AI-enabled precision evaluation of adrenal masses: radiomics, deep learning, and explainable imaging biomarkers

Radiomics and artificial intelligence in pituitary adenomas (PitNETs): from imaging biomarkers to clinical translation.

Pituitary neuroendocrine tumors (PitNETs) are common intracranial neoplasms with heterogeneous hormonal activity, invasiveness, and treatment response. Conventional MRI is central to diagnosis, but is limited in quantifying tumor heterogeneity and predicting clinically relevant features such as consistency, molecular subtype, proliferation, and clinical outcomes. To review current evidence on MRI-based radiomics and artificial intelligence (AI) in PitNETs, focusing on clinical applications, methodological quality, and future integration into precision medicine. Narrative review of studies published between 2019 and 2025 evaluating radiomics, machine learning, and deep learning applied to PitNETs, highlighting tumor consistency, molecular and histological subtypes, proliferation, invasiveness, treatment response, recurrence, visual outcomes, and differential diagnosis of sellar lesions. Radiomics has been applied across the PitNET clinical trajectory. Texture- and shape-based features from T2-weighted and multiparametric MRI predict intraoperative tumor consistency with AUCs often > 0.80, outperforming conventional radiology. Radiomic signatures allow non-invasive differentiation of functional vs. non-functional adenomas, somatotroph granulation patterns, silent corticotroph adenomas, prolactinomas, and prediction of Ki-67 and PIT-1 expression. Models also predict cavernous sinus invasion, postoperative regrowth, recurrence, visual outcomes, and treatment response, including dopamine-agonist therapy. Differential diagnosis of hypophysitis and Rathke's cleft cyst has also been explored. Methodological quality remains heterogeneous, with frequent single-center, retrospective designs, limited external validation, and suboptimal adherence to reporting guidelines. Radiomics and AI show promise for risk stratification and personalized therapy in PitNETs, particularly for predicting tumor consistency, molecular subtypes, and recurrence. Clinical implementation requires standardized imaging protocols, multicenter datasets, reproducible segmentation, interpretable models, and prospective validation.

EP183 - ECE_3184 - Artificial intelligence in adrenal imaging: detection and segmentation of adrenal glands

Accurate visualization of the adrenal glands is crucial for the evaluation of adrenal pathology. However, their small size, variable shape, and proximity to other retroperitoneal structures make automated analysis challenging. Artificial intelligence (AI) tools capable of detecting and segmenting adrenal glands could significantly improve workflow efficiency and lay the groundwork for future tumor characterization. At the current stage of the project, we aim to develop and validate an AI-based algorithm for automated detection and 3D segmentation of adrenal glands in non-contrast CT scans. This constitutes a foundational step for subsequent modules that will analyze adrenal lesions. A multidisciplinary team from the Medical University of Warsaw and Warsaw University of Technology is collaborating to build a comprehensive dataset of anonymized abdominal CT scans. Using state-of-the-art deep learning architectures, we are training models to precisely identify and segment both adrenal glands, generating accurate three-dimensional reconstructions. The performance of the model is evaluated based on segmentation accuracy and anatomical consistency. The AI algorithm successfully detects and segments adrenal glands in three dimensions, offering a robust and scalable tool for future applications in adrenal imaging. This stage represents a critical foundation for further development of AI systems aimed at lesion detection and classification in adrenal pathology.

Artificial intelligence in thyroid ultrasound: clinical applications and perspectives

This review summarizes AI applications in thyroid ultrasound, including image preprocessing, nodule segmentation, quantitative feature analysis, benign-malignant differentiation, TIRADS optimization and automated reporting, and highlights AI’s potential in enhancing diagnostic consistency and accuracy.

ARTIFICIAL INTELLIGENCE IN THE DIAGNOSIS OF CLINICALLY SIGNIFICANT PROSTATE CANCER: A SYSTEMATIC REVIEW

Introduction: Accurate detection of clinically significant prostate cancer (csPCa) is critical for optimizing treatment strategies and reducing overdiagnosis of indolent disease. Artificial intelligence (AI), particularly deep learning algorithms integrated with multiparametric magnetic resonance imaging (mpMRI) and digital pathology, has emerged as a transformative tool in urological oncology. Objective: To systematically review and synthesize the current clinical evidence regarding the diagnostic performance, accuracy, and clinical utility of AI models compared with standard clinical pathways in identifying csPCa. Evidence Acquisition: A systematic search of the PubMed, Embase, and Cochrane Library databases was conducted for peer-reviewed literature published between January 2018 and May 2026. Studies evaluating AI algorithms (machine learning or deep learning) for csPCa detection using mpMRI, histopathology, or biomarker inputs were included. PRISMA guidelines were followed. Evidence Synthesis: Data from 24 high-quality prospective and retrospective studies were analyzed. AI models utilizing convolutional neural networks (CNNs) for mpMRI interpretation demonstrated an area under the receiver operating characteristic curve (AUC) ranging from 0.84 to 0.92, comparable to or exceeding that of experienced uroradiologists. In histopathology, deep learning systems achieved up to 98% sensitivity in identifying Gleason patterns, substantially reducing inter-observer variability. Integration of multimodal data (imaging + genomics + clinical biomarkers) yielded the highest diagnostic precision, significantly reducing unnecessary biopsies by 25–35%. Conclusions: AI algorithms exhibit robust diagnostic accuracy for csPCa detection, matching expert clinicians and offering significant potential to standardize prostate cancer care. Future efforts must focus on large-scale external validation across diverse healthcare systems and prospective clinical trials to establish long-term clinical utility.

An Explainable Machine Learning Framework for Early Detection of Brain Tumours with Statistical Analysis of Clinical and Imaging Data

Early and accurate detection of brain tumors is critical for improving patient outcomes, yet diagnostic delays and interpretability gaps limit the clinical adoption of artificial intelligence (AI) systems. This study proposes an explainable machine learning framework that integrates clinical and imaging data for early detection of brain tumors. Using a retrospective cohort of 1,248 patients, we developed and evaluated baseline statistical models, ensemble methods, and deep learning architectures, with systematic incorporation of SHAP values, Grad-CAM heatmaps, and patient-specific explanations. The hybrid model achieved an AUC-ROC of 0.97, accuracy of 93.2%, and well-calibrated predictions, outperforming imaging-only and tabular baselines. Explainability outputs demonstrated high concordance with radiologist annotations and were rated as clinically plausible. The framework maintained robust performance across tumor types, age groups, and imaging modalities, including CT-only cases. These findings support the feasibility of trustworthy AI-assisted diagnostics in neuro-oncology, particularly for resource-constrained settings. Future work should focus on prospective validation, human-factors evaluation, and integration with molecular data to further enhance clinical utility and generalizability. REFERENCES [1] World Health Organization, "Research and development landscape for childhood cancer: a 2023 perspective," World Health Organization, 2023. [2] U. Iqbal and Y. Bhutto, "Digital transformation through artificial intelligence and advance business analytic in American operational management," Journal of Theoretical and Applied Econometrics, vol. 3, no. 1, pp. 37-50, 2026. [3] Q. T. Ostrom, M. Price, C. Neff, G. Cioffi, K. A. Waite, C. Kruchko, and J. S. Barnholtz-Sloan, "CBTRUS statistical report: primary brain and other central nervous system tumours diagnosed in the United States in 2015--2019," Neuro-oncology, vol. 24, no. Supplement_5, pp. v1-v95, 2022. [4] G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, et al., "A survey on deep learning in medical image analysis," Medical image analysis, vol. 42, pp. 60-88, 2017. [5] E. J. Topol, "High-performance medicine: the convergence of human and artificial intelligence," Nature medicine, vol. 25, no. 1, pp. 44-56, 2019. [6] M. A. Rahman, M. I. K. Jabed, R. K. Devnath, C. M. Mehedi, M. Begum, and T. Mahmud, "MSRFF: An Interpretable CNN--Vision Transformer Framework for Diabetic Retinopathy Detection," in 2026 2nd International Conference on Computational Intelligence Approaches and Applications (ICCIAA), 2026, pp. 1-7. [7] B. J. Erickson, P. Korfiatis, Z. Akkus, and T. L. Kline, "Machine learning for medical imaging," radiographics, vol. 37, no. 2, pp. 505-515, 2017. [8] S. M. Lundberg and S. I. Lee, "A unified approach to interpreting model predictions," Advances in neural information processing systems, vol. 30, 2017. [9] W. Samek, G. Montavon, A. Vedaldi, L. K. Hansen, and K. R. Müller, Eds., Explainable AI: interpreting, explaining and visualizing deep learning. Springer Nature, 2019. [10] B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, J. Kirby, et al., "The multimodal brain tumour image segmentation benchmark (BRATS)," IEEE transactions on medical imaging, vol. 34, no. 10, pp. 1993-2024, 2014. [11] U. Iqbal, "AI-enhanced network optimization for electric vehicle charging infrastructure expansion in the United States using graph theory and demand analytics," Journal of Engineering and Computational Intelligence Review, vol. 2, no. 2, pp. 112-129, 2024. [12] M. I. K. Jabed, M. Imran, A. A. Khan, M. Mehedi, A. Islam, and R. Pervez, "Explainable Machine Learning Framework for Early Heart Disease Detection Using SMOTE and SHAP," Vascular and Endovascular Review, vol. 9, no. 1, pp. 316-324, 2026. [13] S. Bakas, M. Reyes, A. Jakab, S. Bauer, M. Rempfler, A. Crimi, et al., "Identifying the best machine learning algorithms for brain tumour segmentation, progression assessment, and overall survival prediction in the BRATS challenge," arXiv preprint arXiv:1811.02629, 2018. [14] R. Obuchowicz, J. Lasek, M. Wodziński, A. Piórkowski, M. Strzelecki, and K. Nurzynska, "Artificial intelligence-empowered radiology---current status and critical review," Diagnostics, vol. 15, no. 3, p. 282, 2025. [15] E. R. DeLong, D. M. DeLong, and D. L. Clarke-Pearson, "Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach," Biometrics, pp. 837-845, 1988. [16] National Comprehensive Cancer Network, "NCCN clinical practice guidelines in oncology: central nervous system cancers," National Comprehensive Care Network, Inc, 2017. [17] M. I. K. Jabed, M. R. M. Sirazy, S. Mandal, S. A. Akter, A. Hassan, and H. Esa, "Developing AI-based financial forecasting and cybersecurity systems for the US digital economy," Frontiers in Computer Science and Artificial Intelligence, vol. 5, no. 5, pp. 30-38, 2026. [18] A. Esteva, A. Robicquet, B. Ramsundar, V. Kuleshov, M. DePristo, K. Chou, et al., "A guide to deep learning in healthcare," Nature medicine, vol. 25, no. 1, pp. 24-29, 2019. [19] D. N. Louis, A. Perry, P. Wesseling, D. J. Brat, I. A. Cree, D. Figarella-Branger, et al., "The 2021 WHO classification of tumours of the central nervous system: a summary," Neuro-oncology, vol. 23, no. 8, pp. 1231-1251, 2021. [20] World Health Organization, "Measuring survival, driving change: advancing equity through the WHO Global Initiative for Childhood Cancer," World Health Organization, 2026. [21] Network, N. C. C., Clinical Practice Guidelines in Oncology: Central Nervous System Cancers. [22] M. A. Rahman, R. K. Devnath, S. B. Niloy, C. M. Mehedi, T. H. Chowdhury, and M. I. K. Jabed, "A Stacking Ensemble Framework for Predicting Employee Turnover: Explainable AI with SHAP," in 2025 IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS), 2025, pp. 1-6. [23] U. Iqbal, "AI-Driven Predictive Maintenance for U.S. Smart Manufacturing: Deep Learning Models for Equipment Failure Prediction and Operational Resilience," Journal of Engineering and Computational Intelligence Review, vol. 3, no. 1, 2025. [24] U. Iqbal, "AI-Powered Supplier Risk Intelligence: Predicting Financial and Geopolitical Supply Chain Disruptions in U.S. Critical Industries," Journal of Engineering and Computational Intelligence Review, vol. 3, no. 2, 2025. [25] D. Er, "Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach," Biometrics, vol. 44, pp. 837-845, 1988. [26] M. I. K. Jabed, "Stock market price prediction using machine learning techniques," American International Journal of Sciences and Engineering Research, vol. 7, no. 1, pp. 1-6, 2024. [27] A. Al Kium, S. Sarker, S. A. Shikha, M. A. T. Kamal, M. I. K. Jabed, N. K. Munifa, et al., "Health equity and digital disparities in cancer screening and cardiovascular care across socioeconomic and ethnic groups: a systematic review," Vascular and Endovascular Review, vol. 6, no. 2, pp. 35-44, 2023. [28] M. I. K. Jabed, M. A. Manzoor, F. M. Tofa, and M. H. Khan, "Interpretable Ensemble Learning Approach for Breast Cancer Diagnosis Using SHAP-Based Explainable AI," Journal of Computer Science and Technology Studies, vol. 8, no. 8, pp. 244-255, 2026. [29] U. Iqbal, S. Bekmez, and F. A. Qurashi, "Operational risk management through machine learning and business intelligence in US businesses," Spanish Journal of Innovation and Integrity, vol. 54, pp. 239-253, 2026. [30] A. Khan, F. Amin, and U. Imtiaz, "SENTINEL-WHEEL: Entropy-compressed edge intelligence for explainable self-healing cyber defense in connected vehicles," International Journal of Innovative Research, vol. 4, no. 01, pp. 227-237, 2026. [31] F. Amin, U. Imtiaz, and A. Khan, "FALCON-Guard: A lightweight explainable framework for real-time cyber threat detection and adaptive risk mitigation in intelligent driving networks," Multidisciplinary Research in Computing Information Systems, vol. 5, no. 12, pp. 1223-1235, 2025.

Transforming the Imaging Assessment of Thyroid Nodules with Artificial Intelligence: Advancements and Clinical Integration.