Mol Biol Cell. 2025 Jan 22:mbcE24100438. doi: 10.1091/mbc.E24-10-0438. Online ahead of print.

ABSTRACT

Cell fate decisions, such as proliferation, differentiation, and death, are driven by complex molecular interactions and signaling cascades. While significant progress has been made in understanding the molecular determinants of these processes, historically, cell fate transitions were identified through light microscopy that focused on changes in cell morphology and function. Modern techniques have shifted towards probing molecular effectors to quantify these transitions, offering more precise quantification and mechanistic understanding. However, challenges remain in cases where the molecular signals are ambiguous, complicating the assignment of cell fate. During viral infection, programmed cell death (PCD) pathways, including apoptosis, necroptosis, and pyroptosis, exhibit complex signaling and molecular crosstalk. This can lead to simultaneous activation of multiple PCD pathways, which confounds assignment of cell fate based on molecular information alone. To address this challenge, we employed deep learning-based image classification of dying cells to analyze PCD in single Herpes Simplex Virus-1 (HSV-1)-infected cells. Our approach reveals that despite heterogeneous activation of signaling, individual cells adopt predominantly prototypical death morphologies. Nevertheless, PCD is executed heterogeneously within a uniform population of virus-infected cells and varies over time. These findings demonstrate that image-based phenotyping can provide valuable insights into cell fate decisions, complementing molecular assays. [Media: see text] [Media: see text] [Media: see text] [Media: see text].

PMID:39841552 | DOI:10.1091/mbc.E24-10-0438

Sci Adv. 2025 Jan 24;11(4):eadn6377. doi: 10.1126/sciadv.adn6377. Epub 2025 Jan 22.

ABSTRACT

Birth is one of the most important life events for animals. However, its significance in the developmental process is not fully understood. Here, we found that birth-induced alteration of glutamine metabolism in radial glia (RG), the embryonic neural stem cells (NSCs), is required for the acquisition of quiescence and long-term maintenance of postnatal NSCs. Preterm birth impairs this cellular process, leading to transient hyperactivation of RG. Consequently, in the postnatal brain, the NSC pool is depleted and neurogenesis is decreased. We also found that the maintenance of quiescent RG after preterm birth improves postnatal neurogenesis. This study demonstrates the significance of birth in the maintenance of quiescent NSCs.

PMID:39841848 | DOI:10.1126/sciadv.adn6377

Database (Oxford). 2025 Jan 22;2025:baae133. doi: 10.1093/database/baae133.

ABSTRACT

Ontologies and knowledge graphs (KGs) are general-purpose computable representations of some domain, such as human anatomy, and are frequently a crucial part of modern information systems. Most of these structures change over time, incorporating new knowledge or information that was previously missing. Managing these changes is a challenge, both in terms of communicating changes to users and providing mechanisms to make it easier for multiple stakeholders to contribute. To fill that need, we have created KGCL, the Knowledge Graph Change Language (https://github.com/INCATools/kgcl), a standard data model for describing changes to KGs and ontologies at a high level, and an accompanying human-readable Controlled Natural Language (CNL). This language serves two purposes: a curator can use it to request desired changes, and it can also be used to describe changes that have already happened, corresponding to the concepts of "apply patch" and "diff" commonly used for managing changes in text documents and computer programs. Another key feature of KGCL is that descriptions are at a high enough level to be useful and understood by a variety of stakeholders-e.g. ontology edits can be specified by commands like "add synonym 'arm' to 'forelimb'" or "move 'Parkinson disease' under 'neurodegenerative disease'." We have also built a suite of tools for managing ontology changes. These include an automated agent that integrates with and monitors GitHub ontology repositories and applies any requested changes and a new component in the BioPortal ontology resource that allows users to make change requests directly from within the BioPortal user interface. Overall, the KGCL data model, its CNL, and associated tooling allow for easier management and processing of changes associated with the development of ontologies and KGs. Database URL: https://github.com/INCATools/kgcl.

PMID:39841813 | DOI:10.1093/database/baae133

Sci Transl Med. 2025 Jan 22;17(782):eadr4049. doi: 10.1126/scitranslmed.adr4049. Epub 2025 Jan 22.

ABSTRACT

Oxygen is essential for human life, yet a growing body of preclinical research is demonstrating that chronic continuous hypoxia can be beneficial in models of mitochondrial disease, autoimmunity, ischemia, and aging. This research is revealing exciting new and unexpected facets of oxygen biology, but translating these findings to patients poses major challenges, because hypoxia can be dangerous. Overcoming these barriers will require integrating insights from basic science, high-altitude physiology, clinical medicine, and sports technology. Here, we explore the foundations of this nascent field and outline a path to determine how chronic continuous hypoxia can be safely, effectively, and practically delivered to patients.

PMID:39841808 | DOI:10.1126/scitranslmed.adr4049

New Phytol. 2025 Jan 22. doi: 10.1111/nph.20415. Online ahead of print.

ABSTRACT

Precise gene-editing methods are valuable tools to enhance genetic traits. Gene editing is commonly achieved via stable integration of a gene-editing cassette in the plant's genome. However, this technique is unfavorable for field applications, especially in vegetatively propagated plants, such as many commercial tree species, where the gene-editing cassette cannot be segregated away without breaking the genetic constitution of the elite variety. Here, we describe an efficient method for generating gene-edited Populus tremula × P. alba (poplar) trees without incorporating foreign DNA into its genome. Using Agrobacterium tumefaciens, we expressed a base-editing construct targeting CCoAOMT1 along with the ALS genes for positive selection on a chlorsulfuron-containing medium. About 50% of the regenerated shoots were derived from transient transformation and were free of T-DNA. Overall, 7% of the chlorsulfuron-resistant shoots were T-DNA free, edited in the CCoAOMT1 gene and nonchimeric. Long-read whole-genome sequencing confirmed the absence of any foreign DNA in the tested gene-edited lines. Additionally, we evaluated the CodA gene as a negative selection marker to eliminate lines that stably incorporated the T-DNA into their genome. Although the latter negative selection is not essential for selecting transgene-free, gene-edited Populus tremula × P. alba shoots, it may prove valuable for other genotypes or varieties.

PMID:39841625 | DOI:10.1111/nph.20415

Mol Biol Cell. 2025 Jan 22:mbcE24100438. doi: 10.1091/mbc.E24-10-0438. Online ahead of print.

ABSTRACT

Cell fate decisions, such as proliferation, differentiation, and death, are driven by complex molecular interactions and signaling cascades. While significant progress has been made in understanding the molecular determinants of these processes, historically, cell fate transitions were identified through light microscopy that focused on changes in cell morphology and function. Modern techniques have shifted towards probing molecular effectors to quantify these transitions, offering more precise quantification and mechanistic understanding. However, challenges remain in cases where the molecular signals are ambiguous, complicating the assignment of cell fate. During viral infection, programmed cell death (PCD) pathways, including apoptosis, necroptosis, and pyroptosis, exhibit complex signaling and molecular crosstalk. This can lead to simultaneous activation of multiple PCD pathways, which confounds assignment of cell fate based on molecular information alone. To address this challenge, we employed deep learning-based image classification of dying cells to analyze PCD in single Herpes Simplex Virus-1 (HSV-1)-infected cells. Our approach reveals that despite heterogeneous activation of signaling, individual cells adopt predominantly prototypical death morphologies. Nevertheless, PCD is executed heterogeneously within a uniform population of virus-infected cells and varies over time. These findings demonstrate that image-based phenotyping can provide valuable insights into cell fate decisions, complementing molecular assays. [Media: see text] [Media: see text] [Media: see text] [Media: see text].

PMID:39841552 | DOI:10.1091/mbc.E24-10-0438

J Bone Joint Surg Am. 2025 Jan 22. doi: 10.2106/JBJS.24.00261. Online ahead of print.

ABSTRACT

BACKGROUND: Limb-salvage surgery for malignant bone tumors can be associated with considerable perioperative blood loss. The aim of this randomized controlled trial was to assess the safety and efficacy of the intraoperative infusion of tranexamic acid (TXA) in children and adolescents undergoing limb-salvage surgery.

METHODS: All participants were <18 years of age at the time of surgery and diagnosed with a malignant bone tumor of the femur that was treated with resection and reconstruction with a megaprosthesis. Exclusion criteria included anatomic locations other than the femur, reconstruction with a vascularized fibular graft, and a previous history of deep venous thrombosis, coagulopathy, or renal dysfunction. Participants were randomly allocated to either the TXA group (a preoperative loading dose infusion of 10 mg/kg of TXA followed by a continuous infusion of 5 mg/kg/hr until the end of surgery) or the placebo group (the same dosage but with TXA substituted with an infusion of normal saline solution). Intraoperative and perioperative blood loss were calculated with use of the hemoglobin balance method. Perioperative blood loss at postoperative day 1 and at discharge from the hospital were calculated. The total volumes of blood transfused intraoperatively and postoperatively were recorded. A statistical comparison between the groups was performed for blood loss and blood transfusion as well as for possible independent variables other than TXA, including age, body mass index, histopathologic diagnosis, tumor volume, preoperative hemoglobin level, type of resection, and the duration of surgery.

RESULTS: A total of 48 participants, with a mean age of 12.5 ± 3.44 years (range, 5 to 18 years) and a male-to-female ratio of 1.18, were included. All participants were Egyptians by race and ethnicity. There were no minor or major drug-related adverse events. There was no significant difference between the groups with respect to intraoperative blood loss (p = 0.0616) or transfusion requirements (p = 0.812), but there was a significant difference in perioperative blood loss at postoperative day 1 (p = 0.0144) and at discharge from the hospital (p = 0.0106) and in perioperative blood transfusion (p = 0.023).

CONCLUSIONS: TXA can be safely infused intraoperatively in children and adolescents undergoing limb-salvage surgery, and it contributes significantly to the reduction of perioperative blood loss and transfusion requirements.

LEVEL OF EVIDENCE: Therapeutic Level I. See Instructions for Authors for a complete description of levels of evidence.

PMID:39841811 | DOI:10.2106/JBJS.24.00261

ANZ J Surg. 2025 Jan 22. doi: 10.1111/ans.19405. Online ahead of print.

ABSTRACT

BACKGROUND: Metformin is a diabetes medication with anti-mitotic properties. A narrative review was performed to investigate people using metformin and the risk of developing pancreatic ductal adenocarcinoma (PDAC) as well as survival outcomes in established PDAC.

METHODS: Relevant studies on metformin use and PDAC were retrieved from PubMed including observational studies on metformin and the risk of developing PDAC and survival outcomes in PDAC, and randomized controlled trials of metformin as a treatment in PDAC.

RESULTS: Of the 367 studies searched, 26 studies fulfilled the criteria for this review. Metformin was not consistently associated with a reduced risk of developing PDAC. However, metformin use, especially higher cumulative doses, in some studies was associated with longer survival in patients with established PDAC, especially in the subgroup with resectable PDAC. Metformin use was not associated with longer survival in more advanced (non-resectable metastatic) PDAC.

CONCLUSION: Metformin was not consistently associated with a reduced risk of developing PDAC. Metformin may be associated with overall survival benefits in patients with PDAC including the resectable PDAC subgroup but not in the metastatic PDAC subgroup. The evidence to date does not support the routine use of metformin as an adjuvant therapy for advanced PDAC.

PMID:39840695 | DOI:10.1111/ans.19405

Calcif Tissue Int. 2025 Jan 22;116(1):32. doi: 10.1007/s00223-024-01323-z.

ABSTRACT

Rare bone diseases are clinically and genetically heterogenous. Despite those differences, the underlying pathophysiology is not infrequently different. Several of these diseases are characterized by abnormal bone metabolism and turnover with subsequent abnormalities in markers of bone turnover, rendering them useful adjuncts in the diagnostic process. As most rare bone diseases are inherited, genetic testing for implicated pathogenic variants, where known, is another relevant tool that can aid in diagnosis. While some skeletal disorders can be localized or monostotic, others can involve multiple skeletal sites and warrant imaging tools to localize them and determine the severity of disease and/or presence of complications as well as to assess bone quality and the potential risk of fractures. Rare bone disorders pose a great challenge in their diagnosis, ultimately resulting in delayed diagnosis, higher risk of complications and a poor quality of life in affected individuals. In this review we discuss the biochemical and radiological tools that can be utilized to diagnose selected orphan bone disorders, the clinical utility and limitations of these diagnostic tools, and areas where future research is warranted.

PMID:39841287 | DOI:10.1007/s00223-024-01323-z

Dtsch Arztebl Int. 2024 Oct 18;121(21):712-713. doi: 10.3238/arztebl.m2024.0126.

NO ABSTRACT

PMID:39841500 | DOI:10.3238/arztebl.m2024.0126

J Clin Microbiol. 2025 Jan 22:e0148024. doi: 10.1128/jcm.01480-24. Online ahead of print.

ABSTRACT

The Burkholderia cepacia complex (BCC) is a group of Gram-negative bacteria that cause opportunistic infections, most notably in people with cystic fibrosis (CF), and have been associated with outbreaks caused by contaminated medical products. Antimicrobial susceptibility testing (AST) is often used to guide treatment for BCC infections, perhaps most importantly in people with CF who are being considered for lung transplant. However, recent studies have highlighted problems with AST methods. Here, we address limitations from previous studies to further evaluate BCC AST methods. We assessed the performance of reference broth microdilution (BMD), disk diffusion (DD) using Mueller-Hinton agar (MHA) from three manufacturers, agar dilution (AD), and gradient diffusion (ETEST) for ceftazidime (CAZ), levofloxacin (LVX), meropenem (MEM), minocycline (MIN), and trimethoprim-sulfamethoxazole (TMP-SMX) on a set of 205 BCC isolates. The isolate set included 100 isolates from people with CF and 105 isolates from people without CF from a variety of sources, which enabled us to systematically evaluate whether specimen source impacts AST performance. For all BCC isolates, BMD reproducibility was 93%, 98%, 99%, 98%, and 96% for CAZ, LVX, MEM, MIN, and TMP-SMX, respectively. Using BMD as the comparator method, we show that DD, AD, and ETEST perform poorly, with neither MHA manufacturer nor specimen source significantly impacting method performance. Based on our data, we recommend that routine AST should not be performed for BCC isolates. If a provider requests AST, clinical microbiology laboratories should perform Clinical and Laboratory Standards Institute reference methodology for BMD (stored frozen) and report MIC only.IMPORTANCEAntimicrobial susceptibility testing for the Burkholderia cepacia complex (BCC) is often used to determine eligibility for lung transplant in people with cystic fibrosis. However, problems with method performance have been reported. Here, we systematically evaluate the performance of reference broth microdilution, disk diffusion, agar dilution, and gradient diffusion (ETEST) for BCC organisms isolated from people with and without cystic fibrosis. We show that broth microdilution reproducibility is acceptable for levofloxacin, meropenem, minocycline, and trimethoprim-sulfamethoxazole, while ceftazidime was just below the acceptability cut-off. Regardless of specimen source, the results from disk diffusion, agar dilution, and ETEST do not correlate with broth microdilution. Based on these findings, we recommend that antimicrobial susceptibility testing should not be routinely performed for BCC, and if requested by the provider, only broth microdilution following Clinical and Laboratory Standards Institute guidelines should be used. Providers should be aware of the significant limitations of antimicrobial susceptibility testing methods for BCC.

PMID:39840992 | DOI:10.1128/jcm.01480-24

Antimicrob Agents Chemother. 2025 Jan 22:e0116224. doi: 10.1128/aac.01162-24. Online ahead of print.

ABSTRACT

Stenotrophomonas maltophilia is an understudied, gram-negative, aerobic bacterium that is widespread in the environment and increasingly a cause of opportunistic infections. Treating S. maltophilia remains difficult, leading to an increase in disease severity and higher hospitalization rates in people with cystic fibrosis, cancer, and other immunocompromised health conditions. The lack of effective antibiotics has led to renewed interest in phage therapy; however, there remains a great need for well-characterized phages, especially against S. maltophilia. In response to an oncology patient with a sepsis infection, we collected 18 phages from Southern California wastewater influent that exhibit different plaque morphology against S. maltophilia host strain B28B. We hypothesized that, when combined into a cocktail, genetically diverse phages would give rise to distinct lytic infection kinetics that would enhance bacterial killing when compared to the individual phages alone. We identified three genetically distinct clusters of phages, and a representative from each group was further investigated and screened for potential therapeutic use. The results demonstrated that the three-phage cocktail significantly suppressed bacterial growth compared with individual phages when observed for 48 h. We also assessed the lytic impacts of our three-phage cocktail against a collection of 46 S. maltophilia strains to determine if a multi-phage cocktail has an expanded host range. Our phages remained strain-specific and infected >50% of tested strains. In six clinically relevant S. maltophilia strains, the multi-phage cocktail has enhanced suppression of bacterial growth. These findings suggest that specialized phage cocktails may be an effective avenue of treatment for recalcitrant S. maltophilia infections resistant to current antibiotics.

PMID:39840957 | DOI:10.1128/aac.01162-24

J Imaging Inform Med. 2025 Jan 22. doi: 10.1007/s10278-025-01394-w. Online ahead of print.

ABSTRACT

Non-alcoholic fatty liver disease (NAFLD) is a highly prevalent chronic liver condition characterized by excessive hepatic fat accumulation. Early diagnosis is crucial as NAFLD can progress to more severe conditions like steatohepatitis, fibrosis, cirrhosis, and hepatocellular carcinoma without timely intervention. While liver biopsy remains the gold standard for NAFLD assessment, abdominal ultrasound (US) imaging has emerged as a widely adopted non-invasive modality due to convenience and low cost. However, the subjective interpretation of US images is challenging and unpredictable. This study proposes a deep learning-based computer-aided diagnosis (CAD) model, termed potent boosts channel-aware separable intent - ConvNeXt (PBCS-ConvNeXt), for automated NAFLD classification using B-mode US images. The model architecture comprises three key components: The potent stem cell, an advanced trainable preprocessing module for robust feature extraction; Enhanced ConvNeXt Blocks that amplify channel-wise features to refine processing; and the boosting block that integrates multi-stage features for effective information extraction from US data. Utilizing fatty liver gradings from attenuation imaging (ATI) as the ground truth, the PBCS-ConvNeXt model was evaluated using 5-fold cross-validation, achieving an accuracy of 82%, sensitivity of 81% and specificity of 83% for identifying fatty liver on abdominal US. The proposed CAD system demonstrates high diagnostic performance in NAFLD classification from US images, enabling early detection and informing timely clinical management to prevent disease progression.

PMID:39841370 | DOI:10.1007/s10278-025-01394-w

Neuroinformatics. 2025 Jan 22;23(2):12. doi: 10.1007/s12021-024-09701-6.

ABSTRACT

Brain tumours are one of the most deadly and noticeable types of cancer, affecting both children and adults. One of the major drawbacks in brain tumour identification is the late diagnosis and high cost of brain tumour-detecting devices. Most existing approaches use ML algorithms to address problems, but they have drawbacks such as low accuracy, high loss, and high computing cost. To address these challenges, a novel U-Net model for tumour segmentation in magnetic resonance images (MRI) is proposed. Initially, images are claimed from the dataset and pre-processed with the Probabilistic Hybrid Wiener filter (PHWF) to remove unwanted noise and improve image quality. To reduce model complexity, the pre-processed images are submitted to a feature extraction procedure known as 3D Convolutional Vision Transformer (3D-VT). To perform the segmentation approach using chaotic optimization assisted Dilated Channel Gate attention U-Net (CDCG-UNet) model to segment brain tumour regions effectively. The proposed approach segments tumour portions as whole tumour (WT), tumour Core (TC), and Enhancing Tumour (ET) positions. The optimization loss function can be performed using the Chaotic Harris Shrinking Spiral optimization algorithm (CHSOA). The proposed CDCG-UNet model is evaluated with three datasets: BRATS 2021, BRATS 2020, and BRATS 2023. For the BRATS 2021 dataset, the proposed CDCG-UNet model obtained a dice score of 0.972 for ET, 0.987 for CT, and 0.98 for WT. For the BRATS 2020 dataset, the proposed CDCG-UNet model produced a dice score of 98.87% for ET, 98.67% for CT, and 99.1% for WT. The CDCG-UNet model is further evaluated using the BRATS 2023 dataset, which yields 98.42% for ET, 98.08% for CT, and 99.3% for WT.

PMID:39841321 | DOI:10.1007/s12021-024-09701-6

Med Biol Eng Comput. 2025 Jan 22. doi: 10.1007/s11517-025-03297-y. Online ahead of print.

ABSTRACT

The identification and categorization of circulating tumor cells (CTCs) in peripheral blood are imperative for advancing cancer diagnostics and prognostics. The intricacy of various CTCs subtypes, coupled with the difficulty in developing exhaustive datasets, has impeded progress in this specialized domain. To date, no methods have been dedicated exclusively to overcoming the classification challenges of CTCs. To address this deficit, we have developed CTCDet, a large-scale dataset meticulously annotated based on the distinctive pathological characteristics of CTCs, aimed at advancing the application of deep learning techniques in oncological research. Furthermore, we introduce CTCNet, an innovative hybrid architecture that merges the capabilities of CNNs and Transformers to achieve precise classification of CTCs. This architecture features the Parallel Token mixer, which integrates local window self-attention with large-kernel depthwise convolution, enhancing the network's ability to model intricate channel and spatial relationships. Additionally, the Deformable Large Kernel Attention (DLKAttention) module leverages deformable convolution and large-kernel operations to adeptly delineate the nuanced features of CTCs, substantially boosting classification efficacy. Comprehensive evaluations on the CTCDet dataset validate the superior performance of CTCNet, confirming its ability to outperform other general methods in accurate cell classification. Moreover, the generalizability of CTCNet has been established across various datasets, establishing its robustness and applicability. What is more, our proposed method can lead to clinical applications and provide some help in assisting cancer diagnosis and treatment. Code and Data are available at https://github.com/JasonWu404/CTCs_Classification .

PMID:39841310 | DOI:10.1007/s11517-025-03297-y

Abdom Radiol (NY). 2025 Jan 22. doi: 10.1007/s00261-025-04804-3. Online ahead of print.

ABSTRACT

PURPOSE: Intra-pancreatic fat deposition (IPFD) is closely associated with the onset and progression of type 2 diabetes mellitus (T2DM). We aimed to develop an accurate and automated method for assessing IPFD on multi-echo Dixon MRI.

MATERIALS AND METHODS: In this retrospective study, 534 patients from two centers who underwent upper abdomen MRI and completed multi-echo and double-echo Dixon MRI were included. A pancreatic segmentation model was trained on double-echo Dixon water images using nnU-Net. Predicted masks were registered to the proton density fat fraction (PDFF) maps of the multi-echo Dixon sequence. Deep semantic segmentation feature-based radiomics (DSFR) and radiomics features were separately extracted on the PDFF maps and modeled using the support vector machine method with 5-fold cross-validation. The first deep learning radiomics (DLR) model was constructed to distinguish T2DM from non-diabetes and pre-diabetes by averaging the output scores of the DSFR and radiomics models. The second DLR model was then developed to distinguish pre-diabetes from non-diabetes. Two radiologist models were constructed based on the mean PDFF of three pancreatic regions of interest.

RESULTS: The mean Dice similarity coefficient for pancreas segmentation was 0.958 in the total test cohort. The AUCs of the DLR and two radiologist models in distinguishing T2DM from non-diabetes and pre-diabetes were 0.868, 0.760, and 0.782 in the training cohort, and 0.741, 0.724, and 0.653 in the external test cohort, respectively. For distinguishing pre-diabetes from non-diabetes, the AUCs were 0.881, 0.688, and 0.688 in the training cohort, which included data combined from both centers. Testing was not conducted due to limited pre-diabetic patients. Intraclass correlation coefficients between radiologists' pancreatic PDFF measurements were 0.800 and 0.699 at two centers, suggesting good and moderate reproducibility, respectively.

CONCLUSION: The DLR model demonstrated superior performance over radiologists, providing a more efficient, accurate and stable method for monitoring IPFD and predicting the risk of T2DM and pre-diabetes. This enables IPFD assessment to potentially serve as an early biomarker for T2DM, providing richer clinical information for disease progression and management.

PMID:39841227 | DOI:10.1007/s00261-025-04804-3

Radiol Artif Intell. 2025 Jan 22:e230555. doi: 10.1148/ryai.230555. Online ahead of print.

ABSTRACT

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To assess the impact of scanner manufacturer and scan protocol on the performance of deep learning models to classify prostate cancer (PCa) aggressiveness on biparametric MRI (bpMRI). Materials and Methods In this retrospective study, 5,478 cases from ProstateNet, a PCa bpMRI dataset with examinations from 13 centers, were used to develop five deep learning (DL) models to predict PCa aggressiveness with minimal lesion information and test how using data from different subgroups-scanner manufacturers and endorectal coil (ERC) use (Siemens, Philips, GE with and without ERC and the full dataset)-impacts model performance. Performance was assessed using the area under the receiver operating characteristic curve (AUC). The impact of clinical features (age, prostate-specific antigen level, Prostate Imaging Reporting and Data System [PI-RADS] score) on model performance was also evaluated. Results DL models were trained on 4,328 bpMRI cases, and the best model achieved AUC = 0.73 when trained and tested using data from all manufacturers. Hold-out test set performance was higher when models trained with data from a manufacturer were tested on the same manufacturer (within-and between-manufacturer AUC differences of 0.05 on average, P < .001). The addition of clinical features did not improve performance (P = .24). Learning curve analyses showed that performance remained stable as training data increased. Analysis of DL features showed that scanner manufacturer and scan protocol heavily influenced feature distributions. Conclusion In automated classification of PCa aggressiveness using bpMRI data, scanner manufacturer and endorectal coil use had a major impact on DL model performance and features. Published under a CC BY 4.0 license.

PMID:39841063 | DOI:10.1148/ryai.230555

Acta Otolaryngol. 2025 Jan 22:1-6. doi: 10.1080/00016489.2025.2450221. Online ahead of print.

ABSTRACT

BACKGROUND: Gait instability and falls significantly impact life quality and morbi-mortality in elderly populations. Early diagnosis of gait disorders is one of the most effective approaches to minimize severe injuries.

OBJECTIVE: To find a gait instability pattern in older adults through an image representation of data collected by a single sensor.

METHODS: A sample of 13 older adults (71-85 years old) with instability by vestibular hypofunction is compared to a sample of 19 adults (21-75 years old) without instability and normal vestibular function. Image representations of the gait signals acquired on a specific walk path were generated using a continuous wavelet transform and analyzed as a texture using grey level co-occurrence matrix metrics as features. A support vector machine (SVM) algorithm was used to discriminate subjects.

RESULTS: First results show a good classification performance. According to analysis of extracted features, most information relevant to instability is concentrated in the medio-lateral acceleration (X axis) and the frontal plane angular rotation (Z axis gyroscope). Performing a ten-fold cross-validation through the first ten seconds of the sample dataset, the algorithm achieves a 92,3 F1 score corresponding to 12 true-positives, 1 false positive and 1 false negative.

DISCUSSION: This preliminary report suggests that the method has potential use in assessing gait disorders in controlled and non-controlled environments. It suggests that deep learning methods could be explored given the availability of a larger population and data samples.

PMID:39840938 | DOI:10.1080/00016489.2025.2450221

Mov Disord. 2025 Jan 22. doi: 10.1002/mds.30113. Online ahead of print.

ABSTRACT

BACKGROUND: Pose estimation algorithms applied to two-dimensional videos evaluate gait disturbances; however, a few studies have used this method to evaluate ataxic gait.

OBJECTIVE: The aim was to assess whether a pose estimation algorithm can predict the severity of cerebellar ataxia by applying it to gait videos.

METHODS: We video-recorded 66 patients with degenerative cerebellar diseases performing the timed up-and-go test. Key points from the gait videos extracted by a pose estimation algorithm were input into a deep learning model to predict the Scale for the Assessment and Rating of Ataxia (SARA) score. We also evaluated video segments that the model focused on to predict ataxia severity.

RESULTS: The model achieved a root-mean-square error of 2.30 and a coefficient of determination of 0.79 in predicting the SARA score. It primarily focused on standing, turning, and body sway to assess severity.

CONCLUSIONS: This study demonstrated that the model may capture gait characteristics from key-point data and has the potential to predict SARA scores. © 2025 International Parkinson and Movement Disorder Society.

PMID:39840857 | DOI:10.1002/mds.30113

Protein Sci. 2025 Feb;34(2):e70031. doi: 10.1002/pro.70031.

ABSTRACT

Protein aggregation is critical to various biological and pathological processes. Besides, it is also an important property in biotherapeutic development. However, experimental methods to profile protein aggregation are costly and labor-intensive, driving the need for more efficient computational alternatives. In this study, we introduce "AggNet," a novel deep learning framework based on the protein language model ESM2 and AlphaFold2, which utilizes physicochemical, evolutionary, and structural information to discriminate amyloid and non-amyloid peptides and identify aggregation-prone regions (APRs) in diverse proteins. Benchmark comparisons show that AggNet outperforms existing methods and achieves state-of-the-art performance on protein aggregation prediction. Also, the predictive ability of AggNet is stable across proteins with different secondary structures. Feature analysis and visualizations prove that the model effectively captures peptides' physicochemical properties effectively, thereby offering enhanced interpretability. Further validation through a case study on MEDI1912 confirms AggNet's practical utility in analyzing protein aggregation and guiding mutation for aggregation mitigation. This study enhances computational tools for predicting protein aggregation and highlights the potential of AggNet in protein engineering. Finally, to improve the accessibility of AggNet, the source code can be accessed at: https://github.com/Hill-Wenka/AggNet.

PMID:39840791 | DOI:10.1002/pro.70031