1. Clinical value of lesion detection by using artificial intelligence system and reports for digital mammography
Chinese Journal of Medical Imaging Technology 2019;35(12):1789-1793
Objective: To explore the clinical value of lesion detection artificial intelligence (AI) system based on deep learning (DL) for digital mammography. Methods: The mammograms and corresponding diagnostic reports of 484 patients were retrospectively analyzed. The sensitivity of AI system was evaluated in patients with Imaging-Reporting and Data System (BI-RADS) 3 and above lesions, χ2 and the consistency across different BI-RADS categories were observed. Among patients with BI-RADS 1 and 2 lesions but AI system indicating positive findings, further validation were performed by 3 attending radiologists, and the extra findings of AI were statistically analyzed according to BI-RADS scoring and types of lesions. Results: There were 103, 79, 23, 40 and 11 lesions categories with BI-RADS 3, 4a, 4b, 4c, 5, respectively, and the sensitivity of AI system was 82.52% (85/103), 97.47% (77/79), 100% (23/23), 100% (40/40) and 100%(11/11), respectively, with the overall sensitivity of 92.19% (236/256). No significant difference was found between report findings and AI findings across lesion categories (calcification, mass, asymmetry and distortion) nor BI-RADS categories (all P>0.05). AI system proposed 203 extra findings out of 254 patients. Validated by 3 attending radiologists, 75 patients with 80 lesions were categorized BI-RADS 0 (requires further information), and 21 patients with 23 lesions were categorized BI-RADS 3 and above. There was no statistically different among different type lesions with categorized BI-RADS 3 and above (all P>0.05). Conclusion: AI system has respectable sensitivity for finding lesions with BI-RADS 3 and above, therefore having the potential to reduce missed diagnosis during clinical practice.
2.CT morphological characteristics of plantar nerves and their significances in diabetic foot
Zhe LYU ; Xionghui GONG ; Tingting HA ; Bin ZHANG ; Juan WANG ; Jiao NIAN
Chinese Journal of Medical Imaging Technology 2018;34(6):919-923
Objective To analyze CT morphologicl characteristics of tibial nerve,lateral and medial plantar nerves and their clinical significances in the diabetic foot (DF) patients.Methods Bilateral feet (DF group) of 33 patients diagnosed as type 2 diabetes mellitus with DF were examined with CT.Meanwhile,36 uninjured feet (NDF group) of patients with single-side foot wound were taken as the controls.CT findings of distal part of tibial nerve,medial plantar nerve and lateral plantar nerve on the same plane were observed with CT post-processing technique.The morphological measurements were done at the points of A1 (tibial nerve measuring position),A2 (proximal part of medial plantar nerve measuring position),A3 (distal part of medial plantar nerve measuring position) and A4 (lateral plantar nerve measuring position).Both of the anteroposterior and transverse diameters were measured and compared between DF and NDF groups.Results Plantar nerves (tibial nerve,medial plantar nerve and lateral plantar nerve) of DF patients were thick (52/66,78.79 %),and the edges of nerve were indistinct (51/66,78.78%).The anteroposterior and transverse diameters of measurement points A1,A2 and A4 in DF group were larger than those in NDF group (all P<0.01).There was no statistical difference of the anteroposterior and transverse diameters of point A3 between the two groups (both P>0.05).Conclusion The plantar nerves of DF patient were thick with indistinct edges.The observation of continuous morphological characteristics and the diameter measurements of the plantar nerve can be performed with CT post-processing technique,which can provide more information for clinical diagnosis of DF.