Generated by Rank Math SEO, this is an llms.txt file designed to help LLMs better understand and index this website.

# Abdüssamet Aslan: Radiologist & Developer

## Sitemaps
[XML Sitemap](https://aslan.md/sitemap_index.xml): Includes all crawlable and indexable pages.

## Posts
- [AI in Radiology and Radiomics 101: Resources and Roadmap](https://aslan.md/ai-in-radiology-and-radiomics-101-resources-and-roadmap/): I have a lot of colleagues who want to learn AI to improve their radiology practice. They frequently ask me how to learn radiomics, machine learning, and deep learning for radiology. I decided to compile resources to help other radiologists and draw a roadmap.
- [How I Learned to Code Before It Was Cool](https://aslan.md/how-i-learned-to-code-before-it-was-cool/): Today is my 30th birthday. I've been developing software since I was 10, so it's been 20 years. I was thinking about how I lived these years, and I noticed software development and building products are a huge part of my life. So I decided to share my story with other people, because most of my doctor friends and colleagues from the software companies I've worked at frequently ask me how I learned all of it without going to school for it.
- [How to Vibe Code on iPhone with Claude Code](https://aslan.md/how-to-vibe-code-on-iphone-with-claude-code/): Use Tailscale, Termius, tmux and Claude Code to turn your iPhone into a remote dev terminal that picks up exactly where you left off.
- [I Built a Telegram Bot That Writes My Ultrasound Reports From Voice Notes](https://aslan.md/i-built-a-telegram-bot-that-writes-my-ultrasound-reports-from-voice-notes/): How I built a Telegram bot in a weekend that turns voice notes into formatted ultrasound reports, using Whisper, Claude, and a library of my own templates.
- [Radiology Normal Values Reference Guide: Ultrasound, CT & MRI](https://aslan.md/radiology-normal-values-ultrasound-ct-mri/): A pillar reference for radiology normal values across ultrasound, CT, and MRI — adult and pediatric — with quick-reference tables and clinical caveats.
- [The Best PubMed App for iPhone in 2026: A Clinician’s Honest Review](https://aslan.md/the-best-pubmed-app-for-iphone-in-2026-a-clinicians-honest-review/): If you're a doctor, keeping up with new research is exhausting. Between clinical work, call shifts, and everything else, the last thing you want is to fight with a clunky interface just to read a paper. And yet, that's exactly what most of us do every day. We bounce between journal websites, lose track of bookmarks, and try to make PubMed work on an iPhone screen that wasn't designed for it.
- [Ultrasound Anatomy Atlas – Images with Interactive Visuals](https://aslan.md/ultrasound-anatomy-atlas-images-with-interactive-visuals/): Interpreting ultrasound images requires a deep understanding of anatomical structures and their sonographic appearance. The challenge many residents, and healthcare professionals face is bridging the gap between theoretical anatomical knowledge and practical ultrasound interpretation.
- [Radiology Reference Values for Adults and Children](https://aslan.md/radiology-reference-values-for-adults-and-children/): Determining whether imaging measurements are normal or abnormal is fundamental to radiology, yet memorizing thousands of reference values across all specialties for both adults and children is impossible. Radiologists need instant access to age-appropriate normal ranges without workflow interruptions.
- [Easy TI-RADS Calculator with Example Cases](https://aslan.md/easy-ti-rads-calculator-with-example-cases/): The TI-RADS Calculator is an essential tool for evaluating thyroid nodules using the Thyroid Imaging Reporting and Data System (TI-RADS). This standardized approach helps determine malignancy risk based on ultrasound characteristics, providing evidence-based recommendations for follow-up and fine-needle aspiration (FNA) decisions.
- [Easy Digital Bone Age Atlas for Children](https://aslan.md/easy-digital-bone-age-atlas-for-children/): Understanding bone age is crucial for pediatric healthcare who need to assess a child's skeletal development and growth patterns. A bone age atlas serves as an essential diagnostic tool that helps determine whether a child's bone development aligns with their chronological age, providing valuable insights into growth disorders, endocrine conditions, and overall health status.
- [NVIDIA MAISI: Generate Synthetic CT Images with AI](https://aslan.md/nvidia-maisi-generate-synthetic-ct-images-with-ai/): NVIDIA MAISI1https://docs.nvidia.com/nim/medical/maisi/latest/overview.html can generate synthetic 3D CT images up to 512×512×768 voxels that are indistinguishable from real scans. Here's how this breakthrough technology works and why it matters for medical AI.
- [Must-Have iPhone Apps Every Doctor Should Know](https://aslan.md/must-have-iphone-apps-every-doctor-should-know/): The modern clinician’s white coat pocket isn’t stuffed with paper anymore. It’s loaded with apps. Whether you’re racing through morning rounds, digging into the literature between cases, or brushing up on a rare pediatric dosage in the elevator, the right tool on your phone can shave minutes off tasks, reduce errors, and even lighten your cognitive load. Below are standout iPhone apps worth a permanent spot on your home screen this year.
- [Radiology Datasets for AI Model Training](https://aslan.md/radiology-datasets/): This dataset comprises 1,937,450 DICOM images (totaling 980.24 GB) drawn from 7,279 training studies, 650 public test studies, and 1,517 private test studies in the RSNA Pulmonary Embolism Detection Challenge. Each image is uniquely identified by a combination of StudyInstanceUID, SeriesInstanceUID, and SOPInstanceUID. Competitors predict various image-level and study-level labels related to pulmonary embolisms, including pe_present_on_image, negative_exam_for_pe, and several other attributes (e.g., rv_lv_ratio_gte_1, rightsided_pe, central_pe).
- [How To Assess Bone Age Easily with Easy Bone Age Atlas App?](https://aslan.md/how-to-assess-bone-age-easily-with-easy-bone-age-atlas-app/): A radiologist's journey from clinical frustration to creating the Easy Bone Age Atlas app that's transforming pediatric radiology workflows worldwide.
- [How to Stay Current with Medical Research?](https://aslan.md/how-to-stay-current-with-medical-research/): As a radiologist and software developer, I was drowning in medical research. Here's how I built a solution that transformed my practice.
- [How I Built Radiology References App During My Residency?](https://aslan.md/how-i-built-radiology-references-app-during-my-residency/): How a frustrated search for pediatric ultrasound values during my residency led me to develop the Radiology References App I wish I'd had from day one.
- [MediPub: Follow Medical Journals & Stay Updated](https://aslan.md/medipub-follow-medical-journals-stay-updated/): During my training and early professional years, I realized I needed a simpler way to manage all the journals I was reading. Following to multiple publications became time-consuming, and constantly hopping between platforms—searching for abstracts on PubMed—felt inefficient. I wanted a single platform that would let me:
- [How to Calculate TI-RADS Score Easily?](https://aslan.md/how-to-calculate-ti-rads-score-easily/): Accurately evaluating thyroid nodules has never been more essential. With the prevalence of thyroid diseases on the rise, clinicians such as radiologists, endocrinologists, and surgeons seek reliable methods to stratify nodule risk and guide patient management. TI-RADS (Thyroid Imaging Reporting and Data System) scoring offers a standardized approach, but traditional manual calculations can be time-consuming and prone to subjective variations.
- [What is Distilled and Quantized Models?](https://aslan.md/what-is-distilled-and-quantized-models/): Researchers make advancements in machine learning every day, and I recently explored two of them: distillation and quantization. While I was familiar with quantization, distillation was entirely new to me. It’s exciting to see how we can create more efficient AI systems that maintain strong performance, and I’ve captured a brief overview of both concepts here.
- [ViT vs CNN: Vision Transformers and Convolutional Neural Networks in Medical Image Analysis](https://aslan.md/vit-vs-cnn-vision-transformers-and-convolutional-neural-networks-in-medical-image-analysis/): I read this article today and took some notes. I want to mention it here for my future work and to look again. The article is titled: Comparison of Vision Transformers and Convolutional Neural Networks in Medical Image Analysis: A Systematic Review7Takahashi, S., Sakaguchi, Y., Kouno, N. et al. Comparison of Vision Transformers and Convolutional Neural Networks in Medical Image Analysis: A Systematic Review. J Med Syst48, 84 (2024). https://doi.org/10.1007/s10916-024-02105-8. Published in the Journal of Medical Systems.
- [Breast Ultrasound Lesion Classification with PyRadiomics and Scikit-Learn](https://aslan.md/breast-ultrasound-lesion-classification-with-pyradiomics-and-scikit-learn/): In the previous post, we explored Radiomics and its Workflow step-by-step. Radiomics is a powerful tool for quantifying imaging features from medical images to extract clinically meaningful patterns. In this post, we'll dive into a practical example: developing a radiomics and machine learning solution to classify breast ultrasound lesions into benign and malignant categories using Python, PyRadiomics, and Scikit-Learn.
- [Introduction to Radiomics with Python](https://aslan.md/introduction-to-radiomics-with-python/): Radiomics is a field at the intersection of medical imaging and data science that focuses on extracting large quantities of quantitative features from clinical images. These features can include texture measurements, shape descriptors, intensity statistics, and more. By converting image data into structured information, radiomics aims to reveal patterns that may not be visible to the naked eye, leading to more personalized and data-driven medical decision-making.
- [NVIDIA Holoscan and IGX Orin: Getting Started](https://aslan.md/nvidia-holoscan-and-igx-orin-getting-started/): I recently had the chance to attend a webinar organized by PNY that focused on industrial and medical edge AI, featuring NVIDIA Holoscan and the NVIDIA IGX Orin platforms. As a radiologist and developer working on healthcare solutions, I’ve always been fascinated by how emerging technologies can optimize workflows, improve patient outcomes, and streamline industrial operations. This event felt like the perfect opportunity to learn more about these cutting-edge platforms and share what I took away with you.
- [Predictive Code Completion Examples in Xcode 16](https://aslan.md/predictive-code-completion-examples-in-xcode-16/): Today was an exciting day for me as a developer. I finally had the chance to test Apple’s new Predictive Code Completion feature in Xcode 16. Here’s how it went and my thoughts on it so far.
- [Social Media Automation with Make: My Workflow](https://aslan.md/social-media-automation-with-make-my-workflow/): Managing social media was becoming a chore. Then I decided to switch a social media automation solution. Between Twitter, LinkedIn, and Instagram, each platform demanded individual attention, and the constant switching felt like a productivity sinkhole. I needed something streamlined, efficient, and easy to maintain. Let me share a productivity hack that has completely changed how I manage social media.
- [Apple Vision Pro Review: My Hands-On Experience](https://aslan.md/apple-vision-pro-review-my-hands-on-experience/): As an indie iOS developer, I recently had an unexpected but fascinating encounter with Apple Vision Pro during my trip to Edinburgh. While I initially planned to check out the new M4 Macs at the Apple Store on Princes Street, fate had different plans for me.
- [Edinburgh Travelogue: Places to Visit in Edingburgh](https://aslan.md/edinburgh-travelogue-places-to-visit-in-edingburgh/): Edinburgh was the second city we visited in the UK, after London, as you may remember from my London Travelogue. We explored this charming city over four days and discovered its unique blend of history and natural beauty. If you ever have the chance to visit, don’t miss it—Edinburgh has a lot to offer.
- [Dr. Esad Feyzi: A Pioneer of Turkish Radiology](https://aslan.md/dr-esad-feyzi-a-pioneer-of-turkish-radiology/): As a radiologist in Türkiye, the story of Dr. Esad Feyzi Bey profoundly influences me. His life’s work, which brought the revolutionary power of X-rays to the Ottoman Empire, reminds me of the immense impact curiosity, determination, and innovation can have in medicine. Inspired by the book authored by Prof. Dr. Aytekin Besim, Prof. Dr. C. Çınar Başekim, and the History and Ethics Research Group of the Turkish Radiology Association, I’ve taken detailed notes on his journey.
- [Book Review: The Almanack of Naval Ravikant](https://aslan.md/book-review-the-almanack-of-naval-ravikant/): After completing my residency exams, I started reading the books on my booklist. I ordered all of them from Amazon and started reading. The Almanack of Naval Ravikant is the first book I read this month. I want to share my notes to return and re-read occasionally.
- [The 14 Features of a Successful Side Project: My Personal Principles](https://aslan.md/the-14-features-of-a-successful-side-project-my-personal-principles/): As I consider embarking on a side project, often referred to as a side hustle, I realize that this can be a transformative journey for me. It offers an opportunity to explore new passions, generate additional income, and build skills outside my main profession. However, to ensure that this endeavor is fruitful and sustainable, I need to define the characteristics that make an ideal side hustle. The essence lies in the idea that consistent small efforts can culminate in significant results over time.
- [What is Vector Store Optimization?](https://aslan.md/what-is-vector-store-optimization/): In the rapidly advancing world of AI, especially with the growth of Large Language Models (LLMs), a new term has emerged for optimizing digital presence: Vector Store Optimization (VSO). While we’re familiar with App Store Optimization (ASO) and Search Engine Optimization (SEO), Vector Store Optimization has unique value in the AI era. But what exactly is it, and why does it matter?
- [How to Issue an Invoice to Apple for AppStore Revenues?](https://aslan.md/how-to-issue-an-invoice-to-apple-for-appstore-revenues/): One of the perks of mobile development is the ability to earn revenue through subscriptions, in-app purchases, or ads—arguably the most rewarding part! But there’s another side to it: accounting and invoicing, which can feel like a chore, especially if you’re a solo developer. I remember being in the same position, unsure of how to navigate invoicing for AppStore revenues. Here’s a straightforward guide I put together to help clarify the process.
- [Cloudflare Tunnel: Ngrok Alternative for Serving Local APIs](https://aslan.md/cloudflare-tunnel-ngrok-alternative-for-serving-local-apis/): After some research, I discovered Cloudflare Tunnel, a service that not only meets my needs but does so at no cost. With Cloudflare Tunnel, you can use your own domain and subdomain without the hassle of constantly changing URLs. The setup process is straightforward, similar to Ngrok, but the benefits it offers are substantial.
- [Top 6 Useful iOS Apps for Researchers and Scientists](https://aslan.md/top-6-useful-ios-apps-for-researchers-and-scientists/): In the fast-paced world of research and science, staying organized, managing references, creating compelling presentations, and writing flawless papers are essential skills. With mobile technology advancing rapidly, researchers can now access powerful tools from their iPhones or iPads. This blog post highlights 6 iOS apps that every researcher and scientist should consider using to improve their workflow and productivity.
- [London Travelogue: My Favorite Places in London](https://aslan.md/london-travelogue-my-favorite-places-in-london/): We have wanted to visit London for years. Finally, this June, my wife and I took a five-day trip. It was quite a hard decision because the visa approval was ambiguous. We could find ourselves in a difficult situation if they rejected our visa, but we decided to try it, at least. After 2 months of effort, we got our visa!
- [NVIDIA Holoscan and IGX Orin For Industrial & Medical Edge AI](https://aslan.md/nvidia-holoscan-and-igx-orin-for-industrial-medical-edge-ai/): PNY organized an event focusing on industrial and medical edge AI, featuring a webinar on NVIDIA Holoscan and NVIDIA IGX platforms. We attended this insightful event and have summarized the key points discussed. You will learn essential information about this ecosystem, including its features, applications, and benefits for various industries.
- [How to Calculate Drug Dose for Children? A Comprehensive Guide](https://aslan.md/how-to-calculate-drug-dose-for-children-a-comprehensive-guide/): Accurately calculating drug doses for children is crucial in ensuring their safety and effectiveness during treatment. Children are not simply small adults; their bodies process medications differently due to size, metabolism, and organ function differences. To help healthcare providers and caregivers calculate safe and accurate doses for pediatric patients, our mobile app, Pediatric Doses, offers a simple yet reliable solution.
- [How to Use MONAI Toolkit Docker Container?](https://aslan.md/how-to-use-monai-toolkit-docker-container/): The MONAI Toolkit leverages NVIDIA's cutting-edge technology to accelerate AI in healthcare imaging. Before diving into the specifics, you can get a general understanding of MONAI from previous discussions at Getting Started with AI in Healthcare and Training Your First Medical AI Model.
- [How to Install NVIDIA Container Toolkit on Ubuntu?](https://aslan.md/how-to-install-nvidia-container-toolkit-on-ubuntu/): In this tutorial, we will guide you through the process of installing the NVIDIA Container Toolkit on Ubuntu. This toolkit allows you to build and run GPU-accelerated Docker containers, which is crucial for many AI and machine learning applications. Let's get started!
- [Brain Tumor Classification with NVIDIA TAO Toolkit](https://aslan.md/brain-tumor-classification-with-nvidia-tao-toolkit/): In this tutorial, we will walk through the process of brain tumor classification using the NVIDIA TAO Toolkit. Previously, we mentioned No-Code AI Model Training with TAO Toolkit and How to Install NVIDIA TAO Toolkit.
- [How to Install NVIDIA TAO Toolkit?](https://aslan.md/how-to-install-nvidia-tao-toolkit/): In the previous No-Code AI Model Training with TAO Toolkit post, we mentioned that you can develop faster, easier ways to create highly accurate, customized, and enterprise-ready AI models without coding using the TAO Toolkit. In this post, we will discuss how to install the TAO Toolkit and get started with the model training.
- [No-Code AI Model Training with TAO Toolkit](https://aslan.md/no-code-ai-model-training-with-tao-toolkit/): In the traditional paradigm, developing AI models necessitated vast amounts of data and a dedicated team of data scientists. However, with transfer learning and pre-trained models, one can leverage pre-existing knowledge from trained models, cutting down the need for new data and time. Even if one is able to access these resources, coding skills are mainly required.
- [Train Your First Medical AI Model with MONAI](https://aslan.md/train-your-first-medical-ai-model-with-monai/): We briefly introduced MONAI in the previous Getting Started AI in Healthcare with MONAI post. Now, we will train our very first and simple medical AI model with MONAI Core. We can leverage the workflows in MONAI to quickly set up a robust training or evaluation program for research experiments.
- [Getting Started AI in Healthcare with MONAI](https://aslan.md/getting-started-ai-in-healthcare-with-monai/): Project development in AI in the healthcare domain can be exhausting without MONAI because computer vision and image processing methods in healthcare are quite different from regular methods. Evaluation methods and KPIs are different in medical models from others. Additionally, there are many imaging modalities, and every modality has its own data and labeling structure. We need healthcare-specific solutions to standardize methods and reproduce research results.
- [NVIDIA GPU Architectures and Product Families](https://aslan.md/nvidia-gpu-architectures-and-product-families/): NVIDIA GPUs stands as one of the paramount semiconductor companies in the world, consistently pushing the boundaries of technology and innovation. Not only have they revolutionized the realm of graphics processing, but they have also emerged as pioneers in the field of artificial intelligence. 
- [What are the FP16, FP32 and FP64?](https://aslan.md/what-are-the-fp16-fp32-and-fp64/): Handling numerical data efficiently and accurately is a cornerstone of modern computing, particularly in scientific simulations, machine learning, and graphics. One of the most common ways to represent real (non-integer) numbers digitally is through floating-point (FP) formats.
- [Top AI Research Papers: Milestones in AI Development](https://aslan.md/top-ai-research-papers-milestones-in-ai-development/): These 29 papers span decades of discoveries and innovations, with each one marking a milestone in AI’s development. From the early days of machine learning and neural networks to more recent advances in deep learning, natural language processing, and reinforcement learning, we will delve into the contributions of these pioneering works that have helped to define and push the boundaries of what AI can achieve today.
- [Accelerating NumPy, Pandas, and Scikit-Learn with GPU](https://aslan.md/accelerating-numpy-pandas-and-scikit-learn-with-gpu/): In the world of machine learning (ML) and data analytics, speed and scalability are key. GPU-accelerated data analytics is a powerful way to boost performance, helping you extract insights faster and handle large datasets more efficiently. One of the leading frameworks enabling this is RAPIDS, an open-source suite of libraries built on NVIDIA CUDA. RAPIDS taps into the enormous parallelism of NVIDIA GPUs to deliver higher throughput and shorter processing times—ideal for modern data-intensive workflows.
- [OpenCV vs VPI: Comparison of Computer Vision Libraries](https://aslan.md/opencv-vs-vpi-comparison-of-computer-vision-libraries/): Computer vision (CV) has become an indispensable component of numerous applications, including robotics, autonomous vehicles, medical imaging, and smart surveillance. As demands grow for real-time performance and optimized resource usage, developers have been turning to specialized libraries that can fully harness modern hardware architectures.
- [Blood Cell Detection Dataset](https://aslan.md/blood-cell-detection-dataset/): During my internship, I noticed a lack of small, educational, medical datasets for object detection and classification tasks. So, I decided to create one.

## Pages
- [Home](https://aslan.md/): I'm building apps for healthcare professionals at HVALABS. I solve the problems my colleagues and I face in the clinic every day.
- [Posts](https://aslan.md/posts/)
- [Equipment](https://aslan.md/equipment/): Development Equipment Apple MacBook Pro 14" M1 Pro Apple iPad Air 4th Gen Custom AI Workstation Monitor: LG UltraFine Ergo 27" 4K Keyboard: Logitech MX Keys Mini Mouse: Logitech MX Master 3 Earphone: Apple AirPods Pro 2nd Gen Desk: IKEA Anfallare Chair: IKEA Markus AI Workstation CPU: AMD ThreadRipper Pro 3550 16C GPU: NVIDIA RTX A5000 24GB Motherboard: ASUS WRX80 SAGE RAM: 256GB (8x32GB) DDR4 3200 Mhz Case: Corsair Crystal 650X PSU: FSP Cannon Pro 2000W CPU Cooler: Corsair H115i
- [About](https://aslan.md/about-me/): I'm building apps for healthcare professionals at HVALABS. I solve the problems my colleagues and I face in the clinic every day.

## Categories
- [Apps](https://aslan.md/category/apps/)
- [Artificial Intelligence](https://aslan.md/category/artificial-intelligence/)
- [Books](https://aslan.md/category/books/)
- [Business](https://aslan.md/category/business/)
- [Development](https://aslan.md/category/development/)
- [Hardware](https://aslan.md/category/hardware/)
- [Radiology](https://aslan.md/category/radiology/)
- [Tools](https://aslan.md/category/tools/)
- [Travel](https://aslan.md/category/travel/)

## Tags