The paper introduces a clinical‑dictionary radiomic bottleneck model for classifying thyroid nodules from ultrasound images. It combines Family‑Aware Radiomic Learning to estimate measurements across feature families with Fidelity‑Guided Bottleneck Modeling to jointly optimize measurement estimation and classification while preserving measurement fidelity. The model decomposes decision evidence through a linear classifier, mapping feature contributions to clinical dictionary categories, and demonstrates competitive performance on ThyroidXL and TN3K datasets with interpretable case studies.
By Guibin Zhang, Weier Luo, Lei Cao
arXiv:2607. 12075v1 Announce Type: cross Abstract: Background: Deep learning models can classify thyroid nodules on ultrasound, but reliable clinical decision support also requires calibrated probabilities, uncertainty estimation, and selective referral, particularly under dataset shift.
By Md. Sadibul Hasan Sadib, Md. Mohayminul Mukit, Rahmatul Kabir Rasel Sarker, Tahmid Alam Tamim, Md. Monir Hossain Shimul
TAM-Chain is a multi‑scale thyroid cytology classification framework that uses Absorbing Markov Chains and Shannon Entropy to quantify uncertainty and dynamically decide when to stop processing and refer to a specialist. It processes images at 10×, 20×, and 40× magnifications, achieving a Macro F1 score of 0.9741 on an internal test set with a 0 % false‑negative rate, and maintains a Macro F1 of 0.7026 on an external validation set with severe domain shift. The method outperforms single‑magnification baselines by adaptively adjusting stopping steps and triggering specialist referrals, thereby reducing critical diagnostic errors.
By Hai Pham Ngoc
arXiv:2608. 10505v1 Announce Type: new Abstract: Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer no control over the sensitivity-specificity trade-off of their diagnostic content.
By Ying Jin, Noel C. F. Codella, John Corring, Mu Wei, Dinei Florencio, Eric Horvitz
This review examines the use of artificial intelligence and radiomics for diagnosing thyroid cancer, summarizing 42 studies that demonstrate the effectiveness of ultrasound-based radiomics in identifying malignancies. It highlights challenges such as interpretability, limited datasets, and operator dependence, and calls for standardization, prospective multicenter trials, and advances in explainable AI and personalized medicine. The authors emphasize that multidisciplinary collaboration and further algorithm refinement could enhance diagnostic accuracy and patient outcomes.
By Milad Yousefi, Hadi Vahedi, Shadi Farabi Maleki, Mahya Ahmadpour Youshanlui, Aida Jafari, Parisa Rostami, Kais I. Abdul-Lateef Al-Abdullah, Ryszard Tadeusiewicz, Pawel Plawiak, Roohallah Alizadehsani, Siamak Pedrammehr
Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer no control over the sensitivity-specificity trade-off of their diagnostic content. Such control is essential because clinical scenarios diverge: emergency triage prioritizes sensitivity to reduce missed findings, whereas confirmatory interpretation emphasizes specificity to limit unnecessary interventions.
arXiv:2608. 12590v1 Announce Type: new Abstract: Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation and provide limited support for clinical review.
By Haifan Gong, Shiyu Chen, Bodong Wang, Yuqi Wang, Shijie Wang, Guoliang You, Xinyu Xiong, Haowei Wang, Mingzhi Mao, Dexing Kong, Qinghua Liu, Wei Lou, Fei Chen, Guanbin Li
arXiv:2608. 13939v1 Announce Type: cross Abstract: Ultrasound is the primary imaging modality for assessing thyroid nodules, and the ACR TI-RADS framework standardizes diagnosis through five ultrasound feature categories that are aggregated into five risk levels (TR1-TR5).
By Bingxin Yu, Xueli Wang, Jerry Zhou, Wenyan Wang, Li Wen, Lan Huang, Xin Feng, Fengfeng Zhou, Kewei Li
arXiv:2609.26578v1 Announce Type: new
Abstract: Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced CT remains clinically challenging because clear cell...
By Yuan Liang, Fangyijie Wang, Kathleen M. Curran, Gu\'enol\'e Silvestre, Sourav Bhattacharjee, Abraham Campbell
The paper presents a method that derives BI‑RADS descriptors from breast MRI segmentation masks and uses a large language model to generate natural‑language rationales grounded in those descriptors. A BI‑RADS decision tree with eight quantitative radiomic measurements, lesion size, and component count informs the descriptors, which are then verbalised by the model. Applying this framework to 1,506 cases in the MAMA‑MIA dataset produced 3,012 reproducible BI‑RADS rationales with high faithfulness (99.98%) and counterfactual accuracy (99.3%).
By Hrishikesh Singh, Aarti Sharma, Divyanshu Kumar, Millie Pant
arXiv:2610.14151v1 Announce Type: cross
Abstract: Reliable probability estimates are important for the clinical interpretation of machine-learning classifiers, yet radiomics--image fusion models for...
By Yuan Liang, Morgan May, Abraham Campbell, Sourav Bhattacharjee, Simon Caton, Pierpaolo Dondio
arXiv:2607. 08084v1 Announce Type: cross Abstract: Radiomic features derived from medical images and segmentation masks are used to support decision making in clinical imaging pipelines.
By Matt Y. Cheung, Ashok Veeraraghavan, Guha Balakrishnan