Overview of the ImageCLEF 2022: Multimedia Retrieval in Medical, Social Media and Nature Applications

Abstract

This paper presents an overview of the ImageCLEF 2022 lab that was organized as part of the Conference and Labs of the Evaluation Forum -CLEF Labs 2022. ImageCLEF is an ongoing evaluation initiative (first run in 2003) that promotes the evaluation of technologies for annotation, indexing and retrieval of visual data with the aim of providing information access to large collections of images in various usage scenarios and domains. In 2022, the 20th edition of ImageCLEF runs four main tasks: (i) a medical task that groups two previous tasks, i.e., caption analysis and tuberculosis prediction, (ii) a social media aware task on estimating potential real-life effects of online image sharing, (iii) a nature coral task about segmenting and labeling collections of coral reef images, and (iv) a new fusion task addressing the design of late fusion schemes for boosting the performance, with two real-world applications: image search diversification (retrieval) and prediction of visual interestingness (regression). The benchmark campaign received the participation of over 25 groups submitting more than 258 runs.

Probabilistic Integration of Object Level Annotations in Chest X-ray Classification

“…With access to large datasets and pre-trained methods the balance shifted towards making automated retrieval methods [26,6]. Especially in the histopathology and radiology domain major strides were made with retrieval methods [2,8]. The use of text to improve image retrieval has been adopted for improving chest X-ray retrieval.…”

“…A reason retrieval augmentation methods are not yet adopted for medical applications lies in the weakness of retrieval methods for the medical domain. Retrieval in the general domain is focused on global image regions [16,8] whereas in medical images global features, such as body/organ structure are similar across patients. Meanwhile more fine-grained aspects are more discriminating as disease indicators, but are easily overlooked.…”

Statistical similarity matching and filtering for clinical image retrieval by machine learning approach

“…/ where Rk is the number of pertinent images in the top returned results. Thus, rank order and precision are effectively the products of two elements in equation (7). The role of the pertinent images in the retrieving set is taken into consideration by the order of ranking factor; however the level of precision is an indicator of the retrieving accuracy despite the precise spot.…”

“…Step 2: Take into account the top images in every ranked list according to individual similarity matching, and use equation (7) to calculate the performance as Q p x .…”

“…Numerous medical CBIR concepts have been put forth throughout the last decade. Many of them are systems created with a particular imaging modality in mind, and their retrieval techniques are task-specific [7]. A few technologies aim to create a CBIR mechanism for heterogeneous image data [8].…”