higher g‐ratios than the vasculitis group. The slope of the regression line from the scatter plots of the diameters and g‐ratios was higher in the demyelination group than in the vasculitis group. Conclusion We developed an application that performs whole slide morphometry of human biopsy samples. Our open‐source software can be used by clinicians and pathologists without specific machine learning skills, which we expect will facilitate data‐driven analysis of sural nerve biopsies for a more detailed understanding of these diseases.