https://abs.twimg.com/emoji/v2/... draggable="false" alt="❓" title="Rotes Fragezeichen-Symbol" aria-label="Emoji: Rotes Fragezeichen-Symbol">Which of the following options is >90% sensitive to diagnose autoimmune pancreatitis?
https://abs.twimg.com/emoji/v2/... draggable="false" alt="📢" title="Lautsprecheranlage" aria-label="Emoji: Lautsprecheranlage">This is why we need another approach to diagnose AIP.
1. Diffusely enlarged pancreas with hypo-attenuated rim -> only in 40% patients
2. IgG4 >2x ULN -> only 53% sensitive
3. EUS FNA/B sensitivity only 58.2% in recent study with as low as 7.9% in other previous studies. 2/n
https://abs.twimg.com/emoji/v2/... draggable="false" alt="🏹" title="Pfeil und Bogen" aria-label="Emoji: Pfeil und Bogen">Focus of the study?
1. Development of CNN (Convoluted neural network) that differentiated AIP from Pancreatic duct adenocarcinoma(PDAC)
2. AIP vs other benign conditions [chronic pancreatitis (CP) and normal pancreas (NP)] 3/n
https://abs.twimg.com/emoji/v2/... draggable="false" alt="📢" title="Lautsprecheranlage" aria-label="Emoji: Lautsprecheranlage">How were the study patients chosen?
All patients with HISORt- verified AIP who had undergone EUS since the introduction of EUS at @MayoClinicGIHep in 1996.
1. 50% from PDAC cohort
2. 50% to benign disorders (50% AIP, 25% CP, 25% NP) 4/n
https://abs.twimg.com/emoji/v2/... draggable="false" alt="📢" title="Lautsprecheranlage" aria-label="Emoji: Lautsprecheranlage">How was the data processed?
1. All available physician captured still (PCS) image and video (all frames) were identified and extracted.
2. minimum resolution (448×448 pixels) chosen
3. potentially confounding image features and patient identifying information removed. 5/n
https://abs.twimg.com/emoji/v2/... draggable="false" alt="📢" title="Lautsprecheranlage" aria-label="Emoji: Lautsprecheranlage">The results were impressive!
When provided full video assets, the CNN model was 90% sensitive and 93% specific for differentiating AIP from PDAC and was 90% sensitive and 85% specific for differentiating AIP from all conditions that were studied. 8/n
https://abs.twimg.com/emoji/v2/... draggable="false" alt="📢" title="Lautsprecheranlage" aria-label="Emoji: Lautsprecheranlage">EUS-CNN processing speed.
Tested on: AMD Ryzen 3600 CPU, an Nvidia GeForce RTX 2080 Ti GPU, and 48GB of RAM.

Minimum speed required for real-time processing on EUS processors? 30 frames per second

Speed bench-marked? 955 frames per second! 10/n
https://abs.twimg.com/emoji/v2/... draggable="false" alt="📢" title="Lautsprecheranlage" aria-label="Emoji: Lautsprecheranlage">Limitations?
1. single center retrospective data over two decades.
2. model was trained on images with meta-data and EUS overlays removed.
3. not tested for real-time analysis and prediction 11/n
https://abs.twimg.com/emoji/v2/... draggable="false" alt="📢" title="Lautsprecheranlage" aria-label="Emoji: Lautsprecheranlage">Summary
1. Large dataset of PDAC, AIP, CP and NP patients used to build EUS-CNN model.
2. Highly accurate for differentiating AIP from PDAC and other benign conditions
3. Current criteria centred on imaging and serologic
analyses identify only 70% of patients with AIP. 12/n
Read more about deep neural networks:
1. He K, Zhang X, Ren S, et al. Identity mappings in deep residual networks: 2016 computer-vision deep-learning microsoft, 2016. https://arxiv.org/pdf/1512.03385.pdf
2.">https://arxiv.org/pdf/1512.... Introduction to ResNets https://towardsdatascience.com/introduction-to-resnets-c0a830a288a4">https://towardsdatascience.com/introduct... 14/n
You can follow @LetuslearnGI.
Tip: mention @twtextapp on a Twitter thread with the keyword “unroll” to get a link to it.

Latest Threads Unrolled: