Muhammad Khalid Khan Niazi
YOU?
Author Swipe
View article: Hyperparameter Optimization and Reproducibility in Deep Learning Model Training
Hyperparameter Optimization and Reproducibility in Deep Learning Model Training Open
Reproducibility remains a critical challenge in foundation model training for histopathology, often hindered by software randomness, hardware non-determinism, and inconsistent hyperparameter reporting. To investigate these issues, we train…
View article: Streamline pathology foundation model by cross-magnification distillation
Streamline pathology foundation model by cross-magnification distillation Open
Foundation models (FM) have transformed computational pathology but remain computationally prohibitive for clinical deployment due to their massive parameter counts and high-magnification processing requirements. Here, we introduce XMAG, a…
View article: LUCID: Intelligent Informative Frame Selection in Otoscopy for Enhanced Diagnostic Utilitys
LUCID: Intelligent Informative Frame Selection in Otoscopy for Enhanced Diagnostic Utilitys Open
Accurate diagnosis of middle ear diseases, such as acute otitis media (AOM), remains a clinical challenge due to the reliance on subjective visual assessment through otoscopy. While deep learning has shown promise in improving diagnostic a…
View article: Predicting Neoadjuvant Chemotherapy Response in Triple-Negative Breast Cancer Using Pre-Treatment Histopathologic Images
Predicting Neoadjuvant Chemotherapy Response in Triple-Negative Breast Cancer Using Pre-Treatment Histopathologic Images Open
Triple-negative breast cancer (TNBC) remains a major clinical challenge due to its aggressive behavior and lack of targeted therapies. Accurate early prediction of response to neoadjuvant chemotherapy (NACT) is essential for guiding person…
View article: Towards a Formal Specification for Self-organized Shape Formation in Swarm Robotics
Towards a Formal Specification for Self-organized Shape Formation in Swarm Robotics Open
The self-organization of robots for the formation of structures and shapes is a stimulating application of the swarm robotic system. It involves a large number of autonomous robots of heterogeneous behavior, coordination among them, and th…
View article: HistoChat: Instruction-tuning multimodal vision language assistant for colorectal histopathology on limited data
HistoChat: Instruction-tuning multimodal vision language assistant for colorectal histopathology on limited data Open
View article: Artificial intelligence in breast pathology: Overview and recent updates
Artificial intelligence in breast pathology: Overview and recent updates Open
Breast cancer remains a major global health concern where timely and accurate pathologic diagnosis is critical for effective management. The traditional reliance on expert interpretation of histopathology is increasingly challenged by risi…
View article: Predicting Neoadjuvant Chemotherapy Response in Triple-Negative Breast Cancer Using Pre-Treatment Histopathologic Images
Predicting Neoadjuvant Chemotherapy Response in Triple-Negative Breast Cancer Using Pre-Treatment Histopathologic Images Open
Triple-negative breast cancer (TNBC) remains a major clinical challenge due to its aggressive behavior and lack of targeted therapies. Accurate early prediction of response to neoadjuvant chemotherapy (NACT) is essential for guiding person…
View article: Developing approaches to incorporate donor-lung computed tomography images into machine learning models to predict severe primary graft dysfunction after lung transplantation
Developing approaches to incorporate donor-lung computed tomography images into machine learning models to predict severe primary graft dysfunction after lung transplantation Open
Primary graft dysfunction (PGD) is a common complication after lung transplantation associated with poor outcomes. Although risk factors have been identified, the complex interactions between clinical variables affecting PGD risk are not w…
View article: Modeling Key Success Factors in the Development of Iran's Cultural Infrastructure (Case Study: The Movie Theater Industry)
Modeling Key Success Factors in the Development of Iran's Cultural Infrastructure (Case Study: The Movie Theater Industry) Open
View article: An interpretable framework for inter-observer agreement measurements in TILs scoring on histopathological breast images: A proof-of-principle study
An interpretable framework for inter-observer agreement measurements in TILs scoring on histopathological breast images: A proof-of-principle study Open
Breast cancer, a widespread and life-threatening disease, necessitates precise diagnostic tools for improved patient outcomes. Tumor-Infiltrating Lymphocytes (TILs), reflective of the immune response against cancer cells, are pivotal in un…
View article: Exploring the host response in infected lung organoids using NanoString technology: A statistical analysis of gene expression data
Exploring the host response in infected lung organoids using NanoString technology: A statistical analysis of gene expression data Open
In this study, we used a three-dimensional airway “organ tissue equivalent” (OTE) model at an air-liquid interface (ALI) to mimic human airways. We investigated the effects of three viruses (Influenza A virus (IAV), Human metapneumovirus (…
View article: Classification-based pathway analysis using GPNet with novel <i>P</i>-value computation
Classification-based pathway analysis using GPNet with novel <i>P</i>-value computation Open
Pathway analysis plays a critical role in bioinformatics, enabling researchers to identify biological pathways associated with various conditions by analyzing gene expression data. However, the rise of large, multi-center datasets has high…
View article: Deep Learning Model for Predicting Lung Adenocarcinoma Recurrence from Whole Slide Images
Deep Learning Model for Predicting Lung Adenocarcinoma Recurrence from Whole Slide Images Open
Lung cancer is the leading cause of cancer-related death in the United States. Lung adenocarcinoma (LUAD) is one of the most common subtypes of lung cancer that can be treated with resection. While resection can be curative, there is a sig…
View article: Machine learning-based analysis of Ebola virus' impact on gene expression in nonhuman primates
Machine learning-based analysis of Ebola virus' impact on gene expression in nonhuman primates Open
Introduction This study introduces the Supervised Magnitude-Altitude Scoring (SMAS) methodology, a novel machine learning-based approach for analyzing gene expression data from non-human primates (NHPs) infected with Ebola virus (EBOV). By…
View article: Gene pointNet for tumor classification
Gene pointNet for tumor classification Open
The rising incidence of cancer underscores the imperative for innovative diagnostic and prognostic methodologies. This study delves into the potential of RNA-Seq gene expression data to enhance cancer classification accuracy. Introducing a…
View article: Cross-Attention-Based Saliency Inference for Predicting Cancer Metastasis on Whole Slide Images
Cross-Attention-Based Saliency Inference for Predicting Cancer Metastasis on Whole Slide Images Open
Although multiple instance learning (MIL) methods are widely used for automatic tumor detection on whole slide images (WSI), they suffer from the extreme class imbalance WSIs containing small tumors where the tumor may include only a few i…
View article: B cells in perivascular and peribronchiolar granuloma-associated lymphoid tissue and B-cell signatures identify asymptomatic <i>Mycobacterium tuberculosis</i> lung infection in Diversity Outbred mice
B cells in perivascular and peribronchiolar granuloma-associated lymphoid tissue and B-cell signatures identify asymptomatic <i>Mycobacterium tuberculosis</i> lung infection in Diversity Outbred mice Open
Because most humans resist Mycobacterium tuberculosis infection, there is a paucity of lung samples to study. To address this gap, we infected Diversity Outbred mice with M. tuberculosis and studied the lungs of mice in different disease s…
View article: A comparative analysis of RNA-Seq and NanoString technologies in deciphering viral infection response in upper airway lung organoids
A comparative analysis of RNA-Seq and NanoString technologies in deciphering viral infection response in upper airway lung organoids Open
In this study, we delved into the comparative analysis of gene expression data across RNA-Seq and NanoString platforms. While RNA-Seq covered 19,671 genes and NanoString targeted 773 genes associated with immune responses to viruses, our p…
View article: Gene PointNet for Tumor Classification
Gene PointNet for Tumor Classification Open
The rising incidence of cancer underscores the imperative for innovative diagnostic and prognostic methodologies. This study delves into the potential of RNA-Seq gene expression data to enhance cancer classification accuracy. Introducing a…
View article: Predicting response to neoadjuvant chemotherapy for colorectal liver metastasis using deep learning on prechemotherapy cross‐sectional imaging
Predicting response to neoadjuvant chemotherapy for colorectal liver metastasis using deep learning on prechemotherapy cross‐sectional imaging Open
Background and Objectives Deep learning models (DLMs) are applied across domains of health sciences to generate meaningful predictions. DLMs make use of neural networks to generate predictions from discrete data inputs. This study employs …
View article: Enhancing colorectal cancer tumor bud detection using deep learning from routine H&E-stained slides
Enhancing colorectal cancer tumor bud detection using deep learning from routine H&E-stained slides Open
Tumor budding refers to a cluster of one to four tumor cells located at the tumor-invasive front. While tumor budding is a prognostic factor for colorectal cancer, counting and grading tumor budding are time consuming and not highly reprod…
View article: Few-shot tumor bud segmentation using generative model in colorectal carcinoma
Few-shot tumor bud segmentation using generative model in colorectal carcinoma Open
Current deep learning methods in histopathology are limited by the small amount of available data and time consumption in labeling the data. Colorectal cancer (CRC) tumor budding quantification performed using H&E-stained slides is crucial…
View article: Adapting SAM to histopathology images for tumor bud segmentation in colorectal cancer
Adapting SAM to histopathology images for tumor bud segmentation in colorectal cancer Open
Colorectal cancer (CRC) is the third most common cancer in the United States. Tumor Budding (TB) detection and quantification are crucial yet labor-intensive steps in determining the CRC stage through the analysis of histopathology images.…
View article: Translating prognostic quantification of c-MYC and BCL2 from tissue microarrays to whole slide images in diffuse large B-cell lymphoma using deep learning
Translating prognostic quantification of c-MYC and BCL2 from tissue microarrays to whole slide images in diffuse large B-cell lymphoma using deep learning Open
View article: Machine Learning-Based Analysis of Ebola Virus' Impact on Gene Expression in Nonhuman Primates
Machine Learning-Based Analysis of Ebola Virus' Impact on Gene Expression in Nonhuman Primates Open
This study introduces the Supervised Magnitude-Altitude Scoring (SMAS) methodology, a machine learning-based approach, for analyzing gene expression data obtained from nonhuman primates (NHPs) infected with Ebola virus (EBOV). We utilize a…
View article: Attention2Minority: A salient instance inference-based multiple instance learning for classifying small lesions in whole slide images
Attention2Minority: A salient instance inference-based multiple instance learning for classifying small lesions in whole slide images Open
Multiple instance learning (MIL) models have achieved remarkable success in analyzing whole slide images (WSIs) for disease classification problems. However, with regard to giga-pixel WSI classification problems, current MIL models are oft…
View article: Cross-attention-based saliency inference for predicting cancer metastasis on whole slide images
Cross-attention-based saliency inference for predicting cancer metastasis on whole slide images Open
Although multiple instance learning (MIL) methods are widely used for automatic tumor detection on whole slide images (WSI), they suffer from the extreme class imbalance within the small tumor WSIs. This occurs when the tumor comprises onl…
View article: Perivascular and peribronchiolar granuloma-associated lymphoid tissue and B-cell gene expression pathways identify asymptomatic<i>Mycobacterium tuberculosis</i>lung infection in Diversity Outbred mice
Perivascular and peribronchiolar granuloma-associated lymphoid tissue and B-cell gene expression pathways identify asymptomatic<i>Mycobacterium tuberculosis</i>lung infection in Diversity Outbred mice Open
Humans are highly genetically diverse, and most are resistant to Mycobacterium tuberculosis. However, lung tissue from genetically resistant humans is not readily available to identify potential mechanisms of resistance. To address this, w…
View article: Association of CT-Derived Skeletal Muscle and Adipose Tissue Metrics with Frailty in Older Adults
Association of CT-Derived Skeletal Muscle and Adipose Tissue Metrics with Frailty in Older Adults Open