Search Articles

View query in Help articles search

Search Results (1 to 10 of 94 Results)

Download search results: CSV END BibTex RIS


Using Segment Anything Model 2 for Zero-Shot 3D Segmentation of Abdominal Organs in Computed Tomography Scans to Adapt Video Tracking Capabilities for 3D Medical Imaging: Algorithm Development and Validation

Using Segment Anything Model 2 for Zero-Shot 3D Segmentation of Abdominal Organs in Computed Tomography Scans to Adapt Video Tracking Capabilities for 3D Medical Imaging: Algorithm Development and Validation

The Segment Anything Model (SAM), introduced by Meta AI, represented a significant leap forward in image segmentation technology [3]. Trained on over a billion masks, SAM demonstrated remarkable versatility in segmenting a wide array of objects across various domains.

Yosuke Yamagishi, Shouhei Hanaoka, Tomohiro Kikuchi, Takahiro Nakao, Yuta Nakamura, Yukihiro Nomura, Soichiro Miki, Takeharu Yoshikawa, Osamu Abe

JMIR AI 2025;4:e72109

Increasing the Uptake of Breast and Cervical Cancer Screening Via the MAwar Application: Stakeholder-Driven Web Application Development Study

Increasing the Uptake of Breast and Cervical Cancer Screening Via the MAwar Application: Stakeholder-Driven Web Application Development Study

These AI values were then summed across all relevant user needs to compute the weighted score (WS)=sum of absolute importance value, ranking the significance of each feature of the “WHATs” within the overall app structure. All these were ranked to highlight the most essential components of the MAwar application [21]. These analytical steps provided a detailed, quantified overview of the key priorities for the MAwar application’s development.

Nurfarhana Nasrudin, Shariff-Ghazali Sazlina, Ai Theng Cheong, Ping Yein Lee, Soo-Hwang Teo, Abdul Rashid Aneesa, Chin Hai Teo, Fakhrul Zaman Rokhani, Nuzul Azam Haron, Noor Harzana Harrun, Bee Kiau Ho, Salbiah Mohamed Isa

JMIR Form Res 2025;9:e65542

Digital Therapeutics–Based Cardio-Oncology Rehabilitation for Lung Cancer Survivors: Randomized Controlled Trial

Digital Therapeutics–Based Cardio-Oncology Rehabilitation for Lung Cancer Survivors: Randomized Controlled Trial

With the app for HCPs, they can (1) check, modify, or confirm the artificial intelligence (AI)–driven tailored exercise prescription and send it to patients; and (2) check the feedback information from patients and optimize the exercise prescription dynamically.

Guangqi Li, Xueyan Zhou, Junyue Deng, Jiao Wang, Ping Ai, Jingyuan Zeng, Xuelei Ma, Hu Liao

JMIR Mhealth Uhealth 2025;13:e60115

Large Language Model Approach for Zero-Shot Information Extraction and Clustering of Japanese Radiology Reports: Algorithm Development and Validation

Large Language Model Approach for Zero-Shot Information Extraction and Clustering of Japanese Radiology Reports: Algorithm Development and Validation

Although this study analyzed text rather than images, CLAIM was followed because it is an established guideline for AI-based research in radiology and is deemed appropriate for NLP [15-17]. The proposed algorithm is illustrated in Figure 1. Using the LLM, key lung cancer findings were extracted from radiology reports and quantified to obtain structured data. The structured data were subsequently used for clustering. Flowchart of radiology reports clustering using LLM. LLM: large language model.

Yosuke Yamagishi, Yuta Nakamura, Shouhei Hanaoka, Osamu Abe

JMIR Cancer 2025;11:e57275