Literature Watch
VGX: VGG19-Based Gradient Explainer Interpretable Architecture for Brain Tumor Detection in Microscopy Magnetic Resonance Imaging (MMRI)
Microsc Res Tech. 2025 Jan 17. doi: 10.1002/jemt.24809. Online ahead of print.
ABSTRACT
The development of deep learning algorithms has transformed medical image analysis, especially in brain tumor recognition. This research introduces a robust automatic microbrain tumor identification method utilizing the VGG16 deep learning model. Microscopy magnetic resonance imaging (MMRI) scans extract detailed features, providing multi-modal insights. VGG16, known for its depth and high performance, is utilized for this purpose. The study demonstrates the model's potential for precise and effective diagnosis by examining how well it can differentiate between areas of normal brain tissue and cancerous regions, leveraging both MRI and microscopy data. We describe in full the pre-processing actions taken to improve the quality of input data and maximize model efficiency. A carefully selected dataset, incorporating diverse tumor sizes and types from both microscopy and MRI sources, is used during the training phase to ensure representativeness. The proposed modified VGG19 model achieved 98.81% validation accuracy. Despite good accuracy, interpretation of the result still questionable. The proposed methodology integrates explainable AI (XAI) for brain tumor detection to interpret system decisions. The proposed study uses a gradient explainer to interpret classification results. Comparative statistical analysis highlights the effectiveness of the proposed explainer model over other XAI techniques.
PMID:39825619 | DOI:10.1002/jemt.24809
TagGen: Diffusion-based generative model for cardiac MR tagging super resolution
Magn Reson Med. 2025 Jan 17. doi: 10.1002/mrm.30422. Online ahead of print.
ABSTRACT
PURPOSE: The aim of the work is to develop a cascaded diffusion-based super-resolution model for low-resolution (LR) MR tagging acquisitions, which is integrated with parallel imaging to achieve highly accelerated MR tagging while enhancing the tag grid quality of low-resolution images.
METHODS: We introduced TagGen, a diffusion-based conditional generative model that uses low-resolution MR tagging images as guidance to generate corresponding high-resolution tagging images. The model was developed on 50 patients with long-axis-view, high-resolution tagging acquisitions. During training, we retrospectively synthesized LR tagging images using an undersampling rate (R) of 3.3 with truncated outer phase-encoding lines. During inference, we evaluated the performance of TagGen and compared it with REGAIN, a generative adversarial network-based super-resolution model that was previously applied to MR tagging. In addition, we prospectively acquired data from 6 subjects with three heartbeats per slice using 10-fold acceleration achieved by combining low-resolution R = 3.3 with GRAPPA-3 (generalized autocalibrating partially parallel acquisitions 3).
RESULTS: For synthetic data (R = 3.3), TagGen outperformed REGAIN in terms of normalized root mean square error, peak signal-to-noise ratio, and structural similarity index (p < 0.05 for all). For prospectively 10-fold accelerated data, TagGen provided better tag grid quality, signal-to-noise ratio, and overall image quality than REGAIN, as scored by two (blinded) radiologists (p < 0.05 for all).
CONCLUSIONS: We developed a diffusion-based generative super-resolution model for MR tagging images and demonstrated its potential to integrate with parallel imaging to reconstruct highly accelerated cine MR tagging images acquired in three heartbeats with enhanced tag grid quality.
PMID:39825522 | DOI:10.1002/mrm.30422
Development of a Deep Learning Tool to Support the Assessment of Thyroid Follicular Cell Hypertrophy in the Rat
Toxicol Pathol. 2025 Jan 17:1926233241309328. doi: 10.1177/01926233241309328. Online ahead of print.
ABSTRACT
Thyroid tissue is sensitive to the effects of endocrine disrupting substances, and this represents a significant health concern. Histopathological analysis of tissue sections of the rat thyroid gland remains the gold standard for the evaluation for agrochemical effects on the thyroid. However, there is a high degree of variability in the appearance of the rat thyroid gland, and toxicologic pathologists often struggle to decide on and consistently apply a threshold for recording low-grade thyroid follicular hypertrophy. This research project developed a deep learning image analysis solution that provides a quantitative score based on the morphological measurements of individual follicles that can be integrated into the standard pathology workflow. To achieve this, a U-Net convolutional deep learning neural network was used that not just identifies the various tissue components but also delineates individual follicles. Further steps to process the raw individual follicle data were developed using empirical models optimized to produce thyroid activity scores that were shown to be superior to the mean epithelial area approach when compared with pathologists' scores. These scores can be used for pathologist decision support using appropriate statistical methods to assess the presence or absence of low-grade thyroid hypertrophy at the group level.
PMID:39825517 | DOI:10.1177/01926233241309328
DNA-based cell typing in menstrual effluent identifies cell type variation by sample collection method: toward noninvasive biomarker development for women's health
Epigenetics. 2025 Dec;20(1):2453275. doi: 10.1080/15592294.2025.2453275. Epub 2025 Jan 18.
ABSTRACT
Menstrual effluent cell profiles have potential as noninvasive biomarkers of female reproductive and gynecological health and disease. We used DNA methylation-based cell type deconvolution (methylation cytometry) to identify cell type profiles in self-collected menstrual effluent. During the second day of their menstrual cycle, healthy participants collected menstrual effluent using a vaginal swab, menstrual cup, and pad. Immune cell proportions were highest in menstrual cup samples, and epithelial cells were highest in swab samples. Our work demonstrates the feasibility and utility of menstrual effluent cell profiling in population-level research using remotely collected samples and DNA methylation.
PMID:39825876 | DOI:10.1080/15592294.2025.2453275
Arrhythmogenic calmodulin variants D131E and Q135P disrupt interaction with the L-type voltage-gated Ca<sup>2+</sup> channel (Ca<sub>v</sub>1.2) and reduce Ca<sup>2+</sup>-dependent inactivation
Acta Physiol (Oxf). 2025 Feb;241(2):e14276. doi: 10.1111/apha.14276.
ABSTRACT
AIM: Long QT syndrome (LQTS) and catecholaminergic polymorphism ventricular tachycardia (CPVT) are inherited cardiac disorders often caused by mutations in ion channels. These arrhythmia syndromes have recently been associated with calmodulin (CaM) variants. Here, we investigate the impact of the arrhythmogenic variants D131E and Q135P on CaM's structure-function relationship. Our study focuses on the L-type calcium channel Cav1.2, a crucial component of the ventricular action potential and excitation-contraction coupling.
METHODS: We used circular dichroism (CD), 1H-15N HSQC NMR, and trypsin digestion to determine the structural and stability properties of CaM variants. The affinity of CaM for Ca2+ and interaction of Ca2+/CaM with Cav1.2 (IQ and NSCaTE domains) were investigated using intrinsic tyrosine fluorescence and isothermal titration calorimetry (ITC), respectively. The effect of CaM variants of Cav1.2 activity was determined using HEK293-Cav1.2 cells (B'SYS) and whole-cell patch-clamp electrophysiology.
RESULTS: Using a combination of protein biophysics and structural biology, we show that the disease-associated mutations D131E and Q135P mutations alter apo/CaM structure and stability. In the Ca2+-bound state, D131E and Q135P exhibited reduced Ca2+ binding affinity, significant structural changes, and altered interaction with Cav1.2 domains (increased affinity for Cav1.2-IQ and decreased affinity for Cav1.2-NSCaTE). We show that the mutations dramatically impair Ca2+-dependent inactivation (CDI) of Cav1.2, which would contribute to abnormal Ca2+ influx, leading to disrupted Ca2+ handling, characteristic of cardiac arrhythmia syndromes.
CONCLUSIONS: These findings provide insights into the molecular mechanisms behind arrhythmia caused by calmodulin mutations, contributing to our understanding of cardiac syndromes at a molecular and cellular level.
PMID:39825574 | DOI:10.1111/apha.14276
NIA Postdoctoral Fellowship Award to Promote Broad Participation in Translational Research for AD/ADRD (F32 Clinical Trial Not Allowed)
Notice of Information: Administrative Supplements to Increase the Number of Training Slots in NIA-funded T32 Awards to Support Within-Scope Training of Music-Science Research
Notice of Information: Re-issue of Longstanding NHLBI T32 Program
Notice of Early Expiration and Reissue of PAR-24-062, "Phased Research to Support Substance Use Epidemiology, Prevention, and Services Studies (R61/R33 Clinical Trials Optional)"
Notice of Early Expiration and Reissue of PAR-24-060, "Pilot and Feasibility Studies in Preparation for Substance Use Prevention Trials (R34 Clinical Trial Optional)"
Notice of Participation of the Environmental Protection Agency in RFA-RM-24-010: Complement-ARIE New Approach Methodologies (NAMs) Technology Development Centers (UM1 Clinical Trial Optional)
Notice of Special Interest (NOSI): Genetic Underpinnings of Endosomal Trafficking as a Pathological Hub in Alzheimer's Disease (AD) and AD-Related Dementias (ADRD)
Notice of Special Interest (NOSI): Addressing Cancer-Related Financial Hardship to Improve Patient Outcomes
Notice to Rescind NOT-CA-18-031 "NIH Applicant Assistance Program (AAP) for New or Previously Unawarded Small Businesses"
NIA Predoctoral Fellowship Award to Promote Broad Participation in Translational Research for AD/ADRD (F31 Clinical Trial Not Allowed)
Notice of Early Expiration of PAR-24-061 "Nursing Research Education Program in Firearm Injury Prevention Research: Short Courses (R25 Independent Clinical Trial Not Allowed)"
Notice of Clarification to PAR-24-272 "Clinical and Translational Science Award (UM1 Clinical Trial Optional)"
Notice of Change: NINDS Interests for PAR-25-143 "Dissemination and Implementation Research in Health (R21 Clinical Trial Optional)"
Genomic reanalysis of a pan-European rare-disease resource yields new diagnoses
Nat Med. 2025 Feb;31(2):478-489. doi: 10.1038/s41591-024-03420-w. Epub 2025 Jan 17.
ABSTRACT
Genetic diagnosis of rare diseases requires accurate identification and interpretation of genomic variants. Clinical and molecular scientists from 37 expert centers across Europe created the Solve-Rare Diseases Consortium (Solve-RD) resource, encompassing clinical, pedigree and genomic rare-disease data (94.5% exomes, 5.5% genomes), and performed systematic reanalysis for 6,447 individuals (3,592 male, 2,855 female) with previously undiagnosed rare diseases from 6,004 families. We established a collaborative, two-level expert review infrastructure that allowed a genetic diagnosis in 506 (8.4%) families. Of 552 disease-causing variants identified, 464 (84.1%) were single-nucleotide variants or short insertions/deletions. These variants were either located in recently published novel disease genes (n = 67), recently reclassified in ClinVar (n = 187) or reclassified by consensus expert decision within Solve-RD (n = 210). Bespoke bioinformatics analyses identified the remaining 15.9% of causative variants (n = 88). Ad hoc expert review, parallel to the systematic reanalysis, diagnosed 249 (4.1%) additional families for an overall diagnostic yield of 12.6%. The infrastructure and collaborative networks set up by Solve-RD can serve as a blueprint for future further scalable international efforts. The resource is open to the global rare-disease community, allowing phenotype, variant and gene queries, as well as genome-wide discoveries.
PMID:39825153 | DOI:10.1038/s41591-024-03420-w
Current progress in CRISPR-Cas systems for rare diseases
Prog Mol Biol Transl Sci. 2025;210:163-203. doi: 10.1016/bs.pmbts.2024.07.019. Epub 2024 Aug 31.
ABSTRACT
The groundbreaking CRISPR-Cas gene editing method permits exact genetic code alteration. The "CRISPR" DNA protects bacteria from viruses. CRISPR-Cas utilizes a guide RNA to steer the Cas enzyme to the genome's gene editing target. After attaching to a sequence, Cas enzymes cleave DNA to insert, delete, or modify genes. The influence of CRISPR-Cas technology on molecular biology and genetics is profound. It allows for gene function research, animal disease models, and patient genetic therapy. Gene editing has transformed biotechnology, agriculture, and customized medicine. CRISPR-Cas could revolutionize genetics and medicine. CRISPR-Cas may accurately correct genetic flaws that underlie rare diseases, improving their therapy. Gene mutations make CRISPR-Cas gene editing a viable cure for uncommon diseases. We can use CRISPR-Cas to correct genetic abnormalities at the molecular level. This strategy offers hope for remedies and disease understanding. CRISPR-Cas genome editing may enable more targeted and effective treatments for rare medical illnesses with few therapy options. By developing base- and prime-editing CRISPR technology, CRISPR-Cas allows for accurate and efficient genome editing and advanced DNA modification. This advanced method provides precise DNA alterations without double-strand breakage. These advances have improved gene editing safety and precision, reducing unfavorable effects. Lipid nanoparticles, which use viral vectors, improve therapeutic cell and tissue targeting. In rare disorders, gene therapy may be possible with CRISPR-Cas clinical trials. CRISPR-Cas research is improving gene editing, delivery, and rare disease treatment.
PMID:39824580 | DOI:10.1016/bs.pmbts.2024.07.019
Pages
