Segment anything model for medical images?

The Segment Anything Model (SAM) is the first foundation model for general image segmentation. It has achieved impressive results on various natural image segmentation tasks. However, medical image segmentation (MIS) is more challenging because of the complex modalities, fine anatomical structures, uncertain and complex object boundaries, and wide-range object scales. To fully validate SAM's performance on medical data, we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks. We comprehensively analyzed different models and strategies on the so-called COSMOS 1050K dataset. Our findings mainly include the following: (1) SAM showed remarkable performance in some specific objects but was unstable, imperfect, or even totally failed in other situations. (2) SAM with the large ViT-H showed better overall performance than that with the small ViT-B. (3) SAM performed better with manual hints, especially box, than the Everything mode. (4) SAM could help human annotation with high labeling quality and less time. (5) SAM was sensitive to the randomness in the center point and tight box prompts, and may suffer from a serious performance drop. (6) SAM performed better than interactive methods with one or a few points, but will be outpaced as the number of points increases. (7) SAM's performance correlated to different factors, including boundary complexity, intensity differences, etc. (8) Finetuning the SAM on specific medical tasks could improve its average DICE performance by 4.39% and 6.68% for ViT-B and ViT-H, respectively. Codes and models are available at: https://github.com/yuhoo0302/Segment-Anything-Model-for-Medical-Images. We hope that this comprehensive report can help researchers explore the potential of SAM applications in MIS, and guide how to appropriately use and develop SAM.

Artificial Intelligence-Assisted Ultrasound Diagnosis on Infant Developmental Dysplasia of the Hip Under Constrained Computational Resources.

OBJECTIVES: Ultrasound (US) is important for diagnosing infant developmental dysplasia of the hip (DDH). However, the accuracy of the diagnosis depends heavily on expertise. We aimed to develop a novel automatic system (DDHnet) for accurate, fast, and robust diagnosis of DDH. METHODS: An automatic system, DDHnet, was proposed to diagnose DDH by analyzing static ultrasound images. A five-fold cross-validation experiment was conducted using a dataset containing 881 patients to verify the performance of DDHnet. In addition, a blind test was conducted on 209 patients (158 normal and 51 abnormal cases). The feasibility and performance of DDHnet were investigated by embedding it into ultrasound machines at low computational cost. RESULTS: DDHnet obtained reliable measurements and accurate diagnosis predictions. It reported an intra-class correlation coefficient (ICC) on α angle of 0.96 (95% CI: 0.93-0.97), ß angle of 0.97 (95% CI: 0.95-0.98), FHC of 0.98 (95% CI: 0.96-0.99) and PFD of 0.94 (95% CI: 0.90-0.96) in abnormal cases. DDHnet achieved a sensitivity of 90.56%, specificity of 100%, accuracy of 98.64%, positive predictive value (PPV) of 100%, and negative predictive value (NPV) of 98.44% for the diagnosis of DDH. For the measurement task on the US device, DDHnet took only 1.1 seconds to operate and complete, whereas the experienced senior expert required an average 41.4 seconds. CONCLUSIONS: The proposed DDHnet demonstrate state-of-the-art performance for all four indicators of DDH diagnosis. Fast and highly accurate DDH diagnosis is achievable through DDHnet, and is accessible under constrained computational resources.

Medical information security in the era of artificial intelligence.

In recent years, biometric technologies, such as iris, facial, and finger vein recognition, have reached consumers and are being increasingly applied. However, it remains unknown whether these highly specific biometric technologies are as safe as declared by their manufacturers. As three-dimensional (3D) reconstruction based on medical imaging and 3D printing are being developed, these biometric technologies may face severe challenges.

The clinical evaluation of the effect of two different apical surgery timing / 实用口腔医学杂志

Objective:To observe the effect of two different apical surgery timing. Methods:68 patients with periapical lesion were divided into 2 groups. 30 patients( control group) were operated by apical surgery at least 1-2 months after root canal therapy( RCT) , while 38 patients(experimental group) were operated immediately after RCT. The patients were followed up 3, 6 and 12 months after apical surgery. Results:The curative effect analysed with the age, sex and tooth position showed no statistical difference between 2 groups(P>0. 05). Conclusion:Immediate and delayed apical surgery apical surger after RCT are similarly effective.

[Observation on the ultrastructure of Spirometra mansoni plerocercoid].

Plerocercoids of Spirometra mansoni were collected from muscles of the frogs. Specimens were treated following the routine procedure, embedded, sliced and stained. The ultrastructure of plerocercoid was observed with transmission electron microscopy. It was found that the wall of plerocercoid consisted of tegument and parenchyma. Thornshape microtriches distributed over the outer surface of the tegument. Matrix zone had a lot of granular discoidal bodies, vesicles, mitochondria and endoplasmic reticulum. Most of the mitochondria were near the basal membrane. Parenchyma zone consisted of muscular layer, tegument cells, parenchymal cells, excretory system, and so on. Many cytoplasmic pathways of tegumentary cells stretch into muscular layer, suggesting that the tegument may be the absorptive site of nutrients.