End-to-End Multi-task Learning Architecture for Brain Tumor Analysis with Uncertainty Estimation in MRI Images DOI

Maria Nazir,

Sadia Shakil, Khurram Khurshid

et al.

Deleted Journal, Journal Year: 2024, Volume and Issue: unknown

Published: April 2, 2024

Brain tumors are a threat to life for every other human being, be it adults or children. Gliomas one of the deadliest brain with an extremely difficult diagnosis. The reason is their complex and heterogenous structure which gives rise subjective as well objective errors. Their manual segmentation laborious task due irregular appearance. To cater all these issues, lot research has been done going on develop AI-based solutions that can help doctors radiologists in effective diagnosis gliomas least errors, but end-to-end system still missing. An all-in-one framework proposed this research. developed multi-task learning (MTL) architecture feature attention module classify, segment, predict overall survival by leveraging relationships between similar tasks. Uncertainty estimation also incorporated into enhance confidence level healthcare practitioners. Extensive experimentation was performed using combinations MRI sequences. tumor (BraTS) challenge datasets 2019 2020 were used experimental purposes. Results best model four sequences show 95.1% accuracy classification, 86.3% dice score segmentation, mean absolute error (MAE) 456.59 prediction test data. It evident from results deep learning–based MTL models have potential automate whole analysis process give efficient inference time without intervention. quantification confirms idea more data improve generalization ability turn produce accurate less uncertainty. utilized clinical setup initial screening glioma patients.

Language: Английский

Vision transformer based classification of gliomas from histopathological images DOI
Evgin Göçeri

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 241, P. 122672 - 122672

Published: Nov. 24, 2023

Language: Английский

Citations

36
Revolutionizing Radiology With Artificial Intelligence DOI Open Access
Abhiyan Bhandari

Cureus, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 29, 2024

Artificial intelligence (AI) is rapidly transforming the field of radiology, offering significant advancements in diagnostic accuracy, workflow efficiency, and patient care. This article explores AI's impact on various subfields emphasizing its potential to improve clinical practices enhance outcomes. AI-driven technologies such as machine learning, deep natural language processing (NLP) are playing a pivotal role automating routine tasks, aiding early disease detection, supporting decision-making, allowing radiologists focus more complex challenges. Key applications AI radiology include improving image analysis through computer-aided diagnosis (CAD) systems, which detection abnormalities imaging, tumors. tools have demonstrated high accuracy analyzing medical images, integrating data from multiple imaging modalities CT, MRI, PET provide comprehensive insights. These facilitate personalized treatment planning complement radiologists' workflows. However, for be fully integrated into workflows, several challenges must addressed, including ensuring transparency how algorithms work, protecting data, avoiding biases that could affect diverse populations. Developing explainable systems can clearly show decisions made crucial, seamlessly fit existing systems. Collaboration between radiologists, developers, policymakers, alongside strong ethical guidelines regulatory oversight, will key implemented safely effectively practice. Overall, holds tremendous promise revolutionizing radiology. Through ability automate capabilities, streamline has significantly quality efficiency practices. Continued research, development, collaboration crucial unlocking full addressing accompany adoption.

Language: Английский

Citations

12
Advances in the Use of Deep Learning for the Analysis of Magnetic Resonance Image in Neuro-Oncology DOI Open Access
Carla Pitarch, Gülnur Ungan, Margarida Julià‐Sapé

et al.

Cancers, Journal Year: 2024, Volume and Issue: 16(2), P. 300 - 300

Published: Jan. 10, 2024

Machine Learning is entering a phase of maturity, but its medical applications still lag behind in terms practical use. The field oncological radiology (and neuro-oncology particular) at the forefront these developments, now boosted by success Deep-Learning methods for analysis images. This paper reviews detail some most recent advances use Deep this field, from broader topic development Machine-Learning-based analytical pipelines to specific instantiations neuro-oncology; latter including groundbreaking ultra-low magnetic resonance imaging.

Language: Английский

Citations

5
Combinations of Methodological Enhancements on the Predictive Ability of Machine Learning Models in Glioma Grading Classification DOI
Dana O. Mohamed,

May Ann Grace P. Palisoc,

Rui Tan

et al.

Smart innovation, systems and technologies, Journal Year: 2025, Volume and Issue: unknown, P. 285 - 297

Published: Jan. 1, 2025

Language: Английский

Citations

0
Potential of MR-based radiomics and optimized statistical machine learning in grading patients with glioma DOI Creative Commons

Mohamed N. Sultan,

Sherif Yehia, Magdy M. Khalil

et al.

The Egyptian Journal of Radiology and Nuclear Medicine, Journal Year: 2025, Volume and Issue: 56(1)

Published: March 17, 2025

Abstract Background Brain cancer is a global health concern, with significant morbidity and mortality worldwide. Distinguishing glioma grades vital for treatment, yet traditional methods like brain imaging biopsy have their own limitations. This study aimed to develop optimized classification predictive models distinguish grade II from III gliomas using statistical machine learning combined radiomic imaging. Methods A total of 135 MRI series tumors (68 67 III) were obtained two distinct public datasets. Every tumor underwent manual segmentation, preprocessing, cropping. large number wavelet-based, first-order, textural, shape characteristics then computed. Principal component analysis was used dimensionality reduction. Two feature selectors, namely K-best percentile employed. Twelve different supervised algorithms applied. selectors along hyperparameter optimization conducted. Results The top three performing linear discriminant (LDA), support vector machine, logistic regression. LDA the highest surpassing all other both selectors. Using selector, attained an area under receiver characteristic curve (AUROC) 0.96, accuracy 0.91, sensitivity 0.95, specificity 0.86. With it maintained strong performance AUROC 0.92, 0.89. Conclusions Statistical approaches significantly high discriminative power. interestingly outperformed others in accuracy, AUC, sensitivity, highlighting advanced capabilities versus gliomas.

Language: Английский

Citations

0
Artificial intelligence in cancer pathology: Applications, challenges, and future directions DOI Open Access

Jiu-Le Wang,

Teng Wang, Rui Han

et al.

CytoJournal, Journal Year: 2025, Volume and Issue: 22, P. 45 - 45

Published: April 19, 2025

The application of artificial intelligence (AI) in cancer pathology has shown significant potential to enhance diagnostic accuracy, streamline workflows, and support precision oncology. This review examines the current applications AI across various types, including breast, lung, prostate, colorectal cancer, where aids tissue classification, mutation detection, prognostic predictions. key technologies driving these advancements include machine learning, deep computer vision, which enable automated analysis histopathological images multi-modal data integration. Despite promising developments, challenges persist, ensuring privacy, improving model interpretability, meeting regulatory standards. Furthermore, this explores future directions AI-driven pathology, real-time diagnostics, explainable AI, global accessibility, emphasizing importance collaboration between pathologists. Addressing leveraging AI’s full could lead a more efficient, equitable, personalized approach care.

Language: Английский

Citations

0
Artificial Intelligence in Radiopharmaceutical Development DOI

J. Shanthalakshmi Revathy,

J. Mangaiyarkkarasi

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 295 - 310

Published: Feb. 28, 2025

AI has changed the way new radiopharmaceuticals are being developed, improved pharmacodynamics in precision medicine and made drug discovery more efficient. Radiopharmaceuticals play an important role both diagnostic imaging as well targeted therapy; however conventional development process is complex lengthy. Here does speed up through machine learning deep techniques, targets can be identified a shorter time, along with molecular designing of better radiolabeling methodology. These enhancements occur biomarker identification, selectivity, pharmacokinetics. In sciences, refines outlook definition, intensifies image reconstruction, optimizes dosing according to patient's characteristics. It also simplifies clinical trials pushing predictive analysis patient categorization. With help AI, will completely change concept healthcare, strengthen quality results obtained, create opportunities for global precise medicine.

Language: Английский

Citations

0
Evolving and Novel Applications of Artificial Intelligence in Cancer Imaging DOI Open Access
Mustaqueem Pallumeera,

Jonathan C. Giang,

Rajanbir Singh

et al.

Cancers, Journal Year: 2025, Volume and Issue: 17(9), P. 1510 - 1510

Published: April 30, 2025

Artificial intelligence (AI) is revolutionizing cancer imaging, enhancing screening, diagnosis, and treatment options for clinicians. AI-driven applications, particularly deep learning machine learning, excel in risk assessment, tumor detection, classification, predictive prognosis. Machine algorithms, especially frameworks, improve lesion characterization automated segmentation, leading to enhanced radiomic feature extraction delineation. Radiomics, which quantifies imaging features, offers personalized response predictions across various modalities. AI models also facilitate technological improvements non-diagnostic tasks, such as image optimization medical reporting. Despite advancements, challenges persist integrating into healthcare, tracking accurate data, ensuring patient privacy. Validation through clinician input multi-institutional studies essential safety model generalizability. This requires support from radiologists worldwide consideration of complex regulatory processes. Future directions include elaborating on existing optimizations, advanced techniques, improving patient-centric medicine, expanding healthcare accessibility. can enhance optimizing precision medicine outcomes. Ongoing multidisciplinary collaboration between radiologists, oncologists, software developers, bodies crucial AI's growing role clinical oncology. review aims provide an overview the applications oncologic while discussing their limitations.

Language: Английский

Citations

0
ResMT: A hybrid CNN-transformer framework for glioma grading with 3D MRI DOI

Honghao Cui,

Zhuoying Ruan,

Zhijian Xu

et al.

Computers & Electrical Engineering, Journal Year: 2024, Volume and Issue: 120, P. 109745 - 109745

Published: Sept. 27, 2024

Language: Английский

Citations

3
AI and Personalised Grading Criteria DOI
Sajeel Ahmed,

Abira Zaki,

Yongmei Bentley

et al.

Advances in educational technologies and instructional design book series, Journal Year: 2024, Volume and Issue: unknown, P. 85 - 113

Published: April 19, 2024

The chapters discuss the potential of artificial intelligence (AI) in transforming higher education assessment, grading, and feedback processes, enabling personalized interventions, data analysis, deeper insights into student performance. chapter discusses significance real-time learning education, focusing on virtual teaching platforms AI-powered assessment methodologies. It evaluates AI-based assessments, machine algorithms, natural language processing techniques.

Language: Английский

Citations

2