arXiv Machine Learning September 25, 2026 By Hai Pham Ngoc

TAM-Chain: Multi-Scale Thyroid Cytology Classification via Absorbing Markov Chains and Shannon Entropy Uncertainty Quantification for False-Negative Suppression and Domain-Shift Adaptation

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

safety

arXiv AI

Jul 15

Calibrated Selective Prediction Using Deep Ensembles for ROI-Based Thyroid Nodule Ultrasound Classification Under Dataset Shift: A Retrospective Evaluation

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

arXiv AI

Aug 14

Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting

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

agents computer-vision multimodal

arXiv AI

Aug 5

CorePath: A Breast-Specialized Pathology Foundation Model for Core Needle Biopsy Diagnosis and Risk-Controlled Report Generation

arXiv:2608. 03079v1 Announce Type: cross Abstract: Breast core needle biopsy (CNB) is central to breast cancer diagnosis yet remains challenging because limited tissue sampling, lesion heterogeneity, and subtle morphologic overlap can obscure subtype distinctions.

By Ting Yin, Danning Li, Chen Shu, Xiaoxia Yao, Boyu Fu, Yujing Chang, Tianyu Shi, Mengna Feng, Jie Chen, Jing Fu, Xiuli Xiao, Tianlin Li, Mumin Shao, Jiaxin Bi, Wenchuan Zhang, Xiaoyan Wu, Xiao Han, Zhang Zhang, Yuhao Yi, Hong Bu

llms fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Sep 23

Radiomics--Foundation Fusion for Interpretable RCC Classification: Internal Benchmarking and Exploratory External Transfer

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

benchmarks safety

arXiv AI

Aug 17

CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification

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

rag multimodal safety

arXiv Machine Learning

Aug 19

MagViT: Interpretable Multi-Magnification Transformers with Patient-Level Model Selection for Breast Histopathology

MagViT is an interpretable multi‑magnification transformer that classifies breast histopathology images by extracting representations from four BreakHis magnifications (40X, 100X, 200X, 400X) and fusing them with a learnable, scale‑gated mechanism that can mask missing scales. The model selects the most accurate architectural branch at the patient level using five‑fold cross‑validation, achieving high performance on BreakHis (mean image accuracy 0.9191, patient accuracy 0.9643, macro‑F1 0.9042) and demonstrating preliminary cross‑dataset generalization on BUSI and IDC. Grad‑CAM visualizations confirm that the network focuses on diagnostically relevant regions across magnifications.

By Nabil Ashab, Soumit Kumar Kundu, Saif Mahmud Parvez, Shahadat Hossain Sohag, Bidhan Biswas, Nazmus Subha

llms computer-vision

One email a morning, machine-written

Related stories

Calibrated Selective Prediction Using Deep Ensembles for ROI-Based Thyroid Nodule Ultrasound Classification Under Dataset Shift: A Retrospective Evaluation

Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting

CorePath: A Breast-Specialized Pathology Foundation Model for Core Needle Biopsy Diagnosis and Risk-Controlled Report Generation

Radiomics--Foundation Fusion for Interpretable RCC Classification: Internal Benchmarking and Exploratory External Transfer

CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification

MagViT: Interpretable Multi-Magnification Transformers with Patient-Level Model Selection for Breast Histopathology