Data Science for Health Image Alignment: A User-Friendly Open-Source ImageJ/Fiji Plugin for Aligning Multimodality/Immunohistochemistry/Immunofluorescence 2D Microscopy Images.

Most of the time, the deep analysis of a biological sample requires the acquisition of images at different time points, using different modalities and/or different stainings. This information gives morphological, functional, and physiological insights, but the acquired images must be aligned to be able to proceed with the co-localisation analysis. Practically speaking, according to Aristotle's principle, "The whole is greater than the sum of its parts", multi-modal image registration is a challenging task that involves fusing complementary signals. In the past few years, several methods for image registration have been described in the literature, but unfortunately, there is not one method that works for all applications. In addition, there is currently no user-friendly solution for aligning images that does not require any computer skills. In this work, DS4H Image Alignment (DS4H-IA), an open-source ImageJ/Fiji plugin for aligning multimodality, immunohistochemistry (IHC), and/or immunofluorescence (IF) 2D microscopy images, designed with the goal of being extremely easy to use, is described. All of the available solutions for aligning 2D microscopy images have also been revised. The DS4H-IA source code; standalone applications for MAC, Linux, and Windows; video tutorials; manual documentation; and sample datasets are publicly available.

Characterization and comparison of gene-centered human interactomes.

The complex web of macromolecular interactions occurring within cells-the interactome-is the backbone of an increasing number of studies, but a clear consensus on the exact structure of this network is still lacking. Different genome-scale maps of human interactome have been obtained through several experimental techniques and functional analyses. Moreover, these maps can be enriched through literature-mining approaches, and different combinations of various 'source' databases have been used in the literature. It is therefore unclear to which extent the various interactomes yield similar results when used in the context of interactome-based approaches in network biology. We compared a comprehensive list of human interactomes on the basis of topology, protein complexes, molecular pathways, pathway cross-talk and disease gene prediction. In a general context of relevant heterogeneity, our study provides a series of qualitative and quantitative parameters that describe the state of the art of human interactomes and guidelines for selecting interactomes in future applications.

Circumventing the curse of dimensionality in magnetic resonance fingerprinting through a deep learning approach.

Magnetic resonance fingerprinting (MRF) is a rapidly developing approach for fast quantitative MRI. A typical drawback of dictionary-based MRF is an explosion of the dictionary size as a function of the number of reconstructed parameters, according to the "curse of dimensionality", which determines an explosion of resource requirements. Neural networks (NNs) have been proposed as a feasible alternative, but this approach is still in its infancy. In this work, we design a deep learning approach to MRF using a fully connected network (FCN). In the first part we investigate, by means of simulations, how the NN performance scales with the number of parameters to be retrieved in comparison with the standard dictionary approach. Four MRF sequences were considered: IR-FISP, bSSFP, IR-FISP-B1 , and IR-bSSFP-B1 , the latter two designed to be more specific for B1+ parameter encoding. Estimation accuracy, memory usage, and computational time required to perform the estimation task were considered to compare the scalability capabilities of the dictionary-based and the NN approaches. In the second part we study optimal training procedures by including different data augmentation and preprocessing strategies during training to achieve better accuracy and robustness to noise and undersampling artifacts. The study is conducted using the IR-FISP MRF sequence exploiting both simulations and in vivo acquisitions. Results demonstrate that the NN approach outperforms the dictionary-based approach in terms of scalability capabilities. Results also allow us to heuristically determine the optimal training strategy to make an FCN able to predict T1 , T2 , and M0 maps that are in good agreement with those obtained with the original dictionary approach. k-SVD denoising is proposed and found to be critical as a preprocessing step to handle undersampled data.

Identification of a Maturation Plasma Cell Index through a Highly Sensitive Droplet Digital PCR Assay Gene Expression Signature Validation in Newly Diagnosed Multiple Myeloma Patients.

DNA microarrays and RNA-based sequencing approaches are considered important discovery tools in clinical medicine. However, cross-platform reproducibility studies undertaken so far have highlighted that microarrays are not able to accurately measure gene expression, particularly when they are expressed at low levels. Here, we consider the employment of a digital PCR assay (ddPCR) to validate a gene signature previously identified by gene expression profile. This signature included ten Hedgehog (HH) pathways' genes able to stratify multiple myeloma (MM) patients according to their self-renewal status. Results show that the designed assay is able to validate gene expression data, both in a retrospective as well as in a prospective cohort. In addition, the plasma cells' differentiation status determined by ddPCR was further confirmed by other techniques, such as flow cytometry, allowing the identification of patients with immature plasma cells' phenotype (i.e., expressing CD19+/CD81+ markers) upregulating HH genes, as compared to others, whose plasma cells lose the expression of these markers and were more differentiated. To our knowledge, this is the first technical report of gene expression data validation by ddPCR instead of classical qPCR. This approach permitted the identification of a Maturation Index through the integration of molecular and phenotypic data, able to possibly define upfront the differentiation status of MM patients that would be clinically relevant in the future.

Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization.

Purpose: In this work, we propose an implementation of the Bienenstock-Cooper-Munro (BCM) model, obtained by a combination of the classical framework and modern deep learning methodologies. The BCM model remains one of the most promising approaches to modeling the synaptic plasticity of neurons, but its application has remained mainly confined to neuroscience simulations and few applications in data science. Methods: To improve the convergence efficiency of the BCM model, we combine the original plasticity rule with the optimization tools of modern deep learning. By numerical simulation on standard benchmark datasets, we prove the efficiency of the BCM model in learning, memorization capacity, and feature extraction. Results: In all the numerical simulations, the visualization of neuronal synaptic weights confirms the memorization of human-interpretable subsets of patterns. We numerically prove that the selectivity obtained by BCM neurons is indicative of an internal feature extraction procedure, useful for patterns clustering and classification. The introduction of competitiveness between neurons in the same BCM network allows the network to modulate the memorization capacity of the model and the consequent model selectivity. Conclusions: The proposed improvements make the BCM model a suitable alternative to standard machine learning techniques for both feature selection and classification tasks.

Impact of concurrency on the performance of a whole exome sequencing pipeline.

BACKGROUND: Current high-throughput technologies-i.e. whole genome sequencing, RNA-Seq, ChIP-Seq, etc.-generate huge amounts of data and their usage gets more widespread with each passing year. Complex analysis pipelines involving several computationally-intensive steps have to be applied on an increasing number of samples. Workflow management systems allow parallelization and a more efficient usage of computational power. Nevertheless, this mostly happens by assigning the available cores to a single or few samples' pipeline at a time. We refer to this approach as naive parallel strategy (NPS). Here, we discuss an alternative approach, which we refer to as concurrent execution strategy (CES), which equally distributes the available processors across every sample's pipeline. RESULTS: Theoretically, we show that the CES results, under loose conditions, in a substantial speedup, with an ideal gain range spanning from 1 to the number of samples. Also, we observe that the CES yields even faster executions since parallelly computable tasks scale sub-linearly. Practically, we tested both strategies on a whole exome sequencing pipeline applied to three publicly available matched tumour-normal sample pairs of gastrointestinal stromal tumour. The CES achieved speedups in latency up to 2-2.4 compared to the NPS. CONCLUSIONS: Our results hint that if resources distribution is further tailored to fit specific situations, an even greater gain in performance of multiple samples pipelines execution could be achieved. For this to be feasible, a benchmarking of the tools included in the pipeline would be necessary. It is our opinion these benchmarks should be consistently performed by the tools' developers. Finally, these results suggest that concurrent strategies might also lead to energy and cost savings by making feasible the usage of low power machine clusters.

Mechanisms Involved in the Promoting Activity of Fibroblasts in HTLV-1-Mediated Lymphomagenesis: Insights into the Plasticity of Lymphomatous Cells.

Among the mechanisms leading to progression to Adult T-cell Leukaemia/Lymphoma in Human T-cell Leukaemia Virus type 1 (HTLV-1)-infected subjects, the contribution of stromal components remains poorly understood. To dissect the role of fibroblasts in HTLV-1-mediated lymphomagenesis, transcriptome studies, cytofluorimetric and qRT-PCR analyses of surface and intracellular markers linked to plasticity and stemness in coculture, and in vivo experiments were performed. A transcriptomic comparison between a more lymphomagenic (C91/III) and the parental (C91/PL) cell line evidenced hyperactivation of the PI3K/Akt pathway, confirmed by phospho-ELISA and 2-DE and WB analyses. C91/III cells also showed higher expression of mesenchymal and stemness genes. Short-term coculture with human foreskin fibroblasts (HFF) induced these features in C91/PL cells, and significantly increased not only the cancer stem cells (CSCs)-supporting CD10+GPR77+ HFF subpopulation, but also the percentage of ALDH1bright C91/PL cells. A non-cytotoxic acetylsalicylic acid treatment decreased HFF-induced ALDH1bright C91/PL cells, downregulated mesenchymal and stemness genes in cocultured cells, and delayed lymphoma growth in immunosuppressed mice, thus hindering the supportive activity of HFF on CSCs. These data suggest that crosstalk with HFF significantly intensifies the aggressiveness and plasticity of C91/PL cells, leading to the enrichment in lymphoma-initiating cells. Additional research is needed to better characterize these preliminary findings.

Linking aberrant chromatin features in chronic lymphocytic leukemia to transcription factor networks.

In chronic lymphocytic leukemia (CLL), a diverse set of genetic mutations is embedded in a deregulated epigenetic landscape that drives cancerogenesis. To elucidate the role of aberrant chromatin features, we mapped DNA methylation, seven histone modifications, nucleosome positions, chromatin accessibility, binding of EBF1 and CTCF, as well as the transcriptome of B cells from CLL patients and healthy donors. A globally increased histone deacetylase activity was detected and half of the genome comprised transcriptionally downregulated partially DNA methylated domains demarcated by CTCF CLL samples displayed a H3K4me3 redistribution and nucleosome gain at promoters as well as changes of enhancer activity and enhancer linkage to target genes. A DNA binding motif analysis identified transcription factors that gained or lost binding in CLL at sites with aberrant chromatin features. These findings were integrated into a gene regulatory enhancer containing network enriched for B-cell receptor signaling pathway components. Our study predicts novel molecular links to targets of CLL therapies and provides a valuable resource for further studies on the epigenetic contribution to the disease.

Aneuploid acute myeloid leukemia exhibits a signature of genomic alterations in the cell cycle and protein degradation machinery.

BACKGROUND: Aneuploidy occurs in more than 20% of acute myeloid leukemia (AML) cases and correlates with an adverse prognosis. METHODS: To understand the molecular bases of aneuploid acute myeloid leukemia (A-AML), this study examined the genomic profile in 42 A-AML cases and 35 euploid acute myeloid leukemia (E-AML) cases. RESULTS: A-AML was characterized by increased genomic complexity based on exonic variants (an average of 26 somatic mutations per sample vs 15 for E-AML). The integration of exome, copy number, and gene expression data revealed alterations in genes involved in DNA repair (eg, SLX4IP, RINT1, HINT1, and ATR) and the cell cycle (eg, MCM2, MCM4, MCM5, MCM7, MCM8, MCM10, UBE2C, USP37, CK2, CK3, CK4, BUB1B, NUSAP1, and E2F) in A-AML, which was associated with a 3-gene signature defined by PLK1 and CDC20 upregulation and RAD50 downregulation and with structural or functional silencing of the p53 transcriptional program. Moreover, A-AML was enriched for alterations in the protein ubiquitination and degradation pathway (eg, increased levels of UHRF1 and UBE2C and decreased UBA3 expression), response to reactive oxygen species, energy metabolism, and biosynthetic processes, which may help in facing the unbalanced protein load. E-AML was associated with BCOR/BCORL1 mutations and HOX gene overexpression. CONCLUSIONS: These findings indicate that aneuploidy-related and leukemia-specific alterations cooperate to tolerate an abnormal chromosome number in AML, and they point to the mitotic and protein degradation machineries as potential therapeutic targets.

Quantifying the contribution of four resistance mechanisms to ciprofloxacin MIC in Escherichia coli: a systematic review.

Background: Reviews assessing the genetic basis of ciprofloxacin resistance in Escherichia coli have mostly been qualitative. However, to predict resistance phenotypes based on genotypic characteristics, it is essential to quantify the contribution of genotypic determinants to resistance. Objectives: We performed a systematic review to assess the relative contribution of known genomic resistance determinants to the MIC of ciprofloxacin in E. coli. Methods: PubMed and Web of Science were searched for English language studies that assessed ciprofloxacin MIC and presence or introduction of genetic determinants of ciprofloxacin resistance in E. coli. We included experimental and observational studies without time restrictions. Medians and ranges of MIC fold changes were calculated for individual resistance determinants and combinations thereof. Results: We included 66 studies, describing 604 E. coli isolates that carried at least one genetic ciprofloxacin resistance determinant. Mutations in gyrA and parC, genes encoding targets of ciprofloxacin, contribute to the largest fold changes in ciprofloxacin resistance in E. coli compared with the WT. Efflux and physical blocking or enzymatic modifications confer smaller increases in ciprofloxacin MIC than mutations in gyrA and parC. However, the presence of these other resistance mechanisms in addition to target alteration mutations further increases ciprofloxacin MIC, thus resulting in ciprofloxacin MIC increases ranging from 250- to 4000-fold. Conclusions: This quantitative review of genomic determinants of ciprofloxacin resistance in E. coli demonstrates the complexity of resistance phenotype prediction from genomic data and serves as a reference point for studies aiming to predict ciprofloxacin MIC from E. coli genomes.

RUNX2 expression in thyroid and breast cancer requires the cooperation of three non-redundant enhancers under the control of BRD4 and c-JUN.

Aberrant reactivation of embryonic pathways is a common feature of cancer. RUNX2 is a transcription factor crucial during embryogenesis that is aberrantly reactivated in many tumors, including thyroid and breast cancer, where it promotes aggressiveness and metastatic spreading. Currently, the mechanisms driving RUNX2 expression in cancer are still largely unknown. Here we showed that RUNX2 transcription in thyroid and breast cancer requires the cooperation of three distantly located enhancers (ENHs) brought together by chromatin three-dimensional looping. We showed that BRD4 controls RUNX2 by binding to the newly identified ENHs and we demonstrated that the anti-proliferative effects of bromodomain inhibitors (BETi) is associated with RUNX2 transcriptional repression. We demonstrated that each RUNX2 ENH is potentially controlled by a distinct set of TFs and we identified c-JUN as the principal pivot of this regulatory platform. We also observed that accumulation of genetic mutations within these elements correlates with metastatic behavior in human thyroid tumors. Finally, we identified RAINs, a novel family of ENH-associated long non-coding RNAs, transcribed from the identified RUNX2 regulatory unit. Our data provide a new model to explain how RUNX2 expression is reactivated in thyroid and breast cancer and how cancer-driving signaling pathways converge on the regulation of this gene.

Systems medicine of inflammaging.

Systems Medicine (SM) can be defined as an extension of Systems Biology (SB) to Clinical-Epidemiological disciplines through a shifting paradigm, starting from a cellular, toward a patient centered framework. According to this vision, the three pillars of SM are Biomedical hypotheses, experimental data, mainly achieved by Omics technologies and tailored computational, statistical and modeling tools. The three SM pillars are highly interconnected, and their balancing is crucial. Despite the great technological progresses producing huge amount of data (Big Data) and impressive computational facilities, the Bio-Medical hypotheses are still of primary importance. A paradigmatic example of unifying Bio-Medical theory is the concept of Inflammaging. This complex phenotype is involved in a large number of pathologies and patho-physiological processes such as aging, age-related diseases and cancer, all sharing a common inflammatory pathogenesis. This Biomedical hypothesis can be mapped into an ecological perspective capable to describe by quantitative and predictive models some experimentally observed features, such as microenvironment, niche partitioning and phenotype propagation. In this article we show how this idea can be supported by computational methods useful to successfully integrate, analyze and model large data sets, combining cross-sectional and longitudinal information on clinical, environmental and omics data of healthy subjects and patients to provide new multidimensional biomarkers capable of distinguishing between different pathological conditions, e.g. healthy versus unhealthy state, physiological versus pathological aging.

Integrated Molecular Characterization of Gastrointestinal Stromal Tumors (GIST) Harboring the Rare D842V Mutation in PDGFRA Gene.

Gastrointestinal stromal tumors (GIST) carrying the D842V activating mutation in the platelet-derived growth factor receptor alpha (PDGFRA) gene are a very rare subgroup of GIST (about 10%) known to be resistant to conventional tyrosine kinase inhibitors (TKIs) and to show an indolent behavior. In this study, we performed an integrated molecular characterization of D842V mutant GIST by whole-transcriptome and whole-exome sequencing coupled with protein-ligand interaction modelling to identify the molecular signature and any additional recurrent genomic event related to their clinical course. We found a very specific gene expression profile of D842V mutant tumors showing the activation of G-protein-coupled receptor (GPCR) signaling and a relative downregulation of cell cycle processes. Beyond D842V, no recurrently mutated genes were found in our cohort. Nevertheless, many private, clinically relevant alterations were found in each tumor (TP53, IDH1, FBXW7, SDH-complex). Molecular modeling of PDGFRA D842V suggests that the mutant protein binds imatinib with lower affinity with respect to wild-type structure, showing higher stability during the interaction with other type I TKIs (like crenolanib). D842V mutant GIST do not show any actionable recurrent molecular events of therapeutic significance, therefore this study supports the rationale of novel TKIs development that are currently being evaluated in clinical studies for the treatment of D842V mutant GIST.

Methods for the integration of multi-omics data: mathematical aspects.

BACKGROUND: Methods for the integrative analysis of multi-omics data are required to draw a more complete and accurate picture of the dynamics of molecular systems. The complexity of biological systems, the technological limits, the large number of biological variables and the relatively low number of biological samples make the analysis of multi-omics datasets a non-trivial problem. RESULTS AND CONCLUSIONS: We review the most advanced strategies for integrating multi-omics datasets, focusing on mathematical and methodological aspects.

Stochastic neutral modelling of the Gut Microbiota's relative species abundance from next generation sequencing data.

BACKGROUND: Interest in understanding the mechanisms that lead to a particular composition of the Gut Microbiota is highly increasing, due to the relationship between this ecosystem and the host health state. Particularly relevant is the study of the Relative Species Abundance (RSA) distribution, that is a component of biodiversity and measures the number of species having a given number of individuals. It is the universal behaviour of RSA that induced many ecologists to look for theoretical explanations. In particular, a simple stochastic neutral model was proposed by Volkov et al. relying on population dynamics and was proved to fit the coral-reefs and rain forests RSA. Our aim is to ascertain if this model also describes the Microbiota RSA and if it can help in explaining the Microbiota plasticity. RESULTS: We analyzed 16S rRNA sequencing data sampled from the Microbiota of three different animal species by Jeraldo et al. Through a clustering procedure (UCLUST), we built the Operational Taxonomic Units. These correspond to bacterial species considered at a given phylogenetic level defined by the similarity threshold used in the clustering procedure. The RSAs, plotted in the form of Preston plot, were fitted with Volkov's model. The model fits well the Microbiota RSA, except in the tail region, that shows a deviation from the neutrality assumption. Looking at the model parameters we were able to discriminate between different animal species, giving also a biological explanation. Moreover, the biodiversity estimator obtained by Volkov's model also differentiates the animal species and is in good agreement with the first and second order Hill's numbers, that are common evenness indexes simply based on the fraction of individuals per species. CONCLUSIONS: We conclude that the neutrality assumption is a good approximation for the Microbiota dynamics and the observation that Volkov's model works for this ecosystem is a further proof of the RSA universality. Moreover, the ability to separate different animals with the model parameters and biodiversity number are promising results if we think about future applications on human data, in which the Microbiota composition and biodiversity are in close relationships with a variety of diseases and life-styles.

Optimized pipeline of MuTect and GATK tools to improve the detection of somatic single nucleotide polymorphisms in whole-exome sequencing data.

BACKGROUND: Detecting somatic mutations in whole exome sequencing data of cancer samples has become a popular approach for profiling cancer development, progression and chemotherapy resistance. Several studies have proposed software packages, filters and parametrizations. However, many research groups reported low concordance among different methods. We aimed to develop a pipeline which detects a wide range of single nucleotide mutations with high validation rates. We combined two standard tools - Genome Analysis Toolkit (GATK) and MuTect - to create the GATK-LODN method. As proof of principle, we applied our pipeline to exome sequencing data of hematological (Acute Myeloid and Acute Lymphoblastic Leukemias) and solid (Gastrointestinal Stromal Tumor and Lung Adenocarcinoma) tumors. We performed experiments on simulated data to test the sensitivity and specificity of our pipeline. RESULTS: The software MuTect presented the highest validation rate (90 %) for mutation detection, but limited number of somatic mutations detected. The GATK detected a high number of mutations but with low specificity. The GATK-LODN increased the performance of the GATK variant detection (from 5 of 14 to 3 of 4 confirmed variants), while preserving mutations not detected by MuTect. However, GATK-LODN filtered more variants in the hematological samples than in the solid tumors. Experiments in simulated data demonstrated that GATK-LODN increased both specificity and sensitivity of GATK results. CONCLUSION: We presented a pipeline that detects a wide range of somatic single nucleotide variants, with good validation rates, from exome sequencing data of cancer samples. We also showed the advantage of combining standard algorithms to create the GATK-LODN method, that increased specificity and sensitivity of GATK results. This pipeline can be helpful in discovery studies aimed to profile the somatic mutational landscape of cancer genomes.

Entropy-Based Network Representation of the Individual Metabolic Phenotype.

We approach here the problem of defining and estimating the nature of the metabolite-metabolite association network underlying the human individual metabolic phenotype in healthy subjects. We retrieved significant associations using an entropy-based approach and a multiplex network formalism. We defined a significantly over-represented network formed by biologically interpretable metabolite modules. The entropy of the individual metabolic phenotype is also introduced and discussed.

Generalizing the Enhanced-Deep-Super-Resolution Neural Network to Brain MR Images: A Retrospective Study on the Cam-CAN Dataset.

The Enhanced-Deep-Super-Resolution (EDSR) model is a state-of-the-art convolutional neural network suitable for improving image spatial resolution. It was previously trained with general-purpose pictures and then, in this work, tested on biomedical magnetic resonance (MR) images, comparing the network outcomes with traditional up-sampling techniques. We explored possible changes in the model response when different MR sequences were analyzed. T1w and T2w MR brain images of 70 human healthy subjects (F:M, 40:30) from the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) repository were down-sampled and then up-sampled using EDSR model and BiCubic (BC) interpolation. Several reference metrics were used to quantitatively assess the performance of up-sampling operations (RMSE, pSNR, SSIM, and HFEN). Two-dimensional and three-dimensional reconstructions were evaluated. Different brain tissues were analyzed individually. The EDSR model was superior to BC interpolation on the selected metrics, both for two- and three- dimensional reconstructions. The reference metrics showed higher quality of EDSR over BC reconstructions for all the analyzed images, with a significant difference of all the criteria in T1w images and of the perception-based SSIM and HFEN in T2w images. The analysis per tissue highlights differences in EDSR performance related to the gray-level values, showing a relative lack of outperformance in reconstructing hyperintense areas. The EDSR model, trained on general-purpose images, better reconstructs MR T1w and T2w images than BC, without any retraining or fine-tuning. These results highlight the excellent generalization ability of the network and lead to possible applications on other MR measurements.

Sulcal Morphometry Predicts Mild Cognitive Impairment Conversion to Alzheimer's Disease.

Background: Being able to differentiate mild cognitive impairment (MCI) patients who would eventually convert (MCIc) to Alzheimer's disease (AD) from those who would not (MCInc) is a key challenge for prognosis. Objective: This study aimed to investigate the ability of sulcal morphometry to predict MCI progression to AD, dedicating special attention to an accurate identification of sulci. Methods: Twenty-five AD patients, thirty-seven MCI and twenty-five healthy controls (HC) underwent a brain-MR protocol (1.5T scanner) including a high-resolution T1-weighted sequence. MCI patients underwent a neuropsychological assessment at baseline and were clinically re-evaluated after a mean of 2.3 years. At follow-up, 12 MCI were classified as MCInc and 25 as MCIc. Sulcal morphometry was investigated using the BrainVISA framework. Consistency of sulci across subjects was ensured by visual inspection and manual correction of the automatic labelling in each subject. Sulcal surface, depth, length, and width were retrieved from 106 sulci. Features were compared across groups and their classification accuracy in predicting MCI conversion was tested. Potential relationships between sulcal features and cognitive scores were explored using Spearman's correlation. Results: The width of sulci in the temporo-occipital region strongly differentiated between each pair of groups. Comparing MCIc and MCInc, the width of several sulci in the bilateral temporo-occipital and left frontal areas was significantly altered. Higher width of frontal sulci was associated with worse performances in short-term verbal memory and phonemic fluency. Conclusions: Sulcal morphometry emerged as a strong tool for differentiating HC, MCI, and AD, demonstrating its potential prognostic value for the MCI population.