Browsing by Research Output - Author "Abbasi, Syed Muhammad Tariq"

ABSTRACTManually segmenting brain tumors in magnetic resonance imaging (MRI) is a time‐consuming task that requires years of professional experience and clinical expertise. To address this challenge, researchers have proposed artificial intelligence–based strategies that enable quick and automatic segmentation of brain tumors. These AI techniques are crucial for the early identification of brain tumors, leading to earlier diagnoses and significant therapeutic benefits. convolutional neural networks (CNN), vision transformers (ViT), and other automated approaches that leverage machine learning and deep learning techniques have demonstrated effectiveness in diagnosing tumor type, size, and location. Consequently, brain tumor segmentation has emerged as a prominent issue in medical image analysis. This study aims to provide a concise review of MRI techniques and examine popular approaches for segmenting brain tumors. It highlights notable advancements in this field over the past several years. To ensure comprehensive coverage of technical topics, including network architecture design, segmentation in unbalanced settings, and multi‐modality processes, over 200 scholarly publications have been meticulously selected for discussion. Based on this literature review, CNN‐based methods and hybrid approaches have shown exceptional results in segmenting brain tumors from MRI images. Additionally, our study outlines the challenges and potential avenues for future research in brain tumor segmentation techniques.

AbstractAbsolute quantification of biological samples provides precise numerical expression levels, enhancing accuracy, and performance for rare templates. Current methodologies, however, face challenges‐flow cytometers are costly and complex, whereas fluorescence imaging, relying on software or manual counting, is time‐consuming and error‐prone. It is presented that Deep‐qGFP, a deep learning‐aided pipeline for the automated detection and classification of green fluorescent protein (GFP) labeled microreactors, enables real‐time absolute quantification. This approach achieves an accuracy of 96.23% and accurately measures the sizes and occupancy status of microreactors using standard laboratory fluorescence microscopes, providing precise template concentrations. Deep‐qGFP demonstrates remarkable speed, quantifying over 2000 microreactors across ten images in just 2.5 seconds, with a dynamic range of 56.52–1569.43 copies µL−1. The method demonstrates impressive generalization capabilities, successfully applied to various GFP‐labeling scenarios, including droplet‐based, microwell‐based, and agarose‐based applications. Notably, Deep‐qGFP is the first all‐in‐one image analysis algorithm successfully implemented in droplet digital polymerase chain reaction (PCR), microwell digital PCR, droplet single‐cell sequencing, agarose digital PCR, and bacterial quantification, without requiring transfer learning, modifications, or retraining. This makes Deep‐qGFP readily applicable in biomedical laboratories and holds potential for broader clinical applications.

We present an innovative deep learning-aided paradigm that enables real-time and automated detection and classification of GFP (Green fluorescence protein)-labeled microreactor, overcoming the limitations of conventional methods.