Pinned Repositories
Adafruit_Python_AS7262
Python script for using the Sparkfun AS7262 Visible Spectrometer with the Raspberry Pi
Adafruit_Python_BME280
Python Driver for the Adafruit BME280 Breakout
Adafruit_Python_CCS811
Python driver for CCS811 air quality sensor
Adafruit_Python_TLC59711
Python module for the TLC59711 16-bit 12 channel RGB LED PWM driver.
autokeras
AutoML library for deep learning
CL_RNA_SynthBio
Code to reproduce Angenent-Mari, N. et al 2020. Deep Learning for RNA Synthetic Biology
Gluco
Arduino Code and PCB fabrication files of GlucoPush V1
Gluco_Push_V1
Supplemental Material (GlucoPush: A Do-It-Yourself Add-On for Online Tracking of Personal Glucometer Use)
HAIM
This repository contains the code to replicate the data processing, modeling and reporting of our Holistic AI in Medicine (HAIM) Publication in Nature Machine Intelligence (Soenksen LR, Ma Y, Zeng C et al. 2022).
SPL_UD_DL
A reported 96,480 people were diagnosed with melanoma in the United States in 2019, leading to 7230 reported deaths. Early-stage identification of suspicious pigmented lesions (SPLs) in primary care settings can lead to im- proved melanoma prognosis and a possible 20-fold reduction in treatment cost. Despite this clinical and economic value, efficient tools for SPL detection are mostly absent. To bridge this gap, we developed an SPL analysis system for wide-field images using deep convolutional neural networks (DCNNs) and applied it to a 38,283 dermatological dataset collected from 133 patients and publicly available images. These images were obtained from a variety of consumer-grade cameras (15,244 nondermoscopy) and classified by three board-certified dermatologists. Our system achieved more than 90.3% sensitivity (95% confidence interval, 90 to 90.6) and 89.9% specificity (89.6 to 90.2%) in distinguishing SPLs from nonsuspicious lesions, skin, and complex backgrounds, avoiding the need for cumbersome individual lesion imaging. We also present a new method to extract intrapatient lesion saliency (ugly duckling criteria) on the basis of DCNN features from detected lesions. This saliency ranking was validated against three board-certified dermatologists using a set of 135 individual wide-field images from 68 dermatolog- ical patients not included in the DCNN training set, exhibiting 82.96% (67.88 to 88.26%) agreement with at least one of the top three lesions in the dermatological consensus ranking. This method could allow for rapid and accurate assessments of pigmented lesion suspiciousness within a primary care visit and could enable improved patient triaging, utilization of resources, and earlier treatment of melanoma.
lrsoenksen's Repositories
lrsoenksen/HAIM
This repository contains the code to replicate the data processing, modeling and reporting of our Holistic AI in Medicine (HAIM) Publication in Nature Machine Intelligence (Soenksen LR, Ma Y, Zeng C et al. 2022).
lrsoenksen/SPL_UD_DL
A reported 96,480 people were diagnosed with melanoma in the United States in 2019, leading to 7230 reported deaths. Early-stage identification of suspicious pigmented lesions (SPLs) in primary care settings can lead to im- proved melanoma prognosis and a possible 20-fold reduction in treatment cost. Despite this clinical and economic value, efficient tools for SPL detection are mostly absent. To bridge this gap, we developed an SPL analysis system for wide-field images using deep convolutional neural networks (DCNNs) and applied it to a 38,283 dermatological dataset collected from 133 patients and publicly available images. These images were obtained from a variety of consumer-grade cameras (15,244 nondermoscopy) and classified by three board-certified dermatologists. Our system achieved more than 90.3% sensitivity (95% confidence interval, 90 to 90.6) and 89.9% specificity (89.6 to 90.2%) in distinguishing SPLs from nonsuspicious lesions, skin, and complex backgrounds, avoiding the need for cumbersome individual lesion imaging. We also present a new method to extract intrapatient lesion saliency (ugly duckling criteria) on the basis of DCNN features from detected lesions. This saliency ranking was validated against three board-certified dermatologists using a set of 135 individual wide-field images from 68 dermatolog- ical patients not included in the DCNN training set, exhibiting 82.96% (67.88 to 88.26%) agreement with at least one of the top three lesions in the dermatological consensus ranking. This method could allow for rapid and accurate assessments of pigmented lesion suspiciousness within a primary care visit and could enable improved patient triaging, utilization of resources, and earlier treatment of melanoma.
lrsoenksen/CL_RNA_SynthBio
Code to reproduce Angenent-Mari, N. et al 2020. Deep Learning for RNA Synthetic Biology
lrsoenksen/Adafruit_Python_AS7262
Python script for using the Sparkfun AS7262 Visible Spectrometer with the Raspberry Pi
lrsoenksen/Adafruit_Python_BME280
Python Driver for the Adafruit BME280 Breakout
lrsoenksen/Adafruit_Python_CCS811
Python driver for CCS811 air quality sensor
lrsoenksen/Adafruit_Python_TLC59711
Python module for the TLC59711 16-bit 12 channel RGB LED PWM driver.
lrsoenksen/autokeras
AutoML library for deep learning
lrsoenksen/Gluco
Arduino Code and PCB fabrication files of GlucoPush V1
lrsoenksen/Gluco_Push_V1
Supplemental Material (GlucoPush: A Do-It-Yourself Add-On for Online Tracking of Personal Glucometer Use)
lrsoenksen/LRFinder
Automatic Learning Rate Scheduled for Tensorflow-Keras
lrsoenksen/medical_sentence_tokenizer
Some of my work on splitting medical text into sentences for BERT langauge modeling training.
lrsoenksen/ml4a-guides
practical guides, tutorials, and code samples for ml4a
lrsoenksen/RPI_ZRAM
Script to enable ZRAM on Raspberry Pi 2 & 3
lrsoenksen/aiml-stack-jupyterlab-dockerfiles
Dockerfile to generate AI/ML Ready Docker Container with GPU support and JupyterLab
lrsoenksen/BioAutoMATED
Automated machine learning for analyzing, interpreting, and designing biological sequences
lrsoenksen/conky-pro
Conky file for beautiful & functional resource display in linux desktop
lrsoenksen/OpenDrop
Open Source Digital Microfluidics Bio Lab
lrsoenksen/senolyticsai
Supporting code for the paper "Discovering senolytics with deep learning"