Research Digest — 2026-03-13

This edition features 5 papers from International Conference on Medical Image Computing and Computer-Assisted Intervention, Neural Information Processing Systems.

1. Gall Bladder Cancer Detection from US Images with Only Image Level Labels

Soumen Basu, Ashish Papanai, Mayank Gupta, Pankaj Gupta, Chetan Arora

International Conference on Medical Image Computing and Computer-Assisted Intervention (2023)

Topics: classification · detection · transformer | Body: pelvis | Modality: CT · ultrasound

Automated detection of Gallbladder Cancer (GBC) from Ultrasound (US) images is an important problem, which has drawn increased interest from researchers. However, most of these works use difficult-to-acquire information such as bounding box annotations or additional US videos. In this paper, we focus on GBC detection using only image-level labels. Such annotation is usually available based on the ...

Read paper →

---

2. Sm: enhanced localization in Multiple Instance Learning for medical imaging classification

Francisco M. Castro-Mac'ias, Pablo Morales-Álvarez, Yunan Wu, Rafael Molina, A. Katsaggelos

Neural Information Processing Systems (2024)

Topics: classification · detection · transformer | Body: general | Modality: not specified

Multiple Instance Learning (MIL) is widely used in medical imaging classification to reduce the labeling effort. While only bag labels are available for training, one typically seeks predictions at both bag and instance levels (classification and localization tasks, respectively). Early MIL methods treated the instances in a bag independently. Recent methods account for global and local dependenci...

Read paper →

---

3. Robustly Optimized Deep Feature Decoupling Network for Fatty Liver Diseases Detection

Peng Huang, Shu Hu, Bo Peng, Jiashu Zhang, Xi Wu et al.

International Conference on Medical Image Computing and Computer-Assisted Intervention (2024)

Topics: classification · detection | Body: abdomen | Modality: ultrasound

Current medical image classification efforts mainly aim for higher average performance, often neglecting the balance between different classes. This can lead to significant differences in recognition accuracy between classes and obvious recognition weaknesses. Without the support of massive data, deep learning faces challenges in fine-grained classification of fatty liver. In this paper, we propos...

Read paper →

---

4. Privacy-Preserving Chest X-ray Classification in Latent Space with Homomorphically Encrypted Neural Inference

Jonghun Kim, Gyeongdeok Jo, Shinyoung Ra, Hyunjin Park

International Conference on Medical Image Computing and Computer-Assisted Intervention (2025)

Topics: classification · generation | Body: chest · bone/joint | Modality: X-ray

Medical imaging data contain sensitive patient information requiring strong privacy protection. Many analytical setups require data to be sent to a server for inference purposes. Homomorphic encryption (HE) provides a solution by allowing computations to be performed on encrypted data without revealing the original information. However, HE inference is computationally expensive, particularly for l...

Read paper →

---

5. AbdomenAtlas-8K: Annotating 8, 000 CT Volumes for Multi-Organ Segmentation in Three Weeks

Chongyu Qu, Tiezheng Zhang, Hualin Qiao, Jie Liu, Yucheng Tang et al.

Neural Information Processing Systems (2023)

Topics: segmentation · detection · registration | Body: heart · abdomen · pelvis | Modality: CT

Annotating medical images, particularly for organ segmentation, is laborious and time-consuming. For example, annotating an abdominal organ requires an estimated rate of 30-60 minutes per CT volume based on the expertise of an annotator and the size, visibility, and complexity of the organ. Therefore, publicly available datasets for multi-organ segmentation are often limited in data size and organ...

Read paper →

---