# Multiple Instance Learning

4 related articles

Subscribe to updates

arXiv Oct 14, 2026
Ultrasound diagnosis stops chasing average accuracy: multi-query attention keeps heterogeneous evidence, training-time regularization lifts sensitivity to 0.874
Patient-level ultrasound diagnosis has relied on a single attention bottleneck to aggregate multiple views, which dilutes sparse malignant cues and optimizes only global accuracy. C2LUE replaces that bottleneck with multi-query cross-attention, letting several learnable queries extract complementary morphological evidence, and adds a differentiable sensitivity-specificity geometric-mean regularizer during training. On biopsy-proven thyroid and breast ultrasound datasets, patient-level AUC reaches 0.932 and 0.936, with sensitivity rising to 0.874 and 0.876 at a moderate cost in specificity.
Patient-level ultrasound diagnosis has relied on a single attention bottleneck to aggregate multiple views, which dilutes sparse malignant cues and optimizes only global accuracy. C2LUE replaces that bottleneck with multi-query cross-attention, letting several learnable queries extract complementary morphological evidence, and adds a differentiable sensitivity-specificity geometric-mean regularizer during training. On biopsy-proven thyroid and breast ultrasound datasets, patient-level AUC reaches 0.932 and 0.936, with sensitivity rising to 0.874 and 0.876 at a moderate cost in specificity.
Chinese Academy of Sciences
Qin-Yi Zhang（First author）
C2LUE Patient-level ultrasound diagnosis Multi-query cross-attention Multiple Instance Learning DINOv3
medRxiv Oct 11, 2026
Ten microliters of unstained whole blood, imaged in 12 minutes: a three-class model flags sepsis at 100% sensitivity and 85.3% specificity
Remoscope images 10 microliters of unstained whole blood into 20,000 pictures in about 12 minutes, and a three-class model separated sepsis from non-infectious critical illness and healthy controls in 29 critically ill adults, reaching 100% sensitivity at 85.3% specificity when tuned for rule-out.
University of California, San Francisco
Nicholas Bratvold（First author）Paul M. Lebel（Corresponding author）
Remoscope Remo-ID Sepsis Diagnosis Multiple Instance Learning Label-free imaging cytometry
medRxiv Sep 30, 2026
Gated-attention multiple instance learning triages multi-center cervical cytology slides without per-cell labels, reaching 90.96% accuracy with MobileNetV2 and 80.43% balanced accuracy out-of-distribution with Xception
The work presents a weakly-supervised, detection-free multiple instance learning framework that uses dual-branch gated attention pooling to make slide-level predictions on whole-slide cervical cytology images, treating each slide as a bag of local instance patches so that single-cell bounding boxes or pixel-level annotations are not required; evaluated on internal multi-center cohorts (SIPaKMeD, Herlev, and CRIC) and on the unannotated, out-of-distribution Mendeley LBC validation cohort processed via an unsupervised marker-controlled watershed pipeline, it reports that the lightweight MobileNetV2 backbone optimizes in-distribution multi-center accuracy (90.96% accuracy, 0.9800 ROC-AUC) while the higher-capacity Xception provides better out-of-distribution robustness under domain shift (80.
The work presents a weakly-supervised, detection-free multiple instance learning framework that uses dual-branch gated attention pooling to make slide-level predictions on whole-slide cervical cytology images, treating each slide as a bag of local instance patches so that single-cell bounding boxes or pixel-level annotations are not required; evaluated on internal multi-center cohorts (SIPaKMeD, Herlev, and CRIC) and on the unannotated, out-of-distribution Mendeley LBC validation cohort processed via an unsupervised marker-controlled watershed pipeline, it reports that the lightweight MobileNetV2 backbone optimizes in-distribution multi-center accuracy (90.96% accuracy, 0.9800 ROC-AUC) while the higher-capacity Xception provides better out-of-distribution robustness under domain shift (80.
Muhimbili University of Health and Allied Sciences
Simeon Mayala（First author, Corresponding author）
Multiple Instance Learning Gated Attention Pooling Cervical Cytology Slide Triage
The Cleft Palate-Craniofacial Journal Sep 18, 2026
Artificial Intelligence-Based Hypernasality Diagnosis Using CAPS-A-AM Rated Speech Samples in Pediatric Velopharyngeal Dysfunction
In this prospective, single-center study, speech samples from 40 children aged 2 to 17 (including individuals with velopharyngeal dysfunction, conditions associated with VPD, and healthy participants) were collected during speech-language pathologist-guided evaluation with consensus CAPS-A-AM ratings, and mel spectrograms of high vowels /i/ and /u/ from sustained vowels, isolated words, and sentences were used to train logistic regression, an EfficientNet-V2-S attention multiple-instance-learning CNN, and a CNN-XGBoost hybrid for binary hypernasality classification at two CAPS-A-AM thresholds (absent 0 versus any hypernasality 1-4, and absent/borderline 0-1 versus mild-to-severe 2-4); multiple independent modeling approaches detected clinically rated hypernasality, with EfficientNet-V2-S a
In this prospective, single-center study, speech samples from 40 children aged 2 to 17 (including individuals with velopharyngeal dysfunction, conditions associated with VPD, and healthy participants) were collected during speech-language pathologist-guided evaluation with consensus CAPS-A-AM ratings, and mel spectrograms of high vowels /i/ and /u/ from sustained vowels, isolated words, and sentences were used to train logistic regression, an EfficientNet-V2-S attention multiple-instance-learning CNN, and a CNN-XGBoost hybrid for binary hypernasality classification at two CAPS-A-AM thresholds (absent 0 versus any hypernasality 1-4, and absent/borderline 0-1 versus mild-to-severe 2-4); multiple independent modeling approaches detected clinically rated hypernasality, with EfficientNet-V2-S a
Johns Hopkins University Florida International University University of South Florida
Jordan N Halsey（First author）S Alex Rottgers（Corresponding author）
Hypernasality Detection Multiple Instance Learning Convolutional Neural Network

You’re all caught up

Ultrasound diagnosis stops chasing average accuracy: multi-query attention keeps heterogeneous evidence, training-time regularization lifts sensitivity to 0.874

Ten microliters of unstained whole blood, imaged in 12 minutes: a three-class model flags sepsis at 100% sensitivity and 85.3% specificity

Gated-attention multiple instance learning triages multi-center cervical cytology slides without per-cell labels, reaching 90.96% accuracy with MobileNetV2 and 80.43% balanced accuracy out-of-distribution with Xception

Artificial Intelligence-Based Hypernasality Diagnosis Using CAPS-A-AM Rated Speech Samples in Pediatric Velopharyngeal Dysfunction