❌

Normal view

Received today — 7 October 2026 ⏭

Authors’ Reply: Clarifying the Comparative Interpretation and Clinical Implications of Radiomics-Based AI for Pathological Response Prediction

✇Journal of Medical Internet Research
By: Ziqi Jiang · Yuan Xu · Shuyu Jia · Hongsheng Liu
7 October 2026 at 02:45
This author reply responds to a Letter to the Editor commenting on our systematic review and meta‑analysis evaluating radiomics‑based artificial intelligence for predicting pathological response following neoadjuvant immunochemotherapy in non‑small‑cell lung cancer. We clarify several methodological points raised in the comment, including patient versus assessment counts in a cited study, cross‑study versus within‑patient comparisons of diagnostic metrics, and the sensitivity‑specificity trade‑off between artificial‑intelligence models and conventional response criteria (RECIST 1.1, PERCIST). We acknowledge two textual errors in the original discussion and confirm they do not affect primary pooled analyses. We further elaborate on eligibility constraints, heterogeneity across prediction time points, definitions of pathological complete response, and reporting standards such as DECIDE‑AI. Our core conclusion remains unchanged: radiomics‑based artificial intelligence shows promising predictive performance with a potential sensitivity advantage over RECIST 1.1, though definitive evidence requires prospective same‑patient, same‑time‑point validation studies.
Received — 18 September 2026 ⏭

Non-Invasive Assessment of Microvascular Invasion Risk in Hepatocellular Carcinoma Using Liquid Biopsy: Translational Insights and Clinical Implications

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Dengyuan Xue · Xinyu Gao · Qixingmao Zhang · Hongxin Li · Mengli Chen · Xiuzhi Duan · Xuchu Wang · Pan Yu · Zhihua Tao · Xiaoxue Cheng
15 September 2026 at 18:00

Diagnostics (Basel). 2026 Aug 22;16(17):2686. doi: 10.3390/diagnostics16172686.

ABSTRACT

Microvascular invasion (MVI) is a critical prognostic indicator for recurrence and survival in hepatocellular carcinoma (HCC); however, its accurate preoperative assessment remains clinically challenging. Postoperative histopathology is subject to sampling bias and time delays, while traditional imaging techniques lack the molecular specificity required to predict MVI. Liquid biopsy, through the analysis of circulating tumor DNA (ctDNA), circulating tumor cells (CTCs), circulating tumor RNA (ctRNA), and extracellular vesicles (EVs), provides a minimally invasive approach for capturing tumor-derived molecular and cellular signals associated with vascular invasion. This narrative review comprehensively summarizes the current evidence linking these four liquid biopsy analyte categories to MVI in HCC, evaluates their integration into multi-omics predictive models, including multi-marker, clinicopathological-integrated, and imaging-integrated strategies, and proposes an evidence-level framework that categorizes blood biomarkers according to the strength of their support for MVI prediction, distinguishing direct histopathological validation from indirect associations with aggressive tumor biology. Key challenges are critically examined, including the variable specificity of individual biomarkers for MVI, the lack of head-to-head comparative studies, the absence of standardized pre-analytical and analytical protocols, and the methodological limitations of current prediction models. As a narrative review, this work does not employ systematic review methodology, and the evidence synthesis should be interpreted accordingly. The review provides a framework for understanding how liquid biopsy-based MVI risk stratification may inform surgical and perioperative decision-making following prospective validation.

PMID:42739118 | PMC:PMC13564874 | DOI:10.3390/diagnostics16172686

Received — 27 May 2026 ⏭

Refined immune-based molecular subtypes of gastric cancer: Integrating mismatch repair status and tumor microenvironment for enhanced immunotherapy prediction

✇Omics in Gastric
By: Ke Shen · Yanqiang Zhang · Zhiqin Wang · Ruixing Xu · Jintao He · Mengya Zhou · Yiming Lu · Danni Zhu · Yizhou Wei · Weiwei Zhu · Qing Yang · Zhiyuan Xu · Can Hu · Siwei Pan · Xiangdong Cheng
18 May 2026 at 18:00

Chin J Cancer Res. 2026 Apr 30;38(2):234-251. doi: 10.21147/j.issn.1000-9604.2026.02.09.

ABSTRACT

OBJECTIVE: Gastric cancer (GC) is heterogeneous, and current mismatch repair (MMR)-based classifications incompletely predict response to immune checkpoint inhibitors (ICIs).

METHODS: RNA sequencing (RNA-seq) and immune infiltration profiles from 189 resected GC were used to derive four refined immune-MMR subtypes (R1-R4) by integrating MMR status, survival, and tumor microenvironment (TME) features. Multi-omics profiling and pathway analysis defined subtype biology. External transcriptomic cohorts and an ICI-treated cohort were classified with Nearest Template Prediction (NTP). Immune response-associated genes were identified from responder vs. non-responder comparisons within the ICI-sensitive subtype and validated by multiplex immunohistochemistry (mIHC).

RESULTS: R1 showed the best prognosis and highest immunotherapy response with objective response rate (ORR) 54.5%, while R4 had the worst prognosis. R2 represented an immune-unresponsive deficient mismatch repair (dMMR) subset, and R3 captured an immune-active proficient mismatch repair (pMMR) subgroup with moderate therapy sensitivity. Multi-omics integration revealed subtype-specific pathways (e.g., ECM remodeling in R1, metabolic reprogramming in R2). Reclassification of pMMR tumors based on transcriptional similarity to R1 identified a New R3 subset with enhanced immune features and higher ICI response. Eight immune response-associated genes (e.g., CXCL10, CXCL11, ELN, GAD1, IL32, MT1E, OR2I1P, SLC3A1) were identified and validated by mIHC for predictive relevance.

CONCLUSIONS: This immune-based molecular framework refines risk stratification beyond conventional MMR categories, identifies ICI-sensitive subsets among both dMMR and pMMR tumors, and proposes candidate biomarkers for patient selection.

PMID:42147371 | PMC:PMC13171420 | DOI:10.21147/j.issn.1000-9604.2026.02.09

Received — 8 April 2026 ⏭

Open3DBench: Open-Source Benchmark for 3D-IC Backend Implementation and PPA Evaluation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yunqi Shi · Chengrui Gao · Wanqi Ren · Peng Xie · Siyuan Xu · Ke Xue · Mingxuan Yuan · Chao Qian · Zhi-Hua Zhou
7 April 2026 at 12:00
arXiv:2503.12946v2 Announce Type: replace-cross Abstract: This work introduces Open3DBench, an open-source 3D-IC backend implementation benchmark built upon the OpenROAD-flow-scripts framework, enabling comprehensive evaluation of power, performance, area, and thermal metrics. Our proposed flow supports modular integration of 3D partitioning, placement, 3D routing, RC extraction, and thermal simulation, aligning with advanced 3D flows that rely on commercial tools and in-house scripts. We present two foundational 3D placement algorithms: Open3D-Tiling, which emphasizes regular macro placement, and Open3D-DMP, which enhances wirelength optimization through cross-die co-placement with analytical placer DREAMPlace. Experimental results show significant improvements in area (51.19%), wirelength (24.06%), timing (30.84%), and power (5.72%) compared to 2D flows. The results also highlight that better wirelength does not necessarily lead to PPA gain, emphasizing the need of developing PPA-driven methods. Open3DBench offers a standardized, reproducible platform for evaluating 3D EDA methods, effectively bridging the gap between open-source tools and commercial solutions in 3D-IC design.
Received — 2 April 2026 ⏭

Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Control

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zelin Tao · Zeran Su · Peiran Liu · Jingkai Sun · Wenqiang Que · Jiahao Ma · Jialin Yu · Jiahang Cao · Pihai Sun · Hao Liang · Gang Han · Wen Zhao · Zhiyuan Xu · Jian Tang · Qiang Zhang · Yijie Guo
1 April 2026 at 12:00
arXiv:2603.27756v2 Announce Type: replace-cross Abstract: Achieving general-purpose humanoid control requires a delicate balance between the precise execution of commanded motions and the flexible, anthropomorphic adaptability needed to recover from unpredictable environmental perturbations. Current general controllers predominantly formulate motion control as a rigid reference-tracking problem. While effective in nominal conditions, these trackers often exhibit brittle, non-anthropomorphic failure modes under severe disturbances, lacking the generative adaptability inherent to human motor control. To overcome this limitation, we propose Heracles, a novel state-conditioned diffusion middleware that bridges precise motion tracking and generative synthesis. Rather than relying on rigid tracking paradigms or complex explicit mode-switching, Heracles operates as an intermediary layer between high-level reference motions and low-level physics trackers. By conditioning on the robot's real-time state, the diffusion model implicitly adapts its behavior: it approximates an identity map when the state closely aligns with the reference, preserving zero-shot tracking fidelity. Conversely, when encountering significant state deviations, it seamlessly transitions into a generative synthesizer to produce natural, anthropomorphic recovery trajectories. Our framework demonstrates that integrating generative priors into the control loop not only significantly enhances robustness against extreme perturbations but also elevates humanoid control from a rigid tracking paradigm to an open-ended, generative general-purpose architecture.

Dual function of DOT1L suppresses tumor cell-intrinsic immunogenicity in hepatocellular carcinoma

✇Oncogene - Issue - nature.com science feeds
By: Siyuan Xu · Ruijie Gong · Songchen Liu · Jianhua Wang · Yijie Shen · Chuxuan Peng · Qin Feng · Min Luo · Fei Lan · Jia Fan · Jiabin Cai · Xianjiang Lan
31 March 2026 at 08:00

Oncogene, Published online: 31 March 2026; doi:10.1038/s41388-026-03744-6

Dual function of DOT1L suppresses tumor cell-intrinsic immunogenicity in hepatocellular carcinoma
Received — 26 March 2026 ⏭

MedCausalX: Adaptive Causal Reasoning with Self-Reflection for Trustworthy Medical Vision-Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jianxin Lin · Chunzheng Zhu · Peter J. Kneuertz · Yunfei Bai · Yuan Xue
25 March 2026 at 12:00
arXiv:2603.23085v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have enabled interpretable medical diagnosis by integrating visual perception with linguistic reasoning. Yet, existing medical chain-of-thought (CoT) models lack explicit mechanisms to represent and enforce causal reasoning, leaving them vulnerable to spurious correlations and limiting their clinical reliability. We pinpoint three core challenges in medical CoT reasoning: how to adaptively trigger causal correction, construct high-quality causal-spurious contrastive samples, and maintain causal consistency across reasoning trajectories. To address these challenges, we propose MedCausalX, an end-to-end framework explicitly models causal reasoning chains in medical VLMs. We first introduce the CRMed dataset providing fine-grained anatomical annotations, structured causal reasoning chains, and counterfactual variants that guide the learning of causal relationships beyond superficial correlations. Building upon CRMed, MedCausalX employs a two-stage adaptive reflection architecture equipped with $\langle$causal$\rangle$ and $\langle$verify$\rangle$ tokens, enabling the model to autonomously determine when and how to perform causal analysis and verification. Finally, a trajectory-level causal correction objective optimized through error-attributed reinforcement learning refines the reasoning chain, allowing the model to distinguish genuine causal dependencies from shortcut associations. Extensive experiments on multiple benchmarks show that MedCausalX consistently outperforms state-of-the-art methods, improving diagnostic consistency by +5.4 points, reducing hallucination by over 10 points, and attaining top spatial grounding IoU, thereby setting a new standard for causally grounded medical reasoning.
Received — 14 March 2026 ⏭

Advancing Automated Algorithm Design via Evolutionary Stagewise Design with LLMs

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chen Lu · Ke Xue · Chengrui Gao · Yunqi Shi · Siyuan Xu · Mingxuan Yuan · Chao Qian · Zhi-Hua Zhou
10 March 2026 at 12:00
arXiv:2603.07970v1 Announce Type: new Abstract: With the rapid advancement of human science and technology, problems in industrial scenarios are becoming increasingly challenging, bringing significant challenges to traditional algorithm design. Automated algorithm design with LLMs emerges as a promising solution, but the currently adopted black-box modeling deprives LLMs of any awareness of the intrinsic mechanism of the target problem, leading to hallucinated designs. In this paper, we introduce Evolutionary Stagewise Algorithm Design (EvoStage), a novel evolutionary paradigm that bridges the gap between the rigorous demands of industrial-scale algorithm design and the LLM-based algorithm design methods. Drawing inspiration from CoT, EvoStage decomposes the algorithm design process into sequential, manageable stages and integrates real-time intermediate feedback to iteratively refine algorithm design directions. To further reduce the algorithm design space and avoid falling into local optima, we introduce a multi-agent system and a "global-local perspective" mechanism. We apply EvoStage to the design of two types of common optimizers: designing parameter configuration schedules of the Adam optimizer for chip placement, and designing acquisition functions of Bayesian optimization for black-box optimization. Experimental results across open-source benchmarks demonstrate that EvoStage outperforms human-expert designs and existing LLM-based methods within only a couple of evolution steps, even achieving the historically state-of-the-art half-perimeter wire-length results on every tested chip case. Furthermore, when deployed on a commercial-grade 3D chip placement tool, EvoStage significantly surpasses the original performance metrics, achieving record-breaking efficiency. We hope EvoStage can significantly advance automated algorithm design in the real world, helping elevate human productivity.
Received — 11 March 2026 ⏭

Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhengyi Guo · Wenpin Tang · Renyuan Xu
10 March 2026 at 12:00
arXiv:2602.05533v2 Announce Type: replace Abstract: We study conditional generation in diffusion models under hard constraints, where generated samples must satisfy prescribed events with probability one. Such constraints arise naturally in safety-critical applications and in rare-event simulation, where soft or reward-based guidance methods offer no guarantee of constraint satisfaction. Building on a probabilistic interpretation of diffusion models, we develop a principled conditional diffusion guidance framework based on Doob's h-transform, martingale representation and quadratic variation process. Specifically, the resulting guided dynamics augment a pretrained diffusion with an explicit drift correction involving the logarithmic gradient of a conditioning function, without modifying the pretrained score network. Leveraging martingale and quadratic-variation identities, we propose two novel off-policy learning algorithms based on a martingale loss and a martingale-covariation loss to estimate h and its gradient using only trajectories from the pretrained model. We provide non-asymptotic guarantees for the resulting conditional sampler in both total variation and Wasserstein distances, explicitly characterizing the impact of score approximation and guidance estimation errors. Numerical experiments demonstrate the effectiveness of the proposed methods in enforcing hard constraints and generating rare-event samples. The code of the numerical experiments can be found at https://github.com/ZhengyiGuo2002/CDG_Finance.
There are no more articles
❌