Clinical evaluation of artificial intelligence system based on fundus photograph in diabetic retinopathy screening / 中华实验眼科杂志

Objective To study the efficiency and accuracy of artificial intelligence (AI) system based on fundus photograph in diabetic retinopathy(DR)screening,and evaluate the clinical application value of AI system. Methods A diagnostic trial was adopted. Total of 13683 color fundus photos were collected in Zhaoqing Gaoyao People's Hospital from March,2017 to November,2018. The AI system for DR (ZOC-DR-V1) was established,based on transfer learning + NASNet algorithm,by training 4465 precisely labeled fundus images (2510 normal,and 1955 with any stage of DR). One thousand confirmed fundus images (300 normal and 700 with any stage of DR),diagnosed by AI ( AI group ) and doctors ( 3 ophthalmologist doctors and 3 endocrinologist doctors ) ( doctor group ) , respectively. Ophthalmologist group and endocrinologist group were both composed of primary,intermediate and senior physicians. The mean reading time of each image and the total time of 1000 images were recorded. The accuracy and efficiency of AI system and doctor groups were compared. The reading process was divided into two stages. The diagnostic coincidence rate and the average reading time of each group between the two parts were calculated and compared. This study protocol was approved by Ethic Committee of Zhongshan Ophthalmic Center, Sun Yat-sen University (No. 2017KYPJ104). Results After training,the diagnostic coincidence rate of AI system (ZOC-DR-V1) in test set was 94. 7％,AUC was 0. 994. In this "man-machine to war",the diagnostic coincidence rate of primary,intermediate and senior endocrinologist was 94. 0％,91. 4％ and 93. 4％;the diagnostic coincidence rate of primary,intermediate and senior ophthalmologist was 92. 7％,94. 4％ and 95. 6％;the diagnostic coincidence rate of AI system was 95. 2％. There was no difference in the diagnostic coincidence rate between AI system and senior ophthalmologist ( P = 0. 749 ) . The mean reading time of each image of primary, intermediate and senior endocrinologists was (4. 63±1. 87),(3. 74±3. 47) and (5. 71±3. 47) seconds,and the total time of 1000 images of primary,intermediate and senior endocrinologists was 1. 29,1. 04 and 1. 58 hours;the mean reading time of each image of primary,intermediate and senior ophthalmologists was ( 7. 25 ± 6. 58 ) , ( 5. 18 ± 5. 01 ) and ( 5. 18 ± 3. 47 ) seconds,and the total time of 1000 images of primary,intermediate and senior endocrinologists was 2. 02,1. 44 and 1. 44 hours;the mean and total time of AI system was (1. 62±0. 67) seconds and 0. 45 hours,and the reading time of AI system was significantly shorter than that of the doctor groups (all at P=0. 000). The diagnostic coincidence rates between previous and posterior part of primary endocrinologist, primary and intermediate ophthalmologist were significantly different (χ2=11. 986,6. 517,10. 896;all at P<0. 05),and the mean reading time in the posterior part was significantly shorter than that in the previous part of intermediate and senior endocrinologist and primary ophthalmologist (t=4. 175,8. 189,5. 160;all at P<0. 01). While the reading time of AI system remained stable throughout the process(χ2=3. 151,P=0. 103;t=0. 038,P=0. 970). Conclusions The ophthalmic AI system based on fundus images has a good diagnostic efficiency,and its diagnostic coincidence rate can compare with senior ophthalmologist,providing a new method and platform for large-scale DR screening.

Diabetic retinopathy detection algorithm based on transfer learning / 中华实验眼科杂志

Objective To investigate a diabetic retinopathy ( DR ) detection algorithm based on transfer learning in small sample dataset. Methods Total of 4465 fundus color photographs taken by Gaoyao People ' s Hospital was used as the full dataset. The model training strategies using fixed pre-trained parameters and fine-tuning pre-trained parameters were used as the transfer learning group to compare with the non-transfer learning strategy that randomly initializes parameters. These three training strategies were applied to the training of three deep learning networks:ResNet50,Inception V3 and NASNet. In addition,a small dataset randomly extracted from the full dataset was used to study the impact of the reduction of training data on different strategies. The accuracy and training time of the diagnostic model were used to analyze the performance of different training strategies. Results The best results in different network architectures were chosen. The accuracy of the model obtained by fine-tuning pre-training parameters strategy was 90. 9％,which was higher than the strategy of fixed pre-training parameters (88. 1％) and the strategy of randomly initializing parameters ( 88. 4％) . The training time for fixed pre-training parameters was 10 minutes,less than the strategy of fine-tuning pre-training parameters ( 16 hours ) and the strategy of randomly initializing parameters (24 hours). After the training data was reduced,the accuracy of the model obtained by the strategy of randomly initializing parameters decreased by 8. 6％ on average,while the accuracy of the transfer learning group decreased by 2. 5％ on average. Conclusions The proposed automated and novel DR detection algorithm based on fine-tune and NASNet structure maintains high accuracy in small sample dataset,is found to be robust,and effective for the preliminary diagnosis of DR.

Novel missense mutations of the FLG gene identified in two Chinese families affected with ichthyosis vulgaris / 中华医学遗传学杂志

<p><b>OBJECTIVE</b>To identify potential mutations of the FLG gene in two Chinese families affected with ichthyosis vulgaris.</p><p><b>METHODS</b>All coding exons and exon-intron boundary of the FLG gene were amplified by polymerase chain reaction (PCR) and analyzed by direct sequencing. The results were compared with those of 100 unrelated healthy controls.</p><p><b>RESULTS</b>Two novel missense mutations, c.1360A>G (p.T454A) and c.10363G>T (p.D3455Y), were detected in all affected individuals from family 1 and family 2 respectively but none of the controls.</p><p><b>CONCLUSION</b>The c.1360A>G (p.T454A) and c.10363G>T (p.D3455Y) of the FLG gene may lead to alteration of the structure and function of the FLG protein and cause ichthyosis vulgaris in the two families.</p>

Mutation analysis of STK11 gene in a Chinese family with Peutz-Jeghers syndrome / 中华医学遗传学杂志

<p><b>OBJECTIVE</b>To investigate STK11 gene mutation in a pedigree with Peutz-Jeghers syndrome (PJS).</p><p><b>METHODS</b>A pedigree of PJS was investigated. DNA was extracted from peripheral blood samples from affected and unaffected members of the pedigree and 100 unrelated healthy controls. PCR was performed to amplify all of the 9 coding exons of STK11 gene. PCR products were directly sequenced to detect mutation.</p><p><b>RESULTS</b>A missense mutation p.F354L (c.1062C>G) in exon 8 of the STK11 gene has been identified in all patients with PJS, but was not found in normal individuals from the pedigree and 100 unrelated controls.</p><p><b>CONCLUSION</b>A missense mutation p.F354L of STK11 gene probably underlies the disease in this pedigree.</p>

Curative effect of Cynergy dual wavelength laser in treatment of skin vascular pathological changes in children / 中华医学美学美容杂志

Objective To explore the curative effect and adverse reactions through Cynergy dual wavelength laser to cure skin vascular pathological changes in children.Methods Cynergy dual wavelength (595 nm and 1064 nm) laser were used to treat the skin vascular pathological changes in children (650 cases) including strawberry-shaped hemangioma (398 cases) and port wine stain (252 cases).Anergy density was 5-15 J/cm2 and 30-80 J/cm2.The curative effect and adverse reaction and also the relationship between the port wine stain curative effect and the age of patient,location,and colour of skin lesions were analyzed.Results In total 650 cases after 3-7 times treatments under suitable pulse width and energy density,the curative effect for strawberry-shaped hemangioma was 92.2 ％,that for pink type port wine stain was 77.9 ％,that for purple type port wine stain was 38.9 ％,and that for thickening type port wine stain was 14.3 ％ ; the overall adverse reaction rate was 2.3 ％.After test with x2 analysis,the curative effect of port wine stain also varied depending on the age of patient,location,and colour of skin lesions.The younger the age of patient and shallower of colour of skin lesions,and the better the curative effect.The curative effect for location around the eyes was better than frontal face and limbs.Conclusions Application of Cynergy dual wavelength laser in treatment of the skin vascular pathological changes in children has notable curative effect and low adverse reaction.It is a new curative technology and also safe and reliable.It is worthy of popularization and application.