❌

Normal view

Received today — 7 October 2026 ⏭

A streamlined hybrid-capture and genome-wide multi-omic platform for highly sensitive ctDNA minimal residual disease monitoring

✇Omics in Hepatocellular
By: Tu Nguyen · Van-Anh Nguyen Hoang · Cang Huynh · Vy Nguyen · Son-Nam H Le · Quang Thinh Trac · Thien-Phuc Nguyen Hoang · Nhat-Anh Dao · Minh Tran Binh Nguyen · Nam Hb Tran · Duy Minh Phan · Hoa Giang · Hoai-Nghia Nguyen · Lan N Tu
5 October 2026 at 18:00

J Liq Biopsy. 2026 Sep 19;14:100496. doi: 10.1016/j.jlb.2026.100496. eCollection 2026 Dec.

ABSTRACT

BACKGROUND: Circulating tumor DNA (ctDNA) analysis has revolutionized minimal residual disease (MRD) monitoring, but conventional tumor-informed amplicon-based sequencing (AMP) is limited by the narrow variant capacity and diversity. Hybrid capture-based sequencing (HYB) is more versatile and enables both tumor-informed and tumor-naïve liquid biopsy profiling.

METHODS: We analytically validated the performance of our novel HYB workflow and VarSURE variant calling pipeline, using reference standards (n = 6), plasma samples of cancer patients (n = 75) and healthy donors (n = 90). Genome-wide (GW) non-mutation features including copy number alterations, fragmentomics, and end-motif signatures were also evaluated to enhance ctDNA-MRD detection. Clinical performance was directly compared against our legacy AMP method (K-TRACK, Gene Solutions), using pre-treatment blood samples across multiple cancers (n = 290) and longitudinal cohorts of colorectal cancer (CRC, n = 64), and hepatocellular carcinoma (HCC, n = 47).

RESULTS: Optimal parameters to maximize assay performance included single-stranded DNA ligation technology, cfDNA input ≥ 15 ng, post-UMI sequencing depth ≥ 2500X, and high number of tracked mutations. In the tumor-informed setting, the HYB workflow was modestly better than the AMP method in detection of pre-treatment ctDNA; addition of GW features was marginally beneficial except in lung cancer. Surveillance ctDNA determined by the HYB workflow had superior sensitivity to predict recurrence in both CRC (AMP: 90.0%, HYB: 100%) and HCC (AMP: 80.0%, HYB: 96.0%). In the tumor-naïve setting, the performance gap widened significantly, and the combined HYB and GW workflow showed the highest performance in baseline ctDNA detection across all cancers, and achieved sensitivity of 90.0% and 92.0% to detect recurrence in CRC and HCC respectively.

CONCLUSIONS: The new methodology offers a streamlined and scalable solution for both comprehensive liquid biopsy profiling and longitudinal MRD tracking in routine clinical practice.

PMID:42830887 | PMC:PMC13634064 | DOI:10.1016/j.jlb.2026.100496

A streamlined hybrid-capture and genome-wide multi-omic platform for highly sensitive ctDNA minimal residual disease monitoring

✇MRD
By: Tu Nguyen · Van-Anh Nguyen Hoang · Cang Huynh · Vy Nguyen · Son-Nam H Le · Quang Thinh Trac · Thien-Phuc Nguyen Hoang · Nhat-Anh Dao · Minh Tran Binh Nguyen · Nam Hb Tran · Duy Minh Phan · Hoa Giang · Hoai-Nghia Nguyen · Lan N Tu
5 October 2026 at 18:00

J Liq Biopsy. 2026 Sep 19;14:100496. doi: 10.1016/j.jlb.2026.100496. eCollection 2026 Dec.

ABSTRACT

BACKGROUND: Circulating tumor DNA (ctDNA) analysis has revolutionized minimal residual disease (MRD) monitoring, but conventional tumor-informed amplicon-based sequencing (AMP) is limited by the narrow variant capacity and diversity. Hybrid capture-based sequencing (HYB) is more versatile and enables both tumor-informed and tumor-naïve liquid biopsy profiling.

METHODS: We analytically validated the performance of our novel HYB workflow and VarSURE variant calling pipeline, using reference standards (n = 6), plasma samples of cancer patients (n = 75) and healthy donors (n = 90). Genome-wide (GW) non-mutation features including copy number alterations, fragmentomics, and end-motif signatures were also evaluated to enhance ctDNA-MRD detection. Clinical performance was directly compared against our legacy AMP method (K-TRACK, Gene Solutions), using pre-treatment blood samples across multiple cancers (n = 290) and longitudinal cohorts of colorectal cancer (CRC, n = 64), and hepatocellular carcinoma (HCC, n = 47).

RESULTS: Optimal parameters to maximize assay performance included single-stranded DNA ligation technology, cfDNA input ≥ 15 ng, post-UMI sequencing depth ≥ 2500X, and high number of tracked mutations. In the tumor-informed setting, the HYB workflow was modestly better than the AMP method in detection of pre-treatment ctDNA; addition of GW features was marginally beneficial except in lung cancer. Surveillance ctDNA determined by the HYB workflow had superior sensitivity to predict recurrence in both CRC (AMP: 90.0%, HYB: 100%) and HCC (AMP: 80.0%, HYB: 96.0%). In the tumor-naïve setting, the performance gap widened significantly, and the combined HYB and GW workflow showed the highest performance in baseline ctDNA detection across all cancers, and achieved sensitivity of 90.0% and 92.0% to detect recurrence in CRC and HCC respectively.

CONCLUSIONS: The new methodology offers a streamlined and scalable solution for both comprehensive liquid biopsy profiling and longitudinal MRD tracking in routine clinical practice.

PMID:42830887 | PMC:PMC13634064 | DOI:10.1016/j.jlb.2026.100496

Received — 8 April 2026 ⏭

Optimizing Neurorobot Policy under Limited Demonstration Data through Preference Regret

✇cs.AI, q-bio.NC updates on arXiv.org
By: Viet Dung Nguyen · Yuhang Song · Anh Nguyen · Jamison Heard · Reynold Bailey · Alexander Ororbia
7 April 2026 at 12:00
arXiv:2604.03523v1 Announce Type: cross Abstract: Robot reinforcement learning from demonstrations (RLfD) assumes that expert data is abundant; this is usually unrealistic in the real world given data scarcity as well as high collection cost. Furthermore, imitation learning algorithms assume that the data is independently and identically distributed, which ultimately results in poorer performance as gradual errors emerge and compound within test-time trajectories. We address these issues by introducing the "master your own expertise" (MYOE) framework, a self-imitation framework that enables robotic agents to learn complex behaviors from limited demonstration data samples. Inspired by human perception and action, we propose and design what we call the queryable mixture-of-preferences state space model (QMoP-SSM), which estimates the desired goal at every time step. These desired goals are used in computing the "preference regret", which is used to optimize the robot control policy. Our experiments demonstrate the robustness, adaptability, and out-of-sample performance of our agent compared to other state-of-the-art RLfD schemes. The GitHub repository that supports this work can be found at: https://github.com/rxng8/neurorobot-preference-regret-learning.
Received — 11 March 2026 ⏭

MedSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering

✇cs.AI, q-bio.NC updates on arXiv.org
By: Trong-Thang Pham · Loc Nguyen · Anh Nguyen · Hien Nguyen · Ngan Le
10 March 2026 at 12:00
arXiv:2603.07066v1 Announce Type: cross Abstract: Generative diffusion models are increasingly used for medical imaging data augmentation, but text prompting cannot produce causal training data. Re-prompting rerolls the entire generation trajectory, altering anatomy, texture, and background. Inversion-based editing methods introduce reconstruction error that causes structural drift. We propose MedSteer, a training-free activation-steering framework for endoscopic synthesis. MedSteer identifies a pathology vector for each contrastive prompt pair in the cross-attention layers of a diffusion transformer. At inference time, it steers image activations along this vector, generating counterfactual pairs from scratch where the only difference is the steered concept. All other structure is preserved by construction. We evaluate MedSteer across three experiments on Kvasir v3 and HyperKvasir. On counterfactual generation across three clinical concept pairs, MedSteer achieves flip rates of 0.800, 0.925, and 0.950, outperforming the best inversion-based baseline in both concept flip rate and structural preservation. On dye disentanglement, MedSteer achieves 75% dye removal against 20% (PnP) and 10% (h-Edit). On downstream polyp detection, augmenting with MedSteer counterfactual pairs achieves ViT AUC of 0.9755 versus 0.9083 for quantity-matched re-prompting, confirming that counterfactual structure drives the gain. Code is at link https://github.com/phamtrongthang123/medsteer
Received — 5 March 2026 ⏭

Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tuan-Anh Vu · Duc Thanh Nguyen · Qing Guo · Nhat Chung · Binh-Son Hua · Ivor W. Tsang · Sai-Kit Yeung
5 March 2026 at 13:00
arXiv:2312.17505v2 Announce Type: replace-cross Abstract: Text-to-image diffusion techniques have shown exceptional capabilities in producing high-quality, dense visual predictions from open-vocabulary text. This indicates a strong correlation between visual and textual domains in open concepts and that diffusion-based text-to-image models can capture rich and diverse information for computer vision tasks. However, we found that those advantages do not hold for learning of features of camouflaged individuals because of the significant blending between their visual boundaries and their surroundings. In this paper, while leveraging the benefits of diffusion-based techniques and text-image models in open-vocabulary settings, we aim to address a challenging problem in computer vision: open-vocabulary camouflaged instance segmentation (OVCIS). Specifically, we propose a method built upon state-of-the-art diffusion empowered by open-vocabulary to learn multi-scale textual-visual features for camouflaged object representation learning. Such cross-domain representations are desirable in segmenting camouflaged objects where visual cues subtly distinguish the objects from the background, and in segmenting novel object classes which are not seen in training. To enable such powerful representations, we devise complementary modules to effectively fuse cross-domain features, and to engage relevant features towards respective foreground objects. We validate and compare our method with existing ones on several benchmark datasets of camouflaged and generic open-vocabulary instance segmentation. The experimental results confirm the advances of our method over existing ones. We believe that our proposed method would open a new avenue for handling camouflages such as computer vision-based surveillance systems, wildlife monitoring, and military reconnaissance.
There are no more articles
❌