The study evaluated whole‑slide image classifiers for gastric cancer across five Korean hospitals, using foundation‑model features and leave‑one‑hospital‑out validation. A hierarchical patch‑region‑slide graph aggregator (CHIME‑MIL) with site alignment and two‑scale fusion achieved a mean AUC of 0.837, outperforming six conventional attention and transformer aggregators that lacked these steps. However, when matched with the same alignment and fusion, CHIME‑MIL did not surpass simple attention‑based pooling, and global max pooling performed best (AUC 0.855). The alignment step, which subtracts each hospital’s mean feature vector without labels, enabled onboarding of a new hospital from only ten unlabeled slides but yielded only a modest 0.002 AUC improvement, and the model’s accuracy gains were inconsistent.
"whyItMatters":"The findings show that adding complex aggregation methods does not necessarily improve cross‑hospital discrimination, highlighting the importance of simpler, label‑free onboarding and calibration checks for deployable pathology systems."
By Nheng Vanchhay, Ali Hussain, Khan Ziaullah, Moon-Il Joo, Md Ariful Islam Mozumder, Rashedul Islam Sumon, Won-Ae Lee, Min-Sun Cho, Hyeong-Chan Shin, Yujun Park, Baek Hwan Cho, Nam-Hoon Cho, Heejung An, Heung-Kook Choi, Haeyoun Kang, Hyunki Kim, Hee Cheol Kim
The study evaluates EfficientNet variants B0–B7 for classifying retinal diseases from spectral-domain optical coherence tomography (SD‑OCT) images at a fixed 224×224 resolution. Eight ImageNet‑pretrained models were tested on the Kermany dataset, with training involving a frozen‑backbone head followed by partial fine‑tuning. Results show non‑monotonic accuracy, with B1 achieving the highest overall accuracy (96.95%) and best Drusen F1, while B7 offered a secondary accuracy gain at the cost of larger model size and CPU latency.
By Shkelqim Sherifi
arXiv:2606. 13135v1 Announce Type: cross Abstract: Purpose.
By Elena S. Kozachok, Sergey S. Seregin, Aleksandr V. Kozachok, Ilya P. Latyshev, Oleg I. Samovarov
arXiv:2609.15130v1 Announce Type: cross
Abstract: woma is a real-time foundation model for gastrointestinal endoscopy: a network trained without labels on about a million endoscopy frames, from which...
By Thang Tran, Lan Dang
The study evaluates the performance of the DINOv2 visual representation for classifying Trachomatous Inflammation-Follicular (TF) versus normal conjunctival images. Using 1,546 images processed by the OPTED pipeline, the authors compare six pretrained backbones and then test four lightweight adaptation methods on DINOv2 ViT-B/14. The best results—91.66% accuracy, 90.69% macro‑F1, and 96.06% AUC—were achieved with DINOv2 plus Efficient Channel Attention (ECA) and a focal‑plus‑center loss, though ECA’s benefit varied with the loss function.
By Kibrom Gebremedhin, Hadush Hailu, Bruk Gebregziabher, Yordanos Hailu
MultiAttenGastro is a plug‑and‑play attention framework that adds parallel 1‑D channel, 2‑D spatial, and 3‑D contextual heads to existing CNN and transformer backbones for gastrointestinal endoscopy classification. Across eight backbones and five public GI datasets, the framework improves performance on large‑gap datasets such as Kvasir‑Capsule but shows no benefit on small‑gap benchmarks like Kvasir‑v2, with mixed results elsewhere. Analysis using Centered Kernel Alignment indicates that the gains are linked to representational redundancy: low inter‑head redundancy under large domain gaps yields consistent improvements, while high redundancy under small gaps leads to losses.
By Sadhana Devarajan, Praveen Kumar Chandaliya, Dhruvin Jashvant Kumar Shah, Kishor Upla, Kiran Raja
Handcrafted preprocessing is widely employed in automated dermoscopic analysis to suppress imaging artifacts and enhance lesion visibility. Nevertheless, its actual contribution to modern real-time mo...
arXiv:2610.34529v1 Announce Type: cross
Abstract: Background/Objectives: Rapid differentiation of ischemic and hemorrhagic stroke subtypes is vital for acute management. Although current deep learnin...
By Tansel Uyar
CalibCause is a quality‑gated, interpretable deep learning framework for diabetic retinopathy grading that integrates visual explanations, label‑free image‑quality conditioning, knowledge distillation, and calibrated confidence with deferral. Using 51,310 fundus images from multiple datasets, the distilled student model achieved a quadratic weighted kappa of 0.863 and accuracy of 0.865 on pooled testing, while maintaining comparable performance across held‑out environments. The framework also demonstrated improved calibration (expected calibration error 0.025–0.036) and higher accuracy (up to 0.923) when deferring the least confident 20% of images.
By Sohaib Sulman, Muhammad Atif Saeed, Akhtar Jamil, Alaa Ali Hameed, Roland Aydin
arXiv:2608. 20154v1 Announce Type: new Abstract: Minimally invasive colorectal surgeries (MIS-CRS) are characterised by significant variability and inconsistent outcomes.
By Pietro Mascagni, Julia Alekseenko, Pooja P Jain, Marta Goglia, Andrea Balla, Ludovica Baldari, Gianfranco Silecchia, Claudio Fiorillo, Vincenzo Tondolo, Salvador Morales-Conde, Luigi Boni, Sergio Alfieri, Nicolas Padoy
arXiv:2610.08570v1 Announce Type: new
Abstract: Handcrafted preprocessing is widely employed in automated dermoscopic analysis to suppress imaging artifacts and enhance lesion visibility. Nevertheles...
By Truong Viet Vu, Nguyen Chi Hai, Nguyen Phuc Nguyen, Ngo Hoang Tu, Vo Nguyen Quoc Bao, Nguyen Thai Anh
arXiv:2608.22059v1 Announce Type: cross
Abstract: Pretrained image encoders are central to medical image classification, where expert annotation is costly and task-specific cohorts are often limited....
By Xingtao Lin, Hangqi Ren, Caiwan Sun, You Chen