-
Heliyon Jun 2024Early cancer detection and treatment depend on the discovery of specific genes that cause cancer. The classification of genetic mutations was initially done manually....
Early cancer detection and treatment depend on the discovery of specific genes that cause cancer. The classification of genetic mutations was initially done manually. However, this process relies on pathologists and can be a time-consuming task. Therefore, to improve the precision of clinical interpretation, researchers have developed computational algorithms that leverage next-generation sequencing technologies for automated mutation analysis. This paper utilized four deep learning classification models with training collections of biomedical texts. These models comprise bidirectional encoder representations from transformers for Biomedical text mining (BioBERT), a specialized language model implemented for biological contexts. Impressive results in multiple tasks, including text classification, language inference, and question answering, can be obtained by simply adding an extra layer to the BioBERT model. Moreover, bidirectional encoder representations from transformers (BERT), long short-term memory (LSTM), and bidirectional LSTM (BiLSTM) have been leveraged to produce very good results in categorizing genetic mutations based on textual evidence. The dataset used in the work was created by Memorial Sloan Kettering Cancer Center (MSKCC), which contains several mutations. Furthermore, this dataset poses a major classification challenge in the Kaggle research prediction competitions. In carrying out the work, three challenges were identified: enormous text length, biased representation of the data, and repeated data instances. Based on the commonly used evaluation metrics, the experimental results show that the BioBERT model outperforms other models with an F1 score of 0.87 and 0.850 MCC, which can be considered as improved performance compared to similar results in the literature that have an F1 score of 0.70 achieved with the BERT model.
PubMed: 38912449
DOI: 10.1016/j.heliyon.2024.e32279 -
Clinics in Dermatology Jun 2024Artificial Intelligence (AI) has evolved to become a significant force in various domains, including medicine. We explore the role of AI in pathology, with a specific...
Artificial Intelligence (AI) has evolved to become a significant force in various domains, including medicine. We explore the role of AI in pathology, with a specific focus on dermatopathology and neoplastic dermatopathology. AI, encompassing Machine Learning (ML) and Deep Learning (DL), has demonstrated its potential in tasks ranging from diagnostic applications on Whole Slide Imaging (WSI) to predictive and prognostic functions in skin pathology. In dermatopathology, studies have assessed AI's ability to identify skin lesions, classify melanomas, and improve diagnostic accuracy. Results indicate that AI, particularly Convolutional Neural Networks (CNNs), can outperform human pathologists in terms of sensitivity and specificity. Moreover, AI aids in predicting disease outcomes, identifying aggressive tumors, and differentiating between various skin conditions. Neoplastic dermatopathology showcases AI's prowess in classifying melanocytic lesions, discriminating between melanomas and nevi, and aiding dermatopathologists in making accurate diagnoses. Studies emphasize the reproducibility and diagnostic aid that AI provides, especially in challenging cases. In inflammatory and lymphoproliferative dermatopathology, limited research exists, but studies show attempts to use AI to differentiate conditions like Mycosis Fungoides and eczema. While some results are promising, further exploration is needed in these areas. We highlight the extraordinary interest AI has garnered in the scientific community and its potential to assist clinicians and pathologists. Despite the advancements, we have stress edthe importance of collaboration between medical professionals, computer scientists, bioinformaticians, and engineers to harness AI's benefits while acknowledging its limitations and risks. The integration of AI into dermatopathology holds great promise, positioning it as a valuable tool rather than as a replacement for human expertise.
PubMed: 38909860
DOI: 10.1016/j.clindermatol.2024.06.010 -
BMJ Open Jun 2024The underdevelopment of preterm infants can lead to delayed progression through key early milestones. Demonstration of safe oral feeding skills, constituting proper...
INTRODUCTION
The underdevelopment of preterm infants can lead to delayed progression through key early milestones. Demonstration of safe oral feeding skills, constituting proper suck-swallow reflex are requirements for discharge from the neonatal intensive care unit (NICU) to ensure adequate nutrition acquisition. Helping an infant develop these skills can be draining and emotional for both families and healthcare staff involved in the care of preterm infants with feeding difficulties. Currently, there are no systematic reviews evaluating both family and healthcare team perspectives on aspects of oral feeding. Thus, we first aim to evaluate the current knowledge surrounding the perceptions, experiences and needs of families with preterm babies in the context of oral feeding in the NICU. Second, we aim to evaluate the current knowledge surrounding the perceptions, experiences and needs of healthcare providers (physicians, advanced practice providers, nurses, dietitians, speech-language pathologists and occupational therapists) in the context of oral feeding in the NICU.
METHODS AND ANALYSIS
A literature search will be conducted in multiple electronic databases from their inception, including PubMed, CINHAL, Embase, the Cochrane Central Register for Controlled Trials and PsycINFO. No restrictions will be applied based on language or data of publication. Two authors will screen the titles and abstracts and then review the full text for the studies' inclusion in the review. The data will be extracted into a pilot-tested data collection sheet by three independent authors. To evaluate the quality, reliability and relevance of the included studies, the Critical Appraisal Skills Programme checklist will be used. The overall evidence will be assessed using the Grading of Recommendation Assessment, Development and Evaluation criteria. We will report the results of the systematic review by following the Enhancing Transparency in Reporting the synthesis of Qualitative research checklist.
ETHICS AND DISSEMINATION
Ethical approval of this project is not required as this is a systematic review using published and publicly available data and will not involve contact with human subjects. Findings will be published in a peer-reviewed journal.
PROSPERO REGISTRATION NUMBER
CRD42023479288.
Topics: Humans; Intensive Care Units, Neonatal; Infant, Newborn; Systematic Reviews as Topic; Infant, Premature; Qualitative Research; Health Personnel; Family; Research Design
PubMed: 38908851
DOI: 10.1136/bmjopen-2024-084884 -
A deep learning approach for automatic recognition of abnormalities in the cytoplasm of neutrophils.Computers in Biology and Medicine Jun 2024This study aims to develop and evaluate NeuNN, a system based on convolutional neural networks (CNN) and generative adversarial networks (GAN) for the automatic...
BACKGROUND AND OBJECTIVES
This study aims to develop and evaluate NeuNN, a system based on convolutional neural networks (CNN) and generative adversarial networks (GAN) for the automatic identification of normal neutrophils and those containing several types of inclusions or showing hypogranulation.
METHODS
From peripheral blood smears, a set of 5605 digital images was obtained with neutrophils belonging to seven categories: Normal neutrophils (NEU), Hypogranulated (HYP) or containing cryoglobulins (CRY), Döhle bodies (DB), Howell-Jolly body-like inclusions (HJBLI), Green-blue inclusions of death (GBI) and phagocytosed bacteria (BAC). The dataset utilized in this study has been made publicly available. The class of GBI was augmented using synthetic images generated by GAN. The NeuNN classification model is based on an EfficientNet-B7 architecture trained from scratch.
RESULTS
NeuNN achieved an overall performance of 94.3% accuracy on the test data set. Performance metrics, including sensitivity, specificity, precision, F1-Score, Jaccard index, and Matthews correlation coefficient indicated overall values of 94%, 99.1%, 94.3%, 94.3%, 89.6%, and 93.6%, respectively.
CONCLUSIONS
The proposed approach, combining data augmentation and classification techniques, allows for automated identification of morphological findings in neutrophils, such us inclusions or hypogranulation. The system can be used as a support tool for clinical pathologists to detect these specific abnormalities with clinical relevance.
PubMed: 38905894
DOI: 10.1016/j.compbiomed.2024.108691 -
Frontiers in Medicine 2024Burkitt Lymphoma (BL) is a highly treatable cancer. However, delayed diagnosis of BL contributes to high mortality in BL endemic regions of Africa. Lack of enough...
Burkitt Lymphoma (BL) is a highly treatable cancer. However, delayed diagnosis of BL contributes to high mortality in BL endemic regions of Africa. Lack of enough pathologists in the region is a major reason for delayed diagnosis. The work described in this paper is a proof-of-concept study to develop a targeted, open access AI tool for screening of histopathology slides in suspected BL cases. Slides were obtained from a total of 90 BL patients. 70 Tonsillectomy samples were used as controls. We fine-tuned 6 pre-trained models and evaluated the performance of all 6 models across different configurations. An ensemble-based consensus approach ensured a balanced and robust classification. The tool applies novel features to BL diagnosis including use of multiple image magnifications, thus enabling use of different magnifications of images based on the microscope/scanner available in remote clinics, composite scoring of multiple models and utilizing MIL with weak labeling and image augmentation, enabling use of relatively low sample size to achieve good performance on the inference set. The open access model allows free access to the AI tool from anywhere with an internet connection. The ultimate aim of this work is making pathology services accessible, efficient and timely in remote clinics in regions where BL is endemic. New generation of low-cost slide scanners/microscopes is expected to make slide images available immediately for the AI tool for screening and thus accelerate diagnosis by pathologists available locally or online.
PubMed: 38903819
DOI: 10.3389/fmed.2024.1345611 -
ArXiv Apr 2024Whole Slide Images (WSI), obtained by high-resolution digital scanning of microscope slides at multiple scales, are the cornerstone of modern Digital Pathology. However,...
Whole Slide Images (WSI), obtained by high-resolution digital scanning of microscope slides at multiple scales, are the cornerstone of modern Digital Pathology. However, they represent a particular challenge to AI-based/AI-mediated analysis because pathology labeling is typically done at slide-level, instead of tile-level. It is not just that medical diagnostics is recorded at the specimen level, the detection of oncogene mutation is also experimentally obtained, and recorded by initiatives like The Cancer Genome Atlas (TCGA), at the slide level. This configures a dual challenge: a) accurately predicting the overall cancer phenotype and b) finding out what cellular morphologies are associated with it at the tile level. To address these challenges, a weakly supervised Multiple Instance Learning (MIL) approach was explored for two prevalent cancer types, Invasive Breast Carcinoma (TCGA-BRCA) and Lung Squamous Cell Carcinoma (TCGA-LUSC). This approach was explored for tumor detection at low magnification levels and TP53 mutations at various levels. Our results show that a novel additive implementation of MIL matched the performance of reference implementation (AUC 0.96), and was only slightly outperformed by Attention MIL (AUC 0.97). More interestingly from the perspective of the molecular pathologist, these different AI architectures identify distinct sensitivities to morphological features (through the detection of Regions of Interest, RoI) at different amplification levels. Tellingly, TP53 mutation was most sensitive to features at the higher applications where cellular morphology is resolved.
PubMed: 38903738
DOI: No ID Found -
Global Advances in Integrative Medicine... 2024Authoritative research demonstrating efficacy of traditional dysphagia therapy for Head & Neck Cancer (HNC) patients is limited. A 2019 survey reported...
BACKGROUND
Authoritative research demonstrating efficacy of traditional dysphagia therapy for Head & Neck Cancer (HNC) patients is limited. A 2019 survey reported speech-language-pathologists (SLPs) have started using Manual Therapy (MT) to prevent or rehabilitate dysphagia in HNC patients. This application of MT is supported theoretically but no research has established efficacy. Further, specific contents of MT protocols employed in this setting remain unknown.
OBJECTIVES
In the absence of HNC dysphagia specific MT protocols, this study aimed to better understand MT protocols employed by SLPs to prevent and treat dysphagia in HNC patients during and after Radiation Therapy (RT).
METHODS
An internet-based questionnaire for SLPs who use MT with HNC patients was developed and tested for face/content validity. It was sent to SLPs practicing in the USA, twice, through three national listservs (ASHA-SIG13, ASHA-SIG3, University of Iowa Voiceserv).
RESULTS
Of 64 respondents, 44 completed the survey. Of the 44, 15(34%) provided proactive MT during RT, 37(84%) provided proactive MT after RT (to prevent dysphagia), and 44(100%) provided reactive MT after RT (to treat dysphagia). 40(91%) were trained in MT through a CE course and 25(57%) had HNC-specific MT training. The most common MT techniques were laryngeal manipulation (LM) and myofascial release (MFR). During RT, MT protocols are gentler and highly tailored, with simple home programs of mild intensity. After RT, protocols are more regimented and aggressive, but still highly customized, with more diverse home programs of at least moderate intensity.
CONCLUSION
MT for HNC patients lacks a standard protocol or approach, but MFR and LM, or components of those techniques, are used most frequently. Given the frequency with which MFR and LM are employed to treat dysphagia during and post-RT, and the lack of empirical evidence supporting or refuting their use, a collaboratively designed RCT is warranted to establish the safety and efficacy of MT for HNC patients.
PubMed: 38903482
DOI: 10.1177/27536130241263349 -
Modern Pathology : An Official Journal... Jun 2024Nephrogenic adenoma is a benign, reactive lesion seen predominantly in the urinary bladder and often associated with an antecedent inflammation, instrumentation, or...
Nephrogenic adenoma is a benign, reactive lesion seen predominantly in the urinary bladder and often associated with an antecedent inflammation, instrumentation, or operative history. Its histopathological diversity can create diagnostic dilemmas and pathologists utilize morphological evaluation along with available immunohistochemical markers to navigate these challenges. Immunohistochemical assays currently do not designate or specify nephrogenic adenoma's potential putative cell of origin. Leveraging single-cell RNA sequencing technology, we nominated a principal cell collecting duct marker, L1 cell adhesion molecule (L1CAM), as a potential biomarker for nephrogenic adenoma. Immunohistochemical characterization revealed L1CAM to be positive in all 35 (100%) patient samples of nephrogenic adenoma; negative expression was seen in the benign urothelium, benign prostatic glands, urothelial carcinoma in situ, prostatic adenocarcinoma, majority of high-grade urothelial carcinoma, and metastatic urothelial carcinoma. In the study, we also utilized single-cell RNA sequencing to nominate a novel compendium of biomarkers specific for proximal tubule, loop of Henle, and distal tubule (including principal and intercalated cells) which can be used to perform nephronal mapping utilizing RNA in situ hybridization and immunohistochemistry technology. Employing this technique on nephrogenic adenoma we found enrichment of both principal cell marker L1CAM and, the proximal tubule types-A and -B cells markers, PDZKI1P1 and PIGR respectively. The cell type markers for the intercalated cell of distal tubules (LINC01187 and FOXI1), and the loop of Henle (UMOD and IRX5), were found to be uniformly absent in nephrogenic adenoma. Overall, our findings show that based on cell type-specific implications of L1CAM expression, the shared expression pattern of L1CAM between distal tubule principal cell (P) cells and nephrogenic adenoma. L1CAM expression will be of potential value in assisting surgical pathologists towards a diagnosis of nephrogenic adenoma in challenging patient samples.
PubMed: 38901674
DOI: 10.1016/j.modpat.2024.100540 -
CoDAS 2024To map the vocal risk in professional classical singers, analyzing their self-assessment of voice and self-perception of singing voice handicap and vocal fatigue.
PURPOSE
To map the vocal risk in professional classical singers, analyzing their self-assessment of voice and self-perception of singing voice handicap and vocal fatigue.
METHODS
The study sample comprised of 52 professional classical choir singers, aged 31 to 72 years. They answered an online questionnaire in Google Forms, addressing their characterization, self-assessment of voice, the Voice Handicap Index-10 (VHI-10), Classical Singing Handicap Index (CSHI), and Vocal Fatigue Index (VFI).
RESULTS
The mean self-assessment of voice was between "Good" and "Very good" (1.2). The mean total VHI-10 score was 1.35, which is below the cutoff. The mean total CSHI score was 10.04. The mean total VFI score was 10.83, near the cutoff value. Classical singers who use their voice to give examples to students in their classes had higher scores in VHI-10 (p = 0.013), VFI voice restriction (p = 0.011), and VFI total score (p = 0.015). Besides, classical singers who already visited a Speech-Language Pathologist for voice problems had higher scores in VFI voice restriction (p = 0.040) and VFI recovery with voice rest (p = 0.019), in addition to correlations between instrument scores.
CONCLUSION
Professional classical singers did not have voice handicaps. However, their self-perception of vocal fatigue was more present when the singing voice was used, such as giving examples with their own voice in class. Having had voice problems and visited a Speech-Language Pathologist in the past led to a greater perception of vocal recovery with rest.
Topics: Humans; Voice Quality; Singing; Middle Aged; Adult; Voice Disorders; Male; Self Concept; Female; Aged; Surveys and Questionnaires; Occupational Diseases; Self-Assessment; Disability Evaluation
PubMed: 38896630
DOI: 10.1590/2317-1782/20242023088pt -
Frontiers in Oncology 2024Breast cancer (BC) is the leading cause of female cancer mortality and is a type of cancer that is a major threat to women's health. Deep learning methods have been used...
Breast cancer (BC) is the leading cause of female cancer mortality and is a type of cancer that is a major threat to women's health. Deep learning methods have been used extensively in many medical domains recently, especially in detection and classification applications. Studying histological images for the automatic diagnosis of BC is important for patients and their prognosis. Owing to the complication and variety of histology images, manual examination can be difficult and susceptible to errors and thus needs the services of experienced pathologists. Therefore, publicly accessible datasets called BreakHis and invasive ductal carcinoma (IDC) are used in this study to analyze histopathological images of BC. Next, using super-resolution generative adversarial networks (SRGANs), which create high-resolution images from low-quality images, the gathered images from BreakHis and IDC are pre-processed to provide useful results in the prediction stage. The components of conventional generative adversarial network (GAN) loss functions and effective sub-pixel nets were combined to create the concept of SRGAN. Next, the high-quality images are sent to the data augmentation stage, where new data points are created by making small adjustments to the dataset using rotation, random cropping, mirroring, and color-shifting. Next, patch-based feature extraction using Inception V3 and Resnet-50 (PFE-INC-RES) is employed to extract the features from the augmentation. After the features have been extracted, the next step involves processing them and applying transductive long short-term memory (TLSTM) to improve classification accuracy by decreasing the number of false positives. The results of suggested PFE-INC-RES is evaluated using existing methods on the BreakHis dataset, with respect to accuracy (99.84%), specificity (99.71%), sensitivity (99.78%), and F1-score (99.80%), while the suggested PFE-INC-RES performed better in the IDC dataset based on F1-score (99.08%), accuracy (99.79%), specificity (98.97%), and sensitivity (99.17%).
PubMed: 38894870
DOI: 10.3389/fonc.2024.1300997